CN117993616A - Carbon emission data analysis management method, device, equipment and storage medium - Google Patents
Carbon emission data analysis management method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117993616A CN117993616A CN202410168843.6A CN202410168843A CN117993616A CN 117993616 A CN117993616 A CN 117993616A CN 202410168843 A CN202410168843 A CN 202410168843A CN 117993616 A CN117993616 A CN 117993616A
- Authority
- CN
- China
- Prior art keywords
- data
- cleaning
- carbon emission
- monitoring
- result
- 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.)
- Pending
Links
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 155
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 155
- 238000007726 management method Methods 0.000 title claims abstract description 103
- 238000007405 data analysis Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 40
- 238000004140 cleaning Methods 0.000 claims abstract description 233
- 238000012544 monitoring process Methods 0.000 claims abstract description 149
- 238000004458 analytical method Methods 0.000 claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000012795 verification Methods 0.000 claims description 44
- 230000002159 abnormal effect Effects 0.000 claims description 41
- 238000012545 processing Methods 0.000 claims description 25
- 238000005070 sampling Methods 0.000 claims description 25
- 230000003044 adaptive effect Effects 0.000 claims description 19
- 230000009467 reduction Effects 0.000 claims description 16
- 230000007246 mechanism Effects 0.000 claims description 13
- 230000005856 abnormality Effects 0.000 claims description 11
- 238000000513 principal component analysis Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 8
- 238000012300 Sequence Analysis Methods 0.000 claims description 7
- 230000004807 localization Effects 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 3
- 238000013523 data management Methods 0.000 abstract description 10
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 14
- 230000008569 process Effects 0.000 description 11
- 238000001514 detection method Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 229910002092 carbon dioxide Inorganic materials 0.000 description 7
- 239000001569 carbon dioxide Substances 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 7
- 238000013524 data verification Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000002547 anomalous effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- 230000003442 weekly effect Effects 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of carbon emission, and discloses a carbon emission data analysis and management method, a device, equipment and a storage medium, wherein the method comprises the following steps: configuring a data acquisition layer according to the extracted regional characteristic data of the region to be monitored; reading a monitoring data set of the data acquisition layer and establishing monitoring association nodes; the same node data time sequence of the monitoring data set is cleaned to generate a first cleaning result; configuring association delay by monitoring association nodes, and generating a second cleaning result based on the association delay and the first cleaning result association cleaning; and inputting the second cleaning result into the intelligent analysis model to perform carbon emission analysis management. According to the invention, the accuracy and consistency of the data can be ensured by configuring the associated time delay, the condition that the traditional carbon emission data management adopts centralized storage is avoided, and finally, the second cleaning result is input into the intelligent analysis model to execute carbon emission analysis management, so that the problem of poor reliability and safety of the carbon emission data is solved, and the efficient management of the carbon emission data is realized.
Description
Technical Field
The present invention relates to the field of carbon emission technologies, and in particular, to a method, an apparatus, a device, and a storage medium for analyzing and managing carbon emission data.
Background
Today, one of the increasingly serious environmental challenges facing the world is the problem of carbon emissions. The large amount of carbon emissions has a great influence on climate change and an ecological system, so that measures are taken in various countries to limit and manage the carbon emissions. However, due to factors such as wide monitoring area, huge data volume, high complexity, etc., how to efficiently monitor, collect, clean, store and analyze carbon emission data becomes a technical problem that needs to be solved urgently.
In the traditional carbon emission data management method, the source and the accuracy of data are often difficult to ensure, and a centralized data storage and management mode is adopted, so that the data are easy to tamper or operate. In addition, the analysis and management of data is complicated by the problems of asymmetry and insufficient transparency of the information caused by the relative difficulty in data sharing and communication between the participants.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a carbon emission data analysis and management method, a device, equipment and a storage medium, and aims to solve the technical problems of poor reliability and safety of carbon emission data due to the adoption of a centralized data storage and management mode in the traditional carbon emission data management method.
In order to achieve the above object, the present invention provides a carbon emission data analysis and management method, the method comprising the steps of:
Extracting regional characteristic data of a region to be monitored, and configuring a data acquisition layer based on the regional characteristic data;
Reading a monitoring data set of the data acquisition layer through a data set interface, and establishing a monitoring association node based on the monitoring data set;
Performing time sequence cleaning on the same node data of the monitoring data set through a first self-adaptive cleaning window and a second self-adaptive cleaning window to generate a first cleaning result;
Configuring association delay through the monitoring association node, and performing association cleaning based on the association delay and the first cleaning result to generate a second cleaning result;
And inputting the second cleaning result into an intelligent analysis model to execute carbon emission analysis management.
Optionally, the performing time sequence cleaning on the same node data of the monitoring data set through a first adaptive cleaning window and a second adaptive cleaning window, before generating the first cleaning result, further includes:
analyzing the node data in the monitoring data set to obtain the fluctuation time sequence of the node data;
Performing abnormal positioning on the node data to generate an abnormal positioning result;
establishing positioning association according to the fluctuation time sequence and the abnormal positioning result;
And constructing a first self-adaptive cleaning window and a second self-adaptive cleaning window based on the generation constraint and a window construction decision network by taking the positioning association as the generation constraint.
Optionally, the performing exception positioning on the node data, and generating an exception positioning result includes:
Invoking historical monitoring data of the monitoring associated node;
Performing time period segmentation based on the historical monitoring data to obtain a steady-state average value of the monitoring associated nodes in each time period;
And carrying out abnormal positioning on the node data through the steady-state mean value to obtain an abnormal positioning result.
Optionally, the configuring, by the monitoring association node, association delay, and performing association cleaning based on the association delay and the first cleaning result, to generate a second cleaning result, includes:
Taking the processing delay between the monitoring association nodes as association delay, and constructing carbon emission monitoring association according to the monitoring association nodes;
Performing time sequence backtracking on node data in the monitoring data set based on the associated delay to obtain a time sequence backtracking result;
carrying out random point sampling on the time sequence backtracking result to obtain an average error associated with the carbon emission monitoring;
and performing associated cleaning on the first cleaning result according to the average error to generate a second cleaning result.
Optionally, the performing random point sampling on the time sequence backtracking result to obtain an average error associated with the carbon emission monitoring includes:
Carrying out random point sampling on the time sequence backtracking result to obtain random sampling point data;
Calculating single-point errors of the random sampling point data, and constructing a single-point error set based on the single-point errors;
error clustering is carried out on the single-point error set, and a maximum error clustering group is obtained;
and obtaining a cluster mean value of the maximum error cluster group, and taking the cluster mean value as an average error associated with the carbon emission monitoring.
Optionally, the inputting the second cleaning result to the intelligent analysis model to perform carbon emission analysis management includes:
Storing the second cleaning result to N storage devices, and establishing a consistency verification mechanism;
When the second cleaning result has data abnormality or triggers a preset verification period, carrying out consensus verification on the N storage devices through a consistency verification mechanism to obtain a consensus verification result;
Updating the data in the N storage devices according to the consensus verification result;
And inputting the updated second cleaning result into the intelligent analysis model, and executing carbon emission analysis management.
Optionally, inputting the updated second cleaning result to the intelligent analysis model, and performing carbon emission analysis management, including:
performing time sequence analysis on source characteristics corresponding to the monitoring data set to obtain a time sequence principal component analysis result;
performing dimension reduction processing on the updated second cleaning result according to the time sequence principal component analysis result to obtain a dimension reduction processing result;
and inputting the dimension reduction processing result into an intelligent analysis model, and executing carbon emission analysis management.
In addition, in order to achieve the above object, the present invention also provides a carbon emission data analysis management apparatus, the apparatus comprising:
The data extraction module is used for extracting regional characteristic data of a region to be monitored and configuring a data acquisition layer based on the regional characteristic data;
The data set establishing module is used for reading a monitoring data set of the data acquisition layer through a data set interface and establishing a monitoring association node based on the monitoring data set;
The time sequence cleaning module is used for performing time sequence cleaning on the same node data of the monitoring data set through a first self-adaptive cleaning window and a second self-adaptive cleaning window to generate a first cleaning result;
The association configuration module is used for configuring association delay through the monitoring association node, carrying out association cleaning based on the association delay and the first cleaning result, and generating a second cleaning result;
and the verification analysis module is used for inputting the second cleaning result into the intelligent analysis model to execute carbon emission analysis management.
In addition, in order to achieve the above object, the present invention also proposes a carbon emission data analysis management apparatus comprising: a memory, a processor, and a carbon emission data analysis management program stored on the memory and executable on the processor, the carbon emission data analysis management program configured to implement the steps of the carbon emission data analysis management method as described above.
In addition, in order to achieve the above object, the present invention also proposes a storage medium having stored thereon a carbon emission data analysis management program which, when executed by a processor, implements the steps of the carbon emission data analysis management method as described above.
Firstly, extracting regional characteristic data of a region to be monitored, and configuring a data acquisition layer based on the regional characteristic data; then, a monitoring data set of the data acquisition layer is read through a data set interface, and monitoring association nodes are established based on the monitoring data set; then, carrying out time sequence cleaning on the same node data of the monitoring data set through a first self-adaptive cleaning window and a second self-adaptive cleaning window to generate a first cleaning result; configuring association delay through the monitoring association node, and performing association cleaning based on the association delay and the first cleaning result to generate a second cleaning result; and finally, inputting the second cleaning result into an intelligent analysis model to execute carbon emission analysis management. According to the invention, due to configuration of the associated time delay, the accuracy and consistency of the data can be ensured, the condition that the traditional carbon emission data management adopts centralized storage and management is avoided, and finally, the second cleaning result is input into the intelligent analysis model to execute carbon emission analysis management, so that the problem of poor reliability and safety of the carbon emission data is solved, and the efficient management of the carbon emission data is realized.
Drawings
FIG. 1 is a schematic diagram of a carbon emission data analysis management device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of a carbon emission data analysis and management method according to the present invention;
FIG. 3 is a block chain based overall flowchart of a first embodiment of a carbon emission data analysis and management method according to the present invention;
FIG. 4 is a flowchart of a second embodiment of a carbon emission data analysis and management method according to the present invention;
FIG. 5 is a flowchart illustrating a third embodiment of a carbon emission data analysis and management method according to the present invention;
fig. 6 is a block diagram showing the structure of a first embodiment of the carbon emission data analysis management apparatus of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a carbon emission data analysis management apparatus of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the carbon emission data analysis management apparatus may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the carbon emission data analysis management apparatus, and may include more or fewer components than shown, or certain components may be combined, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a carbon emission data analysis management program may be included in the memory 1005 as one type of storage medium.
In the carbon emission data analysis management apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the carbon emission data analysis management apparatus of the present invention may be provided in the carbon emission data analysis management apparatus, which calls the carbon emission data analysis management program stored in the memory 1005 through the processor 1001 and performs the carbon emission data analysis management method provided by the embodiment of the present invention.
An embodiment of the present invention provides a carbon emission data analysis and management method, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the carbon emission data analysis and management method of the present invention.
In this embodiment, the carbon emission data analysis and management method includes the steps of:
Step S10: and extracting regional characteristic data of the region to be monitored, and configuring a data acquisition layer based on the regional characteristic data.
It should be noted that, the execution body of the method of the present embodiment may be a computing service device, such as a personal computer, a server, etc., with data monitoring, node association, and data cleaning functions, or may be other electronic devices, such as the above-mentioned carbon emission data analysis management device, which can implement the same or similar functions, and the present embodiment is not limited thereto. Here, the present embodiment and the following embodiments will be specifically described with the above-described carbon emission data analysis management apparatus (simply referred to as management apparatus).
It is understood that the area to be monitored is an area that manages carbon emissions monitored by the equipment. Regional characteristic data is various characteristic information collected from the region to be monitored, such as geographic location, land use type, climate conditions, vegetation cover, soil quality, and the like. By means of the regional characteristic data, subsequent data acquisition and analysis can be facilitated.
It should be understood that the data acquisition layer is a module for acquiring data about carbon emission in the regional characteristic data, and the data acquisition layer may include a carbon metering device, a carbon dioxide monitoring device, a carbon data acquisition device, and the like, which is not limited in this embodiment. Through the data acquisition layer, data about carbon emissions can be monitored and acquired in real time.
The carbon metering device can be used for measuring and recording the carbon emission of the area to be monitored, and accurate carbon emission data can be obtained according to different measuring principles and methods (such as a mass method, an energy method, a gas flow method and the like). The carbon dioxide monitoring device can be used for monitoring the carbon dioxide concentration of the area to be monitored in real time so as to monitor and record the change condition of the carbon dioxide in time. The carbon data acquisition equipment can be used for acquiring and transmitting the monitored data, and the data are transmitted to a data center or a cloud platform of the management equipment in a wireless sensor network, an internet of things technology and the like so as to carry out subsequent data analysis and processing.
In a specific implementation, the management device may first extract regional characteristic data of the region to be monitored, such as a geographic location, a land use type, a climate condition, a vegetation cover, a soil quality, and the like, and configure the data acquisition layer based on the regional characteristic data. And through a data acquisition layer, monitoring and acquiring data related to carbon emission in real time.
Step S20: and reading a monitoring data set of the data acquisition layer through a data set interface, and establishing a monitoring association node based on the monitoring data set.
It should be noted that the data set interface is an interface corresponding to the data collected by the data collection layer. The data set interface may be connected to the carbon metering device, the carbon dioxide monitoring device and the carbon data acquisition device to obtain data on carbon emissions in real time.
It is understood that the monitoring dataset is data read from the data acquisition layer through the dataset interface, such as information of time stamp, location, carbon emission, carbon dioxide concentration, etc. of the data.
In the process of establishing the monitoring association node, for each data point of the monitoring data set, a node association may be established according to the source and the monitoring node to which the node belongs, and a unique identifier may be assigned to each monitoring node and associated with the data point. Specifically, a time stamp may be used to assign a unique identifier to the data points, with a timing identifier being added to each data point for subsequent timing cleaning.
In a specific implementation, the management device may read the monitoring dataset of the data acquisition layer through the dataset interface, and for each data point of the monitoring dataset, a unique identifier may be assigned to each monitoring node according to its source and the monitoring node to which it belongs, and the identifier may be associated with the data point to establish a monitoring association node.
Step S30: and carrying out time sequence cleaning on the same node data of the monitoring data set through a first self-adaptive cleaning window and a second self-adaptive cleaning window to generate a first cleaning result.
The first adaptive cleaning window and the second adaptive cleaning window are windows for cleaning data of the monitoring data set. When the same node data is analyzed, the sizes of the first self-adaptive cleaning window and the second self-adaptive cleaning window can be determined first, and the first self-adaptive cleaning window is ensured to be larger than the second self-adaptive cleaning window. The first adaptive cleaning window is typically used on a longer time scale, such as a month or quarter, for detecting and cleaning anomalous data over a longer time frame. While a second adaptive wash window is typically used on a shorter time scale, such as one day or one week, for detecting and washing anomalous data over a shorter time frame.
It can be appreciated that the process of performing time sequence cleaning on the same node data by using the first adaptive cleaning window and the second adaptive cleaning window can be specifically: the method comprises the steps of firstly setting the length of a first self-adaptive cleaning window, sliding according to the length of the first self-adaptive cleaning window aiming at data of each node, and sequentially detecting and cleaning abnormality of the data in each window. The data within each window is anomaly detected using a suitable anomaly detection algorithm, such as a statistical or machine learning based method. Data points outside the normal range are identified and marked as outliers. Setting the length of a second self-adaptive cleaning window, sliding the data of each node according to the length of the second self-adaptive cleaning window on the basis of the first cleaning result, and sequentially detecting and cleaning the abnormality of the data in each window. And (3) carrying out anomaly detection on the data in the second self-adaptive cleaning window by using the same anomaly detection algorithm, and identifying and marking the anomaly value. Finally, the data cleaning results passing through the two cleaning windows are combined, and a first cleaning result is generated.
In a specific implementation, the management device may perform timing sequence identification of the same node data of the monitoring dataset, and perform timing sequence cleaning of the same node data through the first adaptive cleaning window and the second adaptive cleaning window, so as to generate a first cleaning result.
Step S40: and configuring association delay through the monitoring association node, and performing association cleaning based on the association delay and the first cleaning result to generate a second cleaning result.
It should be noted that the association delay refers to a time window in which data from different nodes can be regarded as data associated with each other.
The configuration association delay can be set according to the correlation among nodes, the position, the signal transmission mode and other factors, and can also be adjusted according to the signal transmission distance, the delay and other factors.
It is understood that the associated cleaning process may be: according to the association delay, the data between the nodes can be verified, and the data between the nodes can be compared and matched by using technologies such as time sequence analysis or data mining. For example, data of one node may be used as a reference value and compared with data of other nodes to determine whether an outlier data point exists. If there are outlier data points, a cleaning process is required. If abnormal data points are found, the abnormal data points and other node data can be subjected to association cleaning according to association delay. For example, other node data associated with the abnormal data point can be found according to the time stamp of the abnormal data point, and the data can be cleaned. The cleaning method can adopt interpolation, smoothing or filtering and other technologies to reduce the influence of abnormal data points on data among nodes. And (3) according to the result of the associated cleaning, calculating the steady-state average value of the node data again, and performing the second cleaning. The same cleaning method can be adopted for the second cleaning, so that the accuracy and the reliability of the node data are further improved. And generating a second cleaning result according to the associated cleaning result.
In a specific implementation, the management device may configure association delay through the monitoring association node, perform data verification between nodes based on the association delay, perform association cleaning of the first cleaning result according to the data verification result, and generate the second cleaning result.
Step S50: and inputting the second cleaning result into an intelligent analysis model to execute carbon emission analysis management.
The intelligent analysis model is a model obtained through machine learning training, input data can be processed and analyzed through machine learning, data mining and other technologies, and information about carbon emission is extracted from the input data, wherein the information comprises indexes such as carbon emission, carbon footprint, carbon emission intensity and the like of different activities or processes.
It should be noted that, before the intelligent analysis model performs the carbon emission analysis management, the second cleaning result may be stored in the selected N storage devices. By adopting the distributed storage technology, the data are stored in different devices in a scattered way, so that the reliability and usability of the data are improved.
And in order to ensure consistency of the stored data, a consistency verification mechanism can be established. The consistency of the data is verified by periodically comparing the data in the storage device. If an inconsistent condition is found, the data can be restored through data backup.
In a specific implementation, the management device may store the second cleaning result to N storage devices, and establish a consistency verification mechanism; and finally, inputting the second cleaning result into an intelligent analysis model, wherein the intelligent analysis model can execute a carbon emission analysis management task according to the input data.
Further, in the present embodiment, step S50 includes: storing the second cleaning result to N storage devices, and establishing a consistency verification mechanism; when the second cleaning result has data abnormality or triggers a preset verification period, carrying out consensus verification on the N storage devices through a consistency verification mechanism to obtain a consensus verification result; updating the data in the N storage devices according to the consensus verification result; and inputting the updated second cleaning result into the intelligent analysis model, and executing carbon emission analysis management.
It should be noted that, a preset verification period of data may be set in the management device first, that is, how often data verification is performed. The verification period may be set according to the actual situation, and the verification may be performed daily, weekly or monthly, which is not limited in this embodiment.
In a specific implementation, in a preset verification period, whether the data is abnormal or whether the preset verification period is reached can be monitored. If any data abnormality occurs or a preset verification period is reached, the next device data consensus verification is needed. The device data consensus verification is to ensure the consistency of the data by comparing and verifying the data in the N storage devices. In particular, a consensus algorithm may be selected, such as comparing data hash values in storage devices or using a distributed database for data consistency verification. And according to the result of the device data consensus verification, if the data in the storage devices are found to be inconsistent or abnormal, updating the storage data, and selecting to copy the correct data to all the storage devices or performing data repair operation. And finally, inputting the updated second cleaning result into the intelligent analysis model, and executing carbon emission analysis management.
Further, the inputting the updated second cleaning result to the intelligent analysis model in the embodiment, performing carbon emission analysis management, includes: performing time sequence analysis on source characteristics corresponding to the monitoring data set to obtain a time sequence principal component analysis result; performing dimension reduction processing on the updated second cleaning result according to the time sequence principal component analysis result to obtain a dimension reduction processing result; and inputting the dimension reduction processing result into an intelligent analysis model, and executing carbon emission analysis management.
It should be noted that, before performing the time-series principal component analysis, the source characteristics corresponding to the monitored data set need to be determined, including different activities or processes, such as production, transportation, supply chain, etc. Based on these features, the monitoring data sets may be categorized and grouped for better analysis and management.
It can be understood that the time sequence analysis is a multivariate statistical method, which can analyze the variation trend and periodicity in the time sequence data, thereby extracting the main variation direction and pattern. And (3) obtaining the main component and the contribution rate of each source characteristic through time sequence analysis. The information can be used for judging the importance and influence degree of the characteristics of different sources, and provides a basis for subsequent dimension reduction processing.
In particular implementations, the management device may analyze each source signature using a time-series principal component analysis technique. And then the second cleaning result is processed by using a dimension reduction technology. According to the result of the time sequence principal component analysis, a proper dimension reduction method and parameters can be selected to reduce the dimension of the data to a lower dimension. By the aid of the method, the data processing process can be simplified, and efficiency and accuracy are improved. And finally, inputting the dimension reduction processing result into an intelligent analysis model, and executing carbon emission analysis management.
For ease of understanding, in practical implementation, referring to fig. 3, fig. 3 is an overall block chain-based flowchart of a first embodiment of the carbon emission data analysis management method of the present invention. As shown in fig. 3, in order to perform carbon emission analysis management, first, region characteristic data of a region to be monitored needs to be extracted, and a data acquisition layer is configured according to the characteristics. The data acquisition layer comprises a carbon metering device, carbon dioxide monitoring equipment and carbon data acquisition equipment. And reading data of the data acquisition layer through the data set interface, and establishing a monitoring data set. Then, in the monitoring dataset, an association between monitoring nodes is established. After the node association is established, the same node data in the monitoring data set needs to be identified in time sequence. The data of the same node can be subjected to time sequence cleaning through the first self-adaptive cleaning window and the second self-adaptive cleaning window so as to remove abnormal values and error data and generate a more accurate and reliable first cleaning result. The two cleaning windows are constructed by analysis of the same node data, wherein the time range of the first cleaning window is larger than that of the second cleaning window. In order to ensure the accuracy and consistency of the data, the associated delay is configured and the data verification between the nodes is performed. And executing the associated cleaning of the first cleaning result according to the data verification result, and generating a second cleaning result. To ensure the security and reliability of the data, the KE stores the second cleaning results to the N storage devices and establishes a consistency verification mechanism to verify the integrity of the data. Finally, the stored second cleaning result is input to the intelligent analysis model to perform carbon emission analysis management. The technical problems of poor reliability and safety of carbon emission data in the prior art are solved, and the technical effect of high-efficiency management of the carbon emission data is realized.
The management device of the embodiment can firstly extract regional characteristic data of a region to be monitored, such as geographic position, land utilization type, climate condition, vegetation coverage, soil quality and the like, and configure a data acquisition layer based on the regional characteristic data. And through a data acquisition layer, monitoring and acquiring data related to carbon emission in real time. The monitoring data set of the data acquisition layer can then be read through the data set interface, and for each data point of the monitoring data set, a unique identifier can be assigned to each monitoring node according to the source and the monitoring node to which the monitoring data set belongs, and the identifier can be associated with the data point to establish a monitoring association node. Then, the time sequence identification of the same node data of the monitoring data set can be executed, and the time sequence cleaning of the same node data is carried out through the first self-adaptive cleaning window and the second self-adaptive cleaning window, so that a first cleaning result is generated. And configuring association delay through the monitoring association nodes, verifying data among the nodes based on the association delay, and executing association cleaning of the first cleaning result according to the data verification result to generate a second cleaning result. Finally, storing the second cleaning result to N storage devices, and establishing a consistency verification mechanism; and finally, inputting the second cleaning result into an intelligent analysis model, wherein the intelligent analysis model can execute a carbon emission analysis management task according to the input data. Because the embodiment can ensure the accuracy and consistency of the data by configuring the associated delay, the condition that the traditional carbon emission data management adopts centralized storage and management is avoided, and finally, the second cleaning result is input into the intelligent analysis model to execute the carbon emission analysis management, so that the problem of poor reliability and safety of the carbon emission data is solved, and the efficient management of the carbon emission data is realized.
Referring to fig. 2 and 4, fig. 4 is a flowchart illustrating a second embodiment of a carbon emission data analysis and management method according to the present invention.
Based on the first embodiment, in this embodiment, before step S30, the method further includes:
step S201: and analyzing the node data in the monitoring data set to obtain the fluctuation time sequence of the node data.
The fluctuation time sequence reflects the fluctuation condition of the node data in the monitoring data set. The trend analysis, the periodicity analysis, the outlier detection, etc. may be performed on the node data using a statistical method or a time series analysis, etc. to obtain the fluctuation timing of the node data, which is not limited in this embodiment.
Step S202: and carrying out abnormal positioning on the node data to generate an abnormal positioning result.
The abnormal location result is a result of identifying data points out of the normal range from the node data.
In a specific implementation, based on the fluctuation time sequence of the node data, a proper abnormality detection algorithm, such as a Z-score method, a box diagram method and the like, can be used for carrying out abnormality positioning on the node data. Data points outside the normal range are identified and marked as outliers. This can generate an outlier localization result that determines which data points need to be cleaned.
Step S203: and establishing positioning association according to the fluctuation time sequence and the abnormal positioning result.
In a specific implementation, the anomalous positioning results can be correlated with the timing of the fluctuations. For example, a correspondence relationship can be established with the fluctuation time sequence according to the timestamp of the abnormal positioning result so as to determine the position of the abnormal data point in the fluctuation time sequence.
Step S204: and constructing a first self-adaptive cleaning window and a second self-adaptive cleaning window based on the generation constraint and a window construction decision network by taking the positioning association as the generation constraint.
It should be noted that, the window construction decision network is a network that establishes decisions by splitting a problem into a plurality of time windows when performing decision analysis. The decision network may consider a number of factors, such as the number of outlier data points, periodicity of the fluctuation timing, etc., to trade off different cleaning effects.
It is understood that the generation constraint is a constraint that builds the first adaptive wash window and the second adaptive wash window. These constraints may be based on a time range of outlier data points, such as setting the length of the first adaptive wash window and the second adaptive wash window centered around the outlier data point, which is not limiting in this embodiment.
In a specific implementation, the management device may generate a generation constraint of the adaptive cleaning window according to the result of the positioning association. And constructing a decision network by generating a constraint input window, which is used for determining the specific setting of a final first self-adaptive cleaning window and a final second self-adaptive cleaning window, and finally completing the construction of the first self-adaptive cleaning window and the second self-adaptive cleaning window.
Further, in the present embodiment, step S202 includes: invoking historical monitoring data of the monitoring associated node; performing time period segmentation based on the historical monitoring data to obtain a steady-state average value of the monitoring associated nodes in each time period; and carrying out abnormal positioning on the node data through the steady-state mean value to obtain an abnormal positioning result.
It should be noted that, the historical monitoring data is the monitoring data after authentication in the monitoring associated node, so that the reliability and accuracy of the data can be ensured.
It will be appreciated that in the time period division, a suitable time period may be set according to specific data characteristics and monitoring requirements, for example, division in units of hours, days, weeks or months, which is not limited in this embodiment.
It should be understood that the steady state average is the average of the data in the normal range for each time period in the monitoring-associated node. When calculating the steady-state mean value, the steady-state mean value under each time period can be obtained by using methods such as mean value, median or quantile. These steady state averages may help identify node data within a normal range, facilitating subsequent anomaly detection.
In a specific implementation, the management device may perform anomaly location on the node data based on the steady-state average value, and may perform anomaly location on the node data using various anomaly detection algorithms, such as a method of Z-score, a box graph, and the like. Specifically, the node data can be compared with the steady-state average value of the time period to which the node data belongs, and whether the node data is abnormal or not is judged according to the size of the gap. Data points outside the normal range are identified and marked as outliers. This can generate an outlier localization result that determines which data points need to be cleaned.
In this embodiment, first, trend analysis, periodic analysis, abnormal value detection, etc. are performed on node data in the monitoring data set, so as to obtain a fluctuation time sequence of the node data. Then based on the fluctuation time sequence of the node data, a proper abnormality detection algorithm, such as a Z-score method, a box diagram method and the like, can be used for carrying out abnormality positioning on the node data. Data points outside the normal range are identified and marked as outliers. This can generate an outlier localization result that determines which data points need to be cleaned. The anomalous positioning results can then be correlated with the timing of the fluctuations. For example, a correspondence relationship can be established with the fluctuation time sequence according to the timestamp of the abnormal positioning result so as to determine the position of the abnormal data point in the fluctuation time sequence. Finally, generating a generation constraint of the self-adaptive cleaning window according to the positioning association result. And generating a constraint input window construction decision network for determining the specific settings of the final first self-adaptive cleaning window and the second self-adaptive cleaning window, thereby completing the construction of the first self-adaptive cleaning window and the second self-adaptive cleaning window. Therefore, the data of the same node can be subjected to time sequence cleaning through the first self-adaptive cleaning window and the second self-adaptive cleaning window so as to remove abnormal values and error data, and a more accurate and reliable first cleaning result is generated.
Referring to fig. 2 and 5, fig. 5 is a flowchart illustrating a third embodiment of a carbon emission data analysis and management method according to the present invention.
Based on the above embodiments, in this embodiment, the step S40 includes:
Step S41: and taking the processing delay between the monitoring association nodes as the association delay, and constructing a carbon emission monitoring association according to the monitoring association nodes.
It should be noted that the association delay is a delay time for processing data between the individual nodes. The processing delay between the nodes can be obtained by monitoring the time stamp information of the data to reflect the time difference between the node data for subsequent data analysis and cleaning.
It can be understood that the association relationship can be analyzed according to the monitoring association nodes to generate carbon emission monitoring association among the nodes.
In a specific implementation, the data of different nodes can be aligned by using the delay information of the associated delays, so that the data are consistent in time. Therefore, the relevance of the node data on the time sequence can be established, and the subsequent data analysis and cleaning are convenient.
Step S42: and carrying out time sequence backtracking on the node data in the monitoring data set based on the associated delay to obtain a time sequence backtracking result.
Step S43: and carrying out random point sampling on the time sequence backtracking result to obtain the average error associated with the carbon emission monitoring.
Step S44: and performing associated cleaning on the first cleaning result according to the average error to generate a second cleaning result.
It should be noted that the correlation cleaning may use interpolation, smoothing or filtering techniques to reduce the influence of the abnormal data on the carbon emission monitoring correlation, which is not limited in this embodiment.
In a specific implementation, the management device may utilize the associated delay to perform timing backtracking on the node data. According to the result of time sequence backtracking, random point sampling can be carried out, and average error related to carbon emission monitoring is calculated. The accuracy and reliability of the monitored data is assessed by comparing the differences between the actual measured values and the predicted values. And then, according to the average error, the associated cleaning of the first cleaning result can be completed. And finally, judging which node data are abnormal according to the error size, and performing corresponding cleaning treatment to generate a second cleaning result.
Further, in the present embodiment, step S43 includes: carrying out random point sampling on the time sequence backtracking result to obtain random sampling point data; calculating single-point errors of the random sampling point data, and constructing a single-point error set based on the single-point errors; error clustering is carried out on the single-point error set, and a maximum error clustering group is obtained; and obtaining a cluster mean value of the maximum error cluster group, and taking the cluster mean value as an average error associated with the carbon emission monitoring.
It should be noted that the single-point error is an error between the actual measured value and the predicted value obtained by calculation based on each random sampling point data.
It is understood that the maximum error cluster group is the cluster group having the maximum error value. Error clustering may be performed on a single point error set using a clustering algorithm (e.g., K-means). The purpose of clustering is to divide a single point error set into several groups for subsequent analysis and processing of errors of different groups. For all cluster groups, the cluster group with the largest error value may be found. For the maximum error cluster group, its cluster mean may be calculated. The cluster mean value reflects the average value of the single point errors of the group and is an important index for evaluating the accuracy and reliability of the monitored data.
In a specific implementation, after timing sequence backtracking is performed, the management device may perform random point sampling according to the timing sequence backtracking result, to obtain random sampling point data. For each random sample point, the error between its actual measured value and its predicted value (i.e., a single point error) can be calculated. The single-point errors are used as elements of a single-point error set to construct the single-point error set. And then taking the cluster mean value of the maximum error cluster group as an average error, and finishing the associated cleaning of the first cleaning result. By comparing the single-point error with the average error, abnormal data can be identified and cleaning treatment can be performed, so that the accuracy and reliability of the monitoring data can be improved.
The management device of the embodiment can align the data of different nodes by utilizing the delay information of the associated delay, so that the data of the different nodes are consistent in time. Therefore, the relevance of the node data on the time sequence can be established, and the subsequent data analysis and cleaning are convenient. And then, carrying out time sequence backtracking on the node data by utilizing the associated delay. According to the result of time sequence backtracking, random point sampling can be carried out, and average error related to carbon emission monitoring is calculated. The accuracy and reliability of the monitored data is assessed by comparing the differences between the actual measured values and the predicted values. And then, according to the average error, the associated cleaning of the first cleaning result can be completed. And finally, judging which node data are abnormal according to the error size, and performing corresponding cleaning treatment to generate a second cleaning result. Further, after the time sequence backtracking is performed, the management device can perform random point sampling according to the time sequence backtracking result to obtain random sampling point data. For each random sample point, the error between its actual measured value and its predicted value (i.e., a single point error) can be calculated. The single-point errors are used as elements of a single-point error set to construct the single-point error set. And then taking the cluster mean value of the maximum error cluster group as an average error, and finishing the associated cleaning of the first cleaning result. By comparing the single-point error with the average error, abnormal data can be identified and cleaning treatment can be performed, so that the accuracy and reliability of the monitoring data can be improved.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a carbon emission data analysis management program, and the carbon emission data analysis management program realizes the steps of the carbon emission data analysis management method when being executed by a processor.
Referring to fig. 6, fig. 6 is a block diagram showing the structure of a first embodiment of the carbon emission data analysis management apparatus of the present invention.
As shown in fig. 6, the carbon emission data analysis and management device according to the embodiment of the present invention includes:
The data extraction module 601 is configured to extract region feature data of a region to be monitored, and configure a data acquisition layer based on the region feature data;
The data set establishing module 602 is configured to read a monitoring data set of the data acquisition layer through a data set interface, and establish a monitoring association node based on the monitoring data set;
The time sequence cleaning module 603 is configured to perform time sequence cleaning on the same node data of the monitoring data set through a first adaptive cleaning window and a second adaptive cleaning window, so as to generate a first cleaning result;
The association configuration module 604 is configured to configure association delay through the monitoring association node, and perform association cleaning based on the association delay and the first cleaning result, so as to generate a second cleaning result;
and the verification analysis module 605 is used for inputting the second cleaning result into the intelligent analysis model to execute carbon emission analysis management.
The management device of the embodiment can firstly extract regional characteristic data of a region to be monitored, such as geographic position, land utilization type, climate condition, vegetation coverage, soil quality and the like, and configure a data acquisition layer based on the regional characteristic data. And through a data acquisition layer, monitoring and acquiring data related to carbon emission in real time. The monitoring data set of the data acquisition layer can then be read through the data set interface, and for each data point of the monitoring data set, a unique identifier can be assigned to each monitoring node according to the source and the monitoring node to which the monitoring data set belongs, and the identifier can be associated with the data point to establish a monitoring association node. Then, the time sequence identification of the same node data of the monitoring data set can be executed, and the time sequence cleaning of the same node data is carried out through the first self-adaptive cleaning window and the second self-adaptive cleaning window, so that a first cleaning result is generated. And configuring association delay through the monitoring association nodes, verifying data among the nodes based on the association delay, and executing association cleaning of the first cleaning result according to the data verification result to generate a second cleaning result. Finally, storing the second cleaning result to N storage devices, and establishing a consistency verification mechanism; and finally, inputting the second cleaning result into an intelligent analysis model, wherein the intelligent analysis model can execute a carbon emission analysis management task according to the input data. Because the embodiment can ensure the accuracy and consistency of the data by configuring the associated delay, the condition that the traditional carbon emission data management adopts centralized storage and management is avoided, and finally, the second cleaning result is input into the intelligent analysis model to execute the carbon emission analysis management, so that the problem of poor reliability and safety of the carbon emission data is solved, and the efficient management of the carbon emission data is realized.
Based on the above-described first embodiment of the carbon emission data analysis management device of the present invention, a second embodiment of the carbon emission data analysis management device of the present invention is proposed.
In this embodiment, the carbon emission data analysis management apparatus further includes an anomaly positioning module 606, configured to analyze node data in the monitoring dataset to obtain a fluctuation time sequence of the node data; performing abnormal positioning on the node data to generate an abnormal positioning result; establishing positioning association according to the fluctuation time sequence and the abnormal positioning result; and constructing a first self-adaptive cleaning window and a second self-adaptive cleaning window based on the generation constraint and a window construction decision network by taking the positioning association as the generation constraint.
Further, the anomaly locating module 606 is further configured to invoke historical monitoring data of the monitoring association node; performing time period segmentation based on the historical monitoring data to obtain a steady-state average value of the monitoring associated nodes in each time period; and carrying out abnormal positioning on the node data through the steady-state mean value to obtain an abnormal positioning result.
Further, the association configuration module 604 is further configured to take the processing delay between the monitoring association nodes as an association delay, and construct a carbon emission monitoring association according to the monitoring association nodes; performing time sequence backtracking on node data in the monitoring data set based on the associated delay to obtain a time sequence backtracking result; carrying out random point sampling on the time sequence backtracking result to obtain an average error associated with the carbon emission monitoring; and performing associated cleaning on the first cleaning result according to the average error to generate a second cleaning result.
Further, the association configuration module 604 is further configured to perform random point sampling on the timing trace back result, so as to obtain random sampling point data; calculating single-point errors of the random sampling point data, and constructing a single-point error set based on the single-point errors; error clustering is carried out on the single-point error set, and a maximum error clustering group is obtained; and obtaining a cluster mean value of the maximum error cluster group, and taking the cluster mean value as an average error associated with the carbon emission monitoring.
Further, the verification analysis module 605 is further configured to store the second cleaning result to N storage devices, and establish a consistency verification mechanism; when the second cleaning result has data abnormality or triggers a preset verification period, carrying out consensus verification on the N storage devices through a consistency verification mechanism to obtain a consensus verification result; updating the data in the N storage devices according to the consensus verification result; and inputting the updated second cleaning result into the intelligent analysis model, and executing carbon emission analysis management.
Further, the verification analysis module 605 is further configured to perform a time sequence analysis on the source features corresponding to the monitoring dataset, so as to obtain a time sequence principal component analysis result; performing dimension reduction processing on the updated second cleaning result according to the time sequence principal component analysis result to obtain a dimension reduction processing result; and inputting the dimension reduction processing result into an intelligent analysis model, and executing carbon emission analysis management.
Other embodiments or specific implementation manners of the carbon emission data analysis and management device of the present invention may refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. read-only memory/random-access memory, magnetic disk, optical disk), comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A carbon emission data analysis management method, characterized by comprising:
Extracting regional characteristic data of a region to be monitored, and configuring a data acquisition layer based on the regional characteristic data;
Reading a monitoring data set of the data acquisition layer through a data set interface, and establishing a monitoring association node based on the monitoring data set;
Performing time sequence cleaning on the same node data of the monitoring data set through a first self-adaptive cleaning window and a second self-adaptive cleaning window to generate a first cleaning result;
Configuring association delay through the monitoring association node, and performing association cleaning based on the association delay and the first cleaning result to generate a second cleaning result;
And inputting the second cleaning result into an intelligent analysis model to execute carbon emission analysis management.
2. The method for analyzing and managing carbon emission data according to claim 1, wherein the performing time-series cleaning on the same node data of the monitoring data set through the first adaptive cleaning window and the second adaptive cleaning window, before generating the first cleaning result, further comprises:
analyzing the node data in the monitoring data set to obtain the fluctuation time sequence of the node data;
Performing abnormal positioning on the node data to generate an abnormal positioning result;
establishing positioning association according to the fluctuation time sequence and the abnormal positioning result;
And constructing a first self-adaptive cleaning window and a second self-adaptive cleaning window based on the generation constraint and a window construction decision network by taking the positioning association as the generation constraint.
3. The carbon emission data analysis management method of claim 2, wherein the performing anomaly localization on the node data, generating an anomaly localization result comprises:
Invoking historical monitoring data of the monitoring associated node;
Performing time period segmentation based on the historical monitoring data to obtain a steady-state average value of the monitoring associated nodes in each time period;
And carrying out abnormal positioning on the node data through the steady-state mean value to obtain an abnormal positioning result.
4. The method for analyzing and managing carbon emission data according to claim 1, wherein the configuring of the association delay by the monitoring association node and the performing the association cleaning based on the association delay and the first cleaning result, generating a second cleaning result, comprises:
Taking the processing delay between the monitoring association nodes as association delay, and constructing carbon emission monitoring association according to the monitoring association nodes;
Performing time sequence backtracking on node data in the monitoring data set based on the associated delay to obtain a time sequence backtracking result;
carrying out random point sampling on the time sequence backtracking result to obtain an average error associated with the carbon emission monitoring;
and performing associated cleaning on the first cleaning result according to the average error to generate a second cleaning result.
5. The method for analyzing and managing carbon emission data according to claim 4, wherein the step of performing random point sampling on the time series backtracking result to obtain the average error associated with the carbon emission monitoring comprises the steps of:
Carrying out random point sampling on the time sequence backtracking result to obtain random sampling point data;
Calculating single-point errors of the random sampling point data, and constructing a single-point error set based on the single-point errors;
error clustering is carried out on the single-point error set, and a maximum error clustering group is obtained;
and obtaining a cluster mean value of the maximum error cluster group, and taking the cluster mean value as an average error associated with the carbon emission monitoring.
6. The carbon emission data analysis management method of claim 1, wherein the inputting the second cleaning result to an intelligent analysis model to perform carbon emission analysis management comprises:
Storing the second cleaning result to N storage devices, and establishing a consistency verification mechanism;
When the second cleaning result has data abnormality or triggers a preset verification period, carrying out consensus verification on the N storage devices through a consistency verification mechanism to obtain a consensus verification result;
Updating the data in the N storage devices according to the consensus verification result;
And inputting the updated second cleaning result into the intelligent analysis model, and executing carbon emission analysis management.
7. The carbon emission data analysis management method of claim 6, wherein the inputting the updated second cleaning result to the intelligent analysis model, performing carbon emission analysis management, comprises:
performing time sequence analysis on source characteristics corresponding to the monitoring data set to obtain a time sequence principal component analysis result;
performing dimension reduction processing on the updated second cleaning result according to the time sequence principal component analysis result to obtain a dimension reduction processing result;
and inputting the dimension reduction processing result into an intelligent analysis model, and executing carbon emission analysis management.
8. A carbon emission data analysis management apparatus, characterized by comprising:
The data extraction module is used for extracting regional characteristic data of a region to be monitored and configuring a data acquisition layer based on the regional characteristic data;
The data set establishing module is used for reading a monitoring data set of the data acquisition layer through a data set interface and establishing a monitoring association node based on the monitoring data set;
The time sequence cleaning module is used for performing time sequence cleaning on the same node data of the monitoring data set through a first self-adaptive cleaning window and a second self-adaptive cleaning window to generate a first cleaning result;
The association configuration module is used for configuring association delay through the monitoring association node, carrying out association cleaning based on the association delay and the first cleaning result, and generating a second cleaning result;
and the verification analysis module is used for inputting the second cleaning result into the intelligent analysis model to execute carbon emission analysis management.
9. A carbon emission data analysis management apparatus, characterized by comprising: a memory, a processor, and a carbon emission data analysis management program stored on the memory and executable on the processor, the carbon emission data analysis management program configured to implement the steps of the carbon emission data analysis management method of any one of claims 1 to 7.
10. A storage medium having stored thereon a carbon emission data analysis management program which, when executed by a processor, implements the steps of the carbon emission data analysis management method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410168843.6A CN117993616A (en) | 2024-02-06 | 2024-02-06 | Carbon emission data analysis management method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410168843.6A CN117993616A (en) | 2024-02-06 | 2024-02-06 | Carbon emission data analysis management method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117993616A true CN117993616A (en) | 2024-05-07 |
Family
ID=90892220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410168843.6A Pending CN117993616A (en) | 2024-02-06 | 2024-02-06 | Carbon emission data analysis management method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117993616A (en) |
-
2024
- 2024-02-06 CN CN202410168843.6A patent/CN117993616A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110929036B (en) | Electric power marketing inspection management method, electric power marketing inspection management device, computer equipment and storage medium | |
| CN111614690B (en) | Abnormal behavior detection method and device | |
| US20180348747A1 (en) | System and method for unsupervised root cause analysis of machine failures | |
| WO2019012029A1 (en) | Method and system for deviation detection in sensor datasets | |
| US20180307218A1 (en) | System and method for allocating machine behavioral models | |
| KR101953558B1 (en) | Apparatus and Method for Fault Management of Smart Devices | |
| Atzmueller et al. | Anomaly detection and structural analysis in industrial production environments | |
| CN117934247B (en) | Carbon emission factor prediction method and device based on time sequence decomposition, electronic equipment and storage medium | |
| CN112686773B (en) | Electric power metering all-link key business anomaly positioning model construction method based on fusion business topology | |
| US11665185B2 (en) | Method and apparatus to detect scripted network traffic | |
| CN117993616A (en) | Carbon emission data analysis management method, device, equipment and storage medium | |
| CN118133962A (en) | Correlation analysis method, device and system of fault event and storage medium | |
| CN117195451A (en) | Bridge monitoring data restoration method based on graph theory | |
| Khokhlov et al. | Data security and quality evaluation framework: Implementation empirical study on android devices | |
| US20220050763A1 (en) | Detecting regime change in time series data to manage a technology platform | |
| CN111651753A (en) | User behavior analysis system and method | |
| de Sousa et al. | Integrated detection and localization of concept drifts in process mining with batch and stream trace clustering support | |
| CN116108376A (en) | Monitoring system and method for preventing electricity stealing, electronic equipment and medium | |
| CN115525575A (en) | Data automation testing method and system based on Dataworks platform | |
| Jadhav et al. | Software defect prediction utilizing deterministic and probabilistic approach for optimizing performance through defect association learning | |
| CN111626586B (en) | Data quality detection method, device, computer equipment and storage medium | |
| US12135225B1 (en) | Systems, methods, and media for near real-time anomaly event detection and classification with trend change detection for smart water grid operation management | |
| CN118361650B (en) | Intelligent water-repellent method based on big data model | |
| CN111752984B (en) | Information processing method, device and storage medium | |
| Ko et al. | Pattern-based Reconstruction of Anomalous Traces in Business Process Event Logs |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |