CN106960260B - Wind power prediction system convenient for power dispatching - Google Patents
Wind power prediction system convenient for power dispatching Download PDFInfo
- Publication number
- CN106960260B CN106960260B CN201710190235.5A CN201710190235A CN106960260B CN 106960260 B CN106960260 B CN 106960260B CN 201710190235 A CN201710190235 A CN 201710190235A CN 106960260 B CN106960260 B CN 106960260B
- Authority
- CN
- China
- Prior art keywords
- data
- sample
- preliminary
- support vector
- wind power
- 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.)
- Active
Links
- 239000002245 particle Substances 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000012706 support-vector machine Methods 0.000 claims abstract description 36
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000013075 data extraction Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 25
- 238000012216 screening Methods 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 5
- 238000002922 simulated annealing Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
Abstract
The invention provides a wind power prediction system convenient for power scheduling, which comprises a data extraction module, a data preprocessing module, a training module and a wind power prediction module, wherein the data extraction module is used for obtaining a plurality of preliminary samples; the data preprocessing module is used for preprocessing the data of the preliminary sample and determining a training sample according to the preprocessed data; the training module is used for optimizing parameters of the support vector machine by adopting an improved particle swarm algorithm, and training the support vector machine by adopting a training sample and the optimized parameters of the support vector machine to obtain a support vector machine model; the wind power prediction module is used for predicting wind power by adopting the obtained support vector machine model and outputting a wind power prediction result. The method has the advantages of simple and practical modeling process, capability of quickly and effectively predicting the wind power, great significance for the safety, stability and dispatching operation of the power system, and wide popularization and application value.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a wind power prediction system convenient for electric power scheduling.
Background
After the wind power plant is connected to a power grid, the economic dispatching and the safety and stability of a power system are seriously challenged. If the power of the wind power plant can be accurately and effectively predicted, the power dispatching department can timely and reasonably adjust the dispatching plan in advance according to the output change condition of the wind power plant. Therefore, adverse effects of wind power integration on a power grid are reduced, the reserve capacity of the system is reduced, and the operation cost of the wind power integration is integrally reduced.
Disclosure of Invention
In order to solve the problems, the invention provides a wind power prediction system convenient for power scheduling.
The purpose of the invention is realized by adopting the following technical scheme:
the wind power prediction system convenient for power scheduling comprises a data extraction module, a data preprocessing module, a training module and a wind power prediction module, wherein the data extraction module is used for extracting data from a numerical weather forecast system or a related data acquisition and monitoring control system of a power system to obtain a plurality of preliminary samples; the data preprocessing module is used for preprocessing the data of the preliminary sample and determining a training sample according to the preprocessed data; the training module is used for optimizing parameters of the support vector machine by adopting an improved particle swarm algorithm, and training the support vector machine by adopting a training sample and the optimized parameters of the support vector machine to obtain a support vector machine model; the wind power prediction module is used for predicting wind power by adopting the obtained support vector machine model and outputting a wind power prediction result.
The invention has the beneficial effects that: the modeling process is simple and practical, the wind power prediction can be rapidly and effectively carried out, the method has important significance for the safety, stability and dispatching operation of the power system, and the method has wide popularization and application values.
Drawings
The invention is further illustrated by means of the attached drawings, but the embodiments in the drawings do not constitute any limitation to the invention, and for a person skilled in the art, other drawings can be obtained on the basis of the following drawings without inventive effort.
FIG. 1 is a block diagram of the structural connections of the present invention;
FIG. 2 is a block diagram of the structural connections of the data pre-processing module of the present invention.
Reference numerals:
the system comprises a data extraction module 1, a data preprocessing module 2, a training module 3, a wind power prediction module 4, a sample processing unit 10 and a data screening unit 20.
Detailed Description
The invention is further described with reference to the following examples.
Referring to fig. 1, the wind power prediction system convenient for power scheduling provided by this embodiment includes a data extraction module 1, a data preprocessing module 2, a training module 3, and a wind power prediction module 4, where the data extraction module 1 is configured to extract data from a numerical weather forecast system or a related data acquisition and monitoring control system of a power system to obtain a plurality of preliminary samples; the data preprocessing module 2 is used for preprocessing the data of the preliminary sample and determining a training sample according to the preprocessed data; the training module 3 is used for optimizing parameters of the support vector machine by adopting an improved particle swarm algorithm, and training the support vector machine by adopting a training sample and the optimized parameters of the support vector machine to obtain a support vector machine model; and the wind power prediction module 4 is used for predicting wind power by adopting the obtained support vector machine model and outputting a wind power prediction result.
Preferably, the extracted data comprises wind speed and temperature and wind farm measured output power data, the wind speed and the temperature are used as input data of the training sample of the support vector machine, and the wind farm measured output power data is used as output data of the training sample of the support vector machine.
Preferably, when the obtained support vector machine model is used for wind power prediction, the real-time wind speed and the real-time temperature are used as input of prediction.
The embodiment of the invention has strong adaptability, can be used as a power prediction model of a general wind power plant, has simple and practical modeling process, can quickly and effectively predict the wind power, has important significance for the safety, stability and dispatching operation of a power system, and has wide popularization and application values.
Preferably, as shown in fig. 2, the data preprocessing module 2 includes a sample processing unit 10 for performing a screening process on a preliminary sample, and a data screening unit 20 for performing a screening process on data in the screened preliminary sample;
the sample processing unit 10 is used for screening and processing the primary sample, and specifically comprises:
(1) and (3) calculating the mahalanobis distance between the primary samples:
wherein
In the formula, phi (x)A,xB) Representing a preliminary sample xAAnd the preliminary sample xBThe mahalanobis distance between them,
representing a preliminary sample xAA data and a preliminary sample x ofBMahalanobis distance between, sqrt represents the square root of the kelvin,
is that
The transpose of (a) is performed,
is a preliminary sample xBMean value data of SB -1Representing a preliminary sample xBCovariance matrix of (W)aRepresenting a preliminary sample xAThe number of data of (a);
(2) if the following screening formula is satisfied, the preliminary sample x is deletedA：
Where ρ is1、ρ2In order to adjust the factor for the set threshold,
is the average of the Mahalanobis distances between all preliminary samples, max Φ (x)A,xB) Min Φ (x) as the maximum value of the mahalanobis distance between all preliminary samplesA,xB) The minimum value of mahalanobis distance between all preliminary samples.
The preferred embodiment screens the primary samples with higher similarity, so that the training time of the support vector machine model can be reduced on the whole on the premise of ensuring that effective primary samples are reserved, and the efficiency of wind power prediction is improved.
Preferably, the data screening unit 20 performs the screening process on the data in the screened primary sample according to the following screening function:
Kα＝{Kα(β),Kα(β)＝1，β＝1,…,Wα}
wherein
In the formula, KαRepresenting the training sample, K, corresponding to the alpha-th preliminary sampleα(β) denotes the β -th data in the α -th preliminary sample, WαThe number of data that the alpha-th preliminary sample has; mu.sαExpected value, v, of data for the alpha-th preliminary sampleαIs the standard deviation, η, of the data of the alpha-th preliminary sample1、η2Is a set adjustment factor; f [ x ]]For the decision function, when x is equal to or greater than 0, f [ x ]]When x is 1<At 0, f [ x ]]＝0。
The optimal embodiment can optimize data in the preliminary sample, so that the optimized preliminary sample is adopted to train the support vector machine, on one hand, the training time of the support vector machine model is reduced, on the other hand, a more accurate training effect can be obtained, the prediction precision of the power of the wind power plant can be improved, and the prediction result of the power of the wind power plant with higher precision can be obtained.
Preferably, the optimizing the parameters of the support vector machine by using the improved particle swarm algorithm specifically includes:
(1) the kernel function defining the support vector machine is:
Γ＝ε2xTxα+(1-ε2)exp(g‖x-xα‖2)
in which ε is a weight coefficient, xTxαFor a linear kernel function, exp (g | x-x)α‖2) Is a gaussian kernel function, where g is the width of the gaussian kernel function.
(2) Taking three parameters of a support vector regression penalty coefficient C, a kernel function width g and a weight coefficient delta as parameters to be optimized, and setting the parameters to be optimized as particles in the particle swarm;
(3) and optimizing the parameters to be optimized by adopting an improved particle swarm algorithm.
In the preferred embodiment, the linear kernel function and the Gaussian kernel function are correspondingly combined to be used as a final kernel function, and three parameters of a support vector regression penalty coefficient C, a kernel function width g and a weight coefficient delta are optimized, so that a preliminary sample can be better expressed in a high-dimensional feature space;
in addition, in the preferred embodiment, the optimized parameters are not many, the training process of the support vector machine is simpler compared with other multi-core functions, and the trained support vector machine has better regression precision and generalization capability, so that the prediction precision of the support vector machine model can be improved, and a more excellent wind power prediction effect can be obtained.
Preferably, the parameters to be optimized are optimized by using an improved particle swarm algorithm, specifically:
1) initializing a particle swarm algorithm, setting the number of particles, the iteration times, the learning factor and the simulated annealing coefficient, selecting an orthogonal test design table, setting the search ranges of three parameters of a support vector regression penalty coefficient C, a kernel function width g and a weight coefficient delta and the upper and lower limits of the moving speed, wherein the list number of the orthogonal test design table is greater than the dimension of the particles;
2) calculating the speed of each particle, judging whether the speed of each particle is out of range, and taking the speed of the particle as a critical value if the speed of each particle is out of range;
3) the position of each particle is updated and each particle is evaluated for fitness as calculated by the fitness function:
in the formula, WtFor the total number of training samples, YkFor training the actual value of the sample, Yk' is a training sample prediction value;
4) selecting corresponding dimensions from the optimal particles and the suboptimal particles according to an orthogonal test table, performing an orthogonal test, and evaluating each test particle;
5) designing a final particle and evaluating the particle according to the quality of the factor level in each dimension;
6) selecting the particles with the highest fitness from the final particles and the test particles, comparing the particles with the group history optimal particles, replacing the group history optimal particles if the particles are superior to the group history optimal particles, and carrying out simulated annealing search with a certain probability;
7) and if the maximum iteration times is reached, ending the search and outputting the optimal particles and the power supply circuit function values of the optimal particles.
The optimal embodiment adopts a mode of combining the orthogonal test and the simulated annealing search to optimize parameters, solves the problems of precocity and convergence oscillation existing in the traditional particle swarm optimization, and enhances the capability of the group optimal particles to jump out of local optimal points;
in addition, the preferred embodiment effectively extracts valuable information from the optimal particles and the suboptimal particles in the cluster by adopting the orthogonal test, can improve the performance of the particle swarm algorithm in the aspects of searching the average value, the standard deviation, the evaluation times, the success rate, the success performance and the like of the results, and greatly reduces the operation amount of information extraction compared with the traditional orthogonal particle swarm algorithm by adopting the orthogonal test in the preferred embodiment.
Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the protection scope of the present invention, although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (7)
1. A wind power prediction system convenient for power scheduling is characterized by comprising a data extraction module, a data preprocessing module, a training module and a wind power prediction module, wherein the data extraction module is used for extracting data from a numerical weather forecast system or a related data acquisition and monitoring control system of a power system to obtain a plurality of preliminary samples; the data preprocessing module is used for preprocessing the data of the preliminary sample and determining a training sample according to the preprocessed data; the training module is used for optimizing parameters of the support vector machine by adopting an improved particle swarm algorithm, and training the support vector machine by adopting a training sample and the optimized parameters of the support vector machine to obtain a support vector machine model; the wind power prediction module is used for predicting wind power by adopting the obtained support vector machine model and outputting a wind power prediction result;
the optimization of the parameters of the support vector machine by adopting the improved particle swarm optimization specifically comprises the following steps:
(1) the kernel function defining the support vector machine is:
Γ＝ε2xTxα+(1-ε2)exp(g||x-xα||2)
in which ε is a weight coefficient, xTxαFor linear kernel functions, exp (g | | x-x)α||2) Is a gaussian kernel function, where g is the width of the gaussian kernel function;
(2) taking three parameters of a support vector regression penalty coefficient C, a Gaussian kernel function width g and a weight coefficient epsilon as parameters to be optimized, and setting the parameters to be optimized as particles in the particle swarm;
(3) optimizing the parameters to be optimized by adopting an improved particle swarm algorithm;
the optimization of the parameters to be optimized by adopting the improved particle swarm optimization specifically comprises the following steps:
1) initializing a particle swarm algorithm, setting the number of particles, the iteration times, the learning factor and the simulated annealing coefficient, selecting an orthogonal test design table, setting the search ranges of three parameters of a support vector regression penalty coefficient C, a Gaussian kernel function width g and a weight coefficient epsilon and the upper and lower limits of the moving speed, wherein the list number of the orthogonal test design table is greater than the dimension of the particles;
2) calculating the speed of each particle, judging whether the speed of each particle is out of range, and taking the speed of the particle as a critical value if the speed of each particle is out of range;
3) the position of each particle is updated and each particle is evaluated for fitness as calculated by the fitness function:
in the formula, WtFor the total number of training samples, YkFor the k-th training sample actual value, Yk' is the k-th training sample prediction value;
4) selecting corresponding dimensions from the optimal particles and the suboptimal particles according to an orthogonal test table, performing an orthogonal test, and evaluating each test particle;
5) designing a final particle and evaluating the final particle according to the quality of the factor level in each dimension;
6) selecting the particles with the highest fitness from the final particles and the test particles, comparing the particles with the group history optimal particles, replacing the group history optimal particles if the particles are superior to the group history optimal particles, and carrying out simulated annealing search with a certain probability;
7) and if the maximum iteration times is reached, ending the search and outputting the optimal particles and the power supply circuit function values of the optimal particles.
2. The wind power prediction system convenient for power dispatching of claim 1, wherein the extracted data comprises wind speed, temperature and wind farm measured output power data, the wind speed and the temperature are used as input data of the training sample of the support vector machine, and the wind farm measured output power data is used as output data of the training sample of the support vector machine.
3. The wind power prediction system convenient for power scheduling of claim 2, wherein when the obtained support vector machine model is used for wind power prediction, real-time wind speed and real-time temperature are used as prediction input.
4. The wind power prediction system facilitating power dispatching of claim 3, wherein the data preprocessing module comprises a sample processing unit for performing screening processing on the preliminary samples and a data screening unit for performing screening processing on data in the screened preliminary samples.
5. The wind power prediction system convenient for power dispatching of claim 4, wherein the data preprocessing module comprises a sample processing unit and a data screening unit, the sample processing unit is used for screening the primary samples, the data screening unit is used for screening the data in the remaining primary samples after screening processing, and constructing the screened data into corresponding training samples.
6. The wind power prediction system convenient for power scheduling according to claim 5, wherein the sample processing unit is configured to perform screening processing on the preliminary sample, specifically:
(1) and (3) calculating the mahalanobis distance between the primary samples:
wherein
In the formula, phi (x)A，xB) Representing a preliminary sample xAAnd the preliminary sample xBThe mahalanobis distance between them,
representing a preliminary sample xAAnd the alpha data of (2) and the preliminary sample xBMahalanobis distance between, sqrt represents the square root of the kelvin,
is that
The transpose of (a) is performed,
is a preliminary sample xBMean value data of SB -1Representing a preliminary sample xBCovariance matrix of (W)αRepresenting a preliminary sample xAThe number of data of (a);
(2) if the following screening formula is satisfied, the preliminary sample x is deletedA：
Where ρ is1、ρ2In order to adjust the factor for the set threshold,
is the average of the Mahalanobis distances between all preliminary samples, max Φ (x)A，xB) Min Φ (x) as the maximum value of the mahalanobis distance between all preliminary samplesA，xB) The minimum value of mahalanobis distance between all preliminary samples.
7. The wind power prediction system facilitating power dispatching of claim 5, wherein the data screening unit performs the screening process on the data in the screened preliminary sample according to the following screening function:
Kα＝{Kα(β)，Kα(β)＝1，β＝1，...，Wα}
wherein
In the formula, KαRepresenting the training sample, K, corresponding to the alpha-th preliminary sampleα(β) denotes the β -th data in the α -th preliminary sample, WαThe number of data that the alpha-th preliminary sample has; mu.sαExpected value, v, of data for the alpha-th preliminary sampleαIs the standard deviation, η, of the data of the alpha-th preliminary sample1、η2Is a set adjustment factor; f [ x ]]For the decision function, when x is equal to or greater than 0, f [ x ]]1, when x < 0, f [ x [ ]]＝0。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710190235.5A CN106960260B (en) | 2017-03-27 | 2017-03-27 | Wind power prediction system convenient for power dispatching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710190235.5A CN106960260B (en) | 2017-03-27 | 2017-03-27 | Wind power prediction system convenient for power dispatching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106960260A CN106960260A (en) | 2017-07-18 |
| CN106960260B true CN106960260B (en) | 2021-05-18 |
Family
ID=59471742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710190235.5A Active CN106960260B (en) | 2017-03-27 | 2017-03-27 | Wind power prediction system convenient for power dispatching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106960260B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108549220A (en) * | 2018-03-29 | 2018-09-18 | 广东电网有限责任公司电力调度控制中心 | Coal unit operating status real time evaluating method and its system |
| CN113239638A (en) * | 2021-06-29 | 2021-08-10 | 百维金科(上海)信息科技有限公司 | Overdue risk prediction method for optimizing multi-core support vector machine based on dragonfly algorithm |
| CN116266258B (en) * | 2022-12-15 | 2024-07-23 | 天津大学 | Wind farm arrangement and yaw control method and electronic equipment |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567636B (en) * | 2011-12-27 | 2015-01-07 | 华北电力大学 | High-precision wind electric field power interval forecasting method based on relevance vector machine |
| CN103942620A (en) * | 2014-04-18 | 2014-07-23 | 国家电网公司 | Wind power short-term prediction method using composite data source based on radial basis kernel function support vector machine |
| CN104834981B (en) * | 2015-05-27 | 2018-10-26 | 国家电网公司 | The main cause of short-term power station photovoltaic power implies type prediction technique |
| EP3106133B1 (en) * | 2015-06-19 | 2018-01-31 | Georg-August-Universität Göttingen Stiftung Öffentlichen Rechts Universitätsmedizin | Powered, multi-functional limb movement auxiliary device, particularly prosthesis and movement-assisting orthosis, with combined estimation regimes |
| CN106529706A (en) * | 2016-10-25 | 2017-03-22 | 国家电网公司 | Support-vector-machine-regression-based method for predicting wind speed of wind power plant |
| CN106503867A (en) * | 2016-11-14 | 2017-03-15 | 吉林大学 | A kind of genetic algorithm least square wind power forecasting method |
-
2017
- 2017-03-27 CN CN201710190235.5A patent/CN106960260B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106960260A (en) | 2017-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018045642A1 (en) | A bus bar load forecasting method | |
| CN107766990B (en) | Method for predicting power generation power of photovoltaic power station | |
| CN106447098B (en) | Photovoltaic ultra-short-term power prediction method and device | |
| CN107506865B (en) | Load prediction method and system based on LSSVM optimization | |
| CN109376772B (en) | Power load combination prediction method based on neural network model | |
| CN110705789A (en) | Photovoltaic power station short-term power prediction method | |
| CN106251001A (en) | A kind of based on the photovoltaic power Forecasting Methodology improving fuzzy clustering algorithm | |
| CN114792156B (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
| CN111008504B (en) | Wind power prediction error modeling method based on meteorological pattern recognition | |
| CN109492748B (en) | Method for establishing medium-and-long-term load prediction model of power system based on convolutional neural network | |
| CN106960260B (en) | Wind power prediction system convenient for power dispatching | |
| CN115099296A (en) | Sea wave height prediction method based on deep learning algorithm | |
| CN109376911A (en) | A kind of micro-capacitance sensor short-term load forecasting method based on EMD-KELMs-SDPSO | |
| CN115759389A (en) | Day-ahead photovoltaic power prediction method based on weather type similar day combination strategy | |
| CN115358437A (en) | Power supply load prediction method based on convolutional neural network | |
| CN113487064A (en) | Photovoltaic power prediction method and system based on principal component analysis and improved LSTM | |
| CN117151770A (en) | Attention mechanism-based LSTM carbon price prediction method and system | |
| CN112836876A (en) | Power distribution network line load prediction method based on deep learning | |
| CN112288157A (en) | Wind power plant power prediction method based on fuzzy clustering and deep reinforcement learning | |
| CN115860190A (en) | Training of load detection model, method for detecting power load and related device | |
| CN110991743B (en) | Wind power short-term combination prediction method based on cluster analysis and neural network optimization | |
| CN115330130A (en) | Agricultural park comprehensive energy system evaluation method based on improved AHP-CRITIC | |
| CN110570042A (en) | Short-term electric vehicle charging load prediction method and system | |
| CN113222281A (en) | Power distribution network short-term load prediction method and device based on improved AlexNet-GRU model | |
| CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210421 Address after: 264200 No.1 Zhengqi Road, Weihai Industrial New Area, Shandong Province Applicant after: Guodian Weihai Wind Power Co.,Ltd. Address before: Room 809, Chuangsheng Building, Sunshine Industrial Zone, Xili Street, Nanshan District, Shenzhen City, Guangdong Province Applicant before: SHENZHEN HUICHUANG LIANHE AUTOMATION CONTROL Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |