CN102402726B - Method for predicting electric quantity of large-scale distribution network based on regional load analysis - Google Patents

Method for predicting electric quantity of large-scale distribution network based on regional load analysis Download PDF

Info

Publication number
CN102402726B
CN102402726B CN201110344932.4A CN201110344932A CN102402726B CN 102402726 B CN102402726 B CN 102402726B CN 201110344932 A CN201110344932 A CN 201110344932A CN 102402726 B CN102402726 B CN 102402726B
Authority
CN
China
Prior art keywords
load
power supply
distribution network
region
supply area
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
Application number
CN201110344932.4A
Other languages
Chinese (zh)
Other versions
CN102402726A (en
Inventor
崔艳妍
李志勇
苏剑
刘伟
韦涛
惠慧
侯义明
赵大溥
赵明欣
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.)
CHONGQING CITY ELECTRICAL POWER Co
China Electric Power Research Institute Co Ltd CEPRI
Original Assignee
CHONGQING CITY ELECTRICAL POWER Co
China Electric Power Research Institute Co Ltd CEPRI
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 CHONGQING CITY ELECTRICAL POWER Co, China Electric Power Research Institute Co Ltd CEPRI filed Critical CHONGQING CITY ELECTRICAL POWER Co
Priority to CN201110344932.4A priority Critical patent/CN102402726B/en
Publication of CN102402726A publication Critical patent/CN102402726A/en
Application granted granted Critical
Publication of CN102402726B publication Critical patent/CN102402726B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention provides a method for predicting electric quantity of a large-scale distribution network based on regional load analysis, and belongs to the field of power grid planning. The predicting method comprises the following steps of: dividing power supply regions; selecting a power supply region; calculating correction coefficient; performing electric quantity prediction on the selected power supply region; and predicting the electric quantity of the distribution network according to the electric quantity prediction result of the selected region. The method is high in precision, quick in calculation, strong in actual operability, simple in principle and good in flexibility; the method greatly reduces the workload of electric quantity prediction data acquisition and analytical calculation of the large-scale distribution network, and can be applied to electric quantity prediction of large-scale distribution networks of all regions in China; and by dividing the power supply regions and analyzing the load of each power supply region, the economic development patterns and the load development characteristics of the power supply regions can be better grasped, and important basis is provided for formulating more focused power grid construction schemes.

Description

A kind of extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis
Technical field
The invention belongs to Electric Power Network Planning field, be specifically related to a kind of extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis.
Background technology
Load forecast is the important component part of Power System Planning, is also the basis of Economical Operation of Power Systems, and it is all of crucial importance to Power System Planning and operation.Load prediction work will suit measures to local conditions to select suitable method to predict for different regions, is reasonably predicted the outcome, for Electric Power Network Planning provides the decision-making foundation of science.
For the feature of load prediction and the classification of load prediction, there is at present multiple Forecasting Methodology.Conventional load forecasting method is divided into total load Forecasting Methodology and saturation load forecasting method.Total load Forecasting Methodology comprises classical class Forecasting Methodology and emerging Forecasting Methodology.Wherein the output value unit consumption method computation model in classical class Forecasting Methodology is simple, project period output value unit consumption definite subjective, depend on a large amount of statistical works and expertise; Elastic coefficient method computing method are simple, and it is larger that elasticity coefficient is affected by the market factor, depend on a large amount of statistical works and expertise; Per capita household electricity consumption method computing method are simple, and the horizontal difference of consumption per capita of different regions is larger; Load density method computing method are simple, but the definite of load density target need to do a large amount of load investigation works.Gray model method principle in emerging Forecasting Methodology is simple, computing convenient, short-term forecasting precision is high, but for the electric load that has undulatory property and change, predicated error is larger, is not too applicable to long-term forecasting; The expert system approach construction cycle is long, depends on the quantity of information of knowledge base, implements difficulty large; Neural network has self-learning function, and in the situation of sample abundance, precision of prediction is higher, but adequate sample to obtain difficulty larger.
The load prediction work of science, can not pursue complicated advanced mathematical method simply, or pursues simply the precision of data fitting, thereby has ignored the feature of electric system itself.But should, according to the condition of load prediction and actual needs, in conjunction with the various factors that affects load prediction accuracy, comprehensively select applicable Forecasting Methodology.For extensive power distribution network, because its service area is wide, zones of different load present situation and development trend are variant, also there is very big-difference in interregional Economic Development Mode and construction scheme, especially in whole power distribution network service area, carry out the required related data of load prediction to obtain difficulty larger, adopt conventional method to carry out Electric Power Forecasting Based on Artificial and there is sizable workload and implement difficulty.
Summary of the invention
In order to overcome above-mentioned the deficiencies in the prior art, the invention provides a kind of extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis, extensive power distribution network is divided into a few class power supply areas, from every class power supply area, each one or several regions of selecting are analyzed, by the historical load of regional, the analysis and arrangement of the data such as electric weight rising tendency and part throttle characteristics, in conjunction with the historical rising tendency of GDP per capita and prediction case, dope the power load demand of regional, saturation loading level and regional economic construction and the development program in the flourishing city of reference simultaneously, draw the load density of all kinds of power supply areas, in conjunction with the power supply area of all kinds of power supply areas, static growth and the dynamic change of consideration of regional simultaneously, and then dope the power load of extensive power distribution network.
In order to realize foregoing invention object, the present invention adopts following technical scheme:
Based on an extensive power distribution network Electric Power Forecasting Based on Artificial method for region load Analysis, described Forecasting Methodology comprises following five steps:
(1) divide power supply area;
(2) select power supply area;
(3) calculate correction factor;
(4) power supply area of selecting is carried out to Electric Power Forecasting Based on Artificial;
(5) according to the prediction of result power distribution network quantity of electricity of the Electric Power Forecasting Based on Artificial in selected region.
It is, according to the administrative grade in region, economic development situation and electric power feature factor, the service area of power distribution network is divided into following 6 class power supply areas that described step (1) is divided power supply area: urban core is built district, urban development district, flourishing cities and towns, general cities and towns, general rural area, outlying rural area.
Divide described power supply area according to following index:
1) the year GDP per capita in region;
2) composition of industry in region;
3) the year power distribution network delivery per capita in region;
4) load density in region;
5) the load growth situation in region.
Described load density represent the to load quantization parameter of densely distributed degree, it is the average electric power numerical value of every square kilometre, with MW/km 2metering.
Described step (2) selects power supply area to refer to the several regions of each selection the 6 class power supply areas from dividing, and analyzes the data in selected region, therefrom selects one or several region.
The process that described step (3) is calculated correction factor comprises the following steps:
1) existing load and the electric weight of statistics selected areas;
2) calculate selected areas unit's power supply area load and electric weight, result of calculation is as load and the electric weight index of all kinds of described power supply area units power supply area;
3) the power supply area of all kinds of described power supply areas in statistics service area;
4) calculate the existing total load L of power distribution network in described service area according to the unit area loading of described power supply area, electric weight index and power supply area 0 ∑with electric weight Q 0 ∑;
5) according to the existing load of the reality of power distribution network L 0with electric weight Q 0calculated load correction factor k 1with electric weight correction factor k 2, wherein:
k 1 = L 0 L 0 Σ ; k 2 = Q 0 Q 0 Σ .
Described step (4) is carried out electric power network prediction to the region of selecting and is specifically comprised the following steps:
1) historical load rising tendency and the part throttle characteristics of analysis selected areas;
2) the load growth point of analysis selected areas;
3) determine load forecasting method according to the analysis result of historical load and load growth point, collect load prediction related data;
4) selected areas quantity of electricity is predicted, and carried out verification to predicting the outcome, as all kinds of power supply area load density predicted values.
Described step (5) is carried out extensive power distribution network Electric Power Forecasting Based on Artificial according to the result of the Electric Power Forecasting Based on Artificial in selected region and is specifically comprised the following steps:
1), according to all kinds of described power supply area load density predicted values and power supply area, calculate all kinds of power supply area prediction load L ai(i=1 ..., n) with electric weight Q ai(i=1 ..., n);
2) described all kinds of power supply area prediction loads and electric weight are gathered, obtain the extensive power distribution network prediction of universe load initial value L ∑and prediction power quantity predicting initial value Q ∑, wherein:
L Σ = Σ i = 1 n L Ai ; Q Σ = Σ i = 1 n Q Ai ;
3) utilize the correction factor k of described load 1correction factor k with electric weight 2proofread and correct, obtain the extensive power distribution network load prediction of universe value L and power quantity predicting value Q, wherein:
L＝L ∑×k 1，Q＝Q ∑×k 2。
Compared to the prior art, beneficial effect of the present invention is:
1. precision is higher, calculates soon, has stronger actual operability;
2. principle is simple, and dirigibility is good;
3. significantly reduce the Data Collection of extensive power distribution network Electric Power Forecasting Based on Artificial and the workload of analytical calculation, can be applicable in the Electric Power Forecasting Based on Artificial of China's extensive power distribution network in all kinds of areas;
4. by division of the power supply area and the load Analysis to each power supply area, can better hold Economic Development Mode and the load developing characteristics of every class power supply area, provide important evidence for formulating more targetedly power grid construction scheme.
Brief description of the drawings
Fig. 1 is the process flow diagram of the extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis;
Fig. 2 carries out extensive power distribution network Electric Power Forecasting Based on Artificial process flow diagram according to the result of the Electric Power Forecasting Based on Artificial in selected region.
Embodiment
Below in conjunction with accompanying drawing, the present invention is made to further supplementary notes.
Described Forecasting Methodology comprises following five steps:
(1) divide power supply area;
(2) select power supply area;
(3) calculate correction factor;
(4) power supply area of selecting is carried out to Electric Power Forecasting Based on Artificial;
(5) according to the prediction of result power distribution network quantity of electricity of the Electric Power Forecasting Based on Artificial in selected region.
It is, according to the administrative grade in region, economic development situation and electric power feature factor, the service area of power distribution network is divided into following 6 class power supply areas that described step (1) is divided power supply area: urban core is built district, urban development district, flourishing cities and towns, general cities and towns, general rural area, outlying rural area.
Divide described power supply area according to following index:
1) the year GDP per capita in region;
2) composition of industry in region;
3) the year power distribution network delivery per capita in region;
4) load density in region;
5) the load growth situation in region.
Described load density represent the to load quantization parameter of densely distributed degree, it is the average electric power numerical value of every square kilometre, with MW/km 2metering.
Described step (2) selects power supply area to refer to the several regions of each selection the 6 class power supply areas from dividing, and analyzes the data in selected region, therefrom selects one or several region.
The process that described step (3) is calculated correction factor comprises the following steps:
1) existing load and the electric weight of statistics selected areas;
2) calculate selected areas unit's power supply area load and electric weight, result of calculation is as load and the electric weight index of all kinds of described power supply area units power supply area;
3) the power supply area of all kinds of described power supply areas in statistics service area;
4) calculate the existing total load L of power distribution network in described service area according to the unit area loading of described power supply area, electric weight index and power supply area 0 ∑with electric weight Q 0 ∑;
5) according to the existing load of the reality of power distribution network L 0with electric weight Q 0calculated load correction factor k 1with electric weight correction factor k 2, wherein:
k 1 = L 0 L 0 Σ ; k 2 = Q 0 Q 0 Σ .
Described step (4) is carried out electric power network prediction to the region of selecting and is specifically comprised the following steps:
1) historical load rising tendency and the part throttle characteristics of analysis selected areas;
2) the load growth point of analysis selected areas;
3) determine load forecasting method according to the analysis result of historical load and load growth point, collect load prediction related data;
4) selected areas quantity of electricity is predicted, and carried out verification to predicting the outcome, as all kinds of power supply area load density predicted values.
Described step (5) is carried out extensive power distribution network Electric Power Forecasting Based on Artificial according to the result of the Electric Power Forecasting Based on Artificial in selected region and is specifically comprised the following steps:
1), according to all kinds of described power supply area load density predicted values and power supply area, calculate all kinds of power supply area prediction load L ai(i=1 ..., n) with electric weight Q ai(i=1 ..., n);
2) described all kinds of power supply area prediction loads and electric weight are gathered, obtain the extensive power distribution network prediction of universe load initial value L ∑and prediction power quantity predicting initial value Q ∑, wherein:
L Σ = Σ i = 1 n L Ai ; Q Σ = Σ i = 1 n Q Ai ;
3) utilize the correction factor k of described load 1correction factor k with electric weight 2proofread and correct, obtain the extensive power distribution network load prediction of universe value L and power quantity predicting value Q, wherein:
L＝L ∑×k 1，Q＝Q ∑×k 2。

Claims (5)

1. the extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis, is characterized in that: described Forecasting Methodology comprises following five steps:
(1) divide power supply area;
(2) select power supply area;
(3) calculate correction factor;
(4) power supply area of selecting is carried out to Electric Power Forecasting Based on Artificial;
(5) according to the prediction of result power distribution network quantity of electricity of the Electric Power Forecasting Based on Artificial in selected region;
The process that described step (3) is calculated correction factor comprises the following steps:
1) existing load and the electric weight of statistics selected areas;
2) calculate selected areas unit's power supply area load and electric weight, result of calculation is as load and the electric weight index of all kinds of described power supply area units power supply area;
3) the power supply area of all kinds of described power supply areas in statistics service area;
4) calculate the existing total load L of power distribution network in described service area according to the unit area loading of described power supply area, electric weight index and power supply area 0 Σwith electric weight Q 0 Σ;
5) according to the existing load of the reality of power distribution network L 0with electric weight Q 0calculated load correction factor k 1with electric weight correction factor k 2, wherein:
k 1 = L 0 L 0 Σ ; k 2 = Q 0 Q 0 Σ ;
Described step (4) is carried out Electric Power Forecasting Based on Artificial to the region of selecting and is specifically comprised the following steps:
1) historical load rising tendency and the part throttle characteristics of analysis selected areas;
2) the load growth point of analysis selected areas;
3) determine load forecasting method according to the analysis result of historical load and load growth point, collect load prediction related data;
4) selected areas quantity of electricity is predicted, and carried out verification to predicting the outcome, as all kinds of power supply area load density predicted values;
Described step (5) is carried out extensive power distribution network Electric Power Forecasting Based on Artificial according to the result of the Electric Power Forecasting Based on Artificial in selected region and is specifically comprised the following steps:
1), according to all kinds of described power supply area load density predicted values and power supply area, calculate all kinds of power supply area prediction load L ai(i=1 ..., n) with electric weight Q ai(i=1 ..., n);
2) described all kinds of power supply area prediction loads and electric weight are gathered, obtain the extensive power distribution network prediction of universe load initial value L Σand prediction electric weight initial value Q Σ, wherein:
L Σ = Σ i = 1 n L Ai ; Q Σ = Σ i = 1 n Q Ai ;
3) utilize the correction factor k of described load 1correction factor k with electric weight 2proofread and correct, obtain the extensive power distribution network load prediction of universe value L and power quantity predicting value Q, wherein:
L＝L Σ×k 1，Q＝Q Σ×k 2。
2. a kind of extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis according to claim 1, is characterized in that: it is, according to the administrative grade in region, economic development situation and electric power feature factor, the service area of power distribution network is divided into following 6 class power supply areas that described step (1) is divided power supply area: urban core is built district, urban development district, flourishing cities and towns, general cities and towns, general rural area, outlying rural area.
3. a kind of extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis according to claim 2, is characterized in that: divide described power supply area according to following index:
1) the year GDP per capita in region;
2) composition of industry in region;
3) the year power distribution network delivery per capita in region;
4) load density in region;
5) the load growth situation in region.
4. a kind of extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis according to claim 3, it is characterized in that: described load density represent the to load quantization parameter of densely distributed degree, it is the average electric power numerical value of every square kilometre, with MW/km 2metering.
5. a kind of extensive power distribution network Electric Power Forecasting Based on Artificial method based on region load Analysis according to claim 2, it is characterized in that: described step (2) selects power supply area to refer to the several regions of each selection the 6 class power supply areas from dividing, and analyze the data in selected region, therefrom select one or several region.
CN201110344932.4A 2011-11-04 2011-11-04 Method for predicting electric quantity of large-scale distribution network based on regional load analysis Active CN102402726B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201110344932.4A CN102402726B (en) 2011-11-04 2011-11-04 Method for predicting electric quantity of large-scale distribution network based on regional load analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201110344932.4A CN102402726B (en) 2011-11-04 2011-11-04 Method for predicting electric quantity of large-scale distribution network based on regional load analysis

Publications (2)

Publication Number Publication Date
CN102402726A CN102402726A (en) 2012-04-04
CN102402726B true CN102402726B (en) 2014-08-27

Family

ID=45884908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201110344932.4A Active CN102402726B (en) 2011-11-04 2011-11-04 Method for predicting electric quantity of large-scale distribution network based on regional load analysis

Country Status (1)

Country Link
CN (1) CN102402726B (en)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120330472A1 (en) * 2011-06-21 2012-12-27 General Electric Company Power consumption prediction systems and methods
CN102682198A (en) * 2012-04-26 2012-09-19 上海市电力公司 Method for forecasting annual maximum electrical load
CN103150605B (en) * 2012-05-07 2014-06-25 山东电力集团公司青岛供电公司 Power grid planning auxiliary system
CN102930481B (en) * 2012-11-20 2017-06-13 广东电网公司 network load density analysis method and system
CN103336996A (en) * 2013-06-05 2013-10-02 上海市电力公司 City electric power load prediction method based on computable general equilibrium (CGE) model
CN103514487B (en) * 2013-07-15 2016-08-03 国家电网公司 A kind of distribution network load Forecasting Methodology containing distributed power source
CN103426037A (en) * 2013-08-21 2013-12-04 国家电网公司 Method for predicting multiple power demand scenarios on basis of dynamic computable general equilibrium model
CN103679289B (en) * 2013-12-09 2017-12-22 国家电网公司 Methods of electric load forecasting based on multiple regression extrapolation
CN103903192B (en) * 2014-03-27 2017-07-07 国家电网公司 A kind of method for building up in power distribution network powering mode storehouse
CN104091227B (en) * 2014-06-17 2017-02-08 华南理工大学 Method for analyzing load density of power consumers in city
CN104134999B (en) * 2014-08-06 2016-06-08 国家电网公司 Distribution network based on multi-data source measures the practical method of calculation of efficiency analysis
CN106650986A (en) * 2016-09-13 2017-05-10 云南电网有限责任公司 Method and device for forecasting regional maximum loads of power distribution network
CN106952042A (en) * 2017-03-23 2017-07-14 北京恒华龙信数据科技有限公司 A kind of electricity sales amount Forecasting Methodology and device
CN107146002A (en) * 2017-04-13 2017-09-08 天津天大求实电力新技术股份有限公司 One kind builds area's distribution network planning method and system
CN107622344A (en) * 2017-09-04 2018-01-23 佛山佳牧乐科技有限公司 A kind of method of supplying power to and device
CN108205716A (en) * 2017-12-29 2018-06-26 国网山东省电力公司日照供电公司 Distribution transforming attaching capacity prediction methods and system
CN108388967A (en) * 2018-03-14 2018-08-10 华电电力科学研究院有限公司 A kind of distributed energy load design system and design method
CN108304978A (en) * 2018-05-08 2018-07-20 国网江西省电力有限公司经济技术研究院 A kind of mid-term Electric Power Load Forecast method based on data clusters theory
CN111191811A (en) * 2018-11-14 2020-05-22 中兴通讯股份有限公司 Cluster load prediction method and device and storage medium
CN112348254B (en) * 2020-11-06 2023-09-01 国网新疆电力有限公司昌吉供电公司 Electric power space load prediction and adjustment method
CN116316609B (en) * 2023-04-17 2024-04-09 泰州开泰电力设计有限公司 Power distribution system based on loss application

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1828645A (en) * 2006-04-07 2006-09-06 上海电力学院 Town power distribution network simultaneity factor load prediction method
CN101976841A (en) * 2010-10-21 2011-02-16 河北省电力研究院 Balance matching method for all classes of load forecasting indexes of power system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
IL206232A (en) * 2010-06-07 2017-09-28 Izidor Liberman System and method for planning of demand for power on an electrical power network

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1828645A (en) * 2006-04-07 2006-09-06 上海电力学院 Town power distribution network simultaneity factor load prediction method
CN101976841A (en) * 2010-10-21 2011-02-16 河北省电力研究院 Balance matching method for all classes of load forecasting indexes of power system

Also Published As

Publication number Publication date
CN102402726A (en) 2012-04-04

Similar Documents

Publication Publication Date Title
CN102402726B (en) Method for predicting electric quantity of large-scale distribution network based on regional load analysis
CN111445060B (en) Community carbon emission monitoring and predicting system and method
CN116646933B (en) Big data-based power load scheduling method and system
CN103853106B (en) A kind of energy consumption Prediction Parameters optimization method of building energy supplied equipment
CN107292766B (en) Wind power consumption-oriented power system peak regulation means economical evaluation method and system
CN109492950B (en) Prediction method capable of meeting space saturation load of large area range based on GIS technology
CN110222882A (en) A kind of prediction technique and device of electric system Mid-long Term Load
CN111552923A (en) Load prediction method and load prediction system based on universal distribution
CN106682763B (en) Power load optimization prediction method for large amount of sample data
CN105389636A (en) Low-voltage area KFCM-SVR reasonable line loss prediction method
CN105184455A (en) High dimension visualized analysis method facing urban electric power data analysis
CN102509173B (en) A kind of based on markovian power system load Accurate Prediction method
CN103310388B (en) Based on the composite index of grid operation method of calculation of information source entropy
CN110490409B (en) DNN-based low-voltage transformer area line loss rate benchmarking value setting method
CN102509027B (en) Wind powder combined predication method based on cross entropy theory
Nagaraja et al. A survey on wind energy, load and price forecasting:(Forecasting methods)
Du et al. Prediction of electricity consumption based on GM (1, Nr) model in Jiangsu province, China
CN107679666A (en) A kind of power consumption prediction method based on Shapley values and economic development
CN110533247A (en) A kind of monthly electricity demand forecasting method compensated using temperature record abnormal point
CN117273337A (en) Intelligent electric energy meter evaluation method
CN112365082A (en) Public energy consumption prediction method based on machine learning
CN104091227A (en) Method for analyzing load density of power consumers in city
CN115809718B (en) Cascade power station power generation and ecological cooperative optimization method and system based on multi-objective competition relationship quantification
CN111144628A (en) Distributed energy supply type cooling, heating and power load prediction model system and method
CN113935523A (en) Voltage trend prediction method based on voltage change rule

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant