CN107368932A - A kind of load Analysis forecasting system suitable for power network development specialty - Google Patents

A kind of load Analysis forecasting system suitable for power network development specialty Download PDF

Info

Publication number
CN107368932A
CN107368932A CN201710677307.9A CN201710677307A CN107368932A CN 107368932 A CN107368932 A CN 107368932A CN 201710677307 A CN201710677307 A CN 201710677307A CN 107368932 A CN107368932 A CN 107368932A
Authority
CN
China
Prior art keywords
analysis
module
data
prediction
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.)
Pending
Application number
CN201710677307.9A
Other languages
Chinese (zh)
Inventor
孙东磊
牟宏
汪湲
贾善杰
孙伟
张伟昌
杨金洪
张�杰
杨思
曹相阳
王轶群
付木
付一木
李沐
田鑫
杨斌
王男
薄其滨
高效海
张丽娜
魏鑫
魏佳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Corp of China SGCC
Economic and Technological Research Institute of State Grid Shandong Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
Economic and Technological Research Institute of State Grid Shandong Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid Corp of China SGCC, Economic and Technological Research Institute of State Grid Shandong Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN201710677307.9A priority Critical patent/CN107368932A/en
Publication of CN107368932A publication Critical patent/CN107368932A/en
Pending legal-status Critical Current

Links

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
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Computational Linguistics (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Probability & Statistics with Applications (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Development Economics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Water Supply & Treatment (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The present invention relates to a kind of load Analysis forecasting system suitable for power network development specialty, including data preprocessing module, fundamental analysis module, analysis prediction module and prediction application module, data preprocessing module structure fundamentals of forecasting database；Fundamental analysis module is analyzed based on fundamentals of forecasting database；Analysis prediction module catcher data and processing module and fundamental analysis module data is simultaneously analyzed and processed, and the data of analyzing and processing are sent to predicting application module.The present invention can be achieved to predict the basic data pretreatment, fundamental analysis, analysis that are related to the analysis of power network development specialty workload demand and prediction is applied, play an important roll to the application such as analysis network load demand characteristics and Electric Power Network Planning based on this comprehensively, there is good actual application prospect.

Description

A kind of load Analysis forecasting system suitable for power network development specialty
Technical field：
The present invention relates to a kind of load Analysis forecasting system suitable for power network development specialty, belong to electrical engineering field.
Background technology：
The main task of power system is to provide economic, reliable and high quality electric energy for all types of user, should be met at any time The workload demand amount of user and the requirement of part throttle characteristics.Therefore, handed in planning and design of power system, operational management and electricity market Yi Zhong, it is necessary to which the change to workload demand amount has an accurately prediction with part throttle characteristics.Load Analysis prediction is related to power train System planning and design, many aspects such as economy, reliability and the security of Operation of Electric Systems, power market transaction, it is electricity Power enterprise production and management and the essential part of planning and management.Comprehensive and accurate Load Characteristic Analysis and load Prediction is the guarantee of power system security stable operation, is the basis of power planning, and this is also proposed to load Analysis prediction level New, higher requirement.
As electricity power data, market economy data exponentially increase, complexity increases, this causes electricity market Analysis prediction work amount greatly increases；On the other hand the displaying of traditional load Analysis forecasting system is using method is relatively simple, takes out As and the relevance between data is not strong, it is impossible to from the global running status and growth requirement for disclosing power network, in particular for from Various dimensions (time, space), during multi-angle (laterally, longitudinal direction) contrast district load growth, data volume increases in the outburst of geometry level Long, in face of these mass datas, the limitation of traditional data processing method is more and more obvious, it is necessary to a novel system, can be with Make staff more directly perceived and analysis prediction is globally carried out to electric load demand, and can realize and extract in mass data Global feature and contain pattern, there is provided maximally effective load Analysis prediction data.
The content of the invention：
The present invention to provide it is a kind of can realize it is effective meet analysis prediction data be applied to power network development specialty Load Analysis forecasting system.
Load Analysis forecasting system provided by the present invention suitable for power network development specialty, it is characterized in that, including data are pre- Processing module, fundamental analysis module, analysis prediction module and prediction application module, data preprocessing module structure fundamentals of forecasting number According to storehouse；Fundamental analysis module is analyzed based on fundamentals of forecasting database；Analyze prediction module catcher data and processing module and Fundamental analysis module data is simultaneously analyzed and processed, and the data of analyzing and processing are sent to prediction application module.
Described data preprocessing module access EMS EMS and data acquisition and supervisor control SCADA, The data messages such as electrical power distribution automatization system DAS, power information acquisition system, and based on its mutual incidence relation, carry out Dealing of abnormal data, eliminate the false and retain the true, ensure the reliability and continuity of historical data, it is pre- to carry out the data such as data pick-up, cleaning Valuable information excavating is realized in processing operation, builds load prediction basic database.
The analysis prediction module is on the basis of basic data pre-processes and analyzes, based on artificial intelligence and supporting vector Machine combination forecasting method realizes that power supply and demand is predicted, load sequence prediction is realized based on Markov chains forecasting method, with support Vector machine carries out annual whole society's power quantity predicting, while the kernel function of SVMs is used as using Radial basis kernel function；Secondly, fortune The width parameter in the slack variable and Radial basis kernel function in the loss function of SVMs is carried out with particle cluster algorithm Global optimization.
The prediction application module refers to realize the balance of electric power and ener point based on load prediction and power supply installation situation Analysis, and the power supply and demand early warning based on this；Electric network composition Adaptability Analysis based on load prediction, Pre-estimation Geological power network is not The adaptability come under time window internal loading level, early warning is carried out to electrical network weak link and potential risk.
The beneficial effects of the invention are as follows：
The present invention can be achieved to be related to power network development specialty workload demand analysis basic data pretreatment, fundamental analysis, Analysis prediction and prediction application, there is weight to the application such as analysis network load demand characteristics and Electric Power Network Planning based on this comprehensively Act on, there is good actual application prospect.
Brief description of the drawings
Below in conjunction with the accompanying drawings and embodiment the present invention is further detailed explanation：
Fig. 1 is schematic structural view of the invention.
Specific embodiment：
Include as shown in Figure 1 suitable for the load Analysis forecasting system of power network development specialty, the load Analysis forecasting system：
Data preprocessing module.Data preprocessing module refers to by accessing EMS (EMS) and data acquisition With the data message such as supervisor control (SCADA), electrical power distribution automatization system (DAS), power information acquisition system, and it is based on Mutual incidence relation, dealing of abnormal data is carried out, is eliminated the false and retained the true, is ensured the reliability and continuity of historical data, enter Valuable information excavating is realized in the operation of the data predictions such as row data pick-up, cleaning, builds load prediction basic database；
Fundamental analysis module.Fundamental analysis module refers to be based on load prediction basic database, with reference to data classification, information The technologies such as excavation realize the functions such as large user's electrical energy consumption analysis, Business Process System analysis, power sales analysis, to realize all-sidedly and accurately Workload demand is held to lay the foundation；
Analyze prediction module.Prediction module is analyzed on the basis of basic data pre-processes and analyzes, based on artificial intelligence Realize that power supply and demand is predicted with SVMs combination forecasting method, realize that load sequence is pre- based on Markov chains forecasting method Survey.Annual whole society's power quantity predicting is carried out with SVMs, while the core of SVMs is used as using Radial basis kernel function Function, solve the problems, such as that electricity sample is less and causes prediction deviation excessive.Secondly, with particle cluster algorithm to supporting Width parameter in slack variable and Radial basis kernel function in the loss function of vector machine carries out global optimization, to improve electricity The accuracy of prediction；
Predict application module.Prediction application module refers to realize the electric power electricity based on load prediction and power supply installation situation Measure equilibrium analysis, and the power supply and demand early warning based on this；Electric network composition Adaptability Analysis based on load prediction, Pre-estimation Geological Adaptability of the power network under future time window internal loading level, early warning is carried out to electrical network weak link and potential risk；Realize with Electric Power Network Planning decision system interface, the network optimization upgrading for meeting load growth is realized with this.
Illustrated by taking the prediction of annual Analyzing Total Electricity Consumption as an example based on artificial intelligence and SVMs combination forecasting method work Make principle.Plan forecast tnSomewhere phase, Analyzing Total Electricity Consumption year, the sample data in this area 0 to n-1 periods (fiFor annual whole society's electricity, xiFor the annual gross national product in area) training dataset is used as, optimize with particle cluster algorithm SVM prediction function carry out sample training, draw SVMs training after parameter ai *、aiAfter b, input is new Argument data xnIt is predicted in SVMs after to optimization, draws the prediction result f to regional whole society's electricityn。
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any Belong to those skilled in the art the invention discloses technical scope in, the change or replacement that can readily occur in, all should It is included within the scope of the present invention.Therefore, protection scope of the present invention should be defined by scope of the claims.

Claims (4)

1. a kind of load Analysis forecasting system suitable for power network development specialty, it is characterized in that, including data preprocessing module, base Plinth analysis module, analysis prediction module and prediction application module, data preprocessing module structure fundamentals of forecasting database；Basis point Analysis module is analyzed based on fundamentals of forecasting database；Analyze prediction module catcher data and processing module and fundamental analysis module Data are simultaneously analyzed and processed, and the data of analyzing and processing are sent to prediction application module.
2. a kind of load Analysis forecasting system suitable for power network development specialty according to claim 1, it is characterized in that, institute Data preprocessing module access EMS EMS and the data acquisition and supervisor control SCADA, power distribution automation stated The data messages such as system DAS, power information acquisition system, and based on its mutual incidence relation, carry out at abnormal data Reason, eliminates the false and retains the true, and ensures the reliability and continuity of historical data, and it is real to carry out the operation of the data predictions such as data pick-up, cleaning Existing valuable information excavating, builds load prediction basic database.
3. a kind of load Analysis forecasting system suitable for power network development specialty according to claim 1, it is characterized in that, institute Analysis prediction module is stated on the basis of basic data pre-processes and analyzes, based on artificial intelligence and SVMs combined prediction Method realizes that power supply and demand is predicted, realizes load sequence prediction based on Markov chains forecasting method, is carried out with SVMs Annual whole society's power quantity predicting, while the kernel function of SVMs is used as using Radial basis kernel function；Secondly, calculated with population Method carries out global optimization to the width parameter in the slack variable and Radial basis kernel function in the loss function of SVMs.
4. a kind of load Analysis forecasting system suitable for power network development specialty according to claim 1, it is characterized in that, institute State prediction application module and refer to realize the balance of electric power and ener analysis based on load prediction and power supply installation situation, and be based on This power supply and demand early warning；Electric network composition Adaptability Analysis based on load prediction, Pre-estimation Geological power network is in future time window Adaptability under load level, early warning is carried out to electrical network weak link and potential risk.
CN201710677307.9A 2017-08-09 2017-08-09 A kind of load Analysis forecasting system suitable for power network development specialty Pending CN107368932A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710677307.9A CN107368932A (en) 2017-08-09 2017-08-09 A kind of load Analysis forecasting system suitable for power network development specialty

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710677307.9A CN107368932A (en) 2017-08-09 2017-08-09 A kind of load Analysis forecasting system suitable for power network development specialty

Publications (1)

Publication Number Publication Date
CN107368932A true CN107368932A (en) 2017-11-21

Family

ID=60309615

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710677307.9A Pending CN107368932A (en) 2017-08-09 2017-08-09 A kind of load Analysis forecasting system suitable for power network development specialty

Country Status (1)

Country Link
CN (1) CN107368932A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108037415A (en) * 2017-12-15 2018-05-15 国网江苏省电力有限公司南京供电分公司 Distribution network failure information excavating and diagnostic method based on multi-source heterogeneous data
CN109685277A (en) * 2018-12-28 2019-04-26 国网冀北电力有限公司经济技术研究院 Electricity demand forecasting method and device
CN110009263A (en) * 2019-04-28 2019-07-12 河北建投能源投资股份有限公司 Monitoring method based on power generation data
CN110380407A (en) * 2019-07-05 2019-10-25 河海大学 A kind of power distribution network running optimizatin method considering the electric irrigation and drainage load of agricultural
CN111985701A (en) * 2020-07-31 2020-11-24 国网上海市电力公司 Power utilization prediction method based on power supply enterprise big data model base

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103413254A (en) * 2013-09-04 2013-11-27 国家电网公司 Medium-and-long-term load prediction research and management integration application system
CN104156827A (en) * 2014-08-15 2014-11-19 国家电网公司 Technical collaboration and dynamic intelligent management system for power planning
CN104850918A (en) * 2015-06-02 2015-08-19 国网山东省电力公司经济技术研究院 Node load prediction method taking power grid topology constraints into consideration
CN106157180A (en) * 2016-09-27 2016-11-23 国家电网公司 The early warning system of platform district low-voltage problem

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103413254A (en) * 2013-09-04 2013-11-27 国家电网公司 Medium-and-long-term load prediction research and management integration application system
CN104156827A (en) * 2014-08-15 2014-11-19 国家电网公司 Technical collaboration and dynamic intelligent management system for power planning
CN104850918A (en) * 2015-06-02 2015-08-19 国网山东省电力公司经济技术研究院 Node load prediction method taking power grid topology constraints into consideration
CN106157180A (en) * 2016-09-27 2016-11-23 国家电网公司 The early warning system of platform district low-voltage problem

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108037415A (en) * 2017-12-15 2018-05-15 国网江苏省电力有限公司南京供电分公司 Distribution network failure information excavating and diagnostic method based on multi-source heterogeneous data
CN109685277A (en) * 2018-12-28 2019-04-26 国网冀北电力有限公司经济技术研究院 Electricity demand forecasting method and device
CN110009263A (en) * 2019-04-28 2019-07-12 河北建投能源投资股份有限公司 Monitoring method based on power generation data
CN110380407A (en) * 2019-07-05 2019-10-25 河海大学 A kind of power distribution network running optimizatin method considering the electric irrigation and drainage load of agricultural
CN110380407B (en) * 2019-07-05 2022-09-16 河海大学 Power distribution network operation optimization method considering agricultural electric irrigation and drainage loads
CN111985701A (en) * 2020-07-31 2020-11-24 国网上海市电力公司 Power utilization prediction method based on power supply enterprise big data model base
CN111985701B (en) * 2020-07-31 2024-03-01 国网上海市电力公司 Power consumption prediction method based on power supply enterprise big data model base

Similar Documents

Publication Publication Date Title
CN107368932A (en) A kind of load Analysis forecasting system suitable for power network development specialty
Candelieri et al. Short-term forecasting of hourly water consumption by using automatic metering readers data
WO2018176863A1 (en) Investment efficiency analysis method and device related to power distribution network reliability, and storage medium
CN105809277A (en) Big data based prediction method for the refining and managing of electric power marketing inspection
Quest et al. A 3D indicator for guiding AI applications in the energy sector
Sinchuk Harmonization of modeling systems for assessing the electric-power consumption levels at mining enterprises
CN108230183A (en) A kind of processing method of the grid equipment various dimensions comprehensive warning based on time scale measurement
CN111291498A (en) Steel rail section abrasion prediction system, method, computer device and storage medium
CN112257937B (en) Power distribution network fault prediction system and method based on big data technology
Jiang et al. Supply chain resilience of mineral resources industry in China
CN111914014A (en) Big data platform and application thereof
Sycheva et al. Practical application of the concept of digital twins in the aviation sector
Ye et al. Research on intelligent operation and maintenance technology of pumped storage power plant based on 5G
CN114254806A (en) Power distribution network heavy overload early warning method and device, computer equipment and storage medium
Sarı Ay et al. Observational data-based quality assessment of scenario generation for stochastic programs
Hu et al. Big data management and application research in power load forecasting and power transmission and transformation equipment evaluation
Li et al. Application of artificial intelligence technology in single well production and water cut prediction
Liu et al. For intelligent debugging management of offshore oil engineering with big data
CN110689241A (en) Power grid physical asset evaluation system based on big data
Gao Real-time visualization optimization management simulation of big data stream on industrial heritage cloud platform
Abdi-Oskouei et al. Role of the operator in dragline energy efficiency
Zhang et al. Power Marketing Risk Prevention and Control Management of Power Supply Enterprises Based on Big Data Analysis Technology
Motwani et al. Modeling Implementation of Big Data Analytics in Oil and Gas Industries in India
Li et al. Function Extraction Based on CFPS and Digital Financial Index: Data Mining Techniques for Prognosis of Operational Risks of Financial Institutions
Donghui Short-term Load Forecasting System for Power System Based on Big Data

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20171121