CN114037179B - Big data-based power load prediction system and method - Google Patents
Big data-based power load prediction system and method Download PDFInfo
- Publication number
- CN114037179B CN114037179B CN202111407177.XA CN202111407177A CN114037179B CN 114037179 B CN114037179 B CN 114037179B CN 202111407177 A CN202111407177 A CN 202111407177A CN 114037179 B CN114037179 B CN 114037179B
- Authority
- CN
- China
- Prior art keywords
- data
- analysis
- module
- model
- load
- 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
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000013499 data model Methods 0.000 claims abstract description 90
- 230000010354 integration Effects 0.000 claims abstract description 65
- 230000005611 electricity Effects 0.000 claims abstract description 49
- 239000000284 extract Substances 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 5
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 239000002699 waste material Substances 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
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to the technical field of power load prediction, and discloses a power load prediction system and method based on big data. The invention has the advantages that: the data model is trained through the analysis deviation of the training unit, the data model and the algorithm are optimized, the data model outputs analysis data closest to real data to the association value analysis module, the association value analysis module invokes real load data of the real load database, then compares the analysis data with the analysis data, analyzes the big data association degree to obtain data with the highest association degree, the information integration module obtains the analysis value of the association degree of the association value analysis module, optimizes the information association degree integration, and further improves the association degree of the integrated data and the electricity load during the next prediction, so that the analysis reliability of the data model can be gradually improved through the analysis of the data, the prediction deviation is reduced, and meanwhile, the reliability and the accuracy of the high data model prediction can be further improved through the continuous improvement of the data association degree.
Description
Technical Field
The invention relates to the technical field of power load prediction, in particular to a power load prediction system and method based on big data.
Background
The power load prediction is a key ring of power operation, in order to ensure stable power supply and reduce waste, load analysis is performed, power scheduling and power production can be effectively guided, but the current power load prediction system has the following problems in use:
the existing power load prediction system has a single analysis negative mode, and the lack of automatic optimization causes larger analysis deviation, so that the power dispatching is influenced to make correct judgment.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a power load prediction system and method based on big data, which have the advantages of self-optimization, small deviation and the like and solve the problems in the background art.
(II) technical scheme
In order to achieve the purpose of self-optimization, the invention provides the following technical scheme: the power load prediction system based on big data is characterized by comprising a data model, a data acquisition module, an information integration module, an algorithm library, a correlation value analysis module and a real load database;
the output end of the data acquisition module is in data connection with the input end of the information integration module, the output end of the information integration module is in data connection with the input end of the data model, the input end of the data model is in information connection with the algorithm library, the output end of the data model is in data connection with the input end of the association value analysis module, the output end of the real load database is in data connection with the input ends of the data model and the association value analysis module respectively, and the output end of the association value analysis module is in data connection with the input end of the information integration module.
Preferably, the data acquisition module comprises a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit.
Preferably, the data model comprises a predictive analysis unit and a training unit.
The invention provides a power load prediction method based on big data, which comprises the following steps:
1) The data acquisition module acquires big data through the acquisition of a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit;
2) The information integration module integrates and extracts effective data according to the information association degree;
3) The data model extracts the data integrated by the information integration module, brings the data into the model, and the prediction analysis unit invokes a plurality of algorithms and brings the data into the data to obtain a result;
4) The real load database inputs real load data into the data model, the real data is compared with the prediction model, the data model is trained by analyzing deviation through the training unit, and the model and the algorithm are optimized;
5) Outputting analysis data to a correlation value analysis module by the data model, and calling the real load data of a real load database by the correlation value analysis module, comparing the analysis data with the real load data, and analyzing the correlation degree of big data to obtain data with the highest correlation degree;
6) And the information integration module acquires an analysis value of the association degree of the association value analysis module, optimizes information association degree integration, and further improves the association degree of the integrated data and the power load during the next prediction.
Preferably, a plurality of load analysis algorithms are preset in the algorithm library, different analysis values are obtained by adopting different algorithms in the step 4), the training unit in the step 4) compares the analysis values obtained by the algorithms with the actual load values to obtain deviation values of the algorithms, optimizes the algorithms according to the deviation values, and inputs the deviation values into a model to realize model optimization.
Preferably, the data acquisition module in the step 1) acquires news, real-time electricity consumption data, weather temperature data and power grid load data related to the electric power through a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity load acquisition unit.
Preferably, the information integration module optimizes the information integration capability according to the correlation value analysis result provided by the correlation value analysis module, and gradually improves the correlation degree of the influence of the integrated big data information on the power grid load.
Preferably, the data model is carried into historical data by the training unit for analysis and comparison, so that the construction is completed, and the data model is optimized through continuous training of the training unit.
Preferably, the algorithm library deletes an algorithm with the largest analysis deviation in each prediction analysis round, and the algorithm library supplements a new algorithm in each prediction analysis round.
(III) beneficial effects
Compared with the prior art, the invention provides a power load prediction system and method based on big data, which have the following beneficial effects:
according to the big data-based power load prediction system and method, a data model, a data acquisition module, an information integration module, an algorithm library, a correlation value analysis module and a real load database are arranged. The output end of the data acquisition module is connected with the input end data of the information integration module, the output end of the information integration module is connected with the input end data of the data model, the input end of the data model is connected with the algorithm library information, the output end of the data model is connected with the input end data of the associated value analysis module, the output end of the real load database is respectively connected with the input end data of the data model and the associated value analysis module, the output end of the associated value analysis module is connected with the input end data of the information integration module, the data acquisition module can acquire big data through the acquisition of the real-time news acquisition unit, the electricity consumption data acquisition unit, the weather condition acquisition unit and the electricity consumption load acquisition unit, the data model extracts the data integrated by the information integration module and brings the data into the model, the prediction analysis unit retrieves a plurality of algorithms, the real load data is input into a data model, the real load data is compared with a prediction model to obtain a result, the data model is trained by analyzing deviation through a training unit, an optimization model and an algorithm are carried out, the data model outputs analysis data to a correlation value analysis module, the correlation value analysis module invokes the real load data of the real load database, then compares the analysis data with the correlation value to analyze the correlation degree of big data to obtain data with highest correlation degree, an information integration module obtains the analysis value of the correlation degree of the correlation value analysis module to optimize the information correlation degree integration, and then the correlation degree of the integrated data and the power consumption load is further improved in the next prediction, so that the analysis reliability of the data model can be gradually improved through the analysis of the data to reduce the prediction deviation, and meanwhile the continuous improvement of the data correlation degree is carried out, the reliability and accuracy of the high data model prediction can be further improved.
Drawings
FIG. 1 is a schematic diagram of a system architecture of the present invention;
fig. 2 is a flow chart of the method of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one:
the power load prediction system based on big data comprises a data model, a data acquisition module, an information integration module, an algorithm library, a correlation value analysis module and a real load database;
the output end of the data acquisition module is in data connection with the input end of the information integration module, the output end of the information integration module is in data connection with the input end of the data model, the input end of the data model is in information connection with the algorithm library, the output end of the data model is in data connection with the input end of the association value analysis module, the output end of the real load database is in data connection with the input ends of the data model and the association value analysis module respectively, and the output end of the association value analysis module is in data connection with the input end of the information integration module.
The data acquisition module comprises a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit.
The data model comprises a prediction analysis unit and a training unit.
The invention provides a power load prediction method based on big data, which comprises the following steps:
1) The data acquisition module acquires big data through the acquisition of a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit;
2) The information integration module integrates and extracts effective data according to the information association degree;
3) The data model extracts the data integrated by the information integration module, brings the data into the model, and the prediction analysis unit invokes a plurality of algorithms and brings the data into the data to obtain a result;
4) The real load database inputs real load data into the data model, the real data is compared with the prediction model, the data model is trained by analyzing deviation through the training unit, and the model and the algorithm are optimized;
5) Outputting analysis data to a correlation value analysis module by the data model, and calling the real load data of a real load database by the correlation value analysis module, comparing the analysis data with the real load data, and analyzing the correlation degree of big data to obtain data with the highest correlation degree;
6) And the information integration module acquires an analysis value of the association degree of the association value analysis module, optimizes information association degree integration, and further improves the association degree of the integrated data and the power load during the next prediction.
Presetting a plurality of load analysis algorithms in an algorithm library, respectively adopting different algorithms to obtain different analysis values in the step 4), comparing the analysis values obtained by the algorithms with actual load values by a training unit in the step 4), obtaining deviation values of the algorithms, optimizing the algorithms according to the deviation values, and inputting the deviation values into a model to realize model optimization.
The data acquisition module in the step 1) acquires news, real-time electricity utilization data, weather temperature data and power grid load data related to electric power through the real-time news acquisition unit, the electricity utilization data acquisition unit, the weather condition acquisition unit and the electricity utilization load acquisition unit.
The information integration module optimizes the information integration capability according to the association value analysis result provided by the association value analysis module, and gradually improves the association degree of the integrated big data information on the power grid load.
The data model is carried into historical data by the training unit for analysis and comparison, construction is completed, and the data model is optimized through continuous training of the training unit.
