CN112217208B - Power generation control method based on power generation and power utilization prediction - Google Patents

Power generation control method based on power generation and power utilization prediction Download PDF

Info

Publication number
CN112217208B
CN112217208B CN202011125818.8A CN202011125818A CN112217208B CN 112217208 B CN112217208 B CN 112217208B CN 202011125818 A CN202011125818 A CN 202011125818A CN 112217208 B CN112217208 B CN 112217208B
Authority
CN
China
Prior art keywords
power generation
load
day
power
influence rate
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202011125818.8A
Other languages
Chinese (zh)
Other versions
CN112217208A (en
Inventor
王垚
李�杰
吕书臣
侯逊
石秀刚
叶春明
谢云明
郭登伟
魏克强
李勇
穆维府
张开鹏
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.)
Huaeng Liaocheng Thermal Power Co ltd
Huaneng Shandong Power Generation Co Ltd
Original Assignee
Huaeng Liaocheng Thermal Power Co ltd
Huaneng Shandong Power Generation 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 Huaeng Liaocheng Thermal Power Co ltd, Huaneng Shandong Power Generation Co Ltd filed Critical Huaeng Liaocheng Thermal Power Co ltd
Priority to CN202011125818.8A priority Critical patent/CN112217208B/en
Publication of CN112217208A publication Critical patent/CN112217208A/en
Application granted granted Critical
Publication of CN112217208B publication Critical patent/CN112217208B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/381—Dispersed generators
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/28—The renewable source being wind energy
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A30/00—Adapting or protecting infrastructure or their operation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy
    • Y02E10/56—Power conversion systems, e.g. maximum power point trackers

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

The invention relates to a power generation control method based on power generation and power utilization prediction, belongs to the technical field of power grid prediction, and solves the problems of poor operation reliability and low safety of a generator set caused by lack of data basis for allocation of the generator set in the prior art. The method comprises the steps of obtaining power utilization influence rate and power generation influence rate according to historical power utilization data, historical power generation data and historical weather data of a target area; according to the weather forecast data, the power utilization influence rate and the power generation influence rate, the power utilization requirement of a target forecast date, the power generation amount of new energy power generation, the highest power generation load and the lowest power generation load are obtained; and predicting to obtain the start-stop capacity of thermal power generation on the target prediction date according to the power demand and the power generation condition of the target prediction date, and performing power generation control on the generator set in the target area according to the start-stop capacity. The safety, the reliability and the economical efficiency of the operation of the thermal generator set are improved.

Description

Power generation control method based on power generation and power utilization prediction
Technical Field
The invention relates to the technical field of power grid prediction, in particular to a power generation control method based on power generation and power utilization prediction.
Background
The new energy refers to renewable energy developed and utilized on the basis of new technology, such as wind energy, solar energy, biomass energy, water energy and the like. The scale and range of new energy sources used in the field of power generation are increasing day by day, but the uncertainty of wind power generation and photovoltaic power generation is high, the influence of weather is obvious, and the stable operation of a power grid is not challenged or power supply cannot be stably supplied, so that thermal power generation is required to perform auxiliary power generation to support the new energy sources during power generation. The method is very important for accurately predicting the wind power generation and the photovoltaic power generation amount and planning the thermal power generation according to the prediction results of the wind power generation and the photovoltaic power generation. The method has the advantages that the power demand in the region, the highest power generation load and the lowest power generation load of new energy power generation and the generated energy are accurately predicted, scientific data reference is provided for power grid dispatching and reasonable allocation of the thermal generator set, the safe and stable operation of the thermal generator set is ensured, the stability and the economical efficiency of power generation are improved, and the method becomes a problem to be solved by technical personnel in the field.
In the prior art, the related technologies for power generation control based on regional power demand prediction and power generation maximum load, minimum load and power generation amount prediction are few, so that the allocation of a thermal generator set lacks data basis, and the power generation cannot be allocated reasonably to better assist new energy power generation. And then the power grid can not run safely and reliably, the power demand of a user can not be met, or the resource waste is caused.
Disclosure of Invention
In view of the above analysis, the present invention aims to provide a power generation control method based on power generation and power utilization prediction, so as to solve the problems of poor operation reliability and economy and low safety of a power generation unit due to lack of data basis for the deployment of the power generation unit by a power generation company in the prior art.
The invention provides a power generation control method based on power generation and power utilization prediction, which comprises the following steps of:
acquiring historical electricity utilization data, historical power generation data, historical weather data and weather forecast data of a target prediction date of a target area;
obtaining power utilization influence rate according to the historical weather data and the historical power utilization data, and obtaining power generation influence rate according to the historical weather data and the historical power generation data;
according to the weather forecast data and the power utilization influence rate, predicting the power utilization requirement of the target prediction date;
according to the weather forecast data and the power generation influence rate, predicting to obtain the generated energy and the power generation load of the new energy power generation on the target prediction date;
and predicting according to the power demand, the power generation capacity and the power generation load of the target prediction date to obtain the start-stop capacity of the thermal power generation of the target prediction date, and performing power generation control on the thermal power generator set in the target area according to the start-stop capacity.
Further, the historical electricity consumption data comprises dates, corresponding electricity consumption, electricity utilization highest load and electricity utilization lowest load;
the historical power generation data comprises a new energy power generation mode, a date, corresponding power generation amount, a highest power generation load and a lowest power generation load, and the new energy power generation mode comprises wind power generation, centralized photovoltaic power generation and distributed photovoltaic power generation;
the historical weather data and the weather forecast data of the target forecast date respectively comprise dates, corresponding maximum temperatures, minimum temperatures, average temperatures, wind indexes and weather clear indexes.
Further, the power utilization influence rate comprises an influence rate of the highest temperature on the highest power utilization load, an influence rate of the lowest temperature on the lowest power utilization load and an influence rate of the average temperature on the power utilization amount;
the obtaining of the power utilization influence rate according to the historical weather data and the historical power utilization data comprises the following steps:
the influence rate of the maximum temperature on the maximum load of the power consumption is as follows:
Figure BDA0002733571940000021
wherein the content of the first and second substances,
Figure BDA0002733571940000022
showing the influence rate of the maximum temperature on the maximum load of the power utilization, N showing the number of days of the set ring ratio or the number of days of the same ratio, Pqwhn、Pqwhn-1Respectively represents the highest load of electricity consumption on the nth day and the nth-1 day, Thn、Thn-1The maximum temperatures on day n and day n-1 are indicated, respectively;
the influence rate of the lowest temperature on the lowest power load is as follows:
Figure BDA0002733571940000023
wherein the content of the first and second substances,
Figure BDA0002733571940000024
showing the influence rate of the lowest temperature on the lowest load of the power utilization, N showing the number of days of the ring ratio or the number of days of the same ratio, Pqwln、Pqwln-1Respectively represents the lowest load of electricity utilization on the nth day and the nth-1 day, Tln、Tln-1The minimum temperatures on day n and day n-1, respectively;
the influence rate of the average temperature on the electricity consumption is as follows:
Figure BDA0002733571940000025
wherein the content of the first and second substances,
Figure BDA0002733571940000031
the influence rate of the average temperature on the used amount of electricity is expressed,n represents the number of days of the ring ratio or the number of days of the same ratio, Qqwn、Qqwn-1Respectively represents the power consumption on the nth day and the nth-1 day, Tvn、Tvn-1The average temperatures on the nth day and on the n-1 st day are shown, respectively.
Further, the influence rate of electricity consumption also includes influence rates of holidays on the highest load of electricity consumption, the lowest load of electricity consumption and electricity consumption:
influence rate of seven-day holiday on maximum load of electricity usage:
wherein, the influence rate of the seven-day holiday beginning on the highest load of power utilization is as follows:
Figure BDA0002733571940000032
wherein the content of the first and second substances,
Figure BDA0002733571940000033
showing the influence rate of the seven-day holiday start on the highest power utilization load, M showing the number of seven-day holidays in historical power utilization data, P7shm、P'7shmRespectively representing the highest load of electricity utilization on the first day of a seven-day holiday and the day before the holiday;
influence rate of seven-day holiday end on electricity utilization maximum load:
Figure BDA0002733571940000034
wherein the content of the first and second substances,
Figure BDA0002733571940000035
represents the influence rate of the end of the seven-day holiday period on the highest load of electricity consumption, P'7ehm、P7ehmRespectively representing the highest load of electricity utilization on the last day and the following day of the seven-day holiday;
sequentially obtaining the influence rates of the start of the seven-day holiday and the end of the seven-day holiday on the lowest power consumption load and the lowest power consumption;
and obtaining the influence rates of the double-holiday, the single-holiday and the three-day holiday on the highest power utilization load, the lowest power utilization load and the power consumption respectively; and the double-holiday further comprises influence rates of the saturday to the sunday on the highest power utilization load, the lowest power utilization load and the power consumption.
Further, according to the weather forecast data and the power consumption influence rate, predicting the power consumption demand of the target prediction date, comprising:
predicting to obtain the highest power utilization load of the target prediction date according to the highest temperature corresponding to the target prediction date, the influence rate of the highest temperature on the highest power utilization load, the highest temperature of the day before the target prediction date and the highest power utilization load;
predicting and obtaining the lowest power load of the target prediction date according to the lowest temperature corresponding to the target prediction date, the influence rate of the lowest temperature on the lowest power load, the lowest temperature of the day before the target prediction date and the lowest power load;
and predicting the electricity consumption on the target prediction date according to the average temperature and the influence rate of the average temperature on the electricity consumption corresponding to the target prediction date, the average temperature of the day before the target prediction date and the electricity consumption.
Further, the predicting the power demand of the target prediction date further includes:
correcting the predicted maximum power load on the target prediction date by using the influence rate of the holiday on the maximum power charge;
correcting the predicted lowest load of the electricity utilization on the target prediction date by using the influence rate of the holidays on the lowest load of the electricity utilization;
and correcting the predicted power consumption of the target prediction date by using the influence rate of the holidays on the power consumption.
Further, the power generation influence rate comprises an influence rate of a wind power index on the highest power generation load, the lowest power generation load and the power generation amount of the wind power generation, an influence rate of a weather clear index on the highest power generation load and the power generation amount of the centralized photovoltaic power generation, and an influence rate of the weather clear index on the highest power generation load and the power generation amount of the distributed photovoltaic power generation;
the obtaining of the power generation influence rate according to the historical weather data and the historical power generation data comprises the following steps:
obtaining the influence rate of the wind power index on the highest load of wind power generation, the influence rate of the lowest load of power generation and the influence rate of power generation capacity according to the wind power index in the historical weather data and the historical power generation data corresponding to the wind power generation:
Figure BDA0002733571940000041
Figure BDA0002733571940000042
Figure BDA0002733571940000043
wherein the content of the first and second substances,
Figure BDA0002733571940000044
expressing the influence rate of the wind power index on the maximum load of the wind power generation, N expressing the number of days of the set ring ratio or the number of days of the same ratio, Pflhn、Pflhn-1Respectively represents the highest load of wind power generation on the nth day and the nth-1 day,
Figure BDA0002733571940000045
representing the rate of influence of the wind index on the minimum load of the wind power plant, Pflln、Pflln-1Respectively represents the lowest load of wind power generation on the nth day and the nth-1 day,
Figure BDA0002733571940000046
expressing the influence rate of the wind index on the amount of power generation, Qfln、Qfln-1Respectively representing the wind power generation capacity on the nth day and the n-1 th day, Wn、Wn-1Mean wind indices on day n and day n-1, respectively;
obtaining the influence rate of the weather clear index on the highest load of the centralized photovoltaic power generation and the influence rate of the generated energy according to the weather clear index in the historical weather data and the historical power generation data corresponding to the centralized photovoltaic power generation:
Figure BDA0002733571940000051
Figure BDA0002733571940000052
wherein the content of the first and second substances,
Figure BDA0002733571940000053
the influence rate of the weather clear index on the highest load of the centralized photovoltaic power generation is shown, N represents the set number of days of the ring ratio or the number of days of the same ratio, and P represents the number of days of the ring ratio or the number of days of the same ratiofzhn、Pfzhn-1Respectively represents the concentrated photovoltaic power generation maximum load on the nth day and the (n-1) th day,
Figure BDA0002733571940000054
representing the influence rate of the weather clear index on the generated energy of the centralized photovoltaic power generation, Pjzn、Pjzn-1Respectively represents the concentrated photovoltaic power generation amount on the nth day and the nth-1 day, Sn、Sn-1Respectively representing the average weather clear index of the nth day and the average weather clear index of the (n-1) th day;
and respectively obtaining the influence rate of the weather clear index on the highest load and the generated energy of the distributed photovoltaic power generation according to the weather clear index in the historical weather data and the historical power generation data corresponding to the distributed photovoltaic power generation.
Further, the predicting and obtaining the generated energy and the power generation load of the new energy power generation on the target prediction date according to the weather forecast data and the power generation influence rate on the target prediction date comprises:
predicting to obtain the wind power generation highest load of the target prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation highest load, the average wind power index of the day before the target prediction date and the wind power generation highest load; predicting and obtaining the wind power generation minimum load of the prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation minimum load, the average wind power index of the day before the prediction date and the wind power generation minimum load; predicting to obtain the wind power generation capacity of the target prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation capacity, the average wind power index of the day before the target prediction date and the wind power generation capacity;
and respectively predicting the highest load and the generated energy of the centralized photovoltaic power generation and the highest load and the generated energy of the distributed photovoltaic power generation at the target prediction date.
Further, obtaining the new energy power generation ratio according to historical power generation data;
Figure BDA0002733571940000055
wherein the content of the first and second substances,
Figure BDA0002733571940000056
representing the power generation ratio of new energy, N representing the number of days of the set ring ratio or the number of days of the same ratio, Pwn、Psn1、Psn2Respectively representing the highest load of wind power generation, the highest load of centralized photovoltaic power generation and the highest load of distributed photovoltaic power generation on the nth day, PnAnd the maximum load of the new energy power generation on the nth day is shown.
Further, according to the wind power generation maximum load, the centralized photovoltaic power generation maximum load, the distributed photovoltaic power generation maximum load and the new energy power generation percentage of the target prediction date obtained by prediction, the new energy power generation maximum load of the target prediction date is obtained.
Compared with the prior art, the invention can realize at least one of the following beneficial effects:
1. according to the method and the device, the influence rates of the maximum temperature, the minimum temperature and the average temperature on the maximum power consumption load, the minimum power consumption load and the power consumption of the user are obtained according to historical weather data and historical power consumption data, so that the power consumption demand of the user is predicted according to the temperature of a target prediction date, and in addition, the influence rates of holidays on the maximum power consumption load, the minimum power consumption load and the power consumption are obtained according to the historical weather data and the historical power consumption data corresponding to holidays, so that the power consumption demand of the user during holidays is predicted and obtained, and the power consumption demand of the user can be more accurately predicted by combining the influence rates of the temperature and the holidays on the power consumption of the user.
2. According to the method and the device, the influence rate of the wind power index and the weather clear index on the new energy power generation is obtained according to the historical weather data and the historical power generation data, the highest load of the new energy power generation, the lowest load of the power generation and the power generation amount on the target prediction date are predicted according to the influence rate, further, the highest load of the new energy power generation on the target prediction date is obtained according to the new energy power generation percentage, and the accuracy of the prediction result can be guaranteed.
3. The method determines the starting and stopping capacity of the thermal power generation of the target area based on the predicted power demand of the target area and the new energy power generation capacity, reasonably allocates the thermal power generating set, and performs auxiliary power generation on the new energy power generation, so that the highest power generation load and the lowest power generation load meet the requirement on adjustable output. On one hand, the power utilization requirement of a user is met, the safe and stable operation of a power grid can be guaranteed, the resource utilization rate is improved, the resource waste is prevented and the economical efficiency is good by reasonably allocating the generator set; on the other hand, when the generating set breaks down, can guarantee to satisfy when user's power consumption demand, have sufficient time to carry out generating set maintenance.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
Fig. 1 is a flow chart of a power generation control method based on power generation and power consumption prediction according to an embodiment of the present invention.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The invention discloses a power generation control method based on power generation and power utilization prediction. As shown in fig. 1, the method comprises the steps of:
step 1, obtaining historical electricity utilization data, historical electricity generation data, historical weather data and weather forecast data of a target prediction date of a target area.
And 2, obtaining the power utilization influence rate according to the historical weather data and the historical power utilization data, and obtaining the power generation influence rate according to the historical weather data and the historical power generation data.
And 3, predicting the power consumption requirement of the target prediction date according to the weather forecast data and the power consumption influence rate. Specifically, the electricity demand includes the highest load of electricity, the lowest load of electricity, and the amount of electricity used on the target forecast date.
And 4, predicting to obtain the generated energy and the power generation load of the new energy power generation on the target prediction date according to the weather forecast data and the power generation influence rate.
And 5, predicting to obtain the start-stop capacity of the thermal power generation on the target prediction date according to the power demand, the generated energy and the power generation load of the target prediction date, and performing power generation control on the generator set in the target area according to the start-stop capacity.
Wherein, the sequence of the step 3 and the step 4 can be reversed or synchronously performed.
Preferably, the historical electricity usage data includes a date, a corresponding amount of electricity usage, a highest load of electricity usage, and a lowest load of electricity usage.
The historical power generation data comprises a new energy power generation mode, a date, corresponding power generation amount, the highest power generation load and the lowest power generation load. The new energy power generation mode comprises wind power generation, centralized photovoltaic power generation and distributed photovoltaic power generation.
The historical weather data and the weather forecast data of the target forecast date respectively comprise dates, corresponding highest temperatures, lowest temperatures, average temperatures, wind indexes and weather clear indexes.
And determining the wind power index and the weather clearness index according to the wind power level and the weather condition in the weather data. Specifically, the correspondence between the wind power level and the wind power index and the correspondence between the weather condition and the weather clear index are shown in tables 1 and 2, respectively.
TABLE 1
Figure BDA0002733571940000071
Figure BDA0002733571940000081
TABLE 2
Figure BDA0002733571940000082
Preferably, the influence rate of electricity usage includes an influence rate of a highest temperature on a highest load of electricity usage, an influence rate of a lowest temperature on a lowest load of electricity usage, and an influence rate of an average temperature on an amount of electricity usage.
Specifically, obtaining the power utilization influence rate according to historical weather data and historical power utilization data comprises the following steps:
the influence rate of the maximum temperature on the maximum load of the power utilization is as follows:
Figure BDA0002733571940000091
wherein the content of the first and second substances,
Figure BDA0002733571940000092
showing the influence rate of the maximum temperature on the maximum load of the power utilization, N showing the number of days of the set ring ratio or the number of days of the same ratio, Pqwhn、Pqwhn-1Respectively represents the highest load of electricity consumption on the nth day and the nth-1 day, Thn、Thn-1The maximum temperatures on day n and day n-1 are indicated, respectively.
Specifically, the ring ratio includes a day-to-week ratio, which may be, for example, from last Monday to present Monday, and a month-to-month ratio, which may be from January to October, from No. 1 of each month to the last day of the month. The year-on-year includes a day-on-year and a month-on-year, and illustratively, the day-on-year may be the same day in a successively specified year (e.g., 8 month 5), and the month-on-year may be the same month in a successively specified year (e.g., 8 month 1 to 31 in a successively specified year).
The influence rate of the lowest temperature on the lowest load of the power consumption is as follows:
Figure BDA0002733571940000093
wherein the content of the first and second substances,
Figure BDA0002733571940000094
showing the influence rate of the lowest temperature on the lowest load of the power utilization, N showing the number of days of the ring ratio or the number of days of the same ratio, Pqwln、Pqwln-1Respectively represents the lowest load of electricity utilization on the nth day and the nth-1 day, Tln、Tln-1The minimum temperature on day n and day n-1 are indicated, respectively.
The influence rate of the average temperature on the electricity consumption is as follows:
Figure BDA0002733571940000095
wherein the content of the first and second substances,
Figure BDA0002733571940000096
expressing the influence rate of the average temperature on the electricity consumption, N expressing the number of days of the set ring ratio or the number of days of the same ratio, Qqwn、Qqwn-1Respectively represents the power consumption on the nth day and the nth-1 day, Tvn、Tvn-1The average temperatures on the nth day and on the n-1 st day are shown, respectively.
Preferably, in the above calculating of the influence rate, if a date of the ring ratio is set, the influence rate of the ring ratio is obtained correspondingly, and if a date of the same ratio is set, the influence rate of the same ratio is obtained correspondingly. In specific implementation, the ratio of the same-ratio influence rate and the ring-ratio influence rate can be set according to specific situations to obtain the final influence rate. For example, if the weather is stable in the current time period, the ring ratio influence rate may be set to be larger, for example: the influence rate of the ring ratio is 75 percent, and the influence rate of the same ratio is 25 percent; if the weather is unstable in the current time period and is in a season change period, the same-proportion influence rate can be set to be larger, such as: the influence rate of the ring ratio is 30 percent, and the influence rate of the same ratio is 70 percent. Preferably, the set ratio is continuously optimized and verified by using the historical weather data and the historical electricity utilization data, and the optimal and most accurate ratio is determined.
In consideration of the fact that the holidays have a large influence on the electricity demand of the user, the influence of the holidays is also taken into consideration when predicting the electricity demand of the user. Specifically, the influence rate of electricity consumption also includes influence rates of holidays on the highest load of electricity consumption, the lowest load of electricity consumption and electricity consumption.
The influence rate of the seven-day holiday on electricity utilization comprises:
wherein, the influence rate of the seven-day holiday beginning to the electricity utilization highest load, the electricity utilization lowest load and the electricity consumption is as follows:
Figure BDA0002733571940000101
Figure BDA0002733571940000102
Figure BDA0002733571940000103
wherein the content of the first and second substances,
Figure BDA0002733571940000104
represents the rate of influence of the start of a seven-day holiday on the maximum load of electricity utilization, P7shm、P'7shmRespectively representing the highest load of electricity utilization on the first day of a seven-day holiday and the day before the holiday;
Figure BDA0002733571940000105
represents the influence rate of the seven-day holiday start on the lowest load of electricity utilization, P7slm、P'7slmRespectively representing the lowest load of electricity utilization on the first day of a seven-day holiday and the day before the holiday;
Figure BDA0002733571940000106
shows the rate of influence of the start of a seven-day holiday on the amount of electricity used, Q7sm、Q'7smThe electricity consumption on the first day of the seven-day holiday and the day before the holiday are respectively shown. M represents the number of seven-day holidays in the historical electricity utilization data, and for example, if the time of the national day holiday is 7 days, and the number of the national day holidays from 2017 to 2020 is 4, then M is equal to 4.
Specifically, the influence rates on the electricity consumption on the second day to the seventh day of the seven-day holiday are obtained based on the same principle as described above. Illustratively, the influence rates of the second day of the seven-day holiday on the highest power load, the lowest power load and the power consumption are obtained according to the highest power load, the lowest power load and the power consumption of the second day of the seven-day holiday and the day before the second day of the seven-day holiday, respectively.
The influence rate of the seven-day holiday end on the highest power utilization load, the lowest power utilization load and the power consumption is as follows:
Figure BDA0002733571940000107
Figure BDA0002733571940000111
Figure BDA0002733571940000112
wherein the content of the first and second substances,
Figure BDA0002733571940000113
represents the influence rate of the end of the seven-day holiday period on the highest load of electricity consumption, P'7ehm、P7ehmRespectively representing the highest load of electricity utilization on the last day and the following day of the seven-day holiday;
Figure BDA0002733571940000114
represents the influence rate of the end of the seven-day holiday period on the lowest load of electricity consumption, P'7elm、P7elmRespectively representing the lowest power consumption load of the last day and the following day of the seven-day holiday;
Figure BDA0002733571940000115
represents the influence rate Q 'of the end of the seven-day holiday on the amount of electricity consumption'7em、Q7emThe electricity consumption of the last day of the seven-day holiday and the following day are respectively shown.
The double holiday may be a conventional saturday as a holiday. Specific influence rates of the double-holidays on the electricity consumption include influence rates of saturday, sunday and monday on the highest load of the electricity consumption, the lowest load of the electricity consumption and the electricity consumption.
Specifically, the influence rate of saturday on the highest load of electricity consumption, the lowest load of electricity consumption and the electricity consumption is as follows:
Figure BDA0002733571940000116
Figure BDA0002733571940000117
Figure BDA0002733571940000118
wherein the content of the first and second substances,
Figure BDA0002733571940000119
represents the influence rate of Saturday on the highest load of electricity utilization, P6hc、P'6hcRespectively representing the highest load of electricity utilization on saturday and the day before the saturday;
Figure BDA00027335719400001110
represents the influence rate of Saturday on the lowest load of electricity utilization, P6lc、P'6lcRespectively representing the lowest load of electricity utilization on saturday and the day before the saturday;
Figure BDA00027335719400001111
represents the influence rate of Saturday on the electricity consumption, Q6c、Q'6cThe power consumption of saturday and the day before the saturday are respectively represented. C represents the number of bikes in the selected time period, and the number of bikes included in 2018 to 2019 is C.
The influence rate of the weekdays on the highest power utilization load, the lowest power utilization load and the power consumption is as follows:
Figure BDA00027335719400001112
Figure BDA0002733571940000121
Figure BDA0002733571940000122
wherein the content of the first and second substances,
Figure BDA0002733571940000123
represents the influence rate of the day of the week on the maximum load of electricity consumption, P7hc、P'7hcRespectively representing the highest loads of electricity consumption of sunday and saturday;
Figure BDA0002733571940000124
indicating the power consumption in the weekdaysInfluence of the lowest load, P7lc、P'7lcRespectively representing the lowest loads of electricity consumption of sunday and saturday;
Figure BDA0002733571940000125
shows the influence rate of the weekdays on the electricity consumption, Q7c、Q'7cThe power consumption of sunday and saturday is shown.
The influence rates of the highest load of Monday electricity, the lowest load of electricity and the electricity consumption are as follows:
Figure BDA0002733571940000126
Figure BDA0002733571940000127
Figure BDA0002733571940000128
wherein the content of the first and second substances,
Figure BDA0002733571940000129
represents the influence rate of Monday on the highest load of electricity utilization, P1hc、P'1hcRespectively representing the power consumption maximum loads of Monday and Sunday;
Figure BDA00027335719400001210
represents the influence rate of Monday on the lowest load of electricity utilization, P1lc、P'1lcRespectively representing the lowest loads of power utilization on Monday and Sunday;
Figure BDA00027335719400001211
represents the influence rate of the week on the electricity consumption, Q1c、Q'1cThe power consumption on monday and sunday are shown.
The influence rate of single holidays on electricity utilization comprises:
the influence rate of the single holiday start on the highest load, the lowest load and the electricity consumption is as follows:
Figure BDA00027335719400001212
Figure BDA00027335719400001213
Figure BDA0002733571940000131
wherein the content of the first and second substances,
Figure BDA0002733571940000132
represents the rate of influence of the start of a single day of rest on the maximum load of electricity utilization, Pdshc、P'dshcRespectively representing the single-rest day and the highest load of electricity utilization one day before the single-rest day;
Figure BDA0002733571940000133
represents the influence rate of the single holiday start on the lowest load of electricity utilization, Pdslc、P'dslcRespectively representing the lowest load of electricity consumption on a single rest day and one day before the single rest day;
Figure BDA0002733571940000134
represents the rate of influence of the start of a single holiday on the amount of electricity used, Qdsc、Q'dscRespectively representing the single holiday and the power consumption of the day before the single holiday. Wherein, C1Representing the number of single holidays within the selected historical data time period.
The influence rate of the single holiday end on the highest load, the lowest load and the electricity consumption is as follows:
Figure BDA0002733571940000135
Figure BDA0002733571940000136
Figure BDA0002733571940000137
wherein the content of the first and second substances,
Figure BDA0002733571940000138
represents the rate of influence of the end of a single day of rest on the maximum load of electricity utilization, Pdehc、P'dehcRespectively representing the highest load of electricity utilization of one day after the single-break day and the single-break day;
Figure BDA0002733571940000139
represents the influence rate of the single holiday end on the lowest load of electricity utilization, Pdelc、P'delcRespectively representing the lowest load of electricity consumption of one day after the single-break day and the single-break day;
Figure BDA00027335719400001310
representing the rate of influence of the end of a single holiday on the amount of electricity used, Qdec、Q'decAnd respectively representing the electricity consumption of one day after the single holiday and the electricity consumption of the single holiday.
The influence rate of the three-day holiday on electricity utilization comprises:
the influence rate of the three-day holiday on the highest power utilization load, the lowest power utilization load and the power consumption is as follows:
Figure BDA00027335719400001311
Figure BDA00027335719400001312
Figure BDA0002733571940000141
wherein the content of the first and second substances,
Figure BDA0002733571940000142
to representInfluence rate of three-day holiday onset on maximum load of electricity utilization, P3shc、P'3shcRespectively representing the highest load of electricity utilization on the first day of a three-day holiday and the day before the holiday;
Figure BDA0002733571940000143
represents the influence rate of the three-day holiday on the lowest load of the electricity, P3slc、P'3slcRespectively representing the lowest load of electricity utilization on the first day of a three-day holiday and the day before the holiday;
Figure BDA0002733571940000144
represents the influence rate of the three-day holiday on the electricity consumption, Q3sc、Q'3scThe electricity consumption of the first day of the three-day holiday and the day before the holiday are respectively represented. Wherein, C2Representing the number of three-day holidays within a selected historical data time period.
Specifically, the influence rates of the second day and the third day of the three-day holiday on the electricity consumption are obtained based on the same principle, and illustratively, the influence rates of the second day of the three-day holiday on the highest electricity consumption load, the lowest electricity consumption load and the electricity consumption are obtained according to the highest electricity consumption load, the lowest electricity consumption load and the electricity consumption of the second day of the three-day holiday and the previous day of the three-day holiday respectively.
The influence rate of the three-day holiday end on the highest power utilization load, the lowest power utilization load and the power consumption is as follows:
Figure BDA0002733571940000145
Figure BDA0002733571940000146
Figure BDA0002733571940000147
wherein the content of the first and second substances,
Figure BDA0002733571940000148
represents the influence rate of the end of a three-day holiday on the highest load of electricity, P'3ehc、P3ehcRespectively representing the highest load of electricity utilization on the last day of a three-day holiday and the next day of the holiday;
Figure BDA0002733571940000149
represents the influence rate of the end of three-day holiday on the lowest load of electricity, P'3elc、P3elcRespectively representing the lowest load of electricity utilization on the last day of a three-day holiday and the following day of the holiday;
Figure BDA00027335719400001410
represents the influence rate of the end of a three-day holiday on the amount of electricity consumption, Q'3ec、Q3ecRespectively representing the electricity consumption of the last day of the three-day holiday and the next day of the holiday.
In the above calculation formulas relating to the influence of temperature and holidays on electricity utilization, before averaging, singular values with significant differences need to be filtered.
In addition, the power utilization influence rate corresponding to the holidays needs to be corrected by using the obtained power utilization influence rate corresponding to the temperature, for example, the influence rate of the average temperature corresponding to the start of the seven-day holiday (namely, the first day of the seven-day holiday) on the power utilization amount is 3%, the calculated influence rate of the start of the seven-day holiday on the power utilization amount is 7%, the temperature factor is deducted, and the finally determined influence rate of the start of the seven-day holiday on the power utilization amount is 4%. After correction, namely deducting the temperature factor, the finally determined influence rates of the second day to the seventh day of the seven-day holiday and the second day to the third day of the three-day holiday on the electricity utilization are all 0, namely the influence rates of the second day to the seventh day of the seven-day holiday and the second day to the third day of the three-day holiday on the electricity utilization are only related to the temperature.
Preferably, the power demand of the target forecast date is forecasted and obtained according to the obtained power utilization influence rate and the weather forecast data, and the forecasting method comprises the following steps:
when the average temperature in the target area rises, the highest load of electricity utilization predicted to obtain the target prediction date is as follows:
Figure BDA0002733571940000151
wherein, PfhMaximum load of electricity, P, representing target forecast datehIndicating the highest load of electricity on the day before the target forecast date,
Figure BDA0002733571940000152
shows the influence rate of the maximum temperature on the maximum load of electricity, ThRepresents the maximum temperature, T ', of the target prediction date'hThe highest temperature on the day before the target prediction date is indicated.
The lowest load of electricity utilization on the predicted and obtained target prediction date is as follows:
Figure BDA0002733571940000153
wherein, PflMinimum load of electricity, P, representing target forecast datelRepresents the lowest load of electricity on the day before the target forecast date,
Figure BDA0002733571940000154
represents the influence rate of the lowest temperature on the lowest load of electricity, TlMinimum temperature, T 'representing target forecast date'lIndicating the lowest temperature of the day before the target prediction date.
The electricity consumption amount of the predicted obtained target prediction date is:
Figure BDA0002733571940000155
wherein Q isfA used amount indicating a target prediction date, Q indicates a used amount of electricity on the day before the target prediction date,
Figure BDA0002733571940000156
shows the influence rate of the average temperature on the amount of electricity used, TvMean temperature, T ', representing target prediction date'vRepresents the average temperature of the day before the target prediction dateAnd (4) degree.
Specifically, when the average temperature in the target region is above the temperature scale, the "±" in formulas (1), (2) and (3) is "+", otherwise, "-" is taken.
The formulas for predicting the highest load of electricity, the lowest load of electricity and the amount of electricity used on the target prediction date when the average temperature in the target area decreases are the same as the formulas (1), (2) and (3), except that "±" in the formulas (1), (2) and (3) is "-" when the temperature of the average temperature in the target area is below the temperature scale, and otherwise "+".
Preferably, the temperature graticule is determined based on the maximum and minimum temperatures of the target area per day in historical weather data. For example, the area with a well-defined quarter may be represented by different temperatures according to the quarter, specifically, an average value of the highest temperature and the lowest temperature per day in one quarter is obtained, and then all the average values are averaged, i.e., the temperature scale value is obtained.
Preferably, when the target forecast date is a holiday, then:
and correcting the highest power utilization load of the target prediction date obtained by prediction by using the influence rate of the holiday on the highest power utilization charge. Specifically, after the highest power consumption load on the target prediction date is obtained according to the maximum temperature-to-highest power consumption load influence rate prediction, the product of the highest power consumption load on the day before the target prediction date and the influence rate of the holiday to the highest power consumption load is added, and the obtained highest power consumption load on the target prediction date is obtained through final prediction.
And correcting the predicted lowest load of the electricity utilization on the target prediction date by using the influence rate of the holiday to the lowest load of the electricity utilization. Specifically, after the lowest power consumption load on the target prediction date is obtained according to the lowest temperature-to-power consumption lowest load influence rate prediction, the product of the lowest power consumption load on the day before the target prediction date and the influence rate of the holiday-to-power consumption lowest load is added, and the obtained lowest power consumption load on the target prediction date is obtained through final prediction.
And correcting the predicted power consumption of the target prediction date by using the influence rate of the holidays on the power consumption. Specifically, after the electricity consumption on the target prediction date is obtained through prediction according to the influence rate of the average temperature on the electricity consumption, the product of the electricity consumption on the day before the target prediction date and the influence rate of holidays on the electricity consumption is added, and the electricity consumption on the target prediction date is obtained through final prediction.
Preferably, the power generation influence rate includes influence rates of a wind power index on the highest power generation load, the lowest power generation load and the power generation amount of the wind power generation, influence rates of a weather clear index on the highest power generation load and the power generation amount of the centralized photovoltaic power generation, and influence rates of the weather clear index on the highest power generation load and the power generation amount of the distributed photovoltaic power generation.
Obtaining power generation influence rate according to historical weather data and historical power generation data, and the method comprises the following steps:
obtaining the influence rate of the wind power index on the highest load of wind power generation, the influence rate of the lowest load of power generation and the influence rate of the generated energy according to the wind power index in the historical weather data and the historical power generation data corresponding to the wind power generation:
Figure BDA0002733571940000161
Figure BDA0002733571940000162
Figure BDA0002733571940000163
wherein the content of the first and second substances,
Figure BDA0002733571940000164
expressing the influence rate of the wind power index on the maximum load of the wind power generation, N expressing the number of days of the set ring ratio or the number of days of the same ratio, Pflhn、Pflhn-1Respectively represents the highest load of wind power generation on the nth day and the nth-1 day,
Figure BDA0002733571940000165
representing the rate of influence of the wind index on the minimum load of the wind power plant, Pflln、Pflln-1Respectively represents the lowest load of wind power generation on the nth day and the nth-1 day,
Figure BDA0002733571940000166
expressing the influence rate of the wind index on the amount of power generation, Qfln、Qfln-1Respectively representing the wind power generation capacity on the nth day and the n-1 th day, Wn、Wn-1Mean wind indices on day n and day n-1 are indicated, respectively.
Obtaining the influence rate of the weather clear index on the highest load of the centralized photovoltaic power generation and the influence rate of the generated energy according to the weather clear index in the historical weather data and the historical power generation data corresponding to the centralized photovoltaic power generation:
Figure BDA0002733571940000171
Figure BDA0002733571940000172
wherein the content of the first and second substances,
Figure BDA0002733571940000173
the influence rate of the weather clear index on the highest load of the centralized photovoltaic power generation is shown, N represents the set number of days of the ring ratio or the number of days of the same ratio, and P represents the number of days of the ring ratio or the number of days of the same ratiofzhn、Pfzhn-1Respectively represents the concentrated photovoltaic power generation maximum load on the nth day and the (n-1) th day,
Figure BDA0002733571940000174
representing the influence rate of the weather clear index on the generated energy of the centralized photovoltaic power generation, Pjzn、Pjzn-1Respectively represents the concentrated photovoltaic power generation amount on the nth day and the nth-1 day, Sn、Sn-1Mean weather clear indices on day n and day n-1 are shown, respectively.
And respectively obtaining the influence rate of the weather clear index on the highest load and the generated energy of the distributed photovoltaic power generation according to the weather clear index in the historical weather data and the historical power generation data corresponding to the distributed photovoltaic power generation:
Figure BDA0002733571940000175
Figure BDA0002733571940000176
wherein the content of the first and second substances,
Figure BDA0002733571940000177
the influence rate of the weather clear index on the highest load of the distributed photovoltaic power generation is shown, N represents the set number of days of the ring ratio or the number of days of the same ratio, P represents the number of days of the ring ratiofbhn、Pfbhn-1Respectively represents the distributed photovoltaic power generation maximum load on the nth day and the (n-1) th day,
Figure BDA0002733571940000178
expressing the influence rate of the weather clear index on the generating capacity of the distributed photovoltaic power generation, Qfbn、Qfbn-1Respectively representing the distributed photovoltaic power generation amount on the nth day and the (n-1) th day.
Specifically, when the power generation influence rate is calculated, if the date of the ring ratio is set, the corresponding acquisition is the ring ratio influence rate, and if the date of the same ratio is set, the corresponding acquisition is the same ratio influence rate. In specific implementation, the ratio of the same-ratio influence rate and the ring-ratio influence rate can be set according to specific situations to obtain the final influence rate. The setting mode refers to the setting mode in calculating the influence rate of the temperature on the power generation.
Preferably, the predicting to obtain the power generation amount and the power generation load on the target prediction date according to the weather forecast data and the power generation influence rate on the target prediction date includes:
predicting to obtain the wind power generation highest load of the target prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation highest load, the average wind power index of the day before the target prediction date and the wind power generation highest load; predicting and obtaining the wind power generation minimum load of the prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation minimum load, the average wind power index of the day before the prediction date and the wind power generation minimum load; predicting to obtain the wind power generation capacity of the target prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation capacity, the average wind power index of the day before the target prediction date and the wind power generation capacity;
and respectively predicting the highest load and the generated energy of the centralized photovoltaic power generation and the highest load and the generated energy of the distributed photovoltaic power generation at the target prediction date.
Specifically, the predicting of the highest load of power generation, the lowest load of power generation, and the power generation amount of wind power generation on the date of obtaining the target prediction includes:
predicting the highest load of wind power generation on the target prediction date:
Figure BDA0002733571940000181
wherein, Pfh1Representing the predicted maximum load, P, of the wind power planth1Indicating the wind power generation maximum load the day before the target prediction date,
Figure BDA0002733571940000182
representing the rate of influence of the wind index on the maximum load of the wind power plant, Wf、WhRespectively representing the target forecast date and the average wind index of the day before the target forecast date.
Predicting the lowest load of wind power generation for which the target prediction date is obtained:
Figure BDA0002733571940000183
wherein, Pfl1Indicating the predicted minimum load of the wind power plant, Pl1Indicating the wind power generation minimum load the day before the target prediction date,
Figure BDA0002733571940000184
the influence rate of the wind power index on the minimum load of wind power generation is shown.
The power generation amount of the wind power generation predicted to obtain the target prediction date is as follows:
Figure BDA0002733571940000185
wherein Q isf1Representing the predicted amount of power generation, Qh1Indicating the amount of power generated by the wind power generation the day before the target prediction date,
Figure BDA0002733571940000186
the influence rate of the wind power index on the wind power generation amount is shown.
Specifically, "+/-" in the formulas (4), (5) and (6) is taken as "+" when the average wind index of the target prediction date is increased compared with the average wind index of the previous day, and is taken as "-" when the average wind index is decreased.
Preferably, the predicting of the highest load and the power generation amount of the centralized photovoltaic power generation comprises:
predicting the highest power generation load of the centralized photovoltaic power generation for obtaining the target prediction date:
Figure BDA0002733571940000191
wherein, Pfh2Representing the predicted maximum load of generation, P, for concentrated photovoltaic power generationh2Represents the highest load of power generation of the concentrated photovoltaic power generation the day before the target prediction date,
Figure BDA0002733571940000192
indicating weather clear index pair concentrationFormula photovoltaic power generation maximum load influence ratio, Sf、ShRespectively representing the target prediction date and the average weather clear index of the day before the target prediction date.
Predicting the generated energy of the centralized photovoltaic power generation for obtaining the target prediction date:
Figure BDA0002733571940000193
wherein Q isf2Representing predicted power generation capacity, Q, of concentrated photovoltaic power generationh2Represents the amount of power generation of the concentrated photovoltaic power generation the day before the target prediction date,
Figure BDA0002733571940000194
and the influence rate of the weather clear index on the power generation amount of the centralized photovoltaic power generation is shown.
Preferably, the predicting to obtain the highest load and the power generation amount of the distributed photovoltaic power generation comprises:
predicting the highest power generation load of the distributed photovoltaic power generation with the target prediction date:
Figure BDA0002733571940000195
wherein, Pfh3Representing the predicted maximum load of power generation, P, for distributed photovoltaic power generationh3Represents the highest power generation load of the distributed photovoltaic power generation one day before the target prediction date,
Figure BDA0002733571940000196
representing the influence rate of the weather clear index on the highest load of the distributed photovoltaic power generation, Sf、ShRespectively representing the target prediction date and the average weather clear index of the day before the target prediction date.
Predicting the generated energy of the distributed photovoltaic power generation on the obtained target prediction date:
Figure BDA0002733571940000197
wherein Q isf3Representing the predicted power generation of distributed photovoltaic power generation, Qh3Represents the amount of power generation of the distributed photovoltaic power generation one day before the target prediction date,
Figure BDA0002733571940000198
and the influence rate of the weather clear index on the power generation amount of the distributed photovoltaic power generation is shown.
Specifically, when the average weather clear index of the target prediction date is increased compared with the average weather clear index of the previous day, the "±" in the formulas (7), (8), (9) and (10) is "+", and when the average weather clear index is decreased, the "-".
Considering that there is a difference in the time periods corresponding to the maximum loads generated by wind power generation and photovoltaic power generation, the sum of the maximum load of wind power generation, the maximum load of concentrated photovoltaic power generation, and the maximum load of distributed photovoltaic power generation on the target prediction date obtained by prediction is not the maximum load of new energy power generation, and therefore, it is also necessary to determine the new energy power generation ratio from the historical power generation data,
Figure BDA0002733571940000201
wherein the content of the first and second substances,
Figure BDA0002733571940000202
representing the power generation ratio of new energy, N representing the number of days of the set ring ratio or the number of days of the same ratio, Pwn、Psn1、Psn2Respectively representing the highest load of wind power generation, the highest load of centralized photovoltaic power generation and the highest load of distributed photovoltaic power generation on the nth day, PnAnd the maximum load of the new energy power generation on the nth day is shown.
Preferably, the wind power generation maximum load, the centralized photovoltaic power generation maximum load, the distributed photovoltaic power generation maximum load and the new energy power generation maximum load of the target prediction date are obtained according to the prediction obtained target prediction date.
The method comprises the steps of determining the starting and stopping capacity of the thermal power generation according to the power demand, the power generation load and the power generation amount of a target prediction date in a target area obtained through prediction, reasonably allocating the operation of a thermal power generating set, providing auxiliary power generation for new energy power generation, enabling the highest power generation load and the lowest power generation load to meet the demand for adjustable output, meeting the power demand of users in the target area, and ensuring safe and stable operation of a power grid.
The invention provides a power generation control method based on power generation and power utilization prediction, compared with the prior art, firstly, influence rates of the highest temperature, the lowest temperature and the average temperature on the highest load of power utilization, the lowest load of power utilization and the power consumption of a user are obtained according to historical weather data and historical power utilization data, so that the power utilization demand of the user is predicted according to the temperature of a target prediction date, in addition, the influence rates of holidays on the highest load of power utilization, the lowest load of power utilization and the power consumption are obtained according to the historical weather data and the historical power utilization data corresponding to holidays, so that the power utilization demand of the user in holidays is predicted, and the power utilization demand of the user can be more accurately predicted by combining the influence rates of the temperature and the holidays on the power utilization of the user. Secondly, according to historical weather data and historical power generation data, the influence rate of the wind power index and the weather clear index on new energy power generation is obtained, the highest load of new energy power generation, the lowest load of power generation and the power generation amount on the target prediction date are predicted according to the influence rate, further, the highest load of new energy power generation on the target prediction date is obtained according to the new energy power generation ratio, and the accuracy of the prediction result can be guaranteed. And finally, determining the starting and stopping capacity of the thermal power generation of the target area based on the predicted power demand of the target area and the new energy power generation capacity, reasonably allocating thermal power generating sets, and performing auxiliary power generation on the new energy power generation so as to enable the highest power generation load and the lowest power generation load to meet the requirements for adjustable output. On one hand, the power utilization requirement of a user is met, the safe and stable operation of a power grid can be guaranteed, the resource utilization rate is improved, the resource waste is prevented and the economical efficiency is good by reasonably allocating the generator set; on the other hand, when the generating set breaks down, can guarantee to satisfy when user's power consumption demand, have sufficient time to carry out generating set maintenance.
Those skilled in the art will appreciate that all or part of the flow of the method implementing the above embodiments may be implemented by a computer program, which is stored in a computer readable storage medium, to instruct related hardware. The computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.

Claims (9)

1. A power generation control method based on power generation and power utilization prediction is characterized by comprising the following steps:
acquiring historical electricity utilization data, historical power generation data, historical weather data and weather forecast data of a target prediction date of a target area;
obtaining power utilization influence rate according to the historical weather data and the historical power utilization data, and obtaining power generation influence rate according to the historical weather data and the historical power generation data;
the electricity utilization influence rate comprises the influence rate of the highest temperature on the highest load of electricity utilization, the influence rate of the lowest temperature on the lowest load of electricity utilization and the influence rate of the average temperature on the electricity utilization;
the obtaining of the power utilization influence rate according to the historical weather data and the historical power utilization data comprises the following steps:
the influence rate of the maximum temperature on the maximum load of the power consumption is as follows:
Figure FDA0003462028970000011
wherein the content of the first and second substances,
Figure FDA0003462028970000012
showing the influence rate of the maximum temperature on the maximum load of the power utilization, N showing the number of days of the set ring ratio or the number of days of the same ratio, Pqwhn、Pqwhn-1Respectively represents the highest load of electricity consumption on the nth day and the nth-1 day, Thn、Thn-1The maximum temperatures on day n and day n-1 are indicated, respectively;
the influence rate of the lowest temperature on the lowest power load is as follows:
Figure FDA0003462028970000013
wherein the content of the first and second substances,
Figure FDA0003462028970000014
showing the influence rate of the lowest temperature on the lowest load of the power utilization, N showing the number of days of the ring ratio or the number of days of the same ratio, Pqwln、Pqwln-1Respectively represents the lowest load of electricity utilization on the nth day and the nth-1 day, Tln、Tln-1The minimum temperatures on day n and day n-1, respectively;
the influence rate of the average temperature on the electricity consumption is as follows:
Figure FDA0003462028970000015
wherein the content of the first and second substances,
Figure FDA0003462028970000016
expressing the influence rate of the average temperature on the electricity consumption, N expressing the number of days of the set ring ratio or the number of days of the same ratio, Qqwn、Qqwn-1Respectively represents the power consumption on the nth day and the nth-1 day, Tvn、Tvn-1Mean temperatures on day n and day n-1, respectively;
according to the weather forecast data and the power utilization influence rate, predicting the power utilization requirement of the target prediction date;
according to the weather forecast data and the power generation influence rate, predicting to obtain the generated energy and the power generation load of the new energy power generation on the target prediction date;
and predicting according to the power demand, the power generation capacity and the power generation load of the target prediction date to obtain the start-stop capacity of the thermal power generation of the target prediction date, and performing power generation control on the thermal power generator set in the target area according to the start-stop capacity.
2. The power generation control method based on power generation and power usage prediction according to claim 1,
the historical electricity consumption data comprises dates, corresponding electricity consumption, highest electricity consumption load and lowest electricity consumption load;
the historical power generation data comprises a new energy power generation mode, a date, corresponding power generation amount, a highest power generation load and a lowest power generation load, and the new energy power generation mode comprises wind power generation, centralized photovoltaic power generation and distributed photovoltaic power generation;
the historical weather data and the weather forecast data of the target forecast date respectively comprise dates, corresponding maximum temperatures, minimum temperatures, average temperatures, wind indexes and weather clear indexes.
3. The power generation control method based on power generation and power usage prediction of claim 1, wherein the power usage impact rate further includes impact rates of holidays on power usage top load, power usage bottom load, and power usage amount:
influence rate of seven-day holiday on maximum load of electricity usage:
wherein, the influence rate of the seven-day holiday beginning on the highest load of power utilization is as follows:
Figure FDA0003462028970000021
wherein the content of the first and second substances,
Figure FDA0003462028970000022
indicates that the seven-day holiday begins to be highest negative to the electricity consumptionThe influence rate of the charge, M represents the number of seven-day holidays in the historical electricity consumption data, P7shm、P'7shmRespectively representing the highest load of electricity utilization on the first day of a seven-day holiday and the day before the holiday;
influence rate of seven-day holiday end on electricity utilization maximum load:
Figure FDA0003462028970000023
wherein the content of the first and second substances,
Figure FDA0003462028970000024
represents the influence rate of the end of the seven-day holiday period on the highest load of electricity consumption, P'7ehm、P7ehmRespectively representing the highest load of electricity utilization on the last day and the following day of the seven-day holiday;
sequentially obtaining the influence rates of the start of the seven-day holiday and the end of the seven-day holiday on the lowest power consumption load and the lowest power consumption;
and obtaining the influence rates of the double-holiday, the single-holiday and the three-day holiday on the highest power utilization load, the lowest power utilization load and the power consumption respectively; and the double-holiday further comprises influence rates of the saturday to the sunday on the highest power utilization load, the lowest power utilization load and the power consumption.
4. The power generation control method based on power generation and power utilization prediction as claimed in claim 3, wherein predicting the power utilization demand for obtaining the target prediction date according to the weather forecast data and the power utilization influence rate comprises:
predicting to obtain the highest power utilization load of the target prediction date according to the highest temperature corresponding to the target prediction date, the influence rate of the highest temperature on the highest power utilization load, the highest temperature of the day before the target prediction date and the highest power utilization load;
predicting and obtaining the lowest power load of the target prediction date according to the lowest temperature corresponding to the target prediction date, the influence rate of the lowest temperature on the lowest power load, the lowest temperature of the day before the target prediction date and the lowest power load;
and predicting the electricity consumption on the target prediction date according to the average temperature and the influence rate of the average temperature on the electricity consumption corresponding to the target prediction date, the average temperature of the day before the target prediction date and the electricity consumption.
5. The power generation control method based on power generation and power utilization prediction as claimed in claim 4, wherein the predicting obtains the power utilization demand of the target prediction date, further comprising:
correcting the predicted maximum power load on the target prediction date by using the influence rate of the holiday on the maximum power charge;
correcting the predicted lowest load of the electricity utilization on the target prediction date by using the influence rate of the holidays on the lowest load of the electricity utilization;
and correcting the predicted power consumption of the target prediction date by using the influence rate of the holidays on the power consumption.
6. The power generation control method based on power generation and power utilization prediction according to any one of claims 2 to 5, wherein the power generation influence rate includes an influence rate of a wind power index on a power generation maximum load, a power generation minimum load and power generation amount of wind power generation, an influence rate of a weather clear index on a power generation maximum load and power generation amount of centralized photovoltaic power generation, and an influence rate of a weather clear index on a power generation maximum load and power generation amount of distributed photovoltaic power generation;
the obtaining of the power generation influence rate according to the historical weather data and the historical power generation data comprises the following steps:
obtaining the influence rate of the wind power index on the highest load of wind power generation, the influence rate of the lowest load of power generation and the influence rate of power generation capacity according to the wind power index in the historical weather data and the historical power generation data corresponding to the wind power generation:
Figure FDA0003462028970000031
Figure FDA0003462028970000032
Figure FDA0003462028970000041
wherein the content of the first and second substances,
Figure FDA0003462028970000042
expressing the influence rate of the wind power index on the maximum load of the wind power generation, N expressing the number of days of the set ring ratio or the number of days of the same ratio, Pflhn、Pflhn-1Respectively represents the highest load of wind power generation on the nth day and the nth-1 day,
Figure FDA0003462028970000043
representing the rate of influence of the wind index on the minimum load of the wind power plant, Pflln、Pflln-1Respectively represents the lowest load of wind power generation on the nth day and the nth-1 day,
Figure FDA0003462028970000044
expressing the influence rate of the wind index on the amount of power generation, Qfln、Qfln-1Respectively representing the wind power generation capacity on the nth day and the n-1 th day, Wn、Wn-1Mean wind indices on day n and day n-1, respectively;
obtaining the influence rate of the weather clear index on the highest load of the centralized photovoltaic power generation and the influence rate of the generated energy according to the weather clear index in the historical weather data and the historical power generation data corresponding to the centralized photovoltaic power generation:
Figure FDA0003462028970000045
Figure FDA0003462028970000046
wherein the content of the first and second substances,
Figure FDA0003462028970000047
the influence rate of the weather clear index on the highest load of the centralized photovoltaic power generation is shown, N represents the set number of days of the ring ratio or the number of days of the same ratio, and P represents the number of days of the ring ratio or the number of days of the same ratiofzhn、Pfzhn-1Respectively represents the concentrated photovoltaic power generation maximum load on the nth day and the (n-1) th day,
Figure FDA0003462028970000048
representing the influence rate of the weather clear index on the generated energy of the centralized photovoltaic power generation, Pjzn、Pjzn-1Respectively represents the concentrated photovoltaic power generation amount on the nth day and the nth-1 day, Sn、Sn-1Respectively representing the average weather clear index of the nth day and the average weather clear index of the (n-1) th day;
and respectively obtaining the influence rate of the weather clear index on the highest load and the generated energy of the distributed photovoltaic power generation according to the weather clear index in the historical weather data and the historical power generation data corresponding to the distributed photovoltaic power generation.
7. The power generation control method based on power generation and power utilization prediction according to claim 6, wherein predicting the power generation amount and the power generation load of new energy power generation for which the target prediction date is obtained based on the weather forecast data and the power generation influence rate of the target prediction date includes:
predicting to obtain the wind power generation highest load of the target prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation highest load, the average wind power index of the day before the target prediction date and the wind power generation highest load; predicting and obtaining the wind power generation minimum load of the prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation minimum load, the average wind power index of the day before the prediction date and the wind power generation minimum load; predicting to obtain the wind power generation capacity of the target prediction date according to the average wind power index corresponding to the target prediction date, the influence rate of the wind power index on the wind power generation capacity, the average wind power index of the day before the target prediction date and the wind power generation capacity;
and respectively predicting the highest load and the generated energy of the centralized photovoltaic power generation and the highest load and the generated energy of the distributed photovoltaic power generation at the target prediction date.
8. The power generation control method based on power generation and power usage prediction according to claim 6,
obtaining the new energy power generation ratio according to historical power generation data;
Figure FDA0003462028970000051
wherein the content of the first and second substances,
Figure FDA0003462028970000052
representing the power generation ratio of new energy, N representing the number of days of the set ring ratio or the number of days of the same ratio, Pwn、Psn1、Psn2Respectively representing the highest load of wind power generation, the highest load of centralized photovoltaic power generation and the highest load of distributed photovoltaic power generation on the nth day, PnAnd the maximum load of the new energy power generation on the nth day is shown.
9. The power generation control method based on power generation and power utilization prediction according to claim 8, characterized in that the wind power generation maximum load, the concentrated photovoltaic power generation maximum load, the distributed photovoltaic power generation maximum load, and the new energy power generation maximum load of the target prediction date obtained from the prediction are obtained in accordance with the new energy power generation percentage.
CN202011125818.8A 2020-10-20 2020-10-20 Power generation control method based on power generation and power utilization prediction Active CN112217208B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011125818.8A CN112217208B (en) 2020-10-20 2020-10-20 Power generation control method based on power generation and power utilization prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011125818.8A CN112217208B (en) 2020-10-20 2020-10-20 Power generation control method based on power generation and power utilization prediction

Publications (2)

Publication Number Publication Date
CN112217208A CN112217208A (en) 2021-01-12
CN112217208B true CN112217208B (en) 2022-03-04

Family

ID=74056035

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011125818.8A Active CN112217208B (en) 2020-10-20 2020-10-20 Power generation control method based on power generation and power utilization prediction

Country Status (1)

Country Link
CN (1) CN112217208B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114862293A (en) * 2022-07-09 2022-08-05 山东恒迈信息科技有限公司 Intelligent electricity safety management method and system
CN115333100B (en) * 2022-10-12 2022-12-16 四川中电启明星信息技术有限公司 Roof photovoltaic power generation power cooperative control method and system
CN115347569B (en) * 2022-10-13 2022-12-27 江苏鼎豪电力工程有限公司 Power allocation system based on intelligent prediction
CN115528750B (en) * 2022-11-03 2023-04-07 南方电网数字电网研究院有限公司 Power grid safety and stability oriented data model hybrid drive unit combination method
CN117410981B (en) * 2023-11-01 2024-05-17 中嘉能(广东)能源有限公司 Multi-region electric power energy intelligent scheduling method and system based on big data

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109636063A (en) * 2018-12-26 2019-04-16 武汉理工大学 A kind of method of short-term load forecasting
CN110288111A (en) * 2018-03-19 2019-09-27 浙江昱能科技有限公司 A kind of method and system of family's electric energy management based on weather forecasting

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10977586B2 (en) * 2018-02-13 2021-04-13 The Trustees Of Indiana University Forecasting and managing daily electrical maximum demands

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110288111A (en) * 2018-03-19 2019-09-27 浙江昱能科技有限公司 A kind of method and system of family's electric energy management based on weather forecasting
CN109636063A (en) * 2018-12-26 2019-04-16 武汉理工大学 A kind of method of short-term load forecasting

Also Published As

Publication number Publication date
CN112217208A (en) 2021-01-12

Similar Documents

Publication Publication Date Title
CN112217208B (en) Power generation control method based on power generation and power utilization prediction
Garver Adjusting maintenance schedules to levelize risk
CN106160091B (en) Promote the electric automobile charging station charge and discharge dispatching method of regenerative resource consumption
CN109256799B (en) New energy power system optimal scheduling method based on sample entropy
CN112467730B (en) Power system optimal scheduling method considering wind-solar output prediction error and demand response flexibility
CN108574303B (en) Multi-energy coordination optimization scheduling method considering peak-shaving frequency modulation requirements
CN114492085B (en) Regional power and electric quantity balancing method related to load and power supply joint probability distribution
CN112234638A (en) Power grid peak regulation system and method based on load side intelligent charging pile cluster control
CN108009672B (en) Water-light complementary power station daily power generation planning method based on double-layer optimization model
CN110929428B (en) Method and system for determining power generation capacity adequacy of power system
CN110768302A (en) Evaluation and regulation method for renewable energy consumption capability of regional power grid
CN111934366A (en) Power grid multivariate optimization scheduling method for improving wind power receiving capacity
CN108736498B (en) Energy control method for smart home light storage power generation system
WO2024032483A1 (en) Application method for hydroelectric-photovoltaic complementary scheduling graph of clean energy base
CN112202174B (en) New energy power generation prediction method and system
CN115983589A (en) Multi-type power supply time sequence planning method and system under long-time scale
CN107453377B (en) Solar thermal power generation heat storage proportion analysis method
CN115940234A (en) Intelligent regulation and control method for household renewable energy distributed power generation
CN114400652A (en) Multi-energy power generation optimization scheduling method considering active participation of nuclear power in peak shaving
CN115049431A (en) Pricing method of water and electricity in electric power spot market
CN110417002B (en) Optimization method of island micro-grid energy model
CN110504713B (en) Power grid dispatching method capable of interrupting load to participate in standby
Kong et al. Operational hydropower scheduling with post-spot distribution of reserve obligations
CN112003270B (en) Reactive auxiliary service optimization scheduling method applied to power market environment
CN117424231B (en) Energy-saving power distribution control system and method

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
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20210112

Assignee: YANTAI POWER PLANT, HUANENG SHANDONG GENERATING Co.,Ltd.

Assignor: HUANENG SHANDONG POWER GENERATION Co.,Ltd.

Contract record no.: X2023980051485

Denomination of invention: A Power Generation Control Method Based on Generation and Consumption Prediction

Granted publication date: 20220304

License type: Common License

Record date: 20231220

EE01 Entry into force of recordation of patent licensing contract