CN114238856A - Method, device and equipment for solving future prediction error of wind and light resources and storage medium - Google Patents

Method, device and equipment for solving future prediction error of wind and light resources and storage medium Download PDF

Info

Publication number
CN114238856A
CN114238856A CN202111427537.2A CN202111427537A CN114238856A CN 114238856 A CN114238856 A CN 114238856A CN 202111427537 A CN202111427537 A CN 202111427537A CN 114238856 A CN114238856 A CN 114238856A
Authority
CN
China
Prior art keywords
wind
historical
prediction error
photovoltaic
future
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
CN202111427537.2A
Other languages
Chinese (zh)
Inventor
袁泉
张蔷
邹金
卓映君
王子强
卢斯煜
王巍
李豹
周毓敏
姚海成
周鑫
卢伟辉
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.)
CSG Electric Power Research Institute
China Southern Power Grid Co Ltd
Original Assignee
CSG Electric Power Research Institute
China Southern Power Grid 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 CSG Electric Power Research Institute, China Southern Power Grid Co Ltd filed Critical CSG Electric Power Research Institute
Priority to CN202111427537.2A priority Critical patent/CN114238856A/en
Publication of CN114238856A publication Critical patent/CN114238856A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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—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)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Tourism & Hospitality (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Mathematical Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Development Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Quality & Reliability (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Water Supply & Treatment (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Biology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Primary Health Care (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Public Health (AREA)
  • Algebra (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)

Abstract

The invention discloses a method, a device, equipment and a storage medium for solving future prediction errors of wind and light resources, wherein the method comprises the following steps: based on a wind and light prediction error regression model, respectively obtaining the historical wind power, the photovoltaic installed ratio and the absolute average value of the per unit value of the historical wind and light prediction error in the day and night time of each season in the preset historical time period according to historical wind and light output data, and then performing parameter regression fitting to obtain the wind power and photovoltaic installed influence factors in the day and night time of each season; then, according to preset future wind and light output data and wind power and photovoltaic installation influence factors, obtaining future prediction error values of day and night time periods of each season in a preset future time period; the invention considers the seasonal difference and day-night difference of the wind and light resources and the influence of the installed wind power number and the installed photovoltaic number on the prediction error of the wind and light resources when solving the future prediction error value of the wind and light resources, thereby obtaining the accurate future prediction error value.

Description

Method, device and equipment for solving future prediction error of wind and light resources and storage medium
Technical Field
The invention relates to the technical field of new energy power generation, in particular to a method, a device, equipment and a storage medium for solving future prediction errors of wind and light resources.
Background
The prediction error of the new energy has an important influence on the operation of a power grid, and wind power resources and photovoltaic resources which are used as the new energy are collectively called as wind and light resources, and the randomness and the volatility of the wind and light resources increase the difficulty in solving the future prediction error of the wind and light resources. In the prior art, the method for solving the future prediction error of the wind and light resources does not generally consider the distribution difference of the wind and light resources in a time period and the influence of the installed wind and light numbers on the prediction error of the wind and light resources, so that the accuracy of the prediction error is poor and the reference is difficult to provide for the power grid scheduling.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for solving future prediction errors of wind and light resources, aiming at solving the problem of poor accuracy of solving the future prediction errors of the wind and light resources in the prior art, and fully considering seasonal differences and day-night differences of the wind and light resources and the influence of wind power installation numbers and photovoltaic installation numbers on the prediction errors of the wind and light resources when the future prediction errors of the wind and light resources are subjected to fitting solving, so that accurate future prediction error values are obtained, and reference can be provided for power grid scheduling according to the future prediction error values.
In order to solve the above technical problem, a first aspect of the embodiments of the present invention provides a method for solving a future prediction error of a wind and light resource, including:
based on a pre-acquired wind and light prediction error regression model, respectively acquiring the absolute average values of the historical wind and light installed occupation ratio, the historical photovoltaic installed occupation ratio and the historical wind and light prediction error per unit value in the day and night time of each season in a preset historical time period according to pre-acquired historical wind and light output data;
based on the wind and light prediction error regression model, respectively performing parameter regression fitting according to the historical wind power installed occupation ratio, the historical photovoltaic installed occupation ratio and the absolute average value of the historical wind and light prediction error per unit value of each season in the preset historical time period to obtain wind power installed influence factors and photovoltaic installed influence factors of each season in the day and night time period;
based on the wind and light prediction error regression model, obtaining future prediction error values of day and night time periods of each season in a preset future time period according to preset future wind and light output data, the wind power installation influence factors and the photovoltaic installation influence factors;
the historical wind and photovoltaic output data comprise a historical wind and photovoltaic total installed number, a historical wind and photovoltaic output prediction error and a historical photovoltaic output prediction error of the preset historical time period;
the future wind and light output data comprise the future wind power total installed number and the future photovoltaic total installed number of the preset future time period.
Preferably, the method specifically obtains the wind-solar prediction error regression model in advance through the following steps:
constructing the wind and light prediction error regression model according to the following expression:
Figure BDA0003374543580000021
wherein, CwFor the total installed number of wind power, CpIs the total photovoltaic installed number, X is the wind power installed proportion, Y is the photovoltaic installed proportion, PweiFor the prediction error of wind power output in i time period, PpeiThe method comprises the steps of obtaining a photovoltaic output prediction error in a time period i, obtaining N as the total time period, obtaining Z as the absolute average value of the per-unit values of the wind and photovoltaic output prediction errors in each time period, obtaining a wind power installation influence factor, obtaining b as the photovoltaic installation influence factor, and obtaining c as a constant term.
Preferably, the obtaining, based on the pre-obtained wind-solar prediction error regression model, the absolute average values of the historical wind-power installed proportion, the historical photovoltaic installed proportion, and the historical wind-solar prediction error per unit value in the day and night time periods of each season in the preset historical time period according to the pre-obtained historical wind-solar output data specifically includes:
obtaining the absolute average value of a first historical wind power installed ratio, a first historical photovoltaic installed ratio and a first historical wind-solar prediction error per unit value of the daytime period of each season in a preset historical period based on a pre-obtained wind-solar prediction error regression model according to pre-obtained historical wind-solar output data;
and obtaining the absolute average value of a second historical wind power installed proportion, a second historical photovoltaic installed proportion and a second historical wind power predicted error per unit value of the night time of each season in the preset historical time period based on the wind and light predicted error regression model according to the historical wind power total installed number and the historical wind power output predicted error of the preset historical time period, wherein the second historical photovoltaic installed proportion is zero.
Preferably, the obtaining, based on the wind-light prediction error regression model, a future prediction error value in a day and night time period of each season in a preset future time period according to preset future wind-light output data, the wind power installed influence factor and the photovoltaic installed influence factor specifically includes:
respectively obtaining the future wind power installed proportion and the future photovoltaic installed proportion of each season in the preset future time period in the day and night time period based on the wind and light prediction error regression model according to preset future wind and light output data;
and obtaining future prediction error values of day and night time periods of each season in a preset future time period based on the wind and light prediction error regression model according to the future wind power installation proportion, the future photovoltaic installation proportion, the wind power installation influence factor and the photovoltaic installation influence factor.
The second aspect of the embodiments of the present invention provides a device for solving future prediction errors of wind and light resources, including:
the data acquisition module is used for respectively acquiring the historical wind power installed proportion, the historical photovoltaic installed proportion and the absolute average value of the historical wind power prediction error per unit value in the day and night time periods of each season in the preset historical time period based on the pre-acquired wind and light prediction error regression model;
the parameter regression fitting module is used for performing parameter regression fitting according to the historical wind power installed proportion, the historical photovoltaic installed proportion and the absolute average value of the historical wind power prediction error per unit value in the day and night time of each season in the preset historical time period respectively based on the wind and light prediction error regression model to obtain wind power installed influence factors and photovoltaic installed influence factors in the day and night time of each season;
the future prediction error value obtaining module is used for obtaining future prediction error values of day and night time periods of each season in a preset future time period according to preset future wind and light output data, the wind power installation influence factors and the photovoltaic installation influence factors on the basis of the wind and light prediction error regression model;
the historical wind and photovoltaic output data comprise a historical wind and photovoltaic total installed number, a historical wind and photovoltaic output prediction error and a historical photovoltaic output prediction error of the preset historical time period;
the future wind and light output data comprise the future wind power total installed number and the future photovoltaic total installed number of the preset future time period.
Preferably, the wind and light resource future prediction error solving device further includes a wind and light prediction error regression model obtaining module, configured to:
constructing the wind and light prediction error regression model according to the following expression:
Figure BDA0003374543580000041
wherein, CwFor the total installed number of wind power, CpIs the total photovoltaic installed number, X is the wind power installed proportion, Y is the photovoltaic installed proportion, PweiFor the prediction error of wind power output in i time period, PpeiThe method comprises the steps of obtaining a photovoltaic output prediction error in a time period i, obtaining N as the total time period, obtaining Z as the absolute average value of the per-unit values of the wind and photovoltaic output prediction errors in each time period, obtaining a wind power installation influence factor, obtaining b as the photovoltaic installation influence factor, and obtaining c as a constant term.
Preferably, the data obtaining module is configured to obtain, based on a pre-obtained wind-solar prediction error regression model, an absolute average value of historical wind-power installed ratios, historical photovoltaic installed ratios, and historical wind-solar prediction error per unit values in the day and night periods of each season in a preset historical period according to pre-obtained historical wind-solar output data, and specifically includes:
obtaining the absolute average value of a first historical wind power installed ratio, a first historical photovoltaic installed ratio and a first historical wind-solar prediction error per unit value of the daytime period of each season in a preset historical period based on a pre-obtained wind-solar prediction error regression model according to pre-obtained historical wind-solar output data;
and obtaining the absolute average value of a second historical wind power installed proportion, a second historical photovoltaic installed proportion and a second historical wind power predicted error per unit value of the night time of each season in the preset historical time period based on the wind and light predicted error regression model according to the historical wind power total installed number and the historical wind power output predicted error of the preset historical time period, wherein the second historical photovoltaic installed proportion is zero.
Preferably, the future prediction error value obtaining module is configured to obtain, based on the wind and light prediction error regression model, a future prediction error value of a day and a night time of each season in a preset future time period according to preset future wind and light output data, the wind power installation influence factor, and the photovoltaic installation influence factor, and specifically includes:
respectively obtaining the future wind power installed proportion and the future photovoltaic installed proportion of each season in the preset future time period in the day and night time period based on the wind and light prediction error regression model according to preset future wind and light output data;
and obtaining future prediction error values of day and night time periods of each season in a preset future time period based on the wind and light prediction error regression model according to the future wind power installation proportion, the future photovoltaic installation proportion, the wind power installation influence factor and the photovoltaic installation influence factor.
A third aspect of the embodiments of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor, when executing the computer program, implements the wind and photovoltaic resource future prediction error solving method according to any one of the first aspect.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where the apparatus on which the computer-readable storage medium is located is controlled to execute the method for solving the future prediction error of the wind and photovoltaic resource according to any one of the first aspect when the computer program runs.
Compared with the prior art, the method has the advantages that seasonal differences and day-night differences of the wind and light resources and influences of the installed wind power numbers and the installed photovoltaic numbers on the wind and light resource prediction errors are fully considered when the future prediction errors of the wind and light resources are subjected to fitting solving, so that accurate future prediction error values are obtained, and reference can be provided for power grid scheduling according to the future prediction error values.
Drawings
FIG. 1 is a schematic flow chart of a method for solving future prediction errors of wind and light resources according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a wind and light resource future prediction error solving device provided by an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a first aspect of the embodiment of the present invention provides a flow chart diagram of a method for solving a future prediction error of a wind and light resource, including steps S1 to S3, specifically as follows:
