CN116304669A - Short-term correction distributed photovoltaic power prediction method and system - Google Patents
Short-term correction distributed photovoltaic power prediction method and system Download PDFInfo
- Publication number
- CN116304669A CN116304669A CN202211681969.0A CN202211681969A CN116304669A CN 116304669 A CN116304669 A CN 116304669A CN 202211681969 A CN202211681969 A CN 202211681969A CN 116304669 A CN116304669 A CN 116304669A
- Authority
- CN
- China
- Prior art keywords
- historical
- data set
- power
- weather
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000012937 correction Methods 0.000 title claims abstract description 25
- 238000010219 correlation analysis Methods 0.000 claims abstract description 27
- 238000012216 screening Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims description 48
- 230000015654 memory Effects 0.000 claims description 39
- 238000010248 power generation Methods 0.000 claims description 27
- 238000004458 analytical method Methods 0.000 claims description 21
- 230000001419 dependent effect Effects 0.000 claims description 17
- 230000001502 supplementing effect Effects 0.000 claims description 11
- 230000002596 correlated effect Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000004590 computer program Methods 0.000 description 9
- 238000013480 data collection Methods 0.000 description 8
- 230000000875 corresponding effect Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000003208 petroleum Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Bioethics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a distributed photovoltaic power prediction method and system for short-term correction, and belongs to the technical field of power electronic methods and equipment. The technical scheme of the invention is as follows: acquiring a historical power data set and a historical meteorological data set of the target area; carrying out power correlation analysis on the historical meteorological data set to generate a correlation feature set; screening the historical meteorological data set to obtain a historical related meteorological data set; constructing an objective function based on the historical relevant meteorological data set and the historical power data set; connecting a weather forecast management platform, and obtaining weather characteristic forecast information of a day to be forecast according to the correlation characteristic set; and acquiring a power prediction result according to the objective function based on the weather feature prediction information. The beneficial effects of the invention are as follows: the relation between the photovoltaic power and the meteorological data can be accurately analyzed, and the accuracy of the distributed photovoltaic power prediction is improved.
Description
Technical Field
The invention relates to a short-term correction distributed photovoltaic power prediction method and system, and belongs to the technical field of photovoltaic power prediction methods and equipment.
Background
With the rapid development of social economy, the energy consumption is rapidly increased, fossil energy such as coal, petroleum and the like is frequently and rapidly exhausted, and the environment pollution caused by the combustion of the increasingly fossil fuel is added, so that serious threat is brought to the ecological balance of the earth and the life of human beings, and the construction of a large-scale photovoltaic power station to meet the requirement of the human beings on the energy is the current development trend. Solar energy is taken as a novel green renewable energy source, and is the most ideal renewable energy source compared with other new energy sources. In particular, in recent decades, with the continuous progress of science and technology, solar energy and related industries have become one of the fastest growing industries in the world. However, the photovoltaic power generation output has the characteristics of fluctuation and intermittence, and the large-scale distributed photovoltaic power generation is connected to the regional power grid to bring great influence to the dispatching of the power grid, so that the power prediction of the distributed photovoltaic power generation is necessary, a dispatching plan is formulated for the power grid energy management system, and the dispatching data of the distributed photovoltaic power generation is provided.
At present, the prior art has the technical problem that the accuracy of the prediction of the distributed photovoltaic power is insufficient due to the fact that the analysis of the relation between the photovoltaic power and the meteorological data is not accurate enough.
Disclosure of Invention
The invention aims to provide a short-term correction distributed photovoltaic power prediction method and system, which are used for constructing an objective function based on a historical related meteorological data set and a historical power data set, acquiring a power prediction result based on meteorological feature prediction information according to the objective function, accurately analyzing the relation between photovoltaic power and meteorological data, improving the accuracy of distributed photovoltaic power prediction and effectively solving the problems in the background art.
The technical scheme of the invention is as follows: a short term corrected distributed photovoltaic power prediction method comprising the steps of:
(1) Determining a target area, and acquiring a historical power data set and a historical weather data set of the target area, wherein the historical weather data set corresponds to the historical power data set one by one;
(2) Carrying out power correlation analysis on the historical meteorological data set to generate a correlation feature set;
(3) Screening the historical meteorological data set according to the correlation characteristic set to obtain a historical correlated meteorological data set;
(4) Constructing an objective function based on the historical relevant meteorological data set and the historical power data set;
(5) Connecting a weather forecast management platform, and obtaining weather characteristic forecast information of a day to be forecast according to the correlation characteristic set;
(6) And acquiring a power prediction result according to the objective function based on weather feature prediction information of the day to be predicted.
Specifically, in the step (2), a plurality of meteorological feature types are acquired according to a historical meteorological data set; carrying out power correlation analysis on a plurality of meteorological feature types to obtain a plurality of correlation coefficients; judging by using a plurality of correlation coefficients to obtain a plurality of correlation weather feature types which are larger than or equal to a preset correlation coefficient; a set of correlation features is generated based on the plurality of correlation weather feature types.
Specifically, in the step (1), acquiring a historical power data set of the target area includes:
acquiring a first preset time period according to a day to be predicted;
collecting a historical power data set according to a first preset time period;
detecting the data integrity of the historical power data set, and judging whether the historical power data set has a missing value or not;
and if the historical power data set has missing values, supplementing the missing values.
The above-mentioned supplementing of missing value specifically includes the following steps:
obtaining k pieces of historical power data with nearest missing values, wherein k is an integer greater than or equal to 2;
the average of k historical power data is calculated and the missing values are replaced with the average.
In the step (4), a history-related meteorological data set is taken as an independent variable; taking the historical power data set as a dependent variable; and fitting a function relation based on the independent variable and the dependent variable, and constructing an objective function.
Preferably, the method further comprises the following steps:
acquiring the using time length of the photovoltaic power generation equipment in the target area;
carrying out power influence analysis on the photovoltaic power generation equipment according to the using time length to obtain power influence data of the photovoltaic power generation equipment;
and optimizing the power prediction result according to the power influence data to obtain an optimized power prediction result.
Preferably, the method further comprises the steps of:
obtaining historical weather feature prediction information;
carrying out prediction accuracy analysis on the historical meteorological feature prediction information to obtain a historical prediction error value;
correcting weather feature prediction information of a day to be predicted according to the historical prediction error value to obtain corrected weather feature prediction information;
and replacing the weather feature prediction information with the modified weather feature prediction information to perform power prediction.
The utility model provides a distributed photovoltaic power prediction system of short-term correction, includes historical data collection module, correlation analysis module, historical meteorological data set screening module, objective function builds the module, waits to predict solar and meteorological information acquisition module and power prediction module, historical data collection module connects and confirms the target area, historical data collection module, correlation analysis module and historical meteorological data set screening module connect gradually, the input that objective function builds the module connects historical data collection module and historical meteorological data set screening module respectively, the input that waits to predict solar and meteorological information acquisition module connects weather forecast management platform and correlation analysis module respectively, the output that objective function built the module and wait to predict solar and meteorological information acquisition module is connected with power prediction module respectively.
The system also comprises a meteorological feature type acquisition module, a correlation coefficient judgment module and a correlation feature set acquisition module which are sequentially connected.
Preferably, the system further comprises a first preset time period acquisition module, a historical power data acquisition module, a data integrity detection module and a missing value supplementing module which are sequentially connected.
Preferably, the system further comprises a neighboring historical power data acquisition module and an average calculation module which are connected with each other.
Preferably, the system further comprises an independent variable setting module, a dependent variable setting module and a functional relation fitting module, wherein the output ends of the independent variable setting module and the dependent variable setting module are respectively connected with the functional relation fitting module.
Preferably, the system further comprises a using time length acquisition module, a power influence analysis module and a power prediction result optimization module which are sequentially connected.
Preferably, the system further comprises a historical weather feature prediction information acquisition module, a prediction accuracy analysis module, a modified weather feature prediction information acquisition module and a weather feature prediction information replacement module, which are sequentially connected.
An electronic device for distributed photovoltaic power prediction for short term correction, comprising a processor and a memory, the processor being communicatively coupled to the memory, the processor and the memory being at least one in number, the memory storing instructions executable by the processor, the instructions being executable by the processor to enable the processor to perform the method of any one of claims 1-7.
Preferably, the processor and the memory are integrated structures that are integrated together.
Preferably, the processor and the memory are coupled by a bus.
The beneficial effects of the invention are as follows: by constructing an objective function based on the historical related meteorological data set and the historical power data set and acquiring a power prediction result based on meteorological feature prediction information according to the objective function, the relation between the photovoltaic power and the meteorological data can be accurately analyzed, and the accuracy of the distributed photovoltaic power prediction is improved.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting mid-to-short term correction of distributed photovoltaic power according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a distributed photovoltaic power prediction system with medium-short term correction according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for distributed photovoltaic power prediction for short term correction according to a third embodiment of the present invention;
in the figure: the system comprises a historical data acquisition module 11, a correlation analysis module 12, a historical meteorological data set screening module 13, an objective function construction module 14, a solar meteorological information acquisition module 15 to be predicted, a power prediction module 16, an electronic device 800, a processor 801, a memory 802 and a bus 803.
Detailed Description
The following describes the technical scheme of the present invention in further detail by referring to the accompanying drawings and examples, which are preferred examples of the present invention. It should be understood that the described embodiments are merely some, but not all, embodiments of the present invention; it should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
A short term corrected distributed photovoltaic power prediction method comprising the steps of:
(1) Determining a target area, and acquiring a historical power data set and a historical weather data set of the target area, wherein the historical weather data set corresponds to the historical power data set one by one;
(2) Carrying out power correlation analysis on the historical meteorological data set to generate a correlation feature set;
(3) Screening the historical meteorological data set according to the correlation characteristic set to obtain a historical correlated meteorological data set;
(4) Constructing an objective function based on the historical relevant meteorological data set and the historical power data set;
(5) Connecting a weather forecast management platform, and obtaining weather characteristic forecast information of a day to be forecast according to the correlation characteristic set;
(6) And acquiring a power prediction result according to the objective function based on weather feature prediction information of the day to be predicted.
Further, in the step (2), a plurality of weather feature types are acquired according to the historical weather data set; carrying out power correlation analysis on a plurality of meteorological feature types to obtain a plurality of correlation coefficients; judging by using a plurality of correlation coefficients to obtain a plurality of correlation weather feature types which are larger than or equal to a preset correlation coefficient; a set of correlation features is generated based on the plurality of correlation weather feature types.
Further, in the step (1), acquiring a historical power data set of the target area includes:
acquiring a first preset time period according to a day to be predicted;
collecting a historical power data set according to a first preset time period;
detecting the data integrity of the historical power data set, and judging whether the historical power data set has a missing value or not;
and if the historical power data set has missing values, supplementing the missing values.
The supplementing of the missing value comprises the following steps:
obtaining k pieces of historical power data with nearest missing values, wherein k is an integer greater than or equal to 2;
the average of k historical power data is calculated and the missing values are replaced with the average.
In the step (4), a history-related meteorological data set is taken as an independent variable; taking the historical power data set as a dependent variable; and fitting a function relation based on the independent variable and the dependent variable, and constructing an objective function.
Further, the method also comprises the following steps:
acquiring the using time length of the photovoltaic power generation equipment in the target area;
carrying out power influence analysis on the photovoltaic power generation equipment according to the using time length to obtain power influence data of the photovoltaic power generation equipment;
and optimizing the power prediction result according to the power influence data to obtain an optimized power prediction result.
Further, the method also comprises the following steps:
obtaining historical weather feature prediction information;
carrying out prediction accuracy analysis on the historical meteorological feature prediction information to obtain a historical prediction error value;
correcting weather feature prediction information of a day to be predicted according to the historical prediction error value to obtain corrected weather feature prediction information;
and replacing the weather feature prediction information with the modified weather feature prediction information to perform power prediction.
The utility model provides a distributed photovoltaic power prediction system of short-term correction, includes historical data collection module 11, correlation analysis module 12 historical meteorological data set screening module 13, objective function builds module 14, waits to predict day meteorological information acquisition module 15 and power prediction module 16, historical data collection module 11 connects and confirms the target area, historical data collection module 11, correlation analysis module 12 and historical meteorological data set screening module 13 connect gradually, the input of objective function builds module 14 and connects historical data collection module 11 and historical meteorological data set screening module 13 respectively, the input of waiting to predict day meteorological information acquisition module 15 connects weather forecast management platform and correlation analysis module 12 respectively, the output of objective function builds module 14 and waiting to predict day meteorological information acquisition module 15 and is connected with power prediction module 16 respectively.
Preferably, the short-term correction distributed photovoltaic power prediction system further comprises a meteorological feature type acquisition module, a correlation coefficient judgment module and a correlation feature set acquisition module, which are sequentially connected.
Preferably, the short-term correction distributed photovoltaic power prediction system further comprises a first preset time period acquisition module, a historical power data acquisition module, a data integrity detection module and a missing value supplementing module, which are sequentially connected.
Preferably, a short term corrected distributed photovoltaic power prediction system further comprises a proximity historical power data acquisition module and an average calculation module, which are interconnected.
Preferably, the short-term correction distributed photovoltaic power prediction system further comprises an independent variable setting module, a dependent variable setting module and a functional relation fitting module, wherein the output ends of the independent variable setting module and the dependent variable setting module are respectively connected with the functional relation fitting module.
Preferably, the short-term correction distributed photovoltaic power prediction system further comprises a time length acquisition module, a power influence analysis module and a power prediction result optimization module which are sequentially connected.
Preferably, the short-term corrected distributed photovoltaic power prediction system further comprises a historical meteorological feature prediction information acquisition module, a prediction accuracy analysis module, a corrected meteorological feature prediction information acquisition module and a meteorological feature prediction information replacement module, which are sequentially connected.
An electronic device for distributed photovoltaic power prediction for short term correction, comprising a processor 801 and a memory 802, the processor being communicatively coupled to the memory, the processor 801 and the memory 802 being at least one in number, the memory 802 storing instructions executable by the processor 801, the instructions being executable by the processor 801 to enable the processor 801 to perform the method of any one of claims 1-7.
Preferably, the processor 801 and the memory 802 are integrated structures that are integrated together.
Preferably, the processor 801 and the memory 802 are coupled via a bus 803.
In practical application, a distributed photovoltaic power prediction method for short-term correction includes: determining a target area, and acquiring a historical power data set and a historical meteorological data set of the target area, wherein the historical meteorological data set corresponds to the historical power data set one by one; carrying out power correlation analysis on the historical meteorological data set to generate a correlation feature set; screening the historical meteorological data set according to the correlation characteristic set to obtain a historical correlated meteorological data set; constructing an objective function based on the historical relevant meteorological data set and the historical power data set; connecting a weather forecast management platform, and obtaining weather characteristic forecast information of a day to be forecast according to the correlation characteristic set; and acquiring a power prediction result according to the objective function based on the weather feature prediction information.
