CN118213970A - Distributed photovoltaic power generation prediction method and system - Google Patents
Distributed photovoltaic power generation prediction method and system Download PDFInfo
- Publication number
- CN118213970A CN118213970A CN202410180775.5A CN202410180775A CN118213970A CN 118213970 A CN118213970 A CN 118213970A CN 202410180775 A CN202410180775 A CN 202410180775A CN 118213970 A CN118213970 A CN 118213970A
- Authority
- CN
- China
- Prior art keywords
- power generation
- historical
- photovoltaic power
- data
- weather forecast
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Water Supply & Treatment (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
本发明涉及光伏发电预测的技术领域，特别是涉及一种分布式光伏发电量预测方法及系统，其提高了预测的准确性和实用性，还能够提高经济效益和电网稳定性，从而促进可再生能源的广泛应用；方法包括：采集目标区域历史发电数据，并对历史发电数据进行预处理；历史发电数据包括历史光伏发电量和相应的发电时间；将每日时间划分为若干个时间段，分别统计历史发电数据在每个时间段内的发电功率，获得光伏发电功率集合；获取目标区域的历史天气预报信息；历史天气预报信息包括日照强度、温度、阴雨、风速和季节变化；对历史天气预报信息进行处理，根据光伏发电功率集合的每日划分时间段，对历史天气预报信息进行标记，获得发电功率关联集合。
The invention relates to the technical field of photovoltaic power generation prediction, and in particular to a distributed photovoltaic power generation prediction method and system, which improves the accuracy and practicability of the prediction, and can also improve the economic benefits and grid stability, thereby promoting the widespread application of renewable energy; the method comprises: collecting historical power generation data of a target area, and preprocessing the historical power generation data; the historical power generation data comprises historical photovoltaic power generation and corresponding power generation time; dividing the daily time into a number of time periods, and respectively counting the power generation power of the historical power generation data in each time period, and obtaining a photovoltaic power generation power set; obtaining historical weather forecast information of the target area; the historical weather forecast information comprises sunshine intensity, temperature, cloudy and rainy, wind speed and seasonal changes; processing the historical weather forecast information, marking the historical weather forecast information according to the daily time periods of the photovoltaic power generation power set, and obtaining a power generation power association set.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation prediction, in particular to a distributed photovoltaic power generation amount prediction method and system.
Background
With the implementation of domestic series of new energy development policies, photovoltaic power generation has become one of the most popular renewable energy sources nowadays. However, although photovoltaic power generation has been successfully used in many fields, in actual production, the power of photovoltaic power generation varies greatly due to factors such as weather, foreign matter, shielding, and the like. This not only results in a decrease in output efficiency of photovoltaic power generation, but also brings great economic loss to photovoltaic power generation owners.
At present, in partial areas, some electric energy quality problems such as harmonic waves and the like occur. If a large amount of distributed power sources generate electricity to access an existing power grid, various effects and impacts can be brought. At present, the photovoltaic power generation in China mainly comprises a large-scale centralized development mode, a remote transportation mode and a distributed development mode, and is in on-site digestion mode, and along with the continuous increase of the specific gravity of a distributed power supply in power supply, the power generation characteristic of the distributed power supply is different from that of a conventional power supply, so that the research of a photovoltaic power generation prediction system is more urgent, and therefore, a distributed photovoltaic power generation capacity prediction method and system are needed.
Disclosure of Invention
In order to solve the technical problems, the invention provides the distributed photovoltaic power generation amount prediction method which improves the accuracy and the practicability of prediction and also improves the economic benefit and the power grid stability, thereby promoting the wide application of renewable energy sources.
In a first aspect, the present invention provides a distributed photovoltaic power generation amount prediction method, the method comprising:
collecting historical power generation data of a target area, and preprocessing the historical power generation data; the historical power generation data comprise historical photovoltaic power generation capacity and corresponding power generation time;
dividing the daily time into a plurality of time periods, and respectively counting the power generation power of the historical power generation data in each time period to obtain a photovoltaic power generation power set;
Acquiring historical weather forecast information of a target area; the historical weather forecast information comprises sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
processing the historical weather forecast information, and marking the historical weather forecast information according to the daily divided time periods of the photovoltaic power generation power set to obtain a power generation power association set;
Using a machine learning algorithm to build a prediction model, wherein the model takes a generated power association set as input, and takes a photovoltaic generated power set as output to obtain a generated energy prediction model;
acquiring weather forecast information of a target area in a future preset time, and marking the weather forecast information in the future preset time according to a time period divided every day to obtain a predicted generation power association set;
And inputting the predicted power generation power association set into a power generation amount prediction model, outputting the predicted photovoltaic power generation power set by the model, and obtaining photovoltaic power generation amount in the future preset time according to the predicted photovoltaic power generation power set.
Further, the historical power generation data acquisition and processing method comprises the following steps:
acquiring historical power generation data of a target area through an energy management system installed in a photovoltaic power station;
Performing quality inspection on the data, and processing abnormal values, missing values and error data of the data;
Carrying out time sequence processing on the collected historical power generation data to ensure the correct sequence of the time stamps;
and (3) carrying out standardization and normalization processing on the historical power generation data, and eliminating the influence caused by different scales.
Further, the photovoltaic power generation power set acquisition method includes:
Dividing the daily time into a plurality of discrete time periods according to the hour time interval, and capturing the change of the photovoltaic power generation power;
Grouping the historical power generation data according to time periods, and counting the power generation power of the historical power generation data in each time period to obtain the photovoltaic power generation power of each time period;
And combining the generated power statistical values obtained in different time periods to form a photovoltaic generated power set.
Further, the method for acquiring the historical weather forecast information of the target area comprises the following steps:
Acquiring historical weather forecast information of a target area through a weather department and a weather station;
Selecting meteorological parameters closely related to photovoltaic power generation, including sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
and preprocessing the historical weather forecast information, including data cleaning, missing value processing and abnormal value processing.
Further, the method for acquiring the generated power association set comprises the following steps:
By matching the power generation time period and the weather forecast time, the historical weather forecast information is associated with historical power generation data;
For each time period, the historical weather forecast information is corresponding to the corresponding power generation time;
carrying out standardization treatment on the extracted meteorological features;
and correlating the marked historical weather forecast information with the photovoltaic power generation power set to form a power generation power correlation set.
Further, the method for constructing the power generation amount prediction model comprises the following steps:
taking the generated power association set as a training data set and taking the photovoltaic generated power set as a corresponding target value;
according to the field knowledge of photovoltaic power generation prediction, weather features which have important influence on the power generation power are selected, wherein the weather features comprise sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
Selecting a linear regression model as a basis of the model;
dividing the data set into a training set and a testing set;
Training the selected linear regression model by using a training set, wherein in the training process, the relation between the weather condition and the corresponding power generation power in the historical data is learned;
Evaluating model performance using a test set, the evaluation index including root mean square error and average absolute error;
according to the performance of the model on the test set, performing super-parameter adjustment to optimize the performance of the model;
The trained model is deployed into an actual production environment for future prediction.
Further, the method for obtaining the predicted generation power association set comprises the following steps:
acquiring weather forecast information in a future preset time of a target area through a weather department and a weather station;
dividing the future preset time into proper time periods, and enabling the division granularity to be consistent with the time period of the generated energy data;
Marking the acquired future weather forecast information to enable the weather forecast information to correspond to the daily divided time periods of the generated power association set;
processing future weather forecast information, including processing missing values, outliers and data quality problems;
summarizing the marked data to obtain a predicted power generation associated set.
In another aspect, the present application also provides a distributed photovoltaic power generation prediction system, the system comprising:
The historical power generation data acquisition module is used for acquiring historical power generation data of a target area, preprocessing the historical power generation data and transmitting the historical power generation data; the historical power generation data comprise historical photovoltaic power generation capacity and corresponding power generation time;
the time dividing and counting module is used for receiving the historical power generation data, dividing the daily time into a plurality of time periods, respectively counting the power generation power of the historical power generation data in each time period, obtaining a photovoltaic power generation power set and transmitting the photovoltaic power generation power set;
The historical weather information acquisition module is used for acquiring and transmitting historical weather forecast information of the target area; the historical weather forecast information comprises sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
the weather information marking module is used for receiving the historical weather forecast information, processing the historical weather forecast information, marking the historical weather forecast information according to the daily divided time periods of the photovoltaic power generation power set, obtaining a power generation power association set and sending the power generation power association set;
The prediction model construction module is used for receiving the photovoltaic power generation power set and the power generation power association set, constructing a prediction model by using a machine learning algorithm, wherein the model takes the power generation power association set as input, takes the photovoltaic power generation power set as output, obtains a power generation amount prediction model and sends the power generation amount prediction model;
The future weather information acquisition module is used for acquiring weather forecast information of the target area in a future preset time, marking the weather forecast information in the future preset time according to a time period divided every day, acquiring a predicted generation power association set, and transmitting the predicted generation power association set;
The prediction module is used for receiving the predicted power generation power association set, inputting the predicted power generation power association set into the power generation amount prediction model, outputting the predicted photovoltaic power generation power set by the model, and obtaining the photovoltaic power generation amount in the future preset time according to the predicted photovoltaic power generation power set.
In a third aspect, the present application provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, the computer program when executed by the processor implementing the steps of any of the methods described above.
In a fourth aspect, the application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
Compared with the prior art, the invention has the beneficial effects that: by combining the historical power generation data and the historical weather forecast information, the photovoltaic power generation capacity can be predicted more accurately; the daily time is divided into a plurality of time periods, and each time period is analyzed independently, so that the change trend of the photovoltaic power generation amount in one day can be captured more accurately, and the accuracy and the practicability of prediction are improved;
the machine learning algorithm is utilized to construct a prediction model, so that a large amount of complex data can be processed, and hidden modes and relationships can be learned from the complex data; the model prediction accuracy and robustness are improved; the future generated energy is predicted by analyzing the historical data and weather forecast, so that the method can adapt to different geographic positions and environmental conditions, and has high flexibility and adaptability;
The accurate power generation amount prediction can help the power company to manage resources more effectively, reduce waste and improve economic benefit; the accurate prediction of the photovoltaic power generation amount is beneficial to the better planning of the power grid load of a power grid operator, and the stability of the power grid is ensured; the reliability of renewable energy sources can be improved by improving the prediction accuracy of photovoltaic power generation amount, and the use and development of green energy sources are further promoted;
In conclusion, the method not only improves the accuracy and the practicability of prediction, but also improves the economic benefit and the stability of the power grid, thereby promoting the wide application of renewable energy sources.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of a method of constructing a power generation capacity prediction model;
Fig. 3 is a block diagram of a distributed photovoltaic power generation prediction system.
Detailed Description
In the description of the present application, those skilled in the art will appreciate that the present application may be embodied as methods, apparatus, electronic devices, and computer-readable storage media. Accordingly, the present application may be embodied in the following forms: complete hardware, complete software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, the application may also be embodied in the form of a computer program product in one or more computer-readable storage media, which contain computer program code.
Any combination of one or more computer-readable storage media may be employed by the computer-readable storage media described above. The computer-readable storage medium includes: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer readable storage medium include the following: portable computer magnetic disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disk read-only memories, optical storage devices, magnetic storage devices, or any combination thereof. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device.
The technical scheme of the application obtains, stores, uses, processes and the like the data, which all meet the relevant regulations of national laws.
The application provides a method, a device and electronic equipment through flow charts and/or block diagrams.
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer readable program instructions may also be stored in a computer readable storage medium that can cause a computer or other programmable data processing apparatus to function in a particular manner. Thus, instructions stored in a computer-readable storage medium produce an instruction means which implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The present application will be described below with reference to the drawings in the present application.
Embodiment one: as shown in fig. 1 to 2, the method for predicting the power generation amount of the distributed photovoltaic power of the invention specifically comprises the following steps:
s1, collecting historical power generation data of a target area, and preprocessing the historical power generation data; the historical power generation data comprise historical photovoltaic power generation capacity and corresponding power generation time;
S1, in order to collect historical power generation data of a target area, the historical data used for subsequently establishing a prediction model is guaranteed to be high-quality, reliable and accurate, and a reliable basis is provided for subsequent model training and prediction; the historical power generation data acquisition and processing method comprises the following steps:
s11, acquiring historical power generation data of a target area through an energy management system installed in a photovoltaic power station;
S12, performing quality inspection on the data, and processing abnormal values, missing values and error data of the data;
S13, performing time sequence processing on the collected historical power generation data to ensure the correct sequence of the time stamps;
s14, carrying out standardization and normalization processing on the historical power generation data, and eliminating influences caused by different scales.
In the step, the energy management system installed on the photovoltaic power station can directly acquire real-time and accurate historical power generation data, so that the reliability and the accuracy of the data are ensured, and a reliable basis is provided for subsequent modeling; performing quality inspection, processing abnormal values, missing values and error data, facilitating cleaning of a data set, ensuring that a model is not affected by data quality problems, and improving robustness of a prediction model;
By carrying out time sequence processing on the historical power generation data, the correct sequence of the time stamps is ensured, the time continuity of the data is maintained, and the model can better capture time correlation and trend; the historical power generation data is subjected to standardization and normalization processing, so that the influence caused by different scales is eliminated, the stability and convergence rate of the model can be improved, and the model is better adapted to the data of different scales;
in summary, the step S1 can ensure that the historical data used in the subsequent model training and prediction is high-quality, reliable and accurate, thereby improving the overall performance and reliability of the prediction system.
S2, dividing the daily time into a plurality of time periods, and respectively counting the power generation power of the historical power generation data in each time period to obtain a photovoltaic power generation power set;
S2, dividing the daily time into a plurality of time periods, and counting the power generated by historical power generation data in each time period to obtain a photovoltaic power generation power set, wherein the photovoltaic power generation power set acquisition method comprises the following steps:
S21, dividing the daily time into a plurality of discrete time periods according to the hour time interval, and finely capturing the change of the photovoltaic power generation power;
S22, grouping the historical power generation data according to time periods, and counting the power generation power of the historical power generation data in each time period to obtain the photovoltaic power generation power of each time period;
And S23, combining the generated power statistical values obtained in different time periods to form a photovoltaic generated power set.
In the step, the time of the photovoltaic power generation data is finely captured by dividing the daily time according to the hour time interval, so that the photovoltaic power generation power set can more accurately reflect the power generation performance of the system in different time periods;
The historical power generation data are grouped according to time periods, and the power generation power in each time period is counted, so that the power generation characteristics of the system in different time periods can be revealed, the photovoltaic power generation power sets are more differentiated, and the power generation benefits of the system in different time periods in one day can be reflected;
the generated power statistical values obtained in different time periods are combined to form a photovoltaic generated power set, so that the performance information of the system in a plurality of time periods is synthesized, a comprehensive historical data view angle is provided, input with more information is provided for a machine learning model, and the prediction accuracy of the model is improved;
In summary, the step S2 can overcome the influence of weather, season and time variation on the photovoltaic power generation system, and provides powerful time distribution characteristics for the subsequent power generation prediction model, so that the prediction is more accurate and reliable.
S3, acquiring historical weather forecast information of a target area; the historical weather forecast information comprises sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
In the S3 step, comprehensively considering a plurality of meteorological parameters including sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation, correlating historical weather data with a photovoltaic power generation power set, providing influence information about meteorological conditions on power generation for a subsequent machine learning model, establishing a more accurate power generation capacity prediction model, and improving the reliability and practicability of prediction; the method for acquiring the historical weather forecast information of the target area comprises the following steps:
s31, acquiring historical weather forecast information of a target area through a weather department and a weather station;
s32, selecting meteorological parameters closely related to photovoltaic power generation, including sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
S33, preprocessing historical weather forecast information, including data cleaning, missing value processing and abnormal value processing, so that consistency and integrity of data are ensured, and negative influence on subsequent model training is avoided.
In the step, key input features can be provided for a subsequent machine learning model by acquiring historical weather forecast information, so that the influence of weather on photovoltaic power generation can be more comprehensively known; by associating historical weather data with photovoltaic power generation power data, a more accurate power generation capacity prediction model can be established, so that the prediction accuracy is improved; by comprehensively considering a plurality of meteorological parameters, the influence of various meteorological conditions on photovoltaic power generation can be more comprehensively captured, the reliability of a prediction model is improved, the prediction model is more practical, and therefore more accurate power generation prediction is facilitated;
in summary, the step provides key weather information for the prediction of the photovoltaic power generation amount, so that the prediction model is more accurate, reliable and practical.
S4, processing the historical weather forecast information, and marking the historical weather forecast information according to the daily divided time periods of the photovoltaic power generation power set to obtain a power generation power association set;
In the S4 step, the historical weather forecast information is processed to establish a power generation power association set, so that the influence of meteorological factors on the photovoltaic power generation amount is considered in a prediction model; the method for acquiring the generated power association set comprises the following steps:
S41, associating historical weather forecast information with historical power generation data by matching power generation time periods and weather forecast time, so as to ensure that each time period has corresponding meteorological conditions;
s42, corresponding historical weather forecast information to corresponding power generation time for each time period, and ensuring that each time period has corresponding meteorological conditions;
S43, standardizing the extracted meteorological features to ensure that the meteorological features have similar scales;
and S44, correlating the marked historical weather forecast information with the photovoltaic power generation power set to form a power generation power correlation set.
In the step, the consistency of the historical weather forecast information and the historical power generation data in time can be ensured, and an accurate time corresponding relation is provided for subsequent modeling; the extracted meteorological features are standardized, so that the extracted meteorological features are ensured to have similar scales, the influence of certain features on the model is avoided from being too large, the quality of the features is improved, and the model is easier to understand and generalize;
Correlating the marked historical weather forecast information with a photovoltaic power generation power set to form a power generation power correlation set, and providing useful training data for a machine learning model; by establishing a power generation power association set, the model can learn the relation between historical meteorological conditions and photovoltaic power generation capacity, so that future power generation capacity can be predicted more accurately;
In summary, the step S4 improves the consistency of data and the quality of features, and simultaneously successfully establishes a key generation power association set, thereby providing a solid foundation for training a photovoltaic generation capacity prediction model.
S5, using a machine learning algorithm to construct a prediction model, wherein the model takes a generated power association set as input, and takes a photovoltaic generated power set as output to obtain a generated energy prediction model;
the method for constructing the power generation amount prediction model comprises the following steps:
s51, taking the generated power association set as a training data set and taking the photovoltaic generated power set as a corresponding target value;
S52, selecting meteorological features with important influence on the power generation power according to the field knowledge of photovoltaic power generation prediction, wherein the meteorological features comprise sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
s53, selecting a linear regression model as a model basis;
S54, dividing the data set into a training set and a testing set;
S55, training the selected linear regression model by using a training set, wherein in the training process, the relation between the weather condition and the corresponding power generation power in the historical data is learned;
s56, evaluating the performance of the model by using a test set, wherein the evaluation indexes comprise root mean square error and average absolute error;
s57, performing necessary super-parameter adjustment according to the performance of the model on the test set, and optimizing the performance of the model;
And S58, deploying the trained model into an actual production environment for future prediction.
In the step, the correlation set of the generated power is used as a training data set, the photovoltaic generated power set is used as a target value, and the model can learn the correlation between the meteorological features and the generated power in the historical data, so that the model can better understand the influence of different meteorological conditions on the photovoltaic power generation;
the weather features which have important influence on the power generation power are selected, so that the prediction capability of the model can be improved, and the model has better interpretability and practicability; the linear regression model is selected as a basis, so that the structure of the model is simplified, and the model is easy to understand and explain; the data set is divided into a training set and a testing set to verify the generalization performance of the model on unseen data, so that the reliability of the model in practical application is improved;
By training the model by using the training set, the model can learn the complex relation between the weather conditions and the power generation power in the historical data, so that the model can better capture the influence of different meteorological features on the power generation power, and the prediction accuracy is improved; the performance of the model is estimated by using the test set, and the model is optimized by estimating the performance of the model and performing super-parameter adjustment, so that the prediction accuracy of the model in an actual environment is improved;
In summary, the step enables the constructed power generation amount prediction model to have reliability, practicability and adaptability, accurate prediction information can be provided for photovoltaic power generation owners in actual production, a power generation plan is optimized, and potential economic loss is reduced.
S6, obtaining weather forecast information of the target area in a future preset time, and marking the weather forecast information in the future preset time according to time periods divided every day to obtain a predicted generation power association set;
in the S6 step, obtaining weather forecast information of a target area in a future preset time is a foundation for constructing a generating capacity prediction model, and in the field of photovoltaic power generation prediction, accurate future weather information is critical to model performance; the method for acquiring the predicted generation power association set comprises the following steps:
S61, acquiring weather forecast information in future preset time of a target area through a weather department and a weather station;
s62, dividing the future preset time into proper time periods, and conforming to historical power generation data, so that the division granularity of the time periods is consistent with the time periods of the power generation data;
s63, marking the acquired future weather forecast information so as to enable the weather forecast information to correspond to the daily divided time periods of the generated power association set;
S64, processing future weather forecast information, including processing missing values, abnormal values and data quality problems, so as to ensure stability and reliability of the model;
and S65, summarizing the marked data to obtain a predicted power generation associated set.
In the step, the weather forecast information obtained through cooperation with a weather department and a weather station has high reliability and accuracy, and the prediction accuracy of the generating capacity prediction model is improved; dividing the future preset time into proper time periods, ensuring that the time periods are consistent with the time periods of the historical power generation data, keeping the consistency of the data, and enabling the model to capture the time correlation better;
The future weather forecast information is marked, so that the weather forecast information is ensured to correspond to the daily divided time periods of the power generation power association set, the weather conditions in the specific time period can be considered when the model is predicted, and the prediction accuracy is improved; the future weather forecast information is processed, so that the stability and the reliability of the model can be ensured, and the model is prevented from being influenced by bad data;
Summarizing the marked data to form a predicted power generation power association set, and providing input features for the model so that the model can predict the power generation capacity based on future weather conditions;
In summary, the step S6 can improve the prediction accuracy of the model, ensure the consistency and reliability of the data, prevent adverse effects of bad data on the model, and improve the reliability of the prediction result.
S7, inputting the predicted power generation power association set into a power generation amount prediction model, outputting a predicted photovoltaic power generation power set by the model, and obtaining photovoltaic power generation amount in a future preset time according to the predicted photovoltaic power generation power set;
S7, through application of a machine learning model and combination of weather information in future preset time, accurate prediction of photovoltaic power generation is achieved, and powerful support is provided for actual operation; the following is a detailed description of step S7:
s71, transmitting the predicted power generation associated set as input data to a power generation amount prediction model;
s72, outputting a model to be the predicted photovoltaic power generation power in each time period in the future preset time;
S73, according to the predicted photovoltaic power generation power set, calculating photovoltaic power generation capacity in a preset time in the future by combining the specific length of each time period, converting the power into energy, and accumulating the energy in the time period;
And S74, taking the obtained photovoltaic power generation amount in the future preset time as final output, wherein the result is a time sequence which reflects the expected capacity of the photovoltaic power generation system in a future period of time.
In the step, the photovoltaic power generation power of each time period in the future preset time can be accurately predicted by transmitting the predicted power generation power association set to a power generation amount prediction model and combining a machine learning algorithm, so that the prediction precision is improved, and the power system operation can more accurately know the change of the future photovoltaic power generation amount;
The predicted photovoltaic power generation power set output by the model provides key information for power system operation, and a more reasonable power scheduling plan can be formulated based on the predicted values, so that photovoltaic power generation resources are maximally utilized while meeting power requirements in future time; the accurate photovoltaic power generation capacity prediction can avoid unnecessary power scheduling and use of standby power generation equipment, so that the operation cost of a power system is reduced, and the economic benefit of renewable energy sources is improved;
By applying the machine learning model to photovoltaic power generation capacity prediction, the system can better cope with weather changes and other influencing factors, the reliability of the power system is improved, the dependence on standby energy is reduced, and the stable operation of the power system is ensured;
In summary, the step S7 can provide reliable and accurate prediction information for operation of the photovoltaic power generation system, so as to promote more intelligent, efficient and economical power system management.
Embodiment two: as shown in fig. 3, the distributed photovoltaic power generation amount prediction system of the present invention specifically includes the following modules;
The historical power generation data acquisition module is used for acquiring historical power generation data of a target area, preprocessing the historical power generation data and transmitting the historical power generation data; the historical power generation data comprise historical photovoltaic power generation capacity and corresponding power generation time;
the time dividing and counting module is used for receiving the historical power generation data, dividing the daily time into a plurality of time periods, respectively counting the power generation power of the historical power generation data in each time period, obtaining a photovoltaic power generation power set and transmitting the photovoltaic power generation power set;
The historical weather information acquisition module is used for acquiring and transmitting historical weather forecast information of the target area; the historical weather forecast information comprises sunlight intensity, temperature, overcast and rainy, wind speed and seasonal variation;
the weather information marking module is used for receiving the historical weather forecast information, processing the historical weather forecast information, marking the historical weather forecast information according to the daily divided time periods of the photovoltaic power generation power set, obtaining a power generation power association set and sending the power generation power association set;
The prediction model construction module is used for receiving the photovoltaic power generation power set and the power generation power association set, constructing a prediction model by using a machine learning algorithm, wherein the model takes the power generation power association set as input, takes the photovoltaic power generation power set as output, obtains a power generation amount prediction model and sends the power generation amount prediction model;
The future weather information acquisition module is used for acquiring weather forecast information of the target area in a future preset time, marking the weather forecast information in the future preset time according to a time period divided every day, acquiring a predicted generation power association set, and transmitting the predicted generation power association set;
The prediction module is used for receiving the predicted power generation power association set, inputting the predicted power generation power association set into the power generation amount prediction model, outputting the predicted photovoltaic power generation power set by the model, and obtaining the photovoltaic power generation amount in the future preset time according to the predicted photovoltaic power generation power set.
The system ensures the accuracy and the integrity of the data through preprocessing the historical power generation data, and improves the comprehensive cognition of the system to the historical conditions; the time dividing and counting module divides the daily time into a plurality of time periods, and respectively counts the power generated by the historical power generation data in each time period to form a photovoltaic power generation power set; the change of the power generation power in different time periods is considered, so that the adaptability of the system to timeliness is enhanced; the weather information marking module processes the historical weather forecast information, marks according to daily divided time periods of the photovoltaic power generation power set, and forms a power generation power association set;
By using a machine learning algorithm, the system can learn the relation between the generated energy and each factor according to the historical data, so that the accuracy and the robustness of prediction are improved; the prediction module outputs a predicted photovoltaic power generation power set according to the predicted power generation power association set, so that photovoltaic power generation capacity in a future preset time is obtained; the system considers the continuous growth of the distributed power supply in the power supply, can adapt to the characteristics of distributed photovoltaic power generation, provides more accurate power generation prediction, and reduces economic loss;
in summary, the system can effectively solve the problems of power fluctuation, harmonic waves and the like in photovoltaic power generation, provide reliable power generation capacity prediction and provide important references for operation of a power system.
The various modifications and embodiments of the foregoing power distribution network maintenance method based on fault analysis in the first embodiment are equally applicable to the power distribution network maintenance system based on fault analysis in this embodiment, and those skilled in the art will clearly know the implementation method of the power distribution network maintenance system based on fault analysis in this embodiment through the foregoing detailed description of the power distribution network maintenance method based on fault analysis, so that, for brevity of description, they will not be described in detail herein.
In addition, the application also provides an electronic device, which comprises a bus, a transceiver, a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the transceiver, the memory and the processor are respectively connected through the bus, and when the computer program is executed by the processor, the processes of the method embodiment for controlling output data are realized, and the same technical effects can be achieved, so that repetition is avoided and redundant description is omitted.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that it will be apparent to those skilled in the art that modifications and variations can be made without departing from the technical principles of the present invention, and these modifications and variations should also be regarded as the scope of the invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410180775.5A CN118213970A (en) | 2024-02-18 | 2024-02-18 | Distributed photovoltaic power generation prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410180775.5A CN118213970A (en) | 2024-02-18 | 2024-02-18 | Distributed photovoltaic power generation prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118213970A true CN118213970A (en) | 2024-06-18 |
Family
ID=91455459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410180775.5A Pending CN118213970A (en) | 2024-02-18 | 2024-02-18 | Distributed photovoltaic power generation prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118213970A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118487320A (en) * | 2024-07-15 | 2024-08-13 | 广东阳升建设工程有限公司 | Integrated control method and system for distributed solar photovoltaic power generation system |
| CN118551168A (en) * | 2024-07-29 | 2024-08-27 | 国网浙江省电力有限公司乐清市供电公司 | Method, device, equipment and medium for reconstructing missing power data of photovoltaic energy storage facilities |
| CN118673463A (en) * | 2024-08-21 | 2024-09-20 | 国网甘肃省电力公司白银供电公司 | Multi-source data-based power supply quantity prediction method, system, equipment and storage medium |
| CN119051163A (en) * | 2024-10-30 | 2024-11-29 | 广州市哲明惠科技有限责任公司 | Photovoltaic power generation scheduling method, system, equipment and storage medium |
| CN119051017A (en) * | 2024-10-30 | 2024-11-29 | 国网山东省电力公司菏泽供电公司 | Distributed photovoltaic weather prediction method based on data fusion |
| CN119150705A (en) * | 2024-11-18 | 2024-12-17 | 浙江浙能能源服务有限公司 | Virtual power plant gateway data processing method and system based on edge calculation |
| CN119210332A (en) * | 2024-11-27 | 2024-12-27 | 港华能源创科(深圳)有限公司 | Photovoltaic module water cooling system and method |
| CN119275838A (en) * | 2024-12-09 | 2025-01-07 | 国网浙江省电力有限公司宁波供电公司 | New energy power generation prediction method and platform based on collected data |
| CN120490592A (en) * | 2025-07-16 | 2025-08-15 | 国网山西省电力公司营销服务中心 | Photovoltaic electricity larceny monitoring method based on Beidou communication |
-
2024
- 2024-02-18 CN CN202410180775.5A patent/CN118213970A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118487320A (en) * | 2024-07-15 | 2024-08-13 | 广东阳升建设工程有限公司 | Integrated control method and system for distributed solar photovoltaic power generation system |
| CN118487320B (en) * | 2024-07-15 | 2024-09-24 | 广东阳升建设工程有限公司 | Integrated control method and system for distributed solar photovoltaic power generation system |
| CN118551168A (en) * | 2024-07-29 | 2024-08-27 | 国网浙江省电力有限公司乐清市供电公司 | Method, device, equipment and medium for reconstructing missing power data of photovoltaic energy storage facilities |
| CN118673463A (en) * | 2024-08-21 | 2024-09-20 | 国网甘肃省电力公司白银供电公司 | Multi-source data-based power supply quantity prediction method, system, equipment and storage medium |
| CN119051163B (en) * | 2024-10-30 | 2025-02-14 | 广州市哲明惠科技有限责任公司 | Photovoltaic power generation scheduling method, system, equipment and storage medium |
| CN119051017A (en) * | 2024-10-30 | 2024-11-29 | 国网山东省电力公司菏泽供电公司 | Distributed photovoltaic weather prediction method based on data fusion |
| CN119051163A (en) * | 2024-10-30 | 2024-11-29 | 广州市哲明惠科技有限责任公司 | Photovoltaic power generation scheduling method, system, equipment and storage medium |
| CN119150705A (en) * | 2024-11-18 | 2024-12-17 | 浙江浙能能源服务有限公司 | Virtual power plant gateway data processing method and system based on edge calculation |
| CN119210332A (en) * | 2024-11-27 | 2024-12-27 | 港华能源创科(深圳)有限公司 | Photovoltaic module water cooling system and method |
| CN119210332B (en) * | 2024-11-27 | 2025-03-04 | 港华能源创科(深圳)有限公司 | Photovoltaic module water cooling system and method |
| CN119275838A (en) * | 2024-12-09 | 2025-01-07 | 国网浙江省电力有限公司宁波供电公司 | New energy power generation prediction method and platform based on collected data |
| CN119275838B (en) * | 2024-12-09 | 2025-06-10 | 国网浙江省电力有限公司宁波供电公司 | New energy power generation prediction method and platform based on collected data |
| CN120490592A (en) * | 2025-07-16 | 2025-08-15 | 国网山西省电力公司营销服务中心 | Photovoltaic electricity larceny monitoring method based on Beidou communication |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118213970A (en) | Distributed photovoltaic power generation prediction method and system | |
| CN116646933B (en) | Big data-based power load scheduling method and system | |
| CN117013527A (en) | Distributed photovoltaic power generation power prediction method | |
| CN116914747B (en) | Power user-side load forecasting method and system | |
| CN117595231B (en) | Intelligent power grid distribution management system and method thereof | |
| CN118971200B (en) | A system and method for dynamically evaluating supply capacity under new energy load conditions | |
| CN118300104B (en) | Distributed photovoltaic power prediction method, system, electronic equipment and storage medium based on graph neural network | |
| CN119051158A (en) | Photovoltaic power station integrated scheduling method | |
| CN109978242A (en) | The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics | |
| CN118645987A (en) | Dynamic evaluation method of energy efficiency in microgrid | |
| CN118316029A (en) | A distribution box intelligent power regulation method and system based on artificial intelligence | |
| CN118783396A (en) | A method for predicting low-voltage distributed photovoltaic power in local balancing scenarios | |
| CN114819374B (en) | Regional new energy ultra-short term power prediction method and system | |
| CN118332476B (en) | Fault diagnosis method, system, equipment and storage medium for gateway metering device of factory station | |
| CN118378156B (en) | Factory station gateway metering data missing fitting optimization method and system based on historical data analysis, electronic equipment and storage medium | |
| CN118780642A (en) | A method and system for predicting power of photovoltaic power generation | |
| CN117833361A (en) | Deep peak load prediction method and device for coal-fired power plants based on time series analysis | |
| CN117892939A (en) | Power plant energy consumption control method and system based on energy Internet | |
| CN118095704A (en) | Typical rural energy supply and demand balance method and system based on big data | |
| Kaushik et al. | Performance Analysis of Regression Models in Solar PV Forecasting | |
| CN118332403B (en) | A method for assessing dust accumulation in photovoltaic power plants from particle size to string-level hourly level | |
| CN119401394A (en) | Main grid energy storage power station planning system and method based on wind-solar spatiotemporal correlation | |
| CN118798548A (en) | Edge-to-edge integrated management platform for distributed energy | |
| WO2024171209A1 (en) | A digital twin system for solar power plants and method thereof | |
| Karthick et al. | Prediction of Photovoltaic Output Power using GRU and Weather Data Fusion |
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 |