and step S1, based on the pre-obtained wind and light prediction error regression model, respectively obtaining the historical wind and light installed occupation ratio, the historical photovoltaic installed occupation ratio and the absolute average value of the historical wind and light prediction error per unit value in the day and night time of each season in the preset historical time period according to the pre-obtained historical wind and light output data.
It should be noted that the historical wind and photovoltaic output data includes a historical wind and photovoltaic total installed number, a historical wind and photovoltaic output prediction error and a historical photovoltaic output prediction error of the preset historical time period.
It is worth to be noted that in order to analyze the relationship between the installed numbers of the wind power and the photovoltaic and the wind-solar prediction error, the embodiment of the invention adopts a linear regression model to perform parameter fitting, and reflects the correlation between the installed numbers of the wind power and the photovoltaic and the wind-solar prediction error through the parameter size.
Preferably, the method specifically obtains the wind-solar prediction error regression model in advance through the following steps:
constructing the wind and light prediction error regression model according to the following expression:
Figure BDA0003374543580000061
wherein, CwFor the total installed number of wind power, CpIs the total photovoltaic installed number, X is the wind power installed proportion, Y is the photovoltaic installed proportion, PweiFor the prediction error of wind power output in i time period, PpeiThe method comprises the steps of obtaining a photovoltaic output prediction error in a time period i, obtaining N as the total time period, obtaining Z as the absolute average value of the per-unit values of the wind and photovoltaic output prediction errors in each time period, obtaining a wind power installation influence factor, obtaining b as the photovoltaic installation influence factor, and obtaining c as a constant term.
It should be noted that the above-mentioned i period may be a certain hour in a certain day in a preset historical period, and is not limited in particular here.
According to the method and the device, seasonal division and day and night time division are carried out on historical wind and light output data, and the wind and light prediction error regression model is used for solving the absolute average values of the historical wind and light installed occupation ratio, the historical photovoltaic installed occupation ratio and the historical wind and light prediction error per unit value in the day and night time of each season in the preset historical time period. Specifically, according to seasonal differences of wind and light resources, a wind and light prediction error regression model can be used for solving the absolute average values of the historical wind and light installed ratio, the historical photovoltaic installed ratio and the historical wind and light prediction error per unit value from spring, summer, autumn and winter, and the day and night difference of photovoltaic output is considered, and the solving process of the absolute average values of the historical wind and light installed ratio, the historical photovoltaic installed ratio and the historical wind and light prediction error per unit value by the formula (1) needs to be divided into two time periods of day and night.
Preferably, the obtaining, based on the pre-obtained wind-solar prediction error regression model, the absolute average values of the historical wind-power installed proportion, the historical photovoltaic installed proportion, and the historical wind-solar prediction error per unit value in the day and night time periods of each season in the preset historical time period according to the pre-obtained historical wind-solar output data specifically includes:
obtaining the absolute average value of a first historical wind power installed ratio, a first historical photovoltaic installed ratio and a first historical wind-solar prediction error per unit value of the daytime period of each season in a preset historical period based on a pre-obtained wind-solar prediction error regression model according to pre-obtained historical wind-solar output data;
and obtaining the absolute average value of a second historical wind power installed proportion, a second historical photovoltaic installed proportion and a second historical wind power predicted error per unit value of the night time of each season in the preset historical time period based on the wind and light predicted error regression model according to the historical wind power total installed number and the historical wind power output predicted error of the preset historical time period, wherein the second historical photovoltaic installed proportion is zero.
It can be understood that when the absolute average of the historical wind power installed proportion, the historical wind power installed proportion and the historical wind and light prediction error per unit value in the daytime period is solved, the photovoltaic output needs to be considered, so that the absolute average of the historical wind power installed proportion, the historical wind power installed proportion and the historical wind and light prediction error per unit value in the daytime period is solved according to the formula (1) according to the historical wind power total installed number and the historical photovoltaic total installed number in the preset historical time period.
When solving the absolute average values of the historical wind power installed ratio, the historical wind power installed ratio and the historical wind-light prediction error per unit value at night, the photovoltaic output is not required to be considered, so that in the process of solving by using a wind-light prediction error regression model, the historical photovoltaic output prediction error and the historical photovoltaic total installed number are both set to be 0, the solution of Y and Z is mainly influenced, and the change of the formula (1) is shown as the following formula (2):
Figure BDA0003374543580000081
as an optional embodiment, the preset historical period may be some 5 years in the past, for example, 2014 to 2018, since the total number of the wind power installations and the total number of the photovoltaic installations in each year are different, when the wind-solar prediction error regression model is used for processing according to the historical wind-solar output data of the 5 years, the absolute average values of the wind-power installation occupation ratio, the wind-power installation occupation ratio and the wind-solar prediction error per unit value of 5 groups are finally obtained and used as the absolute average values of the wind-power installation occupation ratio, the wind-power installation occupation ratio and the wind-solar prediction error per unit value in the preset historical period.
And step S2, based on the wind and light prediction error regression model, performing parameter regression fitting according to the historical wind and light installed occupation ratio, the historical photovoltaic installed occupation ratio and the absolute average value of the historical wind and light prediction error per unit value of each season in the preset historical time period respectively to obtain the wind and light installed influence factor and the photovoltaic installed influence factor of each season in the day and night time period.
Specifically, after the absolute average values of the historical wind power installed occupation ratio, the historical photovoltaic installed occupation ratio and the historical wind and light prediction error per unit value of each season in the preset historical time period are obtained through solving in step S1, parameter regression fitting is performed by using a wind and light prediction error regression model according to the absolute average values of the historical wind power installed occupation ratio, the historical photovoltaic installed occupation ratio and the historical wind and light prediction error per unit value of each season in the preset historical time period respectively, and the wind power installed influence factor, the photovoltaic installed influence factor and a constant term in each season in the preset historical time period are obtained.
It should be noted that the wind installation influence factor represents an influence factor of the wind installation on the wind and light prediction error, and the photovoltaic installation influence factor represents an influence factor of the photovoltaic installation on the wind and light prediction error. The wind and light prediction error regression model carries out parameter regression fitting according to historical wind and light output data of a preset historical time period in different seasons and different time periods, so that the wind power installation influence factor and the photovoltaic installation influence factor obtained through fitting have seasonal characteristics and day and night output characteristics.
Further, the present inventionThe embodiment of the invention adopts the determination coefficient R2Evaluating the effect of the model on parameter fitting, determining the coefficient R2The method is generally used in a regression model for evaluating the conformity between a predicted value and an actual value, the closer the numerical value is to 1, the better the regression fitting effect is, and when a coefficient R is determined2When the value of (d) is greater than 0.8, the fitting effect of regression is considered to be good. Determining the coefficient R2Reflecting what percentage of the dependent variable is, can be interpreted by the control variable. The method and the device adopt the average value of the absolute average values of all the wind and light prediction error per unit values in the preset historical time period as the fitting error reference, and observe whether the wind and light prediction error obtained by fitting is larger than or smaller than the mean reference error. The method comprises the following specific steps:
Figure BDA0003374543580000091
wherein R is2Z is the absolute average value of the per unit values of the wind and light prediction errors of each year in the preset historical period for determining the coefficient,
Figure BDA0003374543580000092
is the average value of the absolute average values of all the wind and light prediction error per unit values in the preset historical time period,
Figure BDA0003374543580000093
is a future prediction error value for each year in a preset future time period.
And step S3, obtaining future prediction error values of day and night time periods of each season in a preset future time period according to preset future wind and light output data, the wind power installation influence factors and the photovoltaic installation influence factors based on the wind and light prediction error regression model.
It should be noted that the future wind-solar power output data includes the future wind power total installed number and the future photovoltaic total installed number of the preset future time period.
Preferably, the obtaining, based on the wind-light prediction error regression model, a future prediction error value in a day and night time period of each season in a preset future time period according to preset future wind-light output data, the wind power installed influence factor and the photovoltaic installed influence factor specifically includes:
respectively obtaining the future wind power installed proportion and the future photovoltaic installed proportion of each season in the preset future time period in the day and night time period based on the wind and light prediction error regression model according to preset future wind and light output data;
and obtaining future prediction error values of day and night time periods of each season in a preset future time period based on the wind and light prediction error regression model according to the future wind power installation proportion, the future photovoltaic installation proportion, the wind power installation influence factor and the photovoltaic installation influence factor.
Specifically, the wind power total installed number and the photovoltaic total installed number of a certain year in the future are planned in advance, and then the future wind power total installed proportion X and the future photovoltaic installed proportion Y of each season of the year in the future in the day and night time periods are obtained according to the formula (1) based on the wind and light prediction error regression model.
Based on the wind and light prediction error regression model, fitting the obtained wind and photovoltaic installed influence factors a, b and constant terms c of the day and night time of each season according to the step S2, and combining the future wind and photovoltaic installed occupation ratio X and the future photovoltaic installed occupation ratio Y of the day and night time of each season in the future year according to the following formula:
Figure BDA0003374543580000101
obtaining future prediction error values of the day time and night time of each season of the year
Figure BDA0003374543580000102
According to the method for solving the future prediction error of the wind and light resources, provided by the embodiment of the invention, seasonal difference and day-night difference of the wind and light resources and the influence of the installed wind power number and the installed photovoltaic number on the prediction error of the wind and light resources are fully considered when the future prediction error of the wind and light resources is subjected to fitting solving, so that an accurate future prediction error fitting result is obtained, the prediction error can be accurately analyzed according to the fitting result, and reference is provided for power grid scheduling.
Referring to fig. 2, a second aspect of the embodiment of the present invention provides a wind and photovoltaic resource future prediction error solving device, including:
the data acquisition module 201 is configured to obtain, based on a pre-acquired wind-solar prediction error regression model, an absolute average value of historical wind-solar installed occupation ratios, historical photovoltaic installed occupation ratios and historical wind-solar prediction error per unit values in the day and night periods of each season in a preset historical time period according to pre-acquired historical wind-solar output data;
a parameter regression fitting module 202, configured to perform parameter regression fitting according to the historical wind power installed proportion, the historical photovoltaic installed proportion, and the absolute average of the historical wind power prediction error per unit value in the day and night time of each season in the preset historical time period respectively based on the wind and light prediction error regression model, so as to obtain wind power installed influence factors and photovoltaic installed influence factors in the day and night time of each season;
a future prediction error value obtaining module 203, configured to obtain, based on the wind and light prediction error regression model, a future prediction error value of the day and night time of each season in a preset future time period according to preset future wind and light output data, the wind power installation influence factor, and the photovoltaic installation influence factor;
the historical wind and photovoltaic output data comprise a historical wind and photovoltaic total installed number, a historical wind and photovoltaic output prediction error and a historical photovoltaic output prediction error of the preset historical time period;
the future wind and light output data comprise the future wind power total installed number and the future photovoltaic total installed number of the preset future time period.
Preferably, the wind and light resource future prediction error solving device further includes a wind and light prediction error regression model obtaining module 204, configured to:
constructing the wind and light prediction error regression model according to the following expression:
Figure BDA0003374543580000111
wherein, CwFor the total installed number of wind power, CpIs the total photovoltaic installed number, X is the wind power installed proportion, Y is the photovoltaic installed proportion, PweiFor the prediction error of wind power output in i time period, PpeiThe method comprises the steps of obtaining a photovoltaic output prediction error in a time period i, obtaining N as the total time period, obtaining Z as the absolute average value of the per-unit values of the wind and photovoltaic output prediction errors in each time period, obtaining a wind power installation influence factor, obtaining b as the photovoltaic installation influence factor, and obtaining c as a constant term.
Preferably, the data obtaining module 201 is configured to obtain, based on a pre-obtained wind-solar prediction error regression model, an absolute average value of historical wind-power installed ratios, historical photovoltaic installed ratios, and historical wind-solar prediction error per unit values in the day and night time periods of each season in a preset historical time period according to pre-obtained historical wind-solar output data, and specifically includes:
obtaining the absolute average value of a first historical wind power installed ratio, a first historical photovoltaic installed ratio and a first historical wind-solar prediction error per unit value of the daytime period of each season in a preset historical period based on a pre-obtained wind-solar prediction error regression model according to pre-obtained historical wind-solar output data;
and obtaining the absolute average value of a second historical wind power installed proportion, a second historical photovoltaic installed proportion and a second historical wind power predicted error per unit value of the night time of each season in the preset historical time period based on the wind and light predicted error regression model according to the historical wind power total installed number and the historical wind power output predicted error of the preset historical time period, wherein the second historical photovoltaic installed proportion is zero.
Preferably, the future prediction error value obtaining module 203 is configured to obtain, based on the wind and light prediction error regression model, a future prediction error value of each season in a preset future time period according to preset future wind and light output data, the wind and power installation influence factor, and the photovoltaic installation influence factor, and specifically includes:
respectively obtaining the future wind power installed proportion and the future photovoltaic installed proportion of each season in the preset future time period in the day and night time period based on the wind and light prediction error regression model according to preset future wind and light output data;
and obtaining future prediction error values of day and night time periods of each season in a preset future time period based on the wind and light prediction error regression model according to the future wind power installation proportion, the future photovoltaic installation proportion, the wind power installation influence factor and the photovoltaic installation influence factor.
It should be noted that, the wind and photovoltaic resource future prediction error solving device provided in the embodiment of the present invention can implement all the processes of the wind and photovoltaic resource future prediction error solving method described in any one of the embodiments, and the functions and implemented technical effects of each module in the device are respectively the same as those of the wind and photovoltaic resource future prediction error solving method described in the embodiment, and are not described herein again.
A third aspect of the embodiments of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor, when executing the computer program, implements the method for solving a future prediction error of a wind and photovoltaic resource according to any one of the embodiments of the first aspect.
The terminal device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The terminal device may include, but is not limited to, a processor, a memory. The terminal device may also include input and output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal device and connects the various parts of the whole terminal device using various interfaces and lines.
The memory may be used for storing the computer programs and/or modules, and the processor may implement various functions of the terminal device by executing or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where the apparatus on which the computer-readable storage medium is located is controlled to execute the method for solving the future prediction error of the wind and photovoltaic resource according to any one of the embodiments of the first aspect when the computer program runs.
Through the above description of the embodiments, those skilled in the art will clearly understand that the present invention may be implemented by software plus a necessary hardware platform, and may also be implemented by hardware entirely. With this understanding in mind, all or part of the technical solutions of the present invention that contribute to the background can be embodied in the form of a software product, which can be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods according to the embodiments or some parts of the embodiments of the present invention.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.

Claims (10)

1. A method for solving future prediction errors of wind and light resources is characterized by comprising the following steps:
based on a pre-acquired wind and light prediction error regression model, respectively acquiring the absolute average values of the historical wind and light installed occupation ratio, the historical photovoltaic installed occupation ratio and the historical wind and light prediction error per unit value in the day and night time of each season in a preset historical time period according to pre-acquired historical wind and light output data;
based on the wind and light prediction error regression model, respectively performing parameter regression fitting according to the historical wind power installed occupation ratio, the historical photovoltaic installed occupation ratio and the absolute average value of the historical wind and light prediction error per unit value of each season in the preset historical time period to obtain wind power installed influence factors and photovoltaic installed influence factors of each season in the day and night time period;
based on the wind and light prediction error regression model, obtaining future prediction error values of day and night time periods of each season in a preset future time period according to preset future wind and light output data, the wind power installation influence factors and the photovoltaic installation influence factors;
the historical wind and photovoltaic output data comprise a historical wind and photovoltaic total installed number, a historical wind and photovoltaic output prediction error and a historical photovoltaic output prediction error of the preset historical time period;
the future wind and light output data comprise the future wind power total installed number and the future photovoltaic total installed number of the preset future time period.
2. The method according to claim 1, wherein the method is specifically configured to obtain the wind and light prediction error regression model in advance by:
constructing the wind and light prediction error regression model according to the following expression:
Figure FDA0003374543570000011
wherein, CwFor the total installed number of wind power, CpIs the total photovoltaic installed number, X is the wind power installed proportion, Y is the photovoltaic installed proportion, PweiFor the prediction error of wind power output in i time period, PpeiThe method comprises the steps of obtaining a photovoltaic output prediction error in a time period i, obtaining N as the total time period, obtaining Z as the absolute average value of the per-unit values of the wind and photovoltaic output prediction errors in each time period, obtaining a wind power installation influence factor, obtaining b as the photovoltaic installation influence factor, and obtaining c as a constant term.
3. The method for solving the future prediction error of the wind and light resources according to claim 2, wherein the method for solving the future prediction error of the wind and light resources based on the pre-obtained regression model of the wind and light prediction error respectively obtains the absolute average values of the historical wind and light installed occupation ratio, the historical photovoltaic installed occupation ratio and the historical wind and light prediction error per unit value in the day and night time of each season in the preset historical time period according to the pre-obtained historical wind and light output data, and specifically comprises the following steps:
obtaining the absolute average value of a first historical wind power installed ratio, a first historical photovoltaic installed ratio and a first historical wind-solar prediction error per unit value of the daytime period of each season in a preset historical period based on a pre-obtained wind-solar prediction error regression model according to pre-obtained historical wind-solar output data;
and obtaining the absolute average value of a second historical wind power installed proportion, a second historical photovoltaic installed proportion and a second historical wind power predicted error per unit value of the night time of each season in the preset historical time period based on the wind and light predicted error regression model according to the historical wind power total installed number and the historical wind power output predicted error of the preset historical time period, wherein the second historical photovoltaic installed proportion is zero.
4. The method for solving the future prediction error of the wind and light resources according to claim 3, wherein the obtaining the future prediction error value of the day and night time of each season in the preset future time period based on the wind and light prediction error regression model according to the preset future wind and light output data, the wind and light installed influence factor and the photovoltaic installed influence factor specifically comprises:
respectively obtaining the future wind power installed proportion and the future photovoltaic installed proportion of each season in the preset future time period in the day and night time period based on the wind and light prediction error regression model according to preset future wind and light output data;
and obtaining future prediction error values of day and night time periods of each season in a preset future time period based on the wind and light prediction error regression model according to the future wind power installation proportion, the future photovoltaic installation proportion, the wind power installation influence factor and the photovoltaic installation influence factor.
5. A wind and light resource future prediction error solving device is characterized by comprising:
the data acquisition module is used for respectively acquiring the historical wind power installed proportion, the historical photovoltaic installed proportion and the absolute average value of the historical wind power prediction error per unit value in the day and night time periods of each season in the preset historical time period based on the pre-acquired wind and light prediction error regression model;
the parameter regression fitting module is used for performing parameter regression fitting according to the historical wind power installed proportion, the historical photovoltaic installed proportion and the absolute average value of the historical wind power prediction error per unit value in the day and night time of each season in the preset historical time period respectively based on the wind and light prediction error regression model to obtain wind power installed influence factors and photovoltaic installed influence factors in the day and night time of each season;
the future prediction error value obtaining module is used for obtaining future prediction error values of day and night time periods of each season in a preset future time period according to preset future wind and light output data, the wind power installation influence factors and the photovoltaic installation influence factors on the basis of the wind and light prediction error regression model;
the historical wind and photovoltaic output data comprise a historical wind and photovoltaic total installed number, a historical wind and photovoltaic output prediction error and a historical photovoltaic output prediction error of the preset historical time period;
the future wind and light output data comprise the future wind power total installed number and the future photovoltaic total installed number of the preset future time period.
6. The wind and photovoltaic resource future prediction error solving apparatus of claim 5, further comprising a wind and photovoltaic prediction error regression model obtaining module configured to:
constructing the wind and light prediction error regression model according to the following expression:
Figure FDA0003374543570000031
wherein, CwFor the total installed number of wind power, CpIs the total photovoltaic installed number, X is the wind power installed proportion, Y is the photovoltaic installed proportion, PweiFor the prediction error of wind power output in i time period, PpeiThe method comprises the steps of obtaining a photovoltaic output prediction error in a time period i, obtaining N as the total time period, obtaining Z as the absolute average value of the per-unit values of the wind and photovoltaic output prediction errors in each time period, obtaining a wind power installation influence factor, obtaining b as the photovoltaic installation influence factor, and obtaining c as a constant term.
7. The wind and light resource future prediction error solving device according to claim 6, wherein the data obtaining module is configured to obtain, based on a pre-obtained wind and light prediction error regression model, an absolute average value of historical wind and light installed ratios, historical photovoltaic installed ratios, and historical wind and light prediction error per unit values in the day and night time periods of each season in a preset historical time period according to pre-obtained historical wind and light output data, and specifically includes:
obtaining the absolute average value of a first historical wind power installed ratio, a first historical photovoltaic installed ratio and a first historical wind-solar prediction error per unit value of the daytime period of each season in a preset historical period based on a pre-obtained wind-solar prediction error regression model according to pre-obtained historical wind-solar output data;
and obtaining the absolute average value of a second historical wind power installed proportion, a second historical photovoltaic installed proportion and a second historical wind power predicted error per unit value of the night time of each season in the preset historical time period based on the wind and light predicted error regression model according to the historical wind power total installed number and the historical wind power output predicted error of the preset historical time period, wherein the second historical photovoltaic installed proportion is zero.
8. The wind and photovoltaic resource future prediction error solving device according to claim 7, wherein the future prediction error value obtaining module is configured to obtain, based on the wind and photovoltaic prediction error regression model, a future prediction error value of day and night time of each season in a preset future time period according to preset future wind and photovoltaic output data, the wind and photovoltaic installed influence factor, and specifically includes:
respectively obtaining the future wind power installed proportion and the future photovoltaic installed proportion of each season in the preset future time period in the day and night time period based on the wind and light prediction error regression model according to preset future wind and light output data;
and obtaining future prediction error values of day and night time periods of each season in a preset future time period based on the wind and light prediction error regression model according to the future wind power installation proportion, the future photovoltaic installation proportion, the wind power installation influence factor and the photovoltaic installation influence factor.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method of solving for future prediction errors of wind and light resources of any of claims 1 to 4 when executing the computer program.
10. A computer-readable storage medium, comprising a stored computer program, wherein the computer program, when executed, controls an apparatus on which the computer-readable storage medium is located to perform the method of solving for future prediction errors of a wind/solar resource of any of claims 1 to 4.
CN202111427537.2A 2021-11-25 2021-11-25 Method, device and equipment for solving future prediction error of wind and light resources and storage medium Pending CN114238856A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111427537.2A CN114238856A (en) 2021-11-25 2021-11-25 Method, device and equipment for solving future prediction error of wind and light resources and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111427537.2A CN114238856A (en) 2021-11-25 2021-11-25 Method, device and equipment for solving future prediction error of wind and light resources and storage medium

Publications (1)

Publication Number Publication Date
CN114238856A true CN114238856A (en) 2022-03-25

Family

ID=80751782

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111427537.2A Pending CN114238856A (en) 2021-11-25 2021-11-25 Method, device and equipment for solving future prediction error of wind and light resources and storage medium

Country Status (1)

Country Link
CN (1) CN114238856A (en)

Similar Documents

Publication Publication Date Title
KR102468316B1 (en) Time series prediction method and apparatus based on past prediction data
Shayesteh et al. Scenario reduction, network aggregation, and DC linearisation: which simplifications matter most in operations and planning optimisation?
CN110544112A (en) Method and device for clearing regional frequency modulation market in consideration of renewable energy
WO2017049428A1 (en) Spinning reserve capacity optimization method based on cost-performance ratio of reserve object
CN115759365A (en) Photovoltaic power generation power prediction method and related equipment
US20190356131A1 (en) Methods and systems for determining distribution grid hosting capacity
CN110555242B (en) Method, device, equipment and storage medium for evaluating wind resistance of old towers
CN114238856A (en) Method, device and equipment for solving future prediction error of wind and light resources and storage medium
CN110544958B (en) Method and device for determining capability of electric power system to absorb random output power
CN115577903A (en) Method, device, equipment and medium for evaluating influence of new energy on power grid peak regulation
CN112036607A (en) Wind power output fluctuation prediction method and device based on output level and storage medium
CN116247644A (en) Charging and discharging method and device based on energy storage system, storage medium and terminal
CN113947007A (en) Energy load prediction method, device and equipment
CN113205259A (en) Power grid scheduling decision evaluation method and device and terminal equipment
CN112561732A (en) Method and device for optimizing active power scheduling of power system and readable storage medium
CN117807791A (en) Wind farm probabilistic day-ahead output generation simulation method, system, chip and equipment
CN115063255B (en) Operation and maintenance resource optimal allocation method, device and system for offshore wind farm
CN112531629B (en) Method and device for automatically setting protection setting value of power distribution network and terminal equipment
CN116822658B (en) Early warning method and device for wind-solar resources, computer equipment and storage medium
CN113704984B (en) Annual maintenance plan making method, annual maintenance plan making device and annual maintenance plan making computer equipment for electric power system
CN113689033B (en) Method and device for checking and determining capacity generation price, computer equipment and storage medium
CN115796430A (en) Power supply planning typical scene generation method, device, medium and equipment
Li et al. A novel approach to estimate load factor of variable-speed wind turbines
CN115828515A (en) Modeling method and device for wind power plant
CN117808133A (en) Offshore wind farm resource allocation method and device, computer equipment and storage medium

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