A short term corrected distributed photovoltaic power prediction system comprising: the historical data acquisition module is used for determining a target area and acquiring a historical power data set and a historical meteorological data set of the target area, wherein the historical meteorological data set corresponds to the historical power data set one by one; the correlation analysis module is used for carrying out power correlation analysis on the historical meteorological data set and generating a correlation feature set; the historical meteorological data set screening module is used for screening the historical meteorological data sets according to the correlation characteristic set to obtain historical correlated meteorological data sets; the objective function building module is used for building an objective function based on the historical relevant meteorological data set and the historical power data set; the weather forecast management platform is connected with the weather forecast information acquisition module, and the weather forecast information of the day to be forecast is acquired according to the correlation characteristic set; and the power prediction module is used for acquiring a power prediction result according to the target function based on the weather feature prediction information.
An electronic device for distributed photovoltaic power prediction for short term correction, comprising at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a short term corrected distributed photovoltaic power prediction method.
Example 1
Fig. 1 is a schematic diagram of a short-term corrected distributed photovoltaic power prediction method according to an embodiment of the present application, where the method is applied to a short-term corrected distributed photovoltaic power prediction system, and the system is communicatively connected to a weather forecast management platform, as shown in fig. 1, and the method includes:
step S100: determining a target area, and acquiring a historical power data set and a historical meteorological data set of the target area, wherein the historical meteorological data set corresponds to the historical power data set one by one;
wherein, the step S100 of obtaining the historical power data set of the target area further includes:
step S110: acquiring a first preset time period according to a day to be predicted;
step S120: collecting the historical power data set according to a first preset time period;
step S130: detecting the data integrity of the historical power data set, and judging whether the historical power data set has a missing value or not;
step S140: and if the historical power data set has missing values, supplementing the missing values.
Wherein, to supplement the missing value, step S140 in the embodiment of the present application further includes:
step S141: obtaining k pieces of historical power data with nearest missing values, wherein k is an integer greater than or equal to 2;
step S142: the average of k historical power data is calculated and the missing values are replaced with the average.
Specifically, the distributed photovoltaic power prediction system for short-term correction is a system platform for photovoltaic power prediction, the weather forecast management platform is a platform for calling weather forecast information, and the distributed photovoltaic power prediction system for short-term correction is in communication connection with the weather forecast management platform, so that information interaction can be realized, and the weather forecast information can be called at any time.
Specifically, a target area is determined, the target area is an area needing photovoltaic power prediction, a historical meteorological data set and a historical power data set of the target area are obtained, the historical meteorological data set is meteorological information in the target area in the past period, the historical power data set is photovoltaic power data in the target area in the past period, and the historical meteorological data set and the historical power data set have a one-to-one correspondence, in other words, one historical meteorological data corresponds to one historical power data.
Specifically, the day to be predicted is the time required for photovoltaic power prediction, a first preset time period is obtained according to the day to be predicted, the first preset time period is a period of time for collecting the historical power data set, for example, from the day to be predicted until 12 months pass, or other time periods, the embodiment of the application is not limited herein, the historical power data set is collected according to the first preset time period, the first preset time period is determined, the historical power data set in the first preset time period is collected, the data integrity detection is performed on the historical power data set, whether the historical power data set has a missing value is judged, to be precise, whether the historical power data set has a missing value is detected, for example, if the data of a certain day is possibly lost, the historical power data set has the missing value of the certain day, if the historical power data set has the missing value, the missing value is supplemented, and the historical power data set is further improved.
Specifically, k pieces of historical power data with nearest missing values are obtained, wherein k is an integer greater than or equal to 2, an average value of the k pieces of historical power data is calculated, the average value is used for replacing the missing values, the k value can be set according to actual conditions, for example, when power data of a certain day is missing, 4 pieces of power data can be obtained after power data of 4 days before and after the missing day are obtained, the average value of the 4 pieces of power data is calculated, the average value is used for replacing the missing values, and a complete historical power data set is needed to be explained.
Step S200: carrying out power correlation analysis on the historical meteorological data set to generate a correlation feature set;
the step S200 of the embodiment of the present application further includes:
step S210: acquiring a plurality of meteorological feature types according to a historical meteorological data set;
step S220: carrying out power correlation analysis on a plurality of meteorological feature types to obtain a plurality of correlation coefficients;
step S230: judging by using a plurality of correlation coefficients to obtain a plurality of correlation weather feature types which are greater than or equal to a preset correlation coefficient;
step S240: a set of correlation features is generated based on the plurality of correlation weather feature types.
Specifically, the power correlation analysis is performed on the historical meteorological data set, namely, the correlation between the historical meteorological data set and the photovoltaic power is simply analyzed, the meteorological feature type strongly correlated with the photovoltaic power is determined, and a correlation feature set is generated, wherein the correlation feature set comprises the meteorological feature type strongly correlated with the photovoltaic power.
Specifically, a plurality of weather feature types are obtained according to a historical weather data set, power correlation analysis is performed on the plurality of weather feature types to obtain a plurality of correlation coefficients, that is, the historical weather data set contains a plurality of different types of weather data, the plurality of weather feature types are obtained according to the different types of weather data, the plurality of weather feature types comprise illumination intensity, temperature, humidity, air pressure, cloud quantity, wind speed and the like, but not all weather feature types can influence the magnitude of photovoltaic power, for example, the correlation between wind speed, air pressure and photovoltaic power is very weak, the correlation between the illumination intensity and the photovoltaic power is relatively high, a plurality of correlation coefficients are obtained, the correlation coefficients are parameters used for representing the correlation strength, further, the plurality of correlation coefficients are used for judging, a plurality of correlation feature types larger than or equal to preset correlation coefficients are obtained, the preset correlation coefficients can be set according to actual conditions, whether the plurality of correlation coefficients are larger than or equal to the preset correlation coefficients or not is judged, if the plurality of correlation feature types are larger than the preset correlation coefficients, the correlation feature types are obtained, the correlation feature types are correlated with the weather feature types and the weather feature types are relatively high, and the correlation feature types are the correlation feature sets are generated based on the correlation coefficients.
Step S300: screening the historical meteorological data set according to the correlation characteristic set to obtain a historical correlated meteorological data set;
step S400: constructing an objective function based on the historical relevant meteorological data set and the historical power data set;
the step S400 in the embodiment of the present application further includes:
step S410: taking a historical relevant weather dataset as an independent variable;
step S420: taking the historical power data set as a dependent variable;
step S430: and fitting a function relation based on the independent variable and the dependent variable, and constructing an objective function.
Specifically, according to the historical relevant weather data set and the historical power data set, an objective function is built, the historical relevant weather data set and the historical power data set have a corresponding relation, and the objective function is the corresponding relation of the historical relevant weather data set and the historical power data set.
Specifically, the historical relevant weather data set and the historical power data set have a corresponding relation, the historical relevant weather data set is taken as an independent variable, the historical power data set is taken as a dependent variable, that is, the historical relevant weather data set is changed, the corresponding historical power data set is also changed, fitting of a functional relation is carried out based on the independent variable and the dependent variable, and an objective function is built, wherein the objective function comprises power data changes under different weather data.
Step S500: connecting a weather forecast management platform, and obtaining weather characteristic forecast information of a day to be forecast according to the correlation characteristic set;
specifically, the weather forecast management platform is connected, weather feature forecast information of a day to be forecast is obtained according to the correlation feature set, that is, the correlation feature set contains weather type features related to photovoltaic power, based on the weather feature forecast information of the day to be forecast is obtained according to the weather forecast management platform, and the weather feature forecast information contains temperature forecast information, humidity forecast information, illumination intensity forecast information and the like of the day to be forecast.
Step S600: and acquiring a power prediction result according to the objective function based on the weather feature prediction information.
Specifically, based on weather feature prediction information, a power prediction result is obtained according to an objective function, in short, the objective function includes a corresponding relationship between a history related weather data set and a history power data set, similar history related weather data is matched according to weather feature prediction information, and corresponding power data, that is, a power prediction result, can be obtained according to the objective function.
The step S700 in this embodiment of the present application further includes:
step S710: acquiring the using time length of the photovoltaic power generation equipment in the target area;
step S720: carrying out power influence analysis on the photovoltaic power generation equipment according to the using time length to obtain power influence data of the photovoltaic power generation equipment;
step S730: and optimizing the power prediction result according to the power influence data to obtain an optimized power prediction result.
Specifically, the use duration of the photovoltaic power generation equipment in the target area is acquired and obtained, the photovoltaic power generation equipment is equipment for converting solar energy into electric energy, the use duration is the duration from the beginning of use of the photovoltaic power generation equipment until the current duration, the power influence analysis is carried out on the photovoltaic power generation equipment according to the use duration to obtain power influence data of the photovoltaic power generation equipment, in short, the longer the use duration is, certain abrasion and aging can be caused, the power of the photovoltaic power generation equipment is reduced, the power influence analysis is carried out on the photovoltaic power generation equipment according to the use duration, the power influence value of the photovoltaic power generation equipment is determined, the obtained power influence value is the power influence data, further, the power prediction result is optimized according to the power influence data, the optimized power prediction result is obtained by subtracting the power influence data from the power prediction result, and the photovoltaic power prediction is more accurate based on the power prediction.
The step S800 in this embodiment of the present application further includes:
step S810: obtaining historical weather feature prediction information;
step S820: carrying out prediction accuracy analysis on the historical meteorological feature prediction information to obtain a historical prediction error value;
step S830: correcting weather feature prediction information of a day to be predicted according to the historical prediction error value to obtain corrected weather feature prediction information;
step S840: and replacing the weather feature prediction information with the corrected weather feature prediction information to perform power prediction.
Specifically, historical weather feature prediction information is obtained, the historical weather feature prediction information refers to weather feature prediction information in a period of time, prediction accuracy analysis is conducted on the historical weather feature prediction information, the historical weather feature prediction information and the historical actual weather feature information are compared, a historical prediction error value is obtained, the historical prediction error value is the difference value between the historical weather feature prediction information and the historical actual weather feature information, the historical prediction error value comprises an error direction, namely the deviation direction of the historical weather feature prediction information, for example, the temperature prediction value is larger or smaller, further, correction is conducted on weather feature prediction information of a day to be predicted according to the historical prediction error value, correction is conducted on the weather feature prediction information of the day to be predicted, that is, errors exist in the obtained weather feature prediction information of the day to be predicted, correction is conducted on the weather feature prediction information according to the historical prediction error value, the weather feature prediction information is more accurate, power prediction is conducted by replacing the weather feature prediction information with the weather feature prediction information, and accuracy of a power prediction result is improved.
Based on the analysis, in the embodiment, the historical meteorological data set and the historical power data set of the target area are analyzed, the objective function is built, the weather forecast information of the day to be predicted is obtained, and the photovoltaic power prediction of the day to be predicted is performed according to the objective function, so that the technical effect of improving the accuracy of the photovoltaic power prediction is achieved.
Example two
Based on the same inventive concept as the short-term corrected distributed photovoltaic power prediction method in the embodiment, as shown in fig. 2, the present application further provides a short-term corrected distributed photovoltaic power prediction system, where the short-term corrected distributed photovoltaic power prediction system is communicatively connected to a weather forecast management platform, and includes:
the historical data acquisition module 11 is used for determining a target area and acquiring a historical power data set and a historical meteorological data set of the target area, wherein the historical meteorological data set corresponds to the historical power data set one by one;
the correlation analysis module 12 is used for carrying out power correlation analysis on the historical meteorological data set to generate a correlation feature set;
the historical meteorological data set screening module 13 is used for screening the historical meteorological data sets according to the correlation characteristic set to obtain historical correlated meteorological data sets;
the objective function building module 14 is used for building an objective function based on a historical relevant meteorological data set and a historical power data set;
the weather forecast system comprises a weather forecast day weather information acquisition module 15, a weather forecast management platform and a weather forecast information acquisition module 15, wherein the weather forecast management platform is used for acquiring weather forecast information of a day to be forecast according to a correlation characteristic set;
the power prediction module 16 is configured to obtain a power prediction result according to an objective function based on weather feature prediction information by the power prediction module 16.
Further, the method further comprises the following steps:
the weather feature type acquisition module is used for acquiring a plurality of weather feature types according to the historical weather data set;
the correlation coefficient acquisition module is used for carrying out power correlation analysis on a plurality of meteorological feature types to obtain a plurality of correlation coefficients;
the correlation coefficient judging module is used for judging by a plurality of correlation coefficients to obtain a plurality of correlation weather feature types which are larger than or equal to a preset correlation coefficient;
and the correlation feature set acquisition module is used for generating a correlation feature set based on a plurality of correlation weather feature types.
Further, the method further comprises the following steps:
the first preset time period acquisition module is used for acquiring a first preset time period according to the day to be predicted;
the historical power data acquisition module is used for acquiring a historical power data set according to a first preset time period;
the data integrity detection module is used for detecting the data integrity of the historical power data set and judging whether the historical power data set has a missing value or not;
and the missing value supplementing module is used for supplementing the missing value if the historical power data set has the missing value.
Further, the method further comprises the following steps:
the system comprises a neighboring historical power data acquisition module, a data processing module and a data processing module, wherein the neighboring historical power data acquisition module is used for acquiring k pieces of historical power data with the nearest missing value, wherein k is an integer greater than or equal to 2;
and the average value calculation module is used for calculating the average value of the k pieces of historical power data, and replacing the missing value with the average value.
Further, the method further comprises the following steps:
the independent variable setting module is used for taking a historical relevant weather data set as an independent variable;
a dependent variable setting module for taking the historical power dataset as a dependent variable;
and the functional relation fitting module is used for fitting the functional relation based on the independent variable and the dependent variable and constructing an objective function.
Further, the method further comprises the following steps:
the using time length acquisition module is used for acquiring the using time length of the photovoltaic power generation equipment in the target area;
the power influence analysis module is used for carrying out power influence analysis on the photovoltaic power generation equipment according to the using time length to obtain power influence data of the photovoltaic power generation equipment;
and the power prediction result optimizing module is used for optimizing the power prediction result according to the power influence data to obtain an optimized power prediction result.
Further, the method further comprises the following steps:
the historical weather characteristic prediction information acquisition module is used for acquiring historical weather characteristic prediction information;
the prediction accuracy analysis module is used for performing prediction accuracy analysis on the historical meteorological feature prediction information to obtain a historical prediction error value;
the modified weather feature prediction information obtaining module is used for modifying weather feature prediction information of a day to be predicted according to the historical prediction error value to obtain modified weather feature prediction information;
and the weather feature prediction information replacement module is used for replacing the weather feature prediction information with the corrected weather feature prediction information to perform power prediction.
The specific example of the short-term corrected distributed photovoltaic power prediction method in the first embodiment is also applicable to the short-term corrected distributed photovoltaic power prediction system in the present embodiment, and those skilled in the art will be aware of the short-term corrected distributed photovoltaic power prediction system in the present embodiment through the foregoing detailed description of the short-term corrected distributed photovoltaic power prediction method, so that the details thereof will not be described herein for brevity. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Example III
Fig. 3 is a schematic diagram according to a third embodiment of the present disclosure, as shown in fig. 3, an electronic device 800 may include: a processor 801 and a memory 802.
A memory 802 for storing a program; memory 802, which may include volatile memory (English: volatile memory), such as random-access memory (RAM), such as static random-access memory (SRAM), double data rate synchronous dynamic random-access memory (Double Data Rate Synchronous Dynamic Random Access Memory, DDR SDRAM), and the like; the memory may also include a non-volatile memory (English) such as a flash memory (English). The memory 802 is used to store computer programs (e.g., application programs, functional modules, etc. that implement the methods described above), computer instructions, etc., which may be stored in one or more of the memories 802 in a partitioned manner. And computer programs, computer instructions, data, etc. described above may be called upon by the processor 801.
The computer programs, computer instructions, etc., described above may be stored in one or more of the memories 802 in partitions. And the above-described computer programs, computer instructions, etc. may be invoked by the processor 801.
A processor 801 for executing a computer program stored in a memory 802 to realize the steps in the method according to the above embodiment.
Reference may be made in particular to the description of the embodiments of the method described above.
The processor 801 and the memory 802 may be separate structures or may be integrated structures integrated together. When the processor 801 and the memory 802 are separate structures, the memory 802 and the processor 801 may be coupled by a bus 803.
The electronic device in this embodiment may execute the technical scheme in the above method, and the specific implementation process and the technical principle are the same, which are not described herein again.
According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.
According to an embodiment of the present invention, there is also provided a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any one of the embodiments described above.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be executed in parallel, may be executed sequentially, may be executed in a different order,
the present invention is not limited herein so long as the desired results of the disclosed embodiments of the present invention can be achieved.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for short term corrected distributed photovoltaic power prediction comprising the steps of:
(1) Determining a target area, and acquiring a historical power data set and a historical weather data set of the target area, wherein the historical weather data set corresponds to the historical power data set one by one;
(2) Carrying out power correlation analysis on the historical meteorological data set to generate a correlation feature set;
(3) Screening the historical meteorological data set according to the correlation characteristic set to obtain a historical correlated meteorological data set;
(4) Constructing an objective function based on the historical relevant meteorological data set and the historical power data set;
(5) Connecting a weather forecast management platform, and obtaining weather characteristic forecast information of a day to be forecast according to the correlation characteristic set;
(6) And acquiring a power prediction result according to the objective function based on weather feature prediction information of the day to be predicted.
2. A short term corrected distributed photovoltaic power prediction method according to claim 1, characterized by: in the step (2), a plurality of weather feature types are obtained according to a historical weather data set; carrying out power correlation analysis on a plurality of meteorological feature types to obtain a plurality of correlation coefficients; judging by using a plurality of correlation coefficients to obtain a plurality of correlation weather feature types which are larger than or equal to a preset correlation coefficient; a set of correlation features is generated based on the plurality of correlation weather feature types.
3. A short term corrected distributed photovoltaic power prediction method according to claim 1, characterized by: in the step (1), acquiring a historical power data set of the target area includes:
acquiring a first preset time period according to a day to be predicted;
collecting a historical power data set according to a first preset time period;
detecting the data integrity of the historical power data set, and judging whether the historical power data set has a missing value or not;
and if the historical power data set has missing values, supplementing the missing values.
4. A short term corrected distributed photovoltaic power prediction method according to claim 3, characterized in that: the supplementing of the missing value comprises the following steps:
obtaining k pieces of historical power data with nearest missing values, wherein k is an integer greater than or equal to 2;
the average of k historical power data is calculated and the missing values are replaced with the average.
5. A short term corrected distributed photovoltaic power prediction method according to claim 1, characterized by: in the step (4), a history-related meteorological data set is taken as an independent variable; taking the historical power data set as a dependent variable; and fitting a function relation based on the independent variable and the dependent variable, and constructing an objective function.
6. A short term corrected distributed photovoltaic power prediction method according to claim 1, characterized by: the method also comprises the following steps:
acquiring the using time length of the photovoltaic power generation equipment in the target area;
carrying out power influence analysis on the photovoltaic power generation equipment according to the using time length to obtain power influence data of the photovoltaic power generation equipment;
and optimizing the power prediction result according to the power influence data to obtain an optimized power prediction result.
7. A short term corrected distributed photovoltaic power prediction method according to claim 1, characterized by: the method also comprises the following steps:
obtaining historical weather feature prediction information;
carrying out prediction accuracy analysis on the historical meteorological feature prediction information to obtain a historical prediction error value;
correcting weather feature prediction information of a day to be predicted according to the historical prediction error value to obtain corrected weather feature prediction information;
and replacing the weather feature prediction information with the modified weather feature prediction information to perform power prediction.
8. A short term corrected distributed photovoltaic power prediction system characterized by: the solar and weather information prediction system comprises a historical data acquisition module (11), a correlation analysis module (12), a historical meteorological data set screening module (13), an objective function building module (14), a solar and weather information acquisition module to be predicted (15) and a power prediction module (16), wherein the historical data acquisition module (11) is connected with a target area, the historical data acquisition module (11), the correlation analysis module (12) and the historical meteorological data set screening module (13) are sequentially connected, the input end of the objective function building module (14) is respectively connected with the historical data acquisition module (11) and the historical meteorological data set screening module (13), the input end of the solar and weather information acquisition module to be predicted (15) is respectively connected with a weather prediction management platform and the correlation analysis module (12), and the output end of the objective function building module (14) and the solar and weather information acquisition module to be predicted (15) is respectively connected with the power prediction module (16).
9. An electronic device for distributed photovoltaic power prediction for short term correction, characterized by: comprising a processor (801) and a memory (802), the processor being in communication with the memory, the processor (801) and the memory (802) being at least one in number, the memory (802) storing instructions executable by the processor (801), the instructions being executable by the processor (801) to enable the processor (801) to perform the method of any one of claims 1-7.
10. An electronic device for distributed photovoltaic power prediction for short term correction as claimed in claim 9, wherein: the processor (801) and memory (802) are integrated structures that are integrated together; the processor (801) and the memory (802) are coupled via a bus (803).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211681969.0A CN116304669A (en) | 2022-12-27 | 2022-12-27 | Short-term correction distributed photovoltaic power prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211681969.0A CN116304669A (en) | 2022-12-27 | 2022-12-27 | Short-term correction distributed photovoltaic power prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116304669A true CN116304669A (en) | 2023-06-23 |
Family
ID=86836658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211681969.0A Pending CN116304669A (en) | 2022-12-27 | 2022-12-27 | Short-term correction distributed photovoltaic power prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116304669A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579591A (en) * | 2023-07-13 | 2023-08-11 | 山西景骏建筑工程有限公司 | Building photovoltaic installation management method and system based on power prediction |
| CN116742622A (en) * | 2023-08-09 | 2023-09-12 | 山东理工职业学院 | Photovoltaic power generation-based power generation amount prediction method and system |
| CN117639662A (en) * | 2023-12-07 | 2024-03-01 | 电暴猿(上海)科技有限公司 | Intelligent monitoring-based photovoltaic power station power prediction method and system |
-
2022
- 2022-12-27 CN CN202211681969.0A patent/CN116304669A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116579591A (en) * | 2023-07-13 | 2023-08-11 | 山西景骏建筑工程有限公司 | Building photovoltaic installation management method and system based on power prediction |
| CN116579591B (en) * | 2023-07-13 | 2023-09-29 | 山西景骏建筑工程有限公司 | Building photovoltaic installation management method and system based on power prediction |
| CN116742622A (en) * | 2023-08-09 | 2023-09-12 | 山东理工职业学院 | Photovoltaic power generation-based power generation amount prediction method and system |
| CN116742622B (en) * | 2023-08-09 | 2023-11-03 | 山东理工职业学院 | Photovoltaic power generation-based power generation amount prediction method and system |
| CN117639662A (en) * | 2023-12-07 | 2024-03-01 | 电暴猿(上海)科技有限公司 | Intelligent monitoring-based photovoltaic power station power prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116304669A (en) | Short-term correction distributed photovoltaic power prediction method and system | |
| CN104021427A (en) | Method for predicting daily generating capacity of grid-connected photovoltaic power station based on factor analysis | |
| CN113256033B (en) | Power station site selection and volume fixing method, device, system and medium based on mode complementation | |
| Sogabe et al. | Optimization of decentralized renewable energy system by weather forecasting and deep machine learning techniques | |
| CN114004139A (en) | Photovoltaic power generation power prediction method | |
| CN112785027A (en) | Wind-solar-storage combined power generation system confidence capacity evaluation method and system | |
| KR101467221B1 (en) | A Method for Determining Optimal design capacity for Integrated Hybrid New and Renewable Energy System | |
| CN114971090A (en) | Electric heating load prediction method, system, equipment and medium | |
| CN110991747A (en) | Short-term load prediction method considering wind power plant power | |
| CN111461297B (en) | Solar irradiation quantity optimization prediction algorithm based on MPC and ELM neural network | |
| CN115471086A (en) | Evaluation method, storage medium and device for full-factor energy utilization efficiency | |
| CN113033136B (en) | Simplified photovoltaic cell physical parameter extraction optimization method and system | |
| CN110766296A (en) | Ground power station value evaluation model construction system | |
| CN114444955A (en) | Key parameter data mining and long-term configuration prediction method and system for comprehensive energy | |
| CN112215383A (en) | Distributed photovoltaic power generation power prediction method and system | |
| CN111178593A (en) | Photovoltaic system output power prediction method and device | |
| CN116957171B (en) | Carbon emission reduction optimization method, device, equipment and storage medium | |
| CN116342077B (en) | New energy power transfer learning prediction method suitable for data-missing station | |
| CN113011119B (en) | Photovoltaic cell multi-parameter extraction method and system based on dimension reduction processing | |
| CN111950164B (en) | Modeling method and device for long-term power supply structure planning model | |
| CN113657735B (en) | Power supply structure planning method under carbon neutralization scene considering forest carbon sink capacity constraint | |
| Mantri et al. | Solar Power Generation Prediction for Better Energy Efficiency using Machine Learning | |
| CN107133441B (en) | Method and device for determining power data sampling precision in energy Internet | |
| CN116544929A (en) | Simulation calculation method and system for medium-term and long-term time sequence operation of power system | |
| CN117996757A (en) | Distributed wind power based power distribution network scheduling method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |