CN111860985A - Day-ahead power load prediction method based on load decomposition - Google Patents

Day-ahead power load prediction method based on load decomposition Download PDF

Info

Publication number
CN111860985A
CN111860985A CN202010647064.6A CN202010647064A CN111860985A CN 111860985 A CN111860985 A CN 111860985A CN 202010647064 A CN202010647064 A CN 202010647064A CN 111860985 A CN111860985 A CN 111860985A
Authority
CN
China
Prior art keywords
load
day
predicted
daily
service
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.)
Granted
Application number
CN202010647064.6A
Other languages
Chinese (zh)
Other versions
CN111860985B (en
Inventor
徐玉杰
翟树军
杨霞
马梅
吕岳
袁海洲
胡本哲
彭婧
樊倩男
宋杰
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
State Grid Tianjin Electric Power Co Ltd
Original Assignee
State Grid Corp of China SGCC
State Grid Tianjin 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, State Grid Tianjin Electric Power Co Ltd filed Critical State Grid Corp of China SGCC
Priority to CN202010647064.6A priority Critical patent/CN111860985B/en
Publication of CN111860985A publication Critical patent/CN111860985A/en
Application granted granted Critical
Publication of CN111860985B publication Critical patent/CN111860985B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to a day-ahead power load prediction method based on load decomposition, which comprises the following steps: acquiring historical load data of electricity consumption of agriculture, industry, service industry and residents every seven days before a day to be predicted, and a predicted value of temperature and relative humidity of a load prediction day, respectively predicting the load of the electricity consumption of the agriculture, the industry, the service industry and the residents, and acquiring a predicted value of total load of the day to be predicted according to each predicted value of decomposed load; according to the invention, various load predictions after load decomposition are realized by comprehensively considering external conditions such as historical change rules and temperatures of different types of loads, the load prediction precision is improved, and power scheduling is guided better.

Description

Day-ahead power load prediction method based on load decomposition
Technical Field
The invention belongs to the technical field of power load prediction, and particularly relates to a day-ahead power load prediction method based on load decomposition.
Background
The day-ahead power load prediction is the basis of day-ahead scheduling transaction and is the key for ensuring the safe and stable operation of the power grid. The daily load forecast is unique compared to the medium-and long-term (monthly or annual) load forecast and the ultra-short term (hourly, graded, even second) load forecast for power. The medium and long-term load prediction is greatly influenced by macroscopic economic conditions such as GDP (gas diffusion plate) and industrial structure, and the precision requirement is low; the ultra-short term load prediction time is short, the predictability of related influence factors is strong, and the precision requirement is highest. The day-ahead power load is not only related to the current economic and social development conditions, but also closely related to the prediction of the temperature of the day, whether the day is a holiday, a work and rest rule and the like.
With the development of economic society and the improvement of living standard of people, the electrification degree is higher and higher, the power demand is more and more vigorous, and the power consumption of resident living power and service industry is increased year by year. Statistical data show that industrial load is relatively kept stable, electricity consumption of residents in life and commercial activities is closely related to work and rest rules of residents, load of air conditioners is remarkably increased in peak period of electricity consumption, and traditional load prediction based on historical data cannot objectively reflect change rules of different load types, so that load prediction accuracy is insufficient.
Therefore, based on the problems, the method for predicting the day-ahead power load can comprehensively consider external conditions such as historical change rules and temperatures of different types of loads and realize prediction of various loads after load decomposition, and has important practical significance.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a day-ahead power load prediction method which can comprehensively consider external conditions such as historical change rules, temperature and the like of different types of loads and realize various types of load prediction after load decomposition.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
The method for predicting the day-ahead power load based on load decomposition comprises the following steps:
acquiring historical load data of agricultural, industrial, service and residential electricity consumption for seven consecutive days before a day to be predicted, a predicted value of the temperature and the relative humidity of the load prediction day, and the average temperature and the relative humidity of the current day, wherein P isk,i,n、Pk,i,g、Pk,i,s、Pk,i,jLoads of agricultural, industrial, service and residential electricity utilization at the ith moment of the kth day respectively;
acquiring the agricultural electric load at the time i of the day to be predicted by the following formula:
Pk+1,i,n＝Pi,n×θn
Figure RE-GDA0002631583590000021
in the formula, Pk+1,i,nThe predicted value P of the agricultural electric load at the moment i of the day to be predictedi,nTypical of the daily agricultural power load, KnSimulating days for historical load, taking the value of 7, thetanThe agricultural load adjustment coefficient can be determined according to agricultural production seasons;
acquiring the industrial electric load at the time i of the day to be predicted according to the following formula:
Pk+1,i,g＝Pi,g×θg
Figure RE-GDA0002631583590000022
Figure RE-GDA0002631583590000023
in the formula, Pk+1,i,gThe predicted value of the industrial electrical load at the time i of the day to be predicted, Pi,gTypical of daily industrial electrical loads, KgSimulating days for historical load, taking the value of 7, thetagAdjusting the coefficient, P, for the industrial electrical loadk,i0,g、Pi0,gRespectively representing the current day and the typical day ith0Load of time, i0A point in time when the prediction work is performed;
acquiring the service electric load at the moment i of the day to be predicted by the following formula:
Pk+1,i,s＝Pi,s×Ts
Figure RE-GDA0002631583590000031
Figure RE-GDA0002631583590000032
In the formula, Pk+1,i,sFor predicting the service electric load prediction value at time i of day, Pi,sIs typical daily service electric load; w is as,1Weight of service load versus prediction result for the same day of the week, ws,2And the weight of the service business load on the prediction result on other days meets the following requirements: w is as,1+6ws,21 and ws,1＞＞ws,2；TsAdjustment coefficients for air temperature, relative humidity and service load, t0T is the optimum temperature for body feeling,
Figure RE-GDA0002631583590000036
Predicted values of the daily predicted temperature and the current daily average temperature, l,
Figure RE-GDA0002631583590000035
Predicting the daily relative humidity prediction value and the current daily relative humidity, a, for the load, respectivelys、bsRespectively are influence parameters;
acquiring the residential electricity load at the moment i of the day to be predicted by the following formula:
Pk+1,i,j＝Pi,j×Tj
Figure RE-GDA0002631583590000033
Figure RE-GDA0002631583590000034
in the formula, Pk+1,i,jFor predicting the predicted value of the residential electricity load at the time i of the day, Pi,jTypical daily resident electrical load, wj,1The weight of the electricity load of the residents on the same day of the last week to the prediction result, wj,2And the weight of the electricity load of other daily residents on the prediction result meets the following requirements: w is aj,1+6wj,21 and wj,1＞＞wj,2；TjThe adjustment coefficients of the air temperature and the relative humidity to the electricity load of residents are obtained; t is t0T is the optimum temperature for body feeling,
Figure RE-GDA0002631583590000041
Predicted values of the daily predicted temperature and the current daily average temperature, l,
Figure RE-GDA0002631583590000042
Predicting the daily relative humidity prediction value and the current daily relative humidity, a, for the load, respectively j、bjRespectively are influence parameters;
obtaining a total load predicted value at the moment i of the day to be predicted according to the decomposed load predicted values:
Pk+1,i＝Pk+1,i,n+Pk+1,i,g+Pk+1,i,s+Pk+1,i,j。
further, when the historical load data cannot be obtained in a classified manner, the total power load is decomposed based on sample data, and the load decomposition method based on the sample data comprises the following steps:
randomly selecting part of agricultural, industrial, service and residential users, collecting their daily electric quantities, respectively denoted as Qk,n、Qk,g、Qk,sAnd Qk,jK tableIndicating the date and collecting the total power load Pk,i,total；
First, the industrial electrical load is determined
Figure RE-GDA0002631583590000043
Wherein N is more than or equal to 24;
acquiring the electricity loads of agriculture, service industry and residents:
Figure RE-GDA0002631583590000044
Figure RE-GDA0002631583590000045
Figure RE-GDA0002631583590000046
in the formula, Pk,i,n、Pk,i,s、Pk,i,jThe loads of agricultural, service and residential electricity at the ith time of the kth day, Pk,i,totalThe total power load at the ith moment of the kth day is as follows: 24X 60/N min.
Further, ws,1、ws,2The numerical value of (a) can be simulated according to historical data, and can also be artificially formulated according to the characteristic of the load change rule, the closer the load change and the work and rest rule of people are, the more closely ws,1The larger.
Further, wj,1、wj,2The numerical value of (a) can be simulated according to historical data, and can also be artificially formulated according to the characteristic of the load change rule, the closer the load change and the work and rest rule of people are, the more closely wj,1The larger.
Further, t0Taking the mixture at 25 ℃.
The invention has the advantages and positive effects that:
according to the invention, various load predictions after load decomposition are realized by comprehensively considering external conditions such as historical change rules and temperatures of different types of loads, the load prediction precision is improved, and power scheduling is guided better.
Detailed Description
First, it should be noted that the specific structures, features, advantages, etc. of the present invention will be specifically described below by way of example, but all the descriptions are for illustrative purposes only and should not be construed as limiting the present invention in any way. Furthermore, any individual technical features described or implicit in the embodiments mentioned herein may still be continued in any combination or subtraction between these technical features (or their equivalents) to obtain still further embodiments of the invention that may not be mentioned directly herein.
The present invention will be specifically described below.
The method for predicting the day-ahead power load based on load decomposition provided by the embodiment comprises the following steps:
acquiring historical load data of agricultural, industrial, service and residential electricity consumption for seven consecutive days before a day to be predicted, a predicted value of the temperature and the relative humidity of the load prediction day, and the average temperature and the relative humidity of the current day, wherein P is k,i,n、Pk,i,g、Pk,i,s、Pk,i,jLoads of agricultural, industrial, service and residential electricity utilization at the ith moment of the kth day respectively;
because the agricultural power consumption is small in proportion, the load level is low, the agricultural power consumption is greatly influenced by seasons, and strong regularity exists in a short time, the agricultural power consumption load at the time i of the day to be predicted is obtained through the following formula in order to simplify calculation:
Pk+1,i,n＝Pi,n×θn
Figure RE-GDA0002631583590000061
in the formula, Pk+1,i,nThe predicted value P of the agricultural electric load at the moment i of the day to be predictedi,nTypical of the daily agricultural power load, KnSimulating days for historical load, taking the value of 7, thetanThe coefficient is adjusted for the agricultural load, and the daily change trend of the agricultural load can be reflected, thetanCan be confirmed according to agricultural production timeConsidering the strong regularity of agricultural production in a short time, generally take thetan＝1；
For industrial load, the production has stronger continuity and stability, so the industrial electric load at the time i of the day to be predicted is obtained by the following formula by using a trend extrapolation method:
Pk+1,i,g＝Pi,g×θg
Figure RE-GDA0002631583590000062
Figure RE-GDA0002631583590000063
in the formula, Pk+1,i,gThe predicted value of the industrial electrical load at the time i of the day to be predicted, Pi,gTypical of daily industrial electrical loads, KgSimulating days for historical load, taking the value of 7, thetagThe coefficient is adjusted for the industrial electric load, and the daily change trend, P, of the industrial load can be reflectedk,i0,g、Pi0,gRespectively representing the current day and the typical day ith 0Load of time, i0A point in time when the prediction work is performed;
the service industry power load is closely related to the work and rest rule of people, is influenced by working days and holidays, and is more sensitive to air temperature and relative humidity, so the work and rest rule, the air temperature and the relative humidity are comprehensively considered, the third-generation service power load is predicted, and the service industry power load at the moment i of the day to be predicted is obtained through the following formula:
Pk+1,i,s＝Pi,s×Ts
Figure RE-GDA0002631583590000071
Figure RE-GDA0002631583590000072
in the formula, Pk+1,i,sFor predicting the service electric load prediction value at time i of day, Pi,sIs typical daily service electric load; w is as,1Weight of service load versus prediction result for the same day of the week, ws,2And the weight of the service business load on the prediction result on other days meets the following requirements: w is as,1+6ws,21 and ws,1＞＞ws,2，ws,1、 ws,2The numerical value of (a) can be simulated according to historical data, and can also be artificially formulated according to the characteristic of the load change rule, the closer the load change and the work and rest rule of people are, the more closely ws,1The larger; t issThe adjustment coefficients of the air temperature and the relative humidity to the service business load can be obtained through historical data simulation measurement and calculation; t is t0For sensing optimum temperature, the temperature is generally 25 ℃, t,
Figure RE-GDA0002631583590000073
Predicted values of the daily predicted temperature and the current daily average temperature, l,
Figure RE-GDA0002631583590000074
Respectively predicting a daily relative humidity predicted value and the current daily relative humidity for the load; a is s、bsRespectively are influence parameters which can be obtained by historical data simulation measurement;
resident's power consumption load is closely related with people's work and rest law, receives the influence of working day and holiday, and simultaneously, resident's power consumption action is more sensitive to temperature, relative humidity, consequently, should consider work and rest law, temperature and relative humidity comprehensively, realizes the prediction to resident's power consumption load, resident's power consumption load prediction method as follows:
acquiring the residential electricity load at the moment i of the day to be predicted by the following formula:
Pk+1,i,j＝Pi,j×Tj
Figure RE-GDA0002631583590000075
Figure RE-GDA0002631583590000081
in the formula, Pk+1,i,jFor predicting the predicted value of the residential electricity load at the time i of the day, Pi,jTypical daily resident electrical load, wj,1The weight of the electricity load of the residents on the same day of the last week to the prediction result, wj,2And the weight of the electricity load of other daily residents on the prediction result meets the following requirements: w is aj,1+6wj,21 and wj,1＞＞wj,2，wj,1、 wj,2The numerical value of (a) can be simulated according to historical data, and can also be artificially formulated according to the characteristic of the load change rule, the closer the load change and the work and rest rule of people are, the more closely wj,1The larger; t isjThe adjustment coefficients of the air temperature and the relative humidity to the electricity load of residents are obtained; t is t0For sensing optimum temperature, the temperature is generally 25 ℃, t,
Figure RE-GDA0002631583590000082
Predicted values of the daily predicted temperature and the current daily average temperature, l,
Figure RE-GDA0002631583590000083
Respectively predicting a daily relative humidity predicted value and the current daily relative humidity for the load; a is j、bjRespectively are influence parameters which can be obtained by historical data simulation measurement;
obtaining a total load predicted value at the moment i of the day to be predicted according to the decomposed load predicted values:
Pk+1,i＝Pk+1,i,n+Pk+1,i,g+Pk+1,i,s+Pk+1,i,j。
when the historical load data cannot be obtained in a classified manner, the total power load is decomposed based on sample data, and the load decomposition method based on the sample data is as follows:
randomly selecting part of agricultural, industrial, service and residential users, collecting their daily electric quantities, respectively denoted as Qk,n、Qk,g、Qk,sAnd Qk,jK represents the date, and the total power consumption P is collectedk,i,total；
Considering the relative stability of industrial production, the industrial electric load is obtained by simplifying the simulation calculation
Figure RE-GDA0002631583590000084
Wherein N is not less than 24, of course, in the formula
Figure RE-GDA0002631583590000085
In the method, the larger the value of N is, the better the accuracy of the obtained prediction result is, but practice proves that the requirement of the accuracy of the day-ahead power load prediction can be met by taking 96 of N;
acquiring the electricity loads of agriculture, service industry and residents:
Figure RE-GDA0002631583590000091
Figure RE-GDA0002631583590000092
Figure RE-GDA0002631583590000093
in the formula, Pk,i,n、Pk,i,s、Pk,i,jThe loads of agricultural, service and residential electricity at the ith time of the kth day, Pk,i,totalThe total power load at the ith moment of the kth day is as follows: 24X 60/N min.
For example, in this embodiment, taking a certain provincial power grid load data as an example, a day-ahead power load prediction based on load decomposition is performed: due to space limitation, the embodiment only displays part of the time period historical data and the prediction result; in this embodiment, the load on the 8 th day is predicted from the previous 7 th day history load data, and the prediction accuracy is verified by the actual load, it should be noted that, when the industrial electrical load is calculated, values are taken every 15min for 24 hours, that is, values are taken every 15min
Figure RE-GDA0002631583590000094
The load data is shown in the following table:
Figure RE-GDA0002631583590000095
Figure RE-GDA0002631583590000101
to simplify the calculation, let ws,1＝0.4、ws,2＝0.1，wj,1＝0.34、wj,2The typical daily load prediction is calculated as 0.11, as follows:
Figure RE-GDA0002631583590000102
obtaining a load adjustment coefficient simulation result according to historical load data, air temperature, relative humidity and other data, wherein: thetan＝1，θg＝0.9963，Ts＝0.9933，Tj0.9940, the results of the partial load and total load predictions are obtained as follows:
Figure RE-GDA0002631583590000103
Figure RE-GDA0002631583590000111
the comparison between the prediction result of the embodiment and the actual load on the 8 th day and the conventional trend extrapolation prediction method is shown in the table below, and the result shows that the prediction deviation of the embodiment is between-0.28% and 1.10%, which is significantly better than that of the conventional trend extrapolation prediction method.
Figure RE-GDA0002631583590000112
The present invention has been described in detail with reference to the above examples, but the description is only for the preferred examples of the present invention and should not be construed as limiting the scope of the present invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.

Claims (5)

1. The method for predicting the day-ahead power load based on load decomposition is characterized by comprising the following steps: the method comprises the following steps:
acquiring historical load data of agricultural, industrial, service and residential electricity consumption for seven consecutive days before a day to be predicted, a predicted value of the temperature and the relative humidity of the load prediction day, and the average temperature and the relative humidity of the current day, wherein P is k,i,n、Pk,i,g、Pk,i,s、Pk,i,jLoads of agricultural, industrial, service and residential electricity utilization at the ith moment of the kth day respectively;
acquiring the agricultural electric load at the time i of the day to be predicted by the following formula:
Pk+1,i,n＝Pi,n×θn
Figure FDA0002573460790000011
in the formula, Pk+1,i,nThe predicted value P of the agricultural electric load at the moment i of the day to be predictedi,nTypical of the daily agricultural power load, KnSimulating days for historical load, taking the value of 7, thetanAdjusting the coefficient for the agricultural load;
acquiring the industrial electric load at the time i of the day to be predicted according to the following formula:
Pk+1,i,g＝Pi,g×θg
Figure FDA0002573460790000012
Figure FDA0002573460790000013
in the formula, Pk+1,i,gThe predicted value of the industrial electrical load at the time i of the day to be predicted, Pi,gTypical of daily industrial electrical loads, KgSimulating days for historical load, taking the value of 7, thetagFor industrial electrical load regulationThe coefficients of which are such that,
Figure FDA0002573460790000014
respectively representing the current day and the typical day ith0Load of time, i0A point in time when the prediction work is performed;
acquiring the service electric load at the moment i of the day to be predicted by the following formula:
Pk+1,i,s＝Pi,s×Ts
Figure FDA0002573460790000021
Figure FDA0002573460790000022
in the formula, Pk+1,i,sFor predicting the service electric load prediction value at time i of day, Pi,sIs typical daily service electric load; w is as,1Weight of service load versus prediction result for the same day of the week, ws,2And the weight of the service business load on the prediction result on other days meets the following requirements: w is as,1+6ws,21 and ws,1＞＞ws,2；TsAdjustment coefficients for air temperature, relative humidity and service load, t 0T is the optimum temperature for body feeling,
Figure FDA0002573460790000023
Predicted values of the daily predicted temperature and the current daily average temperature, l,
Figure FDA0002573460790000024
Predicting the daily relative humidity prediction value and the current daily relative humidity, a, for the load, respectivelys、bsRespectively are influence parameters;
acquiring the residential electricity load at the moment i of the day to be predicted by the following formula:
Pk+1,i,j＝Pi,j×Tj
Figure FDA0002573460790000025
Figure FDA0002573460790000026
in the formula, Pk+1,i,jFor predicting the predicted value of the residential electricity load at the time i of the day, Pi,jTypical daily resident electrical load, wj,1The weight of the electricity load of the residents on the same day of the last week to the prediction result, wj,2And the weight of the electricity load of other daily residents on the prediction result meets the following requirements: w is aj,1+6wj,21 and wj,1＞＞wj,2；TjThe adjustment coefficients of the air temperature and the relative humidity to the electricity load of residents are obtained; t is t0T is the optimum temperature for body feeling,
Figure FDA0002573460790000027
Predicted values of the daily predicted temperature and the current daily average temperature, l,
Figure FDA0002573460790000028
Predicting the daily relative humidity prediction value and the current daily relative humidity, a, for the load, respectivelyj、bjRespectively are influence parameters;
obtaining a total load predicted value at the moment i of the day to be predicted according to the decomposed load predicted values:
Pk+1,i＝Pk+1,i,n+Pk+1,i,g+Pk+1,i,s+Pk+1,i,j。
2. the method of claim 1, wherein the method comprises: when the historical load data cannot be obtained in a classified mode, decomposing the total power load based on sample data, wherein the load decomposition method based on the sample data comprises the following steps:
Randomly selecting part of agricultural, industrial, service and residential users, collecting their daily electric quantities, respectively denoted as Qk,n、Qk,g、Qk,sAnd Qk,jK represents the date, and the total power consumption P is collectedk,i,total；
First, the industrial electrical load is determined
Figure FDA0002573460790000031
Wherein N is more than or equal to 24;
acquiring the electricity loads of agriculture, service industry and residents:
Figure FDA0002573460790000032
Figure FDA0002573460790000033
Figure FDA0002573460790000034
in the formula, Pk,i,n、Pk,i,s、Pk,i,jThe loads of agricultural, service and residential electricity at the ith time of the kth day, Pk,i,totalThe total power load at the ith moment of the kth day is as follows: 24X 60/N min.
3. The method of load split based day-ahead electrical load prediction according to claim 2, characterized by: w is as,1、ws,2The numerical value of (a) can be simulated according to historical data, and can also be artificially formulated according to the characteristic of the load change rule, the closer the load change and the work and rest rule of people are, the more closely ws,1The larger.
4. The method of claim 3, wherein the method comprises: w is aj,1、wj,2The numerical value of (a) can be simulated according to historical data, and can also be artificially formulated according to the characteristic of the load change rule, the closer the load change and the work and rest rule of people are, the more closely wj,1The larger.
5. The method of claim 3, wherein the method comprises: t is t 0Taking the mixture at 25 ℃.
CN202010647064.6A 2020-07-07 2020-07-07 Day-ahead power load prediction method based on load decomposition Active CN111860985B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010647064.6A CN111860985B (en) 2020-07-07 2020-07-07 Day-ahead power load prediction method based on load decomposition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010647064.6A CN111860985B (en) 2020-07-07 2020-07-07 Day-ahead power load prediction method based on load decomposition

Publications (2)

Publication Number Publication Date
CN111860985A true CN111860985A (en) 2020-10-30
CN111860985B CN111860985B (en) 2022-04-01

Family

ID=73153691

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010647064.6A Active CN111860985B (en) 2020-07-07 2020-07-07 Day-ahead power load prediction method based on load decomposition

Country Status (1)

Country Link
CN (1) CN111860985B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112598154A (en) * 2020-11-23 2021-04-02 国网浙江海宁市供电有限公司 Method for predicting space load transfer
CN112696728A (en) * 2021-01-22 2021-04-23 北京嘉洁能科技股份有限公司 Control system for balancing electric load and reducing electric capacity increase
CN115800273A (en) * 2023-02-07 2023-03-14 四川智源能诚售电有限公司 Power load curve prediction method and device based on big data and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109242189A (en) * 2018-09-12 2019-01-18 国网安徽省电力有限公司合肥供电公司 A kind of Short-Term Load Forecasting of Electric Power System based on meteorologic factor
CN110503256A (en) * 2019-08-14 2019-11-26 北京国网信通埃森哲信息技术有限公司 Short-term load forecasting method and system based on big data technology
CN110991748A (en) * 2019-12-05 2020-04-10 国网江苏省电力有限公司南通供电分公司 Short-term load prediction method for urban power grid

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109242189A (en) * 2018-09-12 2019-01-18 国网安徽省电力有限公司合肥供电公司 A kind of Short-Term Load Forecasting of Electric Power System based on meteorologic factor
CN110503256A (en) * 2019-08-14 2019-11-26 北京国网信通埃森哲信息技术有限公司 Short-term load forecasting method and system based on big data technology
CN110991748A (en) * 2019-12-05 2020-04-10 国网江苏省电力有限公司南通供电分公司 Short-term load prediction method for urban power grid

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
唐发荣 等: "基于多因素组合分析的配电网负荷预测模型研究", 《电子元器件与信息技术》 *
王成纲 等: "基于小波分解的电力系统短期负荷预测方法研究", 《河北电力技术》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112598154A (en) * 2020-11-23 2021-04-02 国网浙江海宁市供电有限公司 Method for predicting space load transfer
CN112696728A (en) * 2021-01-22 2021-04-23 北京嘉洁能科技股份有限公司 Control system for balancing electric load and reducing electric capacity increase
CN115800273A (en) * 2023-02-07 2023-03-14 四川智源能诚售电有限公司 Power load curve prediction method and device based on big data and storage medium

Also Published As

Publication number Publication date
CN111860985B (en) 2022-04-01

Similar Documents

Publication Publication Date Title
CN111860985B (en) Day-ahead power load prediction method based on load decomposition
Phuangpornpitak et al. A study of load demand forecasting models in electric power system operation and planning
CN106022536B (en) Seasonal power consumption prediction method and system
JP2005158020A (en) Method, system and program for managing energy
CN109886567B (en) Short-term load prediction method considering somatosensory temperature and radiation intensity
CN105762793B (en) The Distribution Network Failure loss of outage appraisal procedure of meter and distributed new
CN102426674A (en) Power system load prediction method based on Markov chain
Belaid et al. Investigating the factors shaping residential energy consumption patterns in France: evidence form quantile regression
CN114254838B (en) Method for determining short-term power load prediction influence factor
JP6617476B2 (en) Demand power prediction apparatus, demand power prediction method, and computer program
CN117239731B (en) Holiday short-term power load prediction method based on hybrid model
CN113205252A (en) Aggregated load scheduling method based on demand side load peak regulation potential parameter prediction
CN109299814A (en) A kind of meteorological effect quantity division prediction technique
Lam et al. An analysis of climatic influences on chiller plant electricity consumption
CN112149309A (en) Temperature-adjusting load curve fitting method considering temperature-load correlation
CN104252647B (en) Electro-load forecast method based on anti-distance weighting interpolation method
CN111160993A (en) User practical and stage release coefficient analysis method based on user load application
CN113313312A (en) Spring festival load rolling prediction method based on short, medium and long time scales
CN111415037A (en) Electric power system short-term load prediction method based on similar day and artificial neural network
Liu et al. Short-term load prediction method for power distributing method based on back-propagation neural network
CN111708987A (en) Method for predicting load of multiple parallel transformers of transformer substation
CN110991750A (en) Short-term power load prediction method based on neural network
CN114169746A (en) Method for determining cooling load of air conditioner in summer
Kostov et al. Power System Load Forecasting by using Sinuses Approximation and Wavelet Transform
CN113033867B (en) Provincial power grid load characteristic analysis method considering electric heating characteristics

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