And deleting an algorithm with the largest analysis deviation from each predictive analysis round in the algorithm library, and supplementing a new algorithm into each predictive analysis round in the algorithm library.
The method has the advantages that the analysis reliability of the data model can be gradually improved through the analysis of the data, so that the prediction deviation is reduced, meanwhile, the reliability and the accuracy of the prediction of the high data model can be further improved through the continuous improvement of the data association degree, and moreover, news references can be introduced through collecting real-time news information, so that the judgment capability of the policy on the influence of the electricity load is improved.
Embodiment two:
the power load prediction system based on big data comprises a data model, a data acquisition module, an information integration module, an algorithm library, a correlation value analysis module and a real load database;
the output end of the data acquisition module is in data connection with the input end of the information integration module, the output end of the information integration module is in data connection with the input end of the data model, the input end of the data model is in information connection with the algorithm library, the output end of the data model is in data connection with the input end of the association value analysis module, the output end of the real load database is in data connection with the input ends of the data model and the association value analysis module respectively, and the output end of the association value analysis module is in data connection with the input end of the information integration module.
The data acquisition module comprises an electricity price data acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit.
The data model comprises a prediction analysis unit and a training unit.
The invention provides a power load prediction method based on big data, which comprises the following steps:
1) The data acquisition module acquires big data through an electricity price data acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit;
2) The information integration module integrates and extracts effective data according to the information association degree;
3) The data model extracts the data integrated by the information integration module, brings the data into the model, and the prediction analysis unit invokes a plurality of algorithms and brings the data into the data to obtain a result;
4) The real load database inputs real load data into the data model, the real data is compared with the prediction model, the data model is trained by analyzing deviation through the training unit, and the model and the algorithm are optimized;
5) Outputting analysis data to a correlation value analysis module by the data model, and calling the real load data of a real load database by the correlation value analysis module, comparing the analysis data with the real load data, and analyzing the correlation degree of big data to obtain data with the highest correlation degree;
6) And the information integration module acquires an analysis value of the association degree of the association value analysis module, optimizes information association degree integration, and further improves the association degree of the integrated data and the power load during the next prediction.
Presetting a plurality of load analysis algorithms in an algorithm library, respectively adopting different algorithms to obtain different analysis values in the step 4), comparing the analysis values obtained by the algorithms with actual load values by a training unit in the step 4), obtaining deviation values of the algorithms, optimizing the algorithms according to the deviation values, and inputting the deviation values into a model to realize model optimization.
The data acquisition module in the step 1) acquires news, real-time electricity utilization data, weather temperature data and power grid load data related to electric power through an electricity price data acquisition unit, an electricity utilization data acquisition unit, a weather condition acquisition unit and an electricity utilization load acquisition unit.
The information integration module optimizes the information integration capability according to the association value analysis result provided by the association value analysis module, and gradually improves the association degree of the integrated big data information on the power grid load.
The data model is carried into historical data by the training unit for analysis and comparison, construction is completed, and the data model is optimized through continuous training of the training unit.
And deleting an algorithm with the largest analysis deviation from each predictive analysis round in the algorithm library, and supplementing a new algorithm into each predictive analysis round in the algorithm library.
The embodiment has the advantages that the electricity price data are collected, the relevance of the electricity price to the influence of the electricity load can be analyzed, and the analysis can provide reference for the electricity load and the electricity price adjustment, so that the practicability is improved.
The beneficial effects of the invention are as follows: the method comprises the steps of setting a data model, a data acquisition module, an information integration module, an algorithm library, a correlation value analysis module and a real load database. The output end of the data acquisition module is connected with the input end data of the information integration module, the output end of the information integration module is connected with the input end data of the data model, the input end of the data model is connected with the algorithm library information, the output end of the data model is connected with the input end data of the associated value analysis module, the output end of the real load database is respectively connected with the input end data of the data model and the associated value analysis module, the output end of the associated value analysis module is connected with the input end data of the information integration module, the data acquisition module can acquire big data through the acquisition of the real-time news acquisition unit, the electricity consumption data acquisition unit, the weather condition acquisition unit and the electricity consumption load acquisition unit, the data model extracts the data integrated by the information integration module and brings the data into the model, the prediction analysis unit retrieves a plurality of algorithms and brings the data, the result is obtained, the real load data is input into the data model by the real load database, the real load data is compared with the prediction model, the data model is trained by the analysis deviation of the training unit, the data model is optimized with the algorithm, the analysis data closest to the real data is output to the association value analysis module by the data model, the real load data of the real load database is called by the association value analysis module, the analysis data is compared, the big data association degree is analyzed, the data with the highest association degree is obtained, the analysis value of the association degree of the association value analysis module is obtained by the information integration module, the information association degree is optimized, the association degree of the integrated data and the power consumption load is further improved in the next prediction, the analysis reliability of the data model can be gradually improved by the analysis of the data, the prediction deviation is reduced, and the association degree of the data is continuously improved, the reliability and accuracy of the high data model prediction can be further improved.
Typical cases: the power load prediction system based on big data comprises a data model, a data acquisition module, an information integration module, an algorithm library, a correlation value analysis module and a real load database;
the output end of the data acquisition module is in data connection with the input end of the information integration module, the output end of the information integration module is in data connection with the input end of the data model, the input end of the data model is in information connection with the algorithm library, the output end of the data model is in data connection with the input end of the association value analysis module, the output end of the real load database is in data connection with the input ends of the data model and the association value analysis module respectively, and the output end of the association value analysis module is in data connection with the input end of the information integration module.
The data acquisition module comprises a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit.
The data model comprises a prediction analysis unit and a training unit.
The invention provides a power load prediction method based on big data, which comprises the following steps:
1) The data acquisition module acquires big data through the acquisition of a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit;
2) The information integration module integrates and extracts effective data according to the information association degree;
3) The data model extracts the data integrated by the information integration module, brings the data into the model, and the prediction analysis unit invokes a plurality of algorithms and brings the data into the data to obtain a result;
4) The real load database inputs real load data into the data model, the real data is compared with the prediction model, the data model is trained by analyzing deviation through the training unit, and the model and the algorithm are optimized;
5) Outputting analysis data closest to real data to a correlation value analysis module by the data model, retrieving real load data of a real load database by the correlation value analysis module, comparing the analysis data with the real load data, and analyzing the correlation degree of big data to obtain data with the highest correlation degree;
6) And the information integration module acquires an analysis value of the association degree of the association value analysis module, optimizes information association degree integration, and further improves the association degree of the integrated data and the power load during the next prediction.
Presetting a plurality of load analysis algorithms in an algorithm library, respectively adopting different algorithms to obtain different analysis values in the step 4), comparing the analysis values obtained by the algorithms with actual load values by a training unit in the step 4), obtaining deviation values of the algorithms, optimizing the algorithms according to the deviation values, and inputting the deviation values into a model to realize model optimization.
The data acquisition module in the step 1) acquires news, real-time electricity utilization data, weather temperature data and power grid load data related to electric power through the real-time news acquisition unit, the electricity utilization data acquisition unit, the weather condition acquisition unit and the electricity utilization load acquisition unit.
The information integration module optimizes the information integration capability according to the association value analysis result provided by the association value analysis module, and gradually improves the association degree of the integrated big data information on the power grid load.
The data model is carried into historical data by the training unit for analysis and comparison, construction is completed, and the data model is optimized through continuous training of the training unit.
And deleting an algorithm with the largest analysis deviation from each predictive analysis round in the algorithm library, and supplementing a new algorithm into each predictive analysis round in the algorithm library.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (1)
1. The power load prediction method based on big data is characterized by comprising a data model, a data acquisition module, an information integration module, an algorithm library, a correlation value analysis module and a real load database;
the output end of the data acquisition module is in data connection with the input end of the information integration module, the output end of the information integration module is in data connection with the input end of the data model, the input end of the data model is in information connection with the algorithm library, the output end of the data model is in data connection with the input end of the association value analysis module, the output end of the real load database is in data connection with the input ends of the data model and the association value analysis module respectively, and the output end of the association value analysis module is in data connection with the input end of the information integration module;
the data acquisition module comprises a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit;
the data model comprises a prediction analysis unit and a training unit;
the method comprises the following steps:
1) The data acquisition module acquires big data through the acquisition of a real-time news acquisition unit, an electricity consumption data acquisition unit, a weather condition acquisition unit and an electricity consumption load acquisition unit;
2) The information integration module integrates and extracts effective data according to the information association degree;
3) The data model extracts the data integrated by the information integration module, brings the data into the model, and the prediction analysis unit invokes a plurality of algorithms and brings the data into the data to obtain a result;
4) The real load database inputs real load data into the data model, the real data is compared with the prediction model, the data model is trained by analyzing deviation through the training unit, and the model and the algorithm are optimized;
5) The data model outputs analysis data to the association value analysis module, the association value analysis module invokes the real load data of the real load database, and then compares the analysis data to analyze the association degree of big data so as to obtain data;
6) The information integration module acquires an analysis value of the association degree of the association value analysis module, optimizes information association degree integration, and further improves the association degree of integrated data and power loads in the next prediction;
presetting a plurality of load analysis algorithms in an algorithm library, respectively adopting different algorithms to obtain different analysis values in the step 4), comparing the analysis values obtained by the algorithms with actual load values by a training unit in the step 4) to obtain deviation values of the algorithms, optimizing the algorithms according to the deviation values, inputting the deviation values into a model, and realizing model optimization;
the data acquisition module in the step 1) acquires news, real-time electricity utilization data, weather temperature data and power grid load data related to electric power through a real-time news acquisition unit, an electricity utilization data acquisition unit, a weather condition acquisition unit and an electricity utilization load acquisition unit;
the information integration module optimizes the information integration capacity according to the correlation value analysis result provided by the correlation value analysis module, and gradually improves the correlation degree of the influence of integrated big data information on the power grid load;
the data model is carried into historical data by a training unit for analysis and comparison, the construction is completed, and the data model is optimized through continuous training of the training unit;
and deleting an algorithm with the largest analysis deviation from each predictive analysis round of the algorithm library, and supplementing a new algorithm into each predictive analysis round of the algorithm library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111407177.XA CN114037179B (en) | 2021-11-24 | 2021-11-24 | Big data-based power load prediction system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111407177.XA CN114037179B (en) | 2021-11-24 | 2021-11-24 | Big data-based power load prediction system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114037179A CN114037179A (en) | 2022-02-11 |
| CN114037179B true CN114037179B (en) | 2023-04-28 |
Family
ID=80138637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111407177.XA Active CN114037179B (en) | 2021-11-24 | 2021-11-24 | Big data-based power load prediction system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114037179B (en) |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107239854A (en) * | 2017-05-22 | 2017-10-10 | 华北电力大学 | Load forecasting method based on EMD GRA MPSO LSSVM models |
| CN111091243A (en) * | 2019-12-13 | 2020-05-01 | 南京工程学院 | PCA-GM-based power load prediction method, system, computer-readable storage medium, and computing device |
| CN111144650A (en) * | 2019-12-26 | 2020-05-12 | 南京工程学院 | Power load prediction method, device, computer readable storage medium and equipment |
| CN111382906B (en) * | 2020-03-06 | 2024-02-27 | 南京工程学院 | Power load prediction method, system, equipment and computer readable storage medium |
| CN111652420A (en) * | 2020-05-26 | 2020-09-11 | 张志远 | Real-time load prediction system |
| AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
-
2021
- 2021-11-24 CN CN202111407177.XA patent/CN114037179B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114037179A (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288136B (en) | Wind power multi-step prediction model establishment method | |
| CN105303263A (en) | Load prediction system of regional power grid and method thereof | |
| CN117013527A (en) | Distributed photovoltaic power generation power prediction method | |
| CN113887912B (en) | Non-invasive load identification method for embedded equipment under deep learning | |
| CN103793756A (en) | Transformer economic operation characteristic analyzing method | |
| CN117132132A (en) | Photovoltaic power generation power prediction method based on meteorological data | |
| CN114037179B (en) | Big data-based power load prediction system and method | |
| CN111612298A (en) | Energy internet collaborative optimization operation method | |
| CN109687428B (en) | Control method of multi-energy complementary distributed energy microgrid operation optimization control system | |
| CN116599036A (en) | Two-stage non-invasive load decomposition method based on TCN and Informar | |
| CN116090604A (en) | Training method, prediction method and device for photovoltaic power model in future and short term | |
| Sicheng et al. | Abnormal line loss data detection and correction method | |
| CN114444955A (en) | Key parameter data mining and long-term configuration prediction method and system for comprehensive energy | |
| CN110659681B (en) | Time sequence data prediction system and method based on pattern recognition | |
| Li et al. | Multi-source heterogeneous log fusion technology of power information system based on big data and imprecise reasoning theory | |
| Xia et al. | Research on short-term load forecasting of power system based on gradient lifting tree | |
| CN118536679B (en) | Building energy consumption data acquisition and analysis method and system based on machine learning | |
| Wen et al. | Bi-Directional BILSTM-Attention Short-Term Load Forecasting based on Correlation Weight | |
| CN112966868A (en) | Building load day-ahead prediction method and system | |
| CN117374963A (en) | Ultra-short-term power demand prediction method for iron and steel enterprises based on load characteristics | |
| CN118643924A (en) | Renewable energy prediction method and system based on machine learning | |
| Wu et al. | Short-term wind power forecast based on Long Short Term Memory | |
| CN113361727A (en) | Optimization method and device for realizing power failure maintenance window period based on data | |
| Xiong et al. | Short-term load forecasting method based on deep learning under digital driving | |
| Wang et al. | Power forecasting for regional distributed photovoltaic based on mRMR-TCN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |