CN118095814A - Energy storage planning method, device, medium and equipment based on user side scene - Google Patents
Energy storage planning method, device, medium and equipment based on user side scene Download PDFInfo
- Publication number
- CN118095814A CN118095814A CN202410525639.5A CN202410525639A CN118095814A CN 118095814 A CN118095814 A CN 118095814A CN 202410525639 A CN202410525639 A CN 202410525639A CN 118095814 A CN118095814 A CN 118095814A
- Authority
- CN
- China
- Prior art keywords
- energy storage
- planning
- target
- scene
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 116
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000009826 distribution Methods 0.000 claims abstract description 61
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 230000009467 reduction Effects 0.000 claims abstract description 14
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 76
- 238000005457 optimization Methods 0.000 claims description 70
- 239000010410 layer Substances 0.000 claims description 48
- 241000039077 Copula Species 0.000 claims description 30
- 238000004590 computer program Methods 0.000 claims description 25
- 238000005315 distribution function Methods 0.000 claims description 20
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 12
- 238000010276 construction Methods 0.000 claims description 10
- 241000345998 Calamus manan Species 0.000 claims description 9
- 235000012950 rattan cane Nutrition 0.000 claims description 9
- 238000007476 Maximum Likelihood Methods 0.000 claims description 7
- 239000002355 dual-layer Substances 0.000 claims description 6
- 238000003462 Bender reaction Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 4
- 238000010248 power generation Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 10
- 230000005611 electricity Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 102100030800 Ras suppressor protein 1 Human genes 0.000 description 2
- 101710102668 Ras suppressor protein 1 Proteins 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an energy storage planning method, device, medium and equipment based on a user side scene, wherein the method comprises the following steps: acquiring historical data of a region to be planned; constructing a joint probability distribution model based on the historical data; generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group; clustering the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction; calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-selected address node; based on the target scenes and the energy storage pre-site selection nodes, a double-layer planning model is adopted to determine an optimal energy storage planning scheme of the area to be planned, so that the accuracy of description of wind-light load correlation in energy storage planning of a user power distribution system can be improved, the rationality of the energy storage planning scheme is improved, and in addition, the power supply reliability of the system can be improved.
Description
Technical Field
The present application relates to the field of energy storage planning, and in particular, to an energy storage planning method, apparatus, medium and device based on a user side scenario.
Background
With the widespread use of renewable energy sources (e.g., photovoltaic and wind), the intermittent, fluctuating nature of renewable energy sources presents challenges to consumer-side power requirements and energy management. The energy storage has the capability of quickly adjusting power and supplying and storing, and is beneficial to improving the local digestion capability of renewable energy sources at the user side. Besides the effects of peak clipping and valley filling and the reduction of electricity purchasing cost of users, when the power interruption caused by the fault of transmission lines among users affects the electricity utilization safety of the users, the energy storage can also quickly respond to the fault condition of the lines to provide a standby power supply so as to maintain the operation of key equipment and service and reduce the inconvenience caused by the power interruption to the users. Therefore, reasonable planning of the energy storage capacity in the user side power transmission line normal-fault comprehensive scene has important significance for improving the power supply reliability of the system.
Disclosure of Invention
In order to solve the technical problems, the embodiment of the application provides an energy storage planning method, device, medium and equipment based on a user side scene.
The embodiment of the application provides an energy storage planning method based on a user side scene, which comprises the following steps:
acquiring historical data of a region to be planned, wherein the historical data comprises historical wind power data, historical photovoltaic output data and historical load data;
constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates a relationship between wind, light, and load;
Generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group;
clustering the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, wherein the target scene group comprises a plurality of target scenes;
calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-selected address node;
And determining an optimal energy storage planning scheme of the region to be planned by adopting a double-layer planning model based on the target scenes and the energy storage pre-site selection nodes, wherein the optimization targets of a lower-layer optimization model of the double-layer planning model comprise minimum user load shedding, and an upper-layer optimization model of the double-layer planning model takes the total cost as the optimization target.
Further, the constructing a joint probability distribution model based on the historical data includes:
Taking the historical wind power data, the historical photovoltaic output data and the historical load data as three random variables;
calculating Kendall correlation coefficients between every two of the three random variables;
selecting one random variable from the three random variables as a root node according to the Kendall correlation coefficient;
constructing a binary joint distribution function by using a Copula function;
based on the root node, updating the binary joint distribution function through a Copula function to obtain a target binary joint distribution function;
Evaluating a plurality of function forms acquired in advance by adopting a red pool information criterion, and selecting an objective function form from the function forms according to an evaluation result, wherein the function forms are used for constructing different binary condition Copula functions of the C rattan Copula;
determining function parameters of a C rattan Copula function through maximum likelihood estimation;
And constructing the joint probability distribution model based on the target binary joint distribution function, the target function form and the function parameters.
Further, the generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group includes:
Generating a plurality of random samples in the range of 0 to 1 through the joint probability distribution model;
Performing inverse transformation sampling processing on the plurality of random samples to convert the plurality of random samples into a random variable scene group consisting of a plurality of random variable scenes;
Wherein the plurality of random variable scenes have correlations between themselves over different time periods.
Further, the clustering processing is performed on the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, including:
In the first iteration, randomly selecting a sample from the random variable scene group to serve as a cluster center selected by the current iteration;
In each iteration which is not the first iteration, calculating the cluster center distance between each of a plurality of other samples and the cluster center selected by all completed iterations, calculating the corresponding selection probability according to the minimum cluster center distance of each other sample, and selecting the cluster center required to be selected for the current iteration from the plurality of other samples based on the selection probability, wherein the plurality of other samples are all samples which are not selected before the current iteration in the random variable scene group, and the cluster center distance is calculated through a kernel function;
Stopping iteration after the iteration number reaches a preset iteration number threshold value to obtain a plurality of clustering centers;
after a plurality of cluster centers are obtained, the following steps are repeatedly executed until a preset stopping condition is met:
respectively calculating the distance between each sample in the random variable scene group and the clustering centers so as to divide the random variable scene group into a plurality of first types;
Updating the first classes based on the number of samples of each first class to obtain a plurality of second classes;
Updating the clustering centers in the plurality of second classes to obtain a plurality of third classes;
Judging whether the stopping condition is met or not based on the third classes or the current repeated execution times;
If not, taking the cluster centers in the third classes as new cluster centers;
If yes, outputting the clustering centers in the third classes as the target scene group.
Further, the determining, based on the multiple target scenes and the energy storage pre-site node, an optimal energy storage planning scheme of the area to be planned by adopting a double-layer planning model includes:
inputting the multiple target scenes and the energy storage pre-site selection node into the lower optimization model so that the lower optimization model outputs a capacity planning scheme corresponding to each target scene, wherein constraint conditions of the lower optimization model comprise at least one of energy storage capacity construction constraint, energy storage operation constraint, user transmission line tide constraint, renewable energy output constraint and user power purchasing constraint to an upper power grid;
And inputting the capacity planning schemes corresponding to the target scenes to the upper optimization model so that the upper optimization model outputs the optimal energy storage planning scheme, wherein the optimal energy storage planning scheme is the capacity planning scheme with the lowest cost.
Furthermore, the optimization target of the lower optimization model further comprises that the loss of load is minimum when the user power distribution system fails, and the constraint conditions of the lower optimization model further comprise system failure constraint, system pre-failure constraint and system operation constraint.
Further, the double-layer planning model is solved through a Benders decomposition algorithm.
The embodiment of the application also provides an energy storage planning device based on the user side scene, which comprises the following steps:
the historical data acquisition module is used for acquiring historical data of the area to be planned, wherein the historical data comprises historical wind power data, historical photovoltaic output data and historical load data;
a joint probability distribution model construction module for constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates a relationship between wind, light and load;
The random variable scene generation module is used for generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group;
the clustering module is used for carrying out clustering processing on the random variable scene group by utilizing an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, wherein the target scene group comprises a plurality of target scenes;
the energy storage pre-addressing node acquisition module is used for calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-addressing node;
The planning module is used for determining an optimal energy storage planning scheme of the area to be planned by adopting a double-layer planning model based on the multiple target scenes and the energy storage pre-site selection nodes, wherein the optimization targets of a lower-layer optimization model of the double-layer planning model comprise minimum user load shedding, and an upper-layer optimization model of the double-layer planning model takes the total cost as the optimization target.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the energy storage planning method based on the user side scene.
The embodiment of the application also provides computer equipment, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor realizes the steps of the energy storage planning method based on the user side scene when executing the computer program.
In summary, the embodiment of the application has at least the following beneficial effects:
According to the embodiment of the application, the historical data of the area to be planned are obtained, wherein the historical data comprise historical wind power data, historical photovoltaic output data and historical load data; constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates a relationship between wind, light, and load; generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group; clustering the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, wherein the target scene group comprises a plurality of target scenes; calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-selected address node; and determining an optimal energy storage planning scheme of the region to be planned by adopting a double-layer planning model based on the target scenes and the energy storage pre-site selection nodes, wherein the optimization targets of a lower-layer optimization model of the double-layer planning model comprise minimum user load shedding, and an upper-layer optimization model of the double-layer planning model takes the total cost as the optimization target. By adopting the embodiment of the application, the accuracy of description of wind-light load correlation in the energy storage planning of the user power distribution system can be improved, thereby improving the rationality of the energy storage planning scheme and improving the power supply reliability of the system.
Drawings
Fig. 1 is a schematic flow chart of an energy storage planning method based on a user side scene according to an embodiment of the present application;
Fig. 2 is a schematic structural diagram of an energy storage planning device based on a user side scenario provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the description of the present application, the terms "first," "second," "third," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first", "a second", "a third", etc. may explicitly or implicitly include one or more such feature. In the description of the present application, unless otherwise indicated, the meaning of "a plurality" is two or more. In the description of the application, the terms "include" and variations thereof are intended to be open-ended, i.e., to include, but not limited to. The term "based on" is based at least in part on. The term "according to" is based, at least in part, on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments.
In the description of the present application, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present application will be understood in specific cases by those of ordinary skill in the art.
In the description of the present application, it should be noted that all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art unless defined otherwise. The terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application, as the particular meaning of the terms described above in the present application will be understood to those of ordinary skill in the art in the detailed description of the application.
Referring to fig. 1, a flow chart of an energy storage planning method based on a user side scene provided by an embodiment of the present application is shown, and the method includes steps S1 to S6, specifically as follows:
S1, acquiring historical data of a region to be planned, wherein the historical data comprise historical wind power data, historical photovoltaic output data and historical load data;
S2, constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates the relationship among wind, light and load;
s3, generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group;
s4, clustering the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, wherein the target scene group comprises a plurality of target scenes;
s5, calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-selected address node;
And S6, determining an optimal energy storage planning scheme of the region to be planned by adopting a double-layer planning model based on the target scenes and the energy storage pre-site selection nodes, wherein the optimization targets of a lower-layer optimization model of the double-layer planning model comprise minimum user load shedding, and an upper-layer optimization model of the double-layer planning model takes the total cost as the optimization target.
By way of example, embodiments of the present application may be applied to consumer power distribution systems designed based on IEEE33 node power distribution systems, where the consumer power distribution systems may be connected to photovoltaic power generation devices as well as wind power generation devices. Table 1 below is the line impedance of the subscriber distribution system.
TABLE 1
In an alternative embodiment, said constructing a joint probability distribution model based on said historical data comprises:
The historical wind power data, the historical photovoltaic output data and the historical load data are used as three random variables and are set as tree root nodes of the C rattan conditions;
Specifically, the historical wind data is expressed as The historical photovoltaic output data is expressed asThe historical load data is expressed as。
Calculating Kendall correlation coefficients between every two of the three random variables;
Specifically, the Kendall correlation coefficient Calculated by the following formula: /(I)
Wherein,To combine the number of elements having the same order relationship in both sequences,To combine numbers of elements having different order relationships in two sequences,Is the number of samples.
Selecting one random variable from the three random variables as a root node according to the Kendall correlation coefficient;
constructing a binary joint distribution function by using a Copula function;
Specifically, the binary joint distribution function is determined by the following formula:
Wherein, AndIs a corresponding condition variable; /(I)An edge distribution function that is a random variable; /(I)Is a Copula function; /(I)Is a simplified form of a marginal condition cumulative bifurcation function; /(I)And the parameters are binary random variables and are estimated by a maximum likelihood method.
Based on the root node, updating the binary joint distribution function through a Copula function to obtain a target binary joint distribution function;
specifically, after the root node is determined, the Copula function may be applied again to connect the newly determined binary random variables, thereby obtaining a final joint probability distribution function. The target binary joint distribution function is determined by the following formula:
wherein the joint probability density function is:
Wherein, A derivative that is a Copula function; /(I)Is an edge probability density function of a random variable.
Evaluating a plurality of function forms acquired in advance by adopting a red pool information criterion, and selecting an objective function form from the function forms according to an evaluation result, wherein the function forms are used for constructing different binary condition Copula functions of the C rattan Copula;
Specifically, the red pool information criterion (AIC) is calculated by the following formula:
Wherein, The number of parameters in the Copula function; /(I)Is the value of the Copula function maximum likelihood function.
In this embodiment, after determining the function structure of the celadon Copula, the functional form of the different binary conditional Copula functions used to construct the celadon Copula is selected. The selected functional form is evaluated using a red pool information criterion (AIC) calculation to select the most appropriate functional form.
Determining function parameters of a C rattan Copula function through maximum likelihood estimation;
Specifically, the maximum likelihood estimate is determined by the following formula:
Wherein, Is a function parameter.
And constructing the joint probability distribution model based on the target binary joint distribution function, the target function form and the function parameters.
Illustratively, the joint probability distribution model is shown in Table 2 below.
TABLE 2
The pair-Copula is used for describing and analyzing the dependency relationship among variables, and the C 12 is used for modeling the correlation relationship between photovoltaic power generation and load; c 13 is used for modeling the correlation between photovoltaic power generation and wind power generation; c 32|1 is used to model the correlation between load and wind power generation. Frank, gummel and Clayton are three different types of Copula functions that are used in multivariate statistical analysis to describe the dependency structure between variables, all belonging to one of archimedes (ARCHIMEDEAN) Copula, with specific mathematical forms and properties.
In an alternative embodiment, the generating a plurality of random samples by the joint probability distribution model and converting to a set of random variable scenes includes:
Generating a plurality of random samples in the range of 0 to 1 through the joint probability distribution model;
Performing inverse transformation sampling processing on the plurality of random samples to convert the plurality of random samples into a random variable scene group consisting of a plurality of random variable scenes;
Wherein the plurality of random variable scenes have correlations between themselves over different time periods.
Specifically, the present embodiment can produce in the range of [0,1]Random samples are then transformed into a set of correlation dimension/>, over each time period, using an inverse transform sampling methodRandom variable scene，，。
In an optional implementation manner, the clustering processing is performed on the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, and the method includes:
In the first iteration, randomly selecting a sample from the random variable scene group to serve as a cluster center selected by the current iteration;
In each iteration which is not the first iteration, calculating the cluster center distance between each of a plurality of other samples and the cluster center selected by all completed iterations, calculating the corresponding selection probability according to the minimum cluster center distance of each other sample, and selecting the cluster center required to be selected for the current iteration from the plurality of other samples based on the selection probability, wherein the plurality of other samples are all samples which are not selected before the current iteration in the random variable scene group, and the cluster center distance is calculated through a kernel function;
Specifically, the kernel function may be determined by the following formula:
Wherein, Is a mapping function for mapping points of an input space to a high-dimensional space,Is a method meeting the requirement that x, z is in the input spaceA function within, whereinForAndInner product ofAs parameters of gaussian kernel functions, an exemplaryThe value is 0.1.
Specifically, the selection probability may be calculated by the following formula:
Wherein, For every other sampleIs the smallest of the cluster center distances, x= [，，]。
Stopping iteration after the iteration number reaches a preset iteration number threshold value to obtain a plurality of clustering centers;
after a plurality of cluster centers are obtained, the following steps are repeatedly executed until a preset stopping condition is met:
respectively calculating the distance between each sample in the random variable scene group and the clustering centers so as to divide the random variable scene group into a plurality of first types;
specifically, the distance between each sample in the random variable scene group and the plurality of cluster centers can be calculated by the following formula:
Wherein, For the cluster centerIs a cluster of the above-mentioned groups.
Updating the first classes based on the number of samples of each first class to obtain a plurality of second classes;
Specifically, it is determined whether the number of samples in each first class is smaller than If the number is smaller than the first class, the first class is dropped, and each sample in the first class is reassigned to the nearest first class in the remaining first classes, so that a plurality of second classes are formed.
Updating the clustering centers in the plurality of second classes to obtain a plurality of third classes;
Specifically, for each second class j=1, 2,3, …, k, the cluster center is updated, and the average distance from the sample in the cluster center to the cluster center is calculated Wherein the cluster center is updated by the following formula:
Average distance Calculated by the following formula:
Judging whether the stopping condition is met or not based on the third classes or the current repeated execution times;
Specifically, the average distance from all samples in each third class to the clustering center is calculated, and if the clustering result indicated by the average distance is unchanged, iteration is stopped.
The average distanceThe calculation can be made by the following formula: /(I)
Specifically, the number of times of the current repeated execution may determine whether the stop condition is satisfied by:
And judging whether to enter a splitting operation or a merging operation by using the current repeated execution times. The judging conditions are as follows: (a) If the number of times of the repeated execution reaches the maximum number of times, then the method causes Then, a merging operation is carried out; (b) If the current cluster number，If the number of times of current repeated execution is even number of times, or the current clustering number/>, the method is characterized in that the number of the current clustering is too small to meet the condition and the splitting operation needs to be carried outThe splitting operation is not performed, but the merging operation is performed, and when the two conditions are not satisfied, the splitting operation is performed; wherein,
The merging operation is as follows: calculating the distance between the clustering centers of all the categories and arranging them in increasing order from small to large, if two clustering centers are usedAndThe distance between them is less thanThe two categories can be combined into a new category, new cluster centerThe method comprises the following steps:
new cluster centers, i.e. the weighted sum of the original two classes of cluster centers, are combined at most in each round And clustering.
The splitting operation is as follows: splitting the class meeting the condition into two subclasses, and assuming that the clustering centers of the new two subclasses are respectivelyAndThe calculation mode is as follows:
Setting a splitting parameter t,0< t <1, which can be set to 0.5, letting WhereinOnly atThe component of (2) is not zero, and two new clustering centers are respectively:
In specific implementation, the stopping condition is that the classification result is not changed or the current repeated execution times reach the maximum times. In this embodiment, k=5 cluster centers are initially input, and after the algorithm splitting operation, the number of cluster centers is 8, and output Wind power generation output, photovoltaic power generation output and load scene，，。
If not, taking the cluster centers in the third classes as new cluster centers;
If yes, outputting the clustering centers in the third classes as the target scene group.
Specifically, in step S5, the vulnerability of any user node i at any time t may be calculated by the following formula：
Wherein,The voltage of the user node i at the moment t; /(I)The rated voltage value of the node i; 0.06 is the maximum voltage offset specified by the user side;
The best access user node for energy storage is selected by utilizing the standard deviation of voltage vulnerability of each user node for one day. Wherein the voltage vulnerability standard deviation of the user node i for one day The method comprises the following steps:
and sequencing all the user nodes from large to small in the voltage vulnerability standard deviation, and selecting the user node with the large voltage vulnerability standard deviation as an energy storage pre-selected address node.
In an optional implementation manner, the determining, based on the multiple target scenes and the energy storage pre-locating node, the optimal energy storage planning scheme of the area to be planned by using a dual-layer planning model includes:
inputting the multiple target scenes and the energy storage pre-site selection node into the lower optimization model so that the lower optimization model outputs a capacity planning scheme corresponding to each target scene, wherein constraint conditions of the lower optimization model comprise at least one of energy storage capacity construction constraint, energy storage operation constraint, user transmission line tide constraint, renewable energy output constraint and user power purchasing constraint to an upper power grid;
And inputting the capacity planning schemes corresponding to the target scenes to the upper optimization model so that the upper optimization model outputs the optimal energy storage planning scheme, wherein the optimal energy storage planning scheme is the capacity planning scheme with the lowest cost.
In this embodiment, the upper layer optimization problem is energy storage planning at the user side under normal operation of the system. The present embodiment uses a two-stage planning solution strategy, the first stage (lower optimization model) is intended to optimize the capacity planning scheme for each clustered scenario, at which stage it will，，And introducing the energy storage capacity planning model at the user side to obtain a capacity planning scheme corresponding to each scene. The goal of the second stage is to determine the optimal capacity planning scheme according to the economic cost optimization decision, at this stage, 8 (or other number of) scenarios can be cross-combined with each capacity planning scheme of the first stage, and the adaptive weighted sum of each combination in all 8 scenarios is calculated to express the economic cost, and finally 8 different combinations are obtained, wherein the capacity planning scheme corresponding to the combination with the smallest weighted sum is the optimal scheme.
Specifically, the objective function of the lower optimization model may be determined by the following formula:
Wherein, AndThe capacity and the charge-discharge power of the ith energy storage are respectively shown in KWh and KW; /(I)Is the energy storage capacity attenuation coefficient,For the discount rate, 0.04 is taken, and n is the service life of energy storage, which is generally 15 years. /(I)AndThe cost per unit capacity and the cost per unit power can be 1500 yuan/kWh and 600 yuan/KW respectively. UserThe system is connected with an upper power grid; /(I)The method comprises the steps of representing the electricity purchasing power of a user to an upper power grid in a t period; the unit is KW; /(I)AndThe square of the current in the transmission line between user i and user j and the line resistance; /(I)AndThe electricity price and the unit network loss cost of electricity purchased by the user to the upper power grid are respectively shown in the unit of yuan/KW. /(I)Is a collection of users connected to user i.
Specifically, the energy storage capacity construction constraint may be determined by the following formula:
In the method, in the process of the invention, AndThe maximum construction capacity and the maximum power of the ith energy storage are respectively 20000KWh and 2000KW.
Specifically, the energy storage operation constraint may be determined by the following formula:
In the method, in the process of the invention, The electricity storage quantity of the ith energy storage in the t period is KWh; /(I)Taking 0.01 as the self-loss rate of the stored energy electric quantity; /(I)AndCharging power and discharging power of the ith energy storage in t time intervals are respectively KW; /(I)AndRespectively charging and discharging efficiencies, and taking 0.95; /(I)AndThe upper limit and the lower limit of the energy storage charge state are respectively the value of 0.1 and 0.9. /(I)AndThe charge and discharge state 0-1 variables are respectively charged (discharged) when the value is 1.
Specifically, the user transmission line power flow constraint may be determined by the following formula:
In the method, in the process of the invention, A parent node representing user node i; /(I)、AndActive power, reactive power and line current of the transmission line between the user i and the user j in the t period are respectively; /(I)、AndThe voltage amplitude, active power demand and reactive power demand of the user node i at the moment t are respectively; /(I)AndThe resistance and reactance of the transmission line between the user i and the user j are; /(I)AndThe upper and lower limits of the voltage of the user i node are 0.94 p.u. and 1.06 p.u.; is the upper limit of line current transmission, and takes the value of 0.12 p.u.;
And processing a nonlinear term in the following formula of the flow constraint of the user transmission line by adopting second order cone relaxation:
then, the user transmission line power flow constraint after the variable relaxation is as follows:
specifically, the renewable energy output constraint may be determined by the following formula:
In the method, in the process of the invention, AndThe output values of the photovoltaic power generation and the wind power generation in the t period are KW respectively; /(I)AndThe method comprises the steps of generating a photovoltaic power generation scene and a wind power generation scene with correlation in a t period; /(I)AndPhotovoltaic and fan nodes accessed by users respectively,，。
Specifically, the user electricity purchasing constraint on the upper power grid can be determined by the following formula:
In the method, in the process of the invention, AndIs the upper limit for the user to purchase active power and reactive power to the upper power grid. The units are KW and KVar, respectively.
In specific implementation, energy storage planning schemes of k systems in normal operation are obtained under k clustered scenesWherein, the method comprises the steps of, wherein,
1) Fixed equipment planning schemeOnly changing the fan output, the photovoltaic output and the load scene, carrying out k times of operation according to the formulaThe corresponding objective function/>, can be obtained，。
2）Cost expectation valueFor kThe sum of the products of the corresponding scene probabilities, namely:
Selecting the minimum cost expectation As an optimal planning scheme。
In an alternative embodiment, the optimization target of the lower optimization model further comprises minimum load loss when the user power distribution system fails, and the constraint condition of the lower optimization model further comprises system failure constraint, system pre-failure constraint and system operation constraint.
In particular, the fault scenario may be expressed as，Indicating that the transmission line between the user node i and the user node j fails in the period t Ln; DG indicates that the renewable energy source of the user node i fails at time t Di;
The objective function corresponding to the minimum loss of load when the user power distribution system fails can be determined by the following formula: Wherein/> Is a system line fault scenario set.
Specifically, the system fault constraint may be determined by the following formula:
In the method, in the process of the invention, The state sequence of the user power transmission line i j under the fault scene o is (the value is 0 if the fault occurs, otherwise, the value is 1); /(I)Is a state sequence of photovoltaic and wind power generation in a fault scene o.
Specifically, the pre-system-fault constraint may be determined by the following formula:
In the method, in the process of the invention, AndRespectively storing energy information in each period before the occurrence of the fault and information corresponding to the normal operation scene.
Specifically, the system operation constraint can include at least one of an energy storage capacity construction constraint, an energy storage operation constraint, a user transmission line tide constraint after variable relaxation, a renewable energy source output constraint and a user power purchasing constraint to an upper-level power grid.
The operational sub-problem of the fault scene o under the kth wind-light load scene is solved and is recorded as RSP. The compact form is as follows:
In the method, in the process of the invention, Continuous variable matrix related to operation of a power distribution system for a user, including、、、、AndEtc.; /(I)Discrete variable matrices related to the operation of a power distribution system for a user, includingAnd；A coefficient matrix in an objective function; /(I)、、、Is a coefficient matrix in the constraint. Record its objective function optimum BLC k,o and obtain the discrete variableOptimal value；
Fixing discrete variables in RSPThe value of (1) is to convert RSP into a linear program, denoted RSP-1: /(I)
In the method, in the process of the invention,A dual variable optimal value matrix for the corresponding constraint;
Calculating the expected load loss of a user ：
In the method, in the process of the invention,The probability of the power distribution network fault in one year is 0.01; /(I)The probability of occurrence of the fault scene o is 0.1.
In an alternative embodiment, the dual layer planning model is solved by a Benders decomposition algorithm.
In specific implementation, the two-layer planning model can be solved by utilizing a Benders decomposition algorithm, and the safety evaluation can be carried out on the energy storage planning scheme obtained by the upper-layer optimization model by solving the objective function under each fault scene, and the reliability cutting constraint is returned to the upper-layer optimization model, and the specific steps are as follows:
Judging Whether is smaller than a set user electricity safety thresholdLet 0KW be the case. If yes, energy storage planning schemeMeeting the safety constraint and outputting the planning result; otherwise, adding security cut constraint to the upper layer. Because the fault running sub-problem RSP is a mixed integer linear programming problem, the reliability cut constraint cannot be constructed directly by using the corresponding dual problem. It is therefore still necessary to construct a reliability cut constraint with RSP-1 and add it to the constraints of the upper layer planning problem, returning to continue the calculation until an energy storage planning solution is found that meets the reliability cut constraint.
Exemplary, the resulting energy storage planning schemes and costs are shown in tables 3 and 4, respectively.
TABLE 3 Table 3
TABLE 4 Table 4
Correspondingly, the embodiment of the application also provides an energy storage planning device based on the user side scene, which can realize all the flows of the energy storage planning method based on the user side scene provided by the embodiment.
Referring to fig. 2, a schematic structural diagram of an energy storage planning device based on a user side scenario provided by an embodiment of the present application is shown, where the device includes:
The historical data acquisition module 101 is configured to acquire historical data of a region to be planned, where the historical data includes historical wind power data, historical photovoltaic output data and historical load data;
a joint probability distribution model construction module 102 for constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates a relationship between wind, light, and load;
A random variable scene generation module 103, configured to generate a plurality of random samples through the joint probability distribution model and convert the random samples into a random variable scene group;
The clustering module 104 is configured to perform clustering processing on the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, where the target scene group includes a plurality of target scenes;
the energy storage pre-addressing node obtaining module 105 is used for calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-addressing node;
and the planning module 106 is configured to determine an optimal energy storage planning scheme of the area to be planned by adopting a double-layer planning model based on the multiple target scenes and the energy storage pre-site node, wherein an optimization target of a lower-layer optimization model of the double-layer planning model comprises a minimum user load shedding, and an upper-layer optimization model of the double-layer planning model uses the minimum total cost as an optimization target.
In an alternative embodiment, said constructing a joint probability distribution model based on said historical data comprises:
Taking the historical wind power data, the historical photovoltaic output data and the historical load data as three random variables;
calculating Kendall correlation coefficients between every two of the three random variables;
selecting one random variable from the three random variables as a root node according to the Kendall correlation coefficient;
constructing a binary joint distribution function by using a Copula function;
based on the root node, updating the binary joint distribution function through a Copula function to obtain a target binary joint distribution function;
Evaluating a plurality of function forms acquired in advance by adopting a red pool information criterion, and selecting an objective function form from the function forms according to an evaluation result, wherein the function forms are used for constructing different binary condition Copula functions of the C rattan Copula;
determining function parameters of a C rattan Copula function through maximum likelihood estimation;
And constructing the joint probability distribution model based on the target binary joint distribution function, the target function form and the function parameters.
In an alternative embodiment, the generating a plurality of random samples by the joint probability distribution model and converting to a set of random variable scenes includes:
Generating a plurality of random samples in the range of 0 to 1 through the joint probability distribution model;
Performing inverse transformation sampling processing on the plurality of random samples to convert the plurality of random samples into a random variable scene group consisting of a plurality of random variable scenes;
Wherein the plurality of random variable scenes have correlations between themselves over different time periods.
In an optional implementation manner, the clustering processing is performed on the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, and the method includes:
In the first iteration, randomly selecting a sample from the random variable scene group to serve as a cluster center selected by the current iteration;
In each iteration which is not the first iteration, calculating the cluster center distance between each of a plurality of other samples and the cluster center selected by all completed iterations, calculating the corresponding selection probability according to the minimum cluster center distance of each other sample, and selecting the cluster center required to be selected for the current iteration from the plurality of other samples based on the selection probability, wherein the plurality of other samples are all samples which are not selected before the current iteration in the random variable scene group, and the cluster center distance is calculated through a kernel function;
Stopping iteration after the iteration number reaches a preset iteration number threshold value to obtain a plurality of clustering centers;
after a plurality of cluster centers are obtained, the following steps are repeatedly executed until a preset stopping condition is met:
respectively calculating the distance between each sample in the random variable scene group and the clustering centers so as to divide the random variable scene group into a plurality of first types;
Updating the first classes based on the number of samples of each first class to obtain a plurality of second classes;
Updating the clustering centers in the plurality of second classes to obtain a plurality of third classes;
Judging whether the stopping condition is met or not based on the third classes or the current repeated execution times;
If not, taking the cluster centers in the third classes as new cluster centers;
If yes, outputting the clustering centers in the third classes as the target scene group.
In an optional implementation manner, the determining, based on the multiple target scenes and the energy storage pre-locating node, the optimal energy storage planning scheme of the area to be planned by using a dual-layer planning model includes:
inputting the multiple target scenes and the energy storage pre-site selection node into the lower optimization model so that the lower optimization model outputs a capacity planning scheme corresponding to each target scene, wherein constraint conditions of the lower optimization model comprise at least one of energy storage capacity construction constraint, energy storage operation constraint, user transmission line tide constraint, renewable energy output constraint and user power purchasing constraint to an upper power grid;
And inputting the capacity planning schemes corresponding to the target scenes to the upper optimization model so that the upper optimization model outputs the optimal energy storage planning scheme, wherein the optimal energy storage planning scheme is the capacity planning scheme with the lowest cost.
In an alternative embodiment, the optimization target of the lower optimization model further comprises minimum load loss when the user power distribution system fails, and the constraint condition of the lower optimization model further comprises system failure constraint, system pre-failure constraint and system operation constraint.
In an alternative embodiment, the dual layer planning model is solved by a Benders decomposition algorithm.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the steps of the energy storage planning method based on the user side scene.
The embodiment of the application also provides computer equipment, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor realizes the steps of the energy storage planning method based on the user side scene when executing the computer program.
Referring to fig. 3, the computer device of this embodiment includes: a processor 301, a memory 302 and a computer program stored in said memory 302 and executable on said processor 301, for example a power storage planning program based on a user side scenario. The processor 301 executes the computer program to implement the steps in the embodiments of the energy storage planning method based on the user side scenario, for example, steps S1-S6 shown in fig. 1.
Illustratively, the computer program may be partitioned into one or more modules/units that are stored in the memory 302 and executed by the processor 301 to accomplish the present application. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments describe the execution of the computer program in the computer device.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer device may include, but is not limited to, a processor 301, a memory 302. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a computer device and is not limiting of the computer device, and may include more or fewer components than shown, or may combine some of the components, or different components, e.g., the computer device may also include input and output devices, network access devices, buses, etc.
The Processor 301 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), off-the-shelf Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor 301 may be any conventional processor or the like, the processor 301 being the control center of the computer device, with various interfaces and lines connecting the various parts of the overall computer device.
The memory 302 may be used to store the computer programs and/or modules, and the processor 301 may implement various functions of the computer device by executing or executing the computer programs and/or modules stored in the memory 302, and invoking data stored in the memory 302. The memory 302 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Wherein the computer device integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of each method embodiment described above when executed by the processor 301. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
In summary, the embodiment of the application has at least the following beneficial effects:
According to the embodiment of the application, the historical data of the area to be planned are obtained, wherein the historical data comprise historical wind power data, historical photovoltaic output data and historical load data; constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates a relationship between wind, light, and load; generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group; clustering the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, wherein the target scene group comprises a plurality of target scenes; calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-selected address node; and determining an optimal energy storage planning scheme of the region to be planned by adopting a double-layer planning model based on the target scenes and the energy storage pre-site selection nodes, wherein the optimization targets of a lower-layer optimization model of the double-layer planning model comprise minimum user load shedding, and an upper-layer optimization model of the double-layer planning model takes the total cost as the optimization target. By adopting the embodiment of the application, the accuracy of description of wind-light load correlation in the energy storage planning of the user power distribution system can be improved, thereby improving the rationality of the energy storage planning scheme and improving the power supply reliability of the system.
From the above description of the embodiments, it will be clear to those skilled in the art that the present application may be implemented by means of software plus necessary hardware platforms, but may of course also be implemented entirely in hardware. With such understanding, all or part of the technical solution of the present application contributing to the background art may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the method described in the embodiments or some parts of the embodiments of the present application.
While the foregoing is directed to the preferred embodiments of the present application, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the application, such changes and modifications are also intended to be within the scope of the application.
Claims (10)
1. An energy storage planning method based on a user side scene is characterized by comprising the following steps:
acquiring historical data of a region to be planned, wherein the historical data comprises historical wind power data, historical photovoltaic output data and historical load data;
constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates a relationship between wind, light, and load;
Generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group;
clustering the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, wherein the target scene group comprises a plurality of target scenes;
calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-selected address node;
And determining an optimal energy storage planning scheme of the region to be planned by adopting a double-layer planning model based on the target scenes and the energy storage pre-site selection nodes, wherein the optimization targets of a lower-layer optimization model of the double-layer planning model comprise minimum user load shedding, and an upper-layer optimization model of the double-layer planning model takes the total cost as the optimization target.
2. The energy storage planning method based on a user side scenario of claim 1, wherein the constructing a joint probability distribution model based on the historical data comprises:
Taking the historical wind power data, the historical photovoltaic output data and the historical load data as three random variables;
calculating Kendall correlation coefficients between every two of the three random variables;
selecting one random variable from the three random variables as a root node according to the Kendall correlation coefficient;
constructing a binary joint distribution function by using a Copula function;
based on the root node, updating the binary joint distribution function through a Copula function to obtain a target binary joint distribution function;
Evaluating a plurality of function forms acquired in advance by adopting a red pool information criterion, and selecting an objective function form from the function forms according to an evaluation result, wherein the function forms are used for constructing different binary condition Copula functions of the C rattan Copula;
determining function parameters of a C rattan Copula function through maximum likelihood estimation;
And constructing the joint probability distribution model based on the target binary joint distribution function, the target function form and the function parameters.
3. The energy storage planning method based on user side scenario of claim 1, wherein generating a plurality of random samples by the joint probability distribution model and converting to a set of random variable scenarios comprises:
Generating a plurality of random samples in the range of 0 to 1 through the joint probability distribution model;
Performing inverse transformation sampling processing on the plurality of random samples to convert the plurality of random samples into a random variable scene group consisting of a plurality of random variable scenes;
Wherein the plurality of random variable scenes have correlations between themselves over different time periods.
4. The energy storage planning method based on the user side scene as set forth in claim 1, wherein the clustering the random variable scene group by using an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction includes:
In the first iteration, randomly selecting a sample from the random variable scene group to serve as a cluster center selected by the current iteration;
In each iteration which is not the first iteration, calculating the cluster center distance between each of a plurality of other samples and the cluster center selected by all completed iterations, calculating the corresponding selection probability according to the minimum cluster center distance of each other sample, and selecting the cluster center required to be selected for the current iteration from the plurality of other samples based on the selection probability, wherein the plurality of other samples are all samples which are not selected before the current iteration in the random variable scene group, and the cluster center distance is calculated through a kernel function;
Stopping iteration after the iteration number reaches a preset iteration number threshold value to obtain a plurality of clustering centers;
after a plurality of cluster centers are obtained, the following steps are repeatedly executed until a preset stopping condition is met:
respectively calculating the distance between each sample in the random variable scene group and the clustering centers so as to divide the random variable scene group into a plurality of first types;
Updating the first classes based on the number of samples of each first class to obtain a plurality of second classes;
Updating the clustering centers in the plurality of second classes to obtain a plurality of third classes;
Judging whether the stopping condition is met or not based on the third classes or the current repeated execution times;
If not, taking the cluster centers in the third classes as new cluster centers;
If yes, outputting the clustering centers in the third classes as the target scene group.
5. The energy storage planning method based on a user side scenario of claim 1, wherein the determining an optimal energy storage planning scheme for the area to be planned using a dual-layer planning model based on the plurality of target scenarios and the energy storage pre-site node comprises:
inputting the multiple target scenes and the energy storage pre-site selection node into the lower optimization model so that the lower optimization model outputs a capacity planning scheme corresponding to each target scene, wherein constraint conditions of the lower optimization model comprise at least one of energy storage capacity construction constraint, energy storage operation constraint, user transmission line tide constraint, renewable energy output constraint and user power purchasing constraint to an upper power grid;
And inputting the capacity planning schemes corresponding to the target scenes to the upper optimization model so that the upper optimization model outputs the optimal energy storage planning scheme, wherein the optimal energy storage planning scheme is the capacity planning scheme with the lowest cost.
6. The energy storage planning method based on the user side scene as set forth in claim 1, wherein the optimization target of the lower optimization model further comprises that the load loss is minimum when the user power distribution system fails, and the constraint condition of the lower optimization model further comprises a system failure constraint, a system pre-failure constraint and a system operation constraint.
7. A method of energy storage planning based on a user side scenario according to any of claims 1-6 wherein the dual layer planning model is solved by means of a Benders decomposition algorithm.
8. An energy storage planning device based on a user side scene is characterized by comprising:
the historical data acquisition module is used for acquiring historical data of the area to be planned, wherein the historical data comprises historical wind power data, historical photovoltaic output data and historical load data;
a joint probability distribution model construction module for constructing a joint probability distribution model based on the historical data, wherein the joint probability distribution model indicates a relationship between wind, light and load;
The random variable scene generation module is used for generating a plurality of random samples through the joint probability distribution model and converting the random samples into a random variable scene group;
the clustering module is used for carrying out clustering processing on the random variable scene group by utilizing an iterative self-organizing data analysis algorithm to obtain a target scene group after scene reduction, wherein the target scene group comprises a plurality of target scenes;
the energy storage pre-addressing node acquisition module is used for calculating based on a preset user side voltage vulnerability index to obtain an energy storage pre-addressing node;
The planning module is used for determining an optimal energy storage planning scheme of the area to be planned by adopting a double-layer planning model based on the multiple target scenes and the energy storage pre-site selection nodes, wherein the optimization targets of a lower-layer optimization model of the double-layer planning model comprise minimum user load shedding, and an upper-layer optimization model of the double-layer planning model takes the total cost as the optimization target.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the energy storage planning method based on a user-side scenario according to any one of claims 1-7.
10. A computer device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the user side scenario-based energy storage planning method of any one of claims 1-7 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410525639.5A CN118095814B (en) | 2024-04-29 | 2024-04-29 | Energy storage planning method, device, medium and equipment based on user side scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410525639.5A CN118095814B (en) | 2024-04-29 | 2024-04-29 | Energy storage planning method, device, medium and equipment based on user side scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118095814A true CN118095814A (en) | 2024-05-28 |
| CN118095814B CN118095814B (en) | 2024-08-13 |
Family
ID=91151084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410525639.5A Active CN118095814B (en) | 2024-04-29 | 2024-04-29 | Energy storage planning method, device, medium and equipment based on user side scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118095814B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115936220A (en) * | 2022-12-09 | 2023-04-07 | 国网福建省电力有限公司 | Garden comprehensive energy system planning and operation optimization method and terminal |
| CN116436085A (en) * | 2023-04-25 | 2023-07-14 | 国网河北省电力有限公司经济技术研究院 | Micro-energy network group hierarchical optimization control method and system based on scene construction |
| CN116502832A (en) * | 2023-04-12 | 2023-07-28 | 国网经济技术研究院有限公司 | Multi-micro-grid joint planning method, system, storage medium and electronic equipment |
| CN116522800A (en) * | 2023-06-01 | 2023-08-01 | 国网湖北省电力有限公司荆州供电公司 | Multi-target wind-power storage station site selection and volume determination method based on scene probability |
| CN116757406A (en) * | 2023-06-01 | 2023-09-15 | 国网湖北省电力有限公司荆州供电公司 | Distributed power supply access distribution network site selection and volume determination method considering uncertainty |
-
2024
- 2024-04-29 CN CN202410525639.5A patent/CN118095814B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115936220A (en) * | 2022-12-09 | 2023-04-07 | 国网福建省电力有限公司 | Garden comprehensive energy system planning and operation optimization method and terminal |
| CN116502832A (en) * | 2023-04-12 | 2023-07-28 | 国网经济技术研究院有限公司 | Multi-micro-grid joint planning method, system, storage medium and electronic equipment |
| CN116436085A (en) * | 2023-04-25 | 2023-07-14 | 国网河北省电力有限公司经济技术研究院 | Micro-energy network group hierarchical optimization control method and system based on scene construction |
| CN116522800A (en) * | 2023-06-01 | 2023-08-01 | 国网湖北省电力有限公司荆州供电公司 | Multi-target wind-power storage station site selection and volume determination method based on scene probability |
| CN116757406A (en) * | 2023-06-01 | 2023-09-15 | 国网湖北省电力有限公司荆州供电公司 | Distributed power supply access distribution network site selection and volume determination method considering uncertainty |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118095814B (en) | 2024-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Robust UC model based on multi‐band uncertainty set considering the temporal correlation of wind/load prediction errors | |
| Yeh et al. | New genetic algorithm for economic dispatch of stand-alone three-modular microgrid in DongAo Island | |
| Ebrahimi et al. | Adaptive robust optimization framework for day-ahead microgrid scheduling | |
| da Silva et al. | Transmission expansion planning optimization by adaptive multi-operator evolutionary algorithms | |
| Shi et al. | Multistage robust energy management for microgrids considering uncertainty | |
| CN111738519A (en) | Power distribution network planning method, system and equipment | |
| CN110852565B (en) | Grid frame planning method considering different functional attributes | |
| CN112636396B (en) | Photovoltaic power distribution network control method and terminal | |
| Gao et al. | Data‐driven distributionally robust joint planning of distributed energy resources in active distribution network | |
| Galvani et al. | Data clustering based probabilistic optimal power flow in power systems | |
| Saberi et al. | Probabilistic congestion driven network expansion planning using point estimate technique | |
| CN116961052A (en) | Method and system for locating and sizing distributed energy storage system | |
| Wen et al. | Optimal distributed energy storage investment scheme for distribution network accommodating high renewable penetration | |
| Ebrahimi et al. | Probabilistic optimal planning in active distribution networks considering non‐linear loads based on data clustering method | |
| CN115313519A (en) | Power distribution network energy storage optimal configuration method, device, equipment and storage medium | |
| Ghavidel et al. | Hybrid power plant bidding strategy for voltage stability improvement, electricity market profit maximization, and congestion management | |
| Tohidi et al. | Stochastic optimisation for investment analysis of flow battery storage systems | |
| CN114757699A (en) | Method, device, equipment and medium for graded clearing of electric power peak regulation auxiliary service market | |
| CN118095814B (en) | Energy storage planning method, device, medium and equipment based on user side scene | |
| CN108960500A (en) | The control method and electronic device of battery energy storage system | |
| CN113937781A (en) | Virtual power plant rolling scheduling technology considering temperature control load polymer | |
| CN115907338A (en) | Active power distribution network distribution robust scheduling method and system | |
| CN115514001A (en) | Method, device, equipment and medium for calculating photovoltaic receiving capacity of power distribution network | |
| Chen et al. | Dynamic optimal power flow model incorporating interval uncertainty applied to distribution network | |
| Sun et al. | Energy storage strategy in a non-agent energy trading platform: energy bank system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |