CN117713039B - Power plant power generation control method based on regional new energy power generation prediction - Google Patents
Power plant power generation control method based on regional new energy power generation prediction Download PDFInfo
- Publication number
- CN117713039B CN117713039B CN202311443439.7A CN202311443439A CN117713039B CN 117713039 B CN117713039 B CN 117713039B CN 202311443439 A CN202311443439 A CN 202311443439A CN 117713039 B CN117713039 B CN 117713039B
- Authority
- CN
- China
- Prior art keywords
- weather
- data
- power generation
- actual measurement
- meteorological
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 147
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005259 measurement Methods 0.000 claims abstract description 97
- 238000006243 chemical reaction Methods 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims description 42
- 238000012544 monitoring process Methods 0.000 claims description 14
- 230000005611 electricity Effects 0.000 claims description 7
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000013486 operation strategy Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a power plant power generation control method based on regional new energy power generation prediction, and relates to the technical field of power prediction, wherein the method comprises the following steps: the method comprises the steps of obtaining weather forecast records of a target area, dividing the target area, obtaining a plurality of target subareas, obtaining weather actual measurement data of the plurality of subareas, obtaining weather error data according to the actual measurement data, obtaining real-time weather forecast data of the target area, and finally carrying out power generation conversion through a new energy power generation device according to the real-time weather forecast data to obtain forecast power. The method mainly solves the problems that the prediction accuracy is low, the stability and the operation efficiency of the power system can be affected between the actual power generation rate and the predicted power generation power, the meteorological data acquisition is inaccurate, and the limitation is caused. The reliability and stability of new energy power generation are improved, the running risk of a power grid is reduced, and the running efficiency of a power system is optimized.
Description
Technical Field
The application relates to the technical field of power prediction, in particular to a power generation control method of a power plant based on regional new energy power generation power prediction.
Background
The power generation control method of the power plant based on regional new energy power generation prediction is developed under the background of a new energy power system. As the degree of human dependence on renewable energy sources increases, the stability and reliability of new energy power generation systems become increasingly important. How to effectively manage and control the power generated by a new energy power plant to ensure the stable operation of a power system becomes a problem to be solved. The utility model provides a power generation control method of a power plant based on regional new energy power generation power prediction, which aims at providing reliable basis for power generation control of the power plant by predicting new energy power generation power so as to optimize the operation of a power system.
The existing method is to establish a hydrodynamic model conforming to meteorological characteristic information of a wind power plant by adopting a microscopic meteorological theory or a hydrodynamic method according to the topographic and physical information around the wind power plant, and then to predict the wind speed, wind direction and other information of the hub height of the wind power plant by adopting the model, so as to further predict the power of the wind power plant.
However, in the process of implementing the technical scheme of the embodiment of the application, the inventor discovers that the above technology has at least the following technical problems:
The prediction accuracy is low, the stability and the operation efficiency of the power system can be affected between the actual power generation rate and the predicted power generation power, and the meteorological data acquisition is inaccurate and has the problem of limitation.
Disclosure of Invention
The method mainly solves the problems that the prediction accuracy is low, the stability and the operation efficiency of the power system can be affected between the actual power generation rate and the predicted power generation power, the meteorological data acquisition is inaccurate, and the limitation is caused.
In view of the above problems, the present application provides a power plant power generation control method based on regional new energy power generation prediction, and in a first aspect, the present application provides a power plant power generation control method based on regional new energy power generation prediction, the method comprising: acquiring a weather forecast record of a target area, wherein the weather forecast record is provided with a time mark, and is acquired through a weather forecast point; dividing the target area according to an area dividing factor to obtain a plurality of target subareas, wherein each target subarea generates electricity through a new energy power generation device, and a first meteorological prediction point of a first target subarea is provided with a first meteorological predictor; monitoring and training a plurality of sub-region weather environment observation records to obtain a plurality of weather actual measurement branches, and adding the branches to a first weather predictor to obtain a plurality of sub-region weather actual measurement data, wherein the sub-region weather actual measurement data have time marks; obtaining a plurality of weather error data according to the weather forecast record and the sub-region weather actual measurement data, wherein the weather forecast record and the sub-region weather actual measurement data have the same time mark; constructing a weather total error distribution of the target area by combining a plurality of weather error data, and adding the weather total error distribution to the first weather predictor; collecting real-time meteorological environment observation data of a plurality of subareas, inputting the data into the first meteorological predictor, and acquiring real-time meteorological prediction data of the target area by combining the total meteorological error distribution; and carrying out power generation conversion through the new energy power generation device according to the real-time weather prediction data, and obtaining predicted power generation.
In a second aspect, the present application provides a power plant power generation control system based on regional new energy generated power prediction, the system comprising: the weather forecast record acquisition module is used for acquiring weather forecast records of the target area, wherein the weather forecast records have time marks, and the weather forecast records are acquired through weather forecast points; the system comprises a plurality of target subarea acquisition modules, a first air image prediction point and a second air image prediction point, wherein the plurality of target subarea acquisition modules are used for dividing the target area according to area division factors to obtain a plurality of target subareas, each target subarea generates electricity through a new energy power generation device, and the first air image prediction point of the first target subarea is provided with a first air image predictor; the monitoring training module is used for monitoring and training a plurality of sub-region weather environment observation records to obtain a plurality of weather actual measurement branches and adding the branches to the first weather predictor to obtain a plurality of sub-region weather actual measurement data, wherein the sub-region weather actual measurement data are provided with time marks; the weather error data acquisition module is used for acquiring a plurality of weather error data according to the weather prediction record and the sub-region weather actual measurement data, and the weather prediction record and the sub-region weather actual measurement data have the same time mark; a first weather predictor adding module for constructing a weather total error distribution of the target area in combination with a plurality of the weather error data and adding to the first weather predictor; the real-time weather forecast data acquisition module is used for acquiring a plurality of sub-region real-time weather environment observation data, inputting the data into the first weather forecast, and acquiring real-time weather forecast data of the target region by combining the weather total error distribution; the prediction power generation power acquisition module is used for carrying out power generation conversion through the new energy power generation device according to real-time weather prediction data and obtaining prediction power generation.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the application provides a power plant power generation control method based on regional new energy power generation prediction, and relates to the technical field of power prediction, wherein the method comprises the following steps: the method comprises the steps of obtaining weather forecast records of a target area, dividing the target area, obtaining a plurality of target subareas, obtaining weather actual measurement data of the plurality of subareas, obtaining weather error data according to the actual measurement data, obtaining real-time weather forecast data of the target area, and finally carrying out power generation conversion through a new energy power generation device according to the real-time weather forecast data to obtain forecast power.
The method mainly solves the problems that the prediction accuracy is low, the stability and the operation efficiency of the power system can be affected between the actual power generation rate and the predicted power generation power, the meteorological data acquisition is inaccurate, and the limitation is caused. The reliability and stability of new energy power generation are improved, the running risk of a power grid is reduced, and the running efficiency of a power system is optimized.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
In order to more clearly illustrate the application or the technical solutions of the prior art, the following brief description will be given of the drawings used in the description of the embodiments or the prior art, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained from the drawings provided without the inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a power plant power generation control method based on regional new energy power generation power prediction according to an embodiment of the application;
FIG. 2 is a schematic flow chart of a method for obtaining meteorological actual measurement data of a plurality of subareas in a power plant power generation control method based on regional new energy power generation prediction according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of a method for obtaining real-time weather forecast data in a power plant power generation control method based on regional new energy power generation power forecast according to an embodiment of the application;
fig. 4 is a schematic structural diagram of a power plant power generation control system based on regional new energy power generation power prediction according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a weather forecast record acquisition module 10, a plurality of target subarea acquisition modules 20, a supervision and training module 30, a weather error data acquisition module 40, a first weather forecast adding module 50, a real-time weather forecast data acquisition module 60 and a forecast power acquisition module 70.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The method mainly solves the problems that the prediction accuracy is low, the stability and the operation efficiency of the power system can be affected between the actual power generation rate and the predicted power generation power, the meteorological data acquisition is inaccurate, and the limitation is caused. The reliability and stability of new energy power generation are improved, the running risk of a power grid is reduced, and the running efficiency of a power system is optimized.
For a better understanding of the foregoing technical solutions, the following detailed description will be given with reference to the accompanying drawings and specific embodiments of the present invention:
example 1
The power generation control method of the power plant based on regional new energy generated power prediction as shown in fig. 1 comprises the following steps:
Acquiring a weather forecast record of a target area, wherein the weather forecast record is provided with a time mark, and is acquired through a weather forecast point;
Specifically, a weather forecast record of a target area is acquired, and the target area is selected: the target area where the weather forecast recording needs to be obtained is determined, which may be a city, a region, or a specific geographic location. Determining a meteorological prediction point: suitable weather prediction points are selected in the target area, and the prediction points can be places for acquiring weather data through observation equipment such as ground observation stations, weather satellites, radars or automatic stations. Collecting meteorological data: and collecting meteorological data in the target area through the selected meteorological prediction points. Such data may include temperature, humidity, wind speed, wind direction, rainfall, etc. Recording time identification: the collected weather data is associated with a corresponding time identifier. The time identifier may be a date and time for recording a specific point in time of the meteorological data acquisition. Weather forecast analysis: based on the collected weather data, an analysis is performed using an appropriate predictive model or algorithm to generate a weather prediction record. These predictive models may be based on statistical methods, machine learning algorithms, or other data analysis techniques. Generating a weather forecast record: and generating a weather forecast record with a time mark according to the analysis result. These records are typically presented in the form of tables, charts, or data files and contain meteorological data and corresponding predicted points in time within the target area.
Dividing the target area according to an area dividing factor to obtain a plurality of target subareas, wherein each target subarea generates electricity through a new energy power generation device, and a first meteorological prediction point of a first target subarea is provided with a first meteorological predictor;
Specifically, the target area is divided according to the area division factor, so that a plurality of target subareas can be obtained, and each target subarea generates power through the new energy power generation device. Wherein the first meteorological prediction point of the first target subregion is provided with a first meteorological predictor. The partitioning may be based on a number of conditions, including geographic conditions: the division is performed according to the geographic conditions of the target area, such as topography, climate and the like. The area under similar geographic conditions can be divided into a sub-area so as to facilitate the deployment and management of the new energy power generation device. Energy resource: dividing according to the energy resource distribution condition of the target area, such as solar energy, wind energy, water energy and the like. The area with similar energy resource distribution can be divided into a sub-area so as to facilitate the site selection and construction of the new energy power generation device. The power grid structure comprises: and dividing according to the power grid structure of the target area, such as a power transmission line, a transformer substation and the like. The area under a similar grid structure may be divided into a sub-area to facilitate management of power delivery and distribution. Social and economic factors: the target areas are divided according to socioeconomic conditions of the target areas, such as population distribution, industrial structures, economic development levels and the like. The area under the similar social and economic conditions can be divided into a sub-area so as to facilitate benefit analysis and marketing of the new energy power generation device. After a plurality of target subregions are obtained, each target subregion generates electricity through the new energy power generation device. These new energy power generation devices may include solar panels, wind power generation sets, hydroelectric power plants, and the like. Each target sub-area may deploy one or more new energy power generation devices to provide a sufficient power supply. In the first target subregion, the first meteorological prediction point has a first meteorological predictor. The first weather forecast point may be one or more weather observation stations for collecting weather data for the target sub-area. The first weather predictor may be one or more prediction models or algorithms for predicting weather conditions of the first target sub-area based on the collected weather data. These predictions can be used to adjust and manage the new energy generation device of the first target sub-area to ensure stable operation of the power system and to optimize the power supply.
Monitoring and training a plurality of sub-region weather environment observation records to obtain a plurality of weather actual measurement branches, and adding the branches to a first weather predictor to obtain a plurality of sub-region weather actual measurement data, wherein the sub-region weather actual measurement data have time marks;
Specifically, by supervised training of meteorological environment observation records for multiple sub-regions, multiple meteorological actual measurement branches can be obtained and added to the first meteorological predictor. Thus, the first weather predictor can utilize the measured data to adjust and perfect the prediction model so as to improve the prediction accuracy. The sub-region weather measured data all have time marks so as to accurately record the observation time corresponding to each data point. These time identifications may be dates and times identifying specific points in time for each meteorological data acquisition. By retaining the time stamp, it is ensured that the first weather predictor is able to perform a correct analysis and prediction from the time series of measured data. When the supervision training is performed, the historical meteorological data and the corresponding actual observed values can be used for training, so that the model learns the mapping relation between the meteorological data and the actual observed values. Thus, when the first weather predictor receives new weather data, it can use the mapping relationship that has been learned to generate a more accurate prediction result. By adding the weather actual measurement data of the plurality of subareas into the first weather predictor, the data source and the diversity of the first weather predictor can be increased, so that the weather actual measurement data can be better adapted to weather conditions of different areas, and the accuracy and the reliability of prediction are improved.
Obtaining a plurality of weather error data according to the weather forecast record and the sub-region weather actual measurement data, wherein the weather forecast record and the sub-region weather actual measurement data have the same time mark;
Specifically, a plurality of weather error data can be obtained from the weather forecast record and the sub-region weather actual measurement data. These weather error data represent the difference between the weather forecast record and the sub-region weather measured data. Since the weather forecast record and the sub-region weather measured data have the same time identification, it can be ensured that these error data are associated with the corresponding points in time. In this way, the weather prediction model may be evaluated and refined based on the error data to reduce prediction errors and improve model accuracy. The manner in which the error data is calculated may be varied. The difference between the predicted and actual observations may be measured using an indicator such as Mean Square Error (MSE) or Root Mean Square Error (RMSE). These metrics may reflect the accuracy and reliability of the predicted results, helping to optimize the model and reduce errors. By analyzing and utilizing the meteorological error data, the meteorological prediction model can be continuously improved and optimized, so that the accuracy and reliability of prediction are improved. These data can also be used to evaluate performance between different models, helping to select a more appropriate model for prediction and management.
Constructing a weather total error distribution of the target area by combining a plurality of weather error data, and adding the weather total error distribution to the first weather predictor;
Specifically, the performance and accuracy of the first weather predictor can be further improved by combining a plurality of weather error data to construct a weather total error distribution of the target area and adding the weather total error distribution to the first weather predictor. The weather total error distribution is constructed by integrating a plurality of weather error data. First, the weather error data of each sub-region is analyzed and processed to obtain the weather error distribution of the sub-region. And integrating the meteorological error distribution of each sub-region to construct the meteorological total error distribution of the target region. By knowing the total meteorological error distribution of the target area, the meteorological prediction error condition in the whole target area can be better known. In this way, the first weather predictor can use this information to optimize its predictive model, improving the accuracy and reliability of the predictions. The weather total error distribution is added to the first weather predictor, which can be provided with additional reference data and information. These data may be used to calibrate and adjust the prediction results of the first weather predictor to reduce overall error and improve prediction accuracy. By continuously monitoring and utilizing the weather total error distribution, the first weather predictor can continuously optimize its predictive model and better adapt to the weather conditions of the entire target area.
Collecting real-time meteorological environment observation data of a plurality of subareas, inputting the data into the first meteorological predictor, and acquiring real-time meteorological prediction data of the target area by combining the total meteorological error distribution;
Specifically, real-time meteorological environment observation data of a plurality of subareas are collected and input into a first meteorological predictor, and real-time meteorological prediction data of a target area can be obtained by combining with meteorological total error distribution. Firstly, meteorological environment observation data are collected in a plurality of subareas through real-time observation equipment. Such data includes, but is not limited to, temperature, humidity, wind speed, wind direction, barometric pressure, and the like. These observation data are real-time and reflect the current weather conditions. The acquired real-time observation data is then input to a first weather predictor. The first weather predictor processes and analyzes the current weather data in combination with the previously constructed weather total error distribution. The first weather forecast data of the target area is generated by the first weather forecast by considering the difference and the characteristics among the subareas and the information of the weather total error distribution. The method for acquiring the real-time weather forecast data can provide accurate and real-time weather information, and has important significance for guiding the operation of the power system, adjusting the power output of the new energy power generation device and guaranteeing the stability of the power system. Meanwhile, the prediction performance of the first weather predictor can be continuously optimized and improved by continuously collecting real-time observation data and updating weather total error distribution.
And carrying out power generation conversion through the new energy power generation device according to the real-time weather forecast data, and obtaining forecast power.
Specifically, the predicted power generation can be obtained by converting the power generated by the new energy power generation device based on the real-time weather prediction data. First, the power output of the new energy power generation device can be predicted based on the real-time weather prediction data. Such forecast data may include meteorological data such as wind speed, wind direction, temperature, humidity, etc., as well as characteristics and performance data of the new energy power generation device. By comprehensively considering these factors, the power generated by the new energy power generation device at different time points can be predicted. Then, based on the predicted generated power, the power generation conversion of the new-energy power generation device can be adjusted. The power generation conversion refers to converting the output power of the new energy power generation device into electric energy available to the power grid. This may be achieved by power electronics converters, transformers, etc. By adjusting the setting and parameters of the power generation conversion, the output power of the new energy power generation device can be controlled, and the power generation device is ensured to be matched with the predicted power generation power. In this way, the power generated by the new energy power generation device can be predicted from the real-time weather prediction data and converted to power for the grid. The power generation control method based on the real-time weather forecast data can improve the reliability and stability of new energy power generation, reduce the running risk of a power grid and optimize the running efficiency of a power system.
Furthermore, in the method of the present application, the target area is divided according to an area division factor, and a plurality of target sub-areas are obtained, and the method includes:
obtaining a region division factor sequence according to the weights of the terrain factors and the altitude factors in the region division factors;
extracting the region division factor sequence, and dividing the target region for multiple times to obtain a plurality of target subregions;
And based on the big data, acquiring actual geographic data of the target subareas, and adjusting a plurality of target subareas.
Specifically, the region division factor sequence may be obtained according to weights of the terrain factors and the altitude factors among the region division factors. These factors may be ranked by their importance and degree of influence, e.g., terrain factors may be more important than altitude factors, and thus given higher weight. Next, a region division factor sequence is extracted, and the target region is divided a plurality of times to obtain a plurality of target sub-regions. In the dividing process, the dividing strategy can be flexibly adjusted, such as adopting different dividing standards, merging adjacent subareas or splitting the existing subareas. In order to obtain the actual geographic data of the target subregion, extraction and analysis can be performed by using the existing big data platform and Geographic Information System (GIS) tools. Such data may include terrain height, topography type, river course, demographics, etc., which are important to further understanding the characteristics and attributes of the target sub-area. Based on the actual geographic data, multiple target subregions may be adjusted and optimized. For example, the regional division result can be corrected according to the actual geographic data, so that the boundary between the subregions is ensured to be more reasonable and accurate. In addition, the actual geographic data may be used to analyze and evaluate the characteristics and attributes of the sub-regions to better understand the uniqueness and variability of each sub-region. By combining the terrain factors, the elevation factors and other related factors to divide the areas and utilizing the actual geographic data to adjust and optimize, more accurate and finer dividing results of the target subareas can be obtained. The results can provide more valuable reference basis for the subsequent application of new energy power generation control and the like.
Further, as shown in fig. 2, in the method of the present application, the monitoring training is performed on the meteorological environment observation records of a plurality of sub-regions to obtain a plurality of branches of meteorological actual measurement, and the branches are added to the first meteorological predictor to obtain a plurality of meteorological actual measurement data of the sub-regions, and the method includes:
the observation parameters of the meteorological environment observation records of the plurality of subareas comprise sunlight intensity of light energy, light energy collection time, wind level of the wind energy and wind energy collection time;
Training a plurality of light energy influence weather channels of a plurality of weather actual measurement branches according to the sunlight intensity and the light energy collection time of a plurality of light energy, and acquiring a plurality of light energy actual measurement data if a plurality of light energy actual measurement accuracy meets a plurality of calibration light energy accuracy;
Taking wind levels and wind energy collection time of a plurality of wind energies as training data, performing supervision training on a plurality of wind energy influence meteorological channels of a plurality of meteorological actual measurement branches, and acquiring a plurality of wind energy prediction data if a plurality of wind energy actual measurement accuracy rates meet a plurality of calibration wind energy accuracy rates;
And combining the plurality of the light energy actual measurement data and the plurality of the wind energy actual measurement data to obtain a plurality of the sub-region weather actual measurement data.
Specifically, the observation parameters of the meteorological environment observation records of the plurality of subareas comprise sunlight intensity of light energy, light energy collection time, wind level of the wind energy and wind energy collection time. These parameters are used to train the plurality of light energy affecting weather channels and the plurality of wind energy affecting weather channels of the plurality of weather branches. First, the sunlight intensities and the light energy collection time of a plurality of light energies are used for training a plurality of light energy influence weather channels of a plurality of weather actual measurement branches. Such training may be based on statistical methods, machine learning algorithms, or other data analysis techniques. In the training process, accuracy and integrity of training data need to be ensured so that the weather actual measurement branch obtained by training can accurately predict the change and influence of light energy. After training is completed, judging whether the weather actual measurement branch obtained by training meets the requirements or not by comparing the optical energy actual measurement accuracy with the calibration optical energy accuracy. And if the requirements are met, acquiring a plurality of light energy actual measurement data. These data can be used to evaluate and optimize the performance and benefits of the new energy power plant in terms of light energy utilization. And then, performing supervision training on a plurality of wind energy influence weather channels of a plurality of weather actual measurement branches by taking wind levels and wind energy acquisition time of a plurality of wind energies as training data. Such training may also be based on statistical methods, machine learning algorithms, or other data analysis techniques. In the process of supervision training, known wind energy data is required to be used as a training label, so that the weather actual measurement branch obtained by training can accurately predict the change and influence of wind energy. And after the training is finished, comparing the actual measurement accuracy of the wind energy with the accuracy of the calibrated wind energy to judge whether the weather actual measurement branch obtained by the training meets the requirement. And if the requirements are met, acquiring a plurality of wind energy prediction data. These data can be used to evaluate and optimize the performance and benefits of the new energy power plant in terms of wind energy utilization. And finally, combining the plurality of sub-area weather actual measurement data according to the plurality of light energy actual measurement data and the plurality of wind energy actual measurement data. These data can be used to evaluate and optimize the weather environment and the performance and benefits of the new energy power plant for the entire target area. Meanwhile, the data can be used for calibrating and adjusting a weather prediction model, so that the prediction accuracy and reliability of the weather prediction model are improved.
Furthermore, in the method of the present application, a plurality of weather error data are obtained according to the weather forecast record and the weather actual measurement data of the sub-area, and the weather forecast record and the weather actual measurement data of the sub-area have the same time identifier, and the method includes:
extracting a first sub-region weather environment observation record according to the plurality of sub-region weather environment observation records, inputting a first weather branch to obtain first sub-region weather measured data, and simultaneously providing the time mark;
Extracting a first weather forecast record according to a plurality of weather forecast records and having the time identifier;
And when the time marks of the first sub-region weather actually measured data and the first weather forecast record are the same, comparing the first sub-region weather actually measured data with the first weather forecast record to obtain the weather error data.
Specifically, according to the multiple sub-region weather environment observation records, a first sub-region weather environment observation record is extracted, a first weather branch is input, first sub-region weather actual measurement data is obtained, and meanwhile, a time mark is provided. The data includes meteorological elements such as wind speed, wind direction, temperature, humidity, etc. for assessing and monitoring meteorological environmental conditions of the first sub-area. Also, a first weather forecast record is extracted based on the plurality of weather forecast records and has a time identification. These predictive records are generated from historical weather data and predictive models for predicting future weather conditions. And when the time identifiers of the first sub-area weather actual measurement data and the first weather forecast record are the same, comparing the first sub-area weather actual measurement data with the first weather forecast record. By comparing the actual observation data with the prediction data, weather error data can be obtained. These error data may reflect the accuracy and reliability of the predictive model at a particular point in time. By comparing and analyzing the first sub-region weather measured data with the first weather forecast record, weather error data with a time identifier can be obtained. These data can be used to evaluate and optimize the weather prediction model, improving its prediction accuracy and reliability. Meanwhile, the error data can be used for adjusting the operation strategy of the new energy power generation device so as to better adapt to the change and the requirement of the actual meteorological environment.
Further, the method of the present application constructs a weather total error distribution of the target area by combining a plurality of weather error data, and adds the weather total error distribution to the first weather predictor, the method includes:
Arranging position nodes in the target area according to meteorological error data of a plurality of target subareas;
Connecting the position nodes to establish an error data network, wherein the meteorological error data in the error data network are increased and decreased in the same proportion;
and constructing the weather total error distribution of the target area according to the error data network.
In particular, the meteorological error data of a plurality of target sub-areas are laid out in the target area with location nodes, which may represent different geographical locations or sub-areas within the target area. These location nodes are then connected to build an error data network. In the error data network, weather error data are displayed in a mode of increasing and decreasing in the same proportion. Through the error data network, the weather error distribution condition in the target area can be more intuitively known. Meanwhile, the data network can be used for analyzing and optimizing a weather prediction model so as to improve the accuracy and reliability of prediction. Next, based on this error data network, a weather total error distribution for the target area can be constructed. The total error distribution can reflect the weather error condition in the whole target area and provide reference basis for subsequent power dispatching and new energy power generation control. In this way, a finer and comprehensive error data network can be constructed using the connection between the weather error data and the location nodes. The data network can help better understand the weather error distribution situation in the target area, and provides a valuable reference basis for optimizing power dispatching and new energy power generation control.
Further, as shown in fig. 3, in the method of the present application, the real-time meteorological environment observation data of the sub-region is collected, the real-time meteorological prediction data of the target region is obtained by inputting the real-time meteorological environment observation data of the sub-region into the first meteorological predictor and combining the total meteorological error distribution, the method includes:
a plurality of meteorological sensors are arranged in a plurality of target subareas, and a plurality of subarea real-time meteorological environment observation data of the target subareas are collected;
Inputting the real-time meteorological environment observation data of a plurality of subareas into the first meteorological predictor to obtain a plurality of real-time meteorological prediction data of a plurality of target subareas;
And matching a plurality of position nodes of the real-time weather forecast data according to the weather total error distribution in the first weather forecast device, and combining to obtain the real-time weather forecast data of the target area.
Specifically, by providing a plurality of meteorological sensors in a plurality of target subregions, real-time meteorological environment observation data of a plurality of subregions of the plurality of target subregions can be acquired. These data include meteorological elements such as wind speed, wind direction, temperature, humidity, etc. for monitoring and assessing the meteorological environmental conditions of each sub-area. The real-time weather environment observation data of the plurality of sub-areas are input into the first weather predictor, and a plurality of real-time weather prediction data of the plurality of target sub-areas can be obtained. These prediction data are generated based on historical weather data and a prediction model for predicting future weather conditions. The position nodes of the plurality of real-time weather forecast data can be matched according to the weather total error distribution in the first weather forecast. This matching process may associate each prediction data with a corresponding sub-region or location node. In this way, real-time weather forecast data for the target area may be obtained. The real-time weather forecast data can provide accurate information about weather conditions of a target area, and has important significance for power dispatching and new energy power generation control. Based on the data, the operation strategy of the power system can be timely adjusted, and the stability and reliability of power supply are ensured. Meanwhile, the data can be used for evaluating the performance and efficiency of the new energy power generation device, and a reference basis is provided for subsequent power generation and energy management.
In a further aspect, the method of the present application further includes, after performing power generation conversion by the new energy power generation device according to the real-time weather prediction data and obtaining the predicted power generation,:
Extracting power generation conversion power thresholds of a plurality of new energy power generation devices, and judging whether a plurality of actually measured power generation conversion powers for obtaining a plurality of predicted power generation powers meet a plurality of power generation conversion power thresholds according to a plurality of real-time weather prediction data;
if the measured power conversion powers are met, obtaining a plurality of predicted power generation powers;
And if the actually measured power conversion power is not satisfied, detecting equipment faults of the new energy power generation devices.
Specifically, the power generation conversion power thresholds of a plurality of new-energy power generation devices are extracted, and the thresholds are determined according to the performance and design requirements of each new-energy power generation device. Based on the plurality of real-time weather forecast data, it can be determined whether or not the plurality of measured power conversion powers for obtaining the plurality of forecast power generation powers satisfy the plurality of power conversion power thresholds. If the plurality of measured power generation conversion powers satisfy the power generation conversion power threshold value, a plurality of predicted power generation powers may be obtained. The predicted generated power is calculated based on the real-time weather predicted data and the performance parameters of the new energy power generation device, and can be used for guiding the operation and the scheduling of the power system. If the measured power conversion powers do not meet the power conversion power threshold, equipment failure detection is required for the new energy power generation devices. Such fault detection may include, but is not limited to, checking the operational status of the equipment, wear of mechanical components, stability of the circuitry, etc. Through equipment fault detection, the existing problems can be found and repaired in time, and the normal operation of the new energy power generation device and the stability of the power system are ensured.
Example two
Based on the same inventive concept as the power plant power generation control method based on regional new energy power generation prediction of the foregoing embodiments, as shown in fig. 4, the present application provides a power plant power generation control system based on regional new energy power generation prediction, the system comprising:
The weather forecast record acquisition module 10 is used for acquiring a weather forecast record of the target area, wherein the weather forecast record has a time identifier, and is acquired through weather forecast point acquisition;
The target sub-area acquisition module 20 is configured to divide the target area according to an area division factor to obtain a plurality of target sub-areas, where each target sub-area generates electricity through a new energy power generation device, and a first meteorological prediction point of a first target sub-area has a first meteorological predictor;
the monitoring training module 30 is used for monitoring and training a plurality of sub-region weather environment observation records to obtain a plurality of weather actual measurement branches and adding the branches to the first weather predictor to obtain a plurality of sub-region weather actual measurement data, wherein the plurality of sub-region weather actual measurement data all have time marks;
the weather error data acquisition module 40 is configured to obtain a plurality of weather error data according to the weather prediction record and the sub-region weather actual measurement data, where the weather prediction record and the sub-region weather actual measurement data have the same time identifier;
A first weather predictor adding module 50, wherein the first weather predictor adding module 50 is used for combining a plurality of weather error data to construct a weather total error distribution of the target area and adding the weather total error distribution to the first weather predictor;
The real-time weather forecast data acquisition module 60 is used for acquiring a plurality of sub-region real-time weather environment observation data, inputting the data into the first weather forecast, and acquiring real-time weather forecast data of the target region by combining the total weather error distribution;
The predicted power generation module 70 is configured to perform power generation conversion by the new energy power generation device according to real-time weather prediction data, and obtain predicted power generation.
Further, the system further comprises:
The actual geographic data acquisition module is used for acquiring a region division factor sequence according to the weights of the terrain factors and the altitude factors in the region division factors; extracting the region division factor sequence, and dividing the target region for multiple times to obtain a plurality of target subregions; and based on the big data, acquiring actual geographic data of the target subareas, and adjusting a plurality of target subareas.
Further, the system further comprises:
the meteorological actual measurement data acquisition module is used for observing observation parameters of the meteorological environment observation records of the plurality of subareas, wherein the observation parameters comprise sunlight intensity of light energy, light energy acquisition time, wind level of the wind energy and wind energy acquisition time; training a plurality of light energy influence weather channels of a plurality of weather actual measurement branches according to the sunlight intensity and the light energy collection time of a plurality of light energy, and acquiring a plurality of light energy actual measurement data if a plurality of light energy actual measurement accuracy meets a plurality of calibration light energy accuracy; taking wind levels and wind energy collection time of a plurality of wind energies as training data, performing supervision training on a plurality of wind energy influence meteorological channels of a plurality of meteorological actual measurement branches, and acquiring a plurality of wind energy prediction data if a plurality of wind energy actual measurement accuracy rates meet a plurality of calibration wind energy accuracy rates; and combining the plurality of the light energy actual measurement data and the plurality of the wind energy actual measurement data to obtain a plurality of the sub-region weather actual measurement data.
Further, the system further comprises:
The meteorological error data acquisition module is used for extracting a first subarea meteorological environment observation record according to the plurality of subarea meteorological environment observation records, inputting a first meteorological actual measurement branch, acquiring first subarea meteorological actual measurement data and simultaneously having the time mark; extracting a first weather forecast record according to a plurality of weather forecast records and having the time identifier; and when the time marks of the first sub-region weather actually measured data and the first weather forecast record are the same, comparing the first sub-region weather actually measured data with the first weather forecast record to obtain the weather error data.
Further, the system further comprises:
the weather total error distribution construction module is used for distributing position nodes in the target area according to weather error data of a plurality of target subareas; connecting the position nodes to establish an error data network, wherein the meteorological error data in the error data network are increased and decreased in the same proportion; and constructing the weather total error distribution of the target area according to the error data network.
Further, the system further comprises:
The real-time weather forecast data acquisition module is used for acquiring real-time weather environment observation data of a plurality of sub-areas of the target sub-areas through arranging a plurality of weather sensors in the target sub-areas; inputting the real-time meteorological environment observation data of a plurality of subareas into the first meteorological predictor to obtain a plurality of real-time meteorological prediction data of a plurality of target subareas; and matching a plurality of position nodes of the real-time weather forecast data according to the weather total error distribution in the first weather forecast device, and combining to obtain the real-time weather forecast data of the target area.
Further, the system further comprises:
The fault detection module is used for extracting power generation conversion power thresholds of the new energy power generation devices, and judging whether the power generation conversion power obtained by the actual measurement of the predicted power generation power meets the power generation conversion power thresholds or not according to the real-time weather prediction data; if the measured power conversion powers are met, obtaining a plurality of predicted power generation powers; and if the actually measured power conversion power is not satisfied, detecting equipment faults of the new energy power generation devices.
The foregoing detailed description of the power generation control method of the power plant based on the regional new energy generated power prediction will be clear to those skilled in the art, and the power generation control system of the power plant based on the regional new energy generated power prediction in this embodiment is described more simply for the system disclosed in the embodiments, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. The power generation control method of the power plant based on regional new energy generated power prediction is characterized by comprising the following steps:
Acquiring a weather forecast record of a target area, wherein the weather forecast record is provided with a time mark, and is acquired through a weather forecast point;
dividing the target area according to an area dividing factor to obtain a plurality of target subareas, wherein each target subarea generates electricity through a new energy power generation device, and a first meteorological prediction point of a first target subarea is provided with a first meteorological predictor;
Monitoring and training a plurality of sub-region weather environment observation records to obtain a plurality of weather actual measurement branches, and adding the branches to a first weather predictor to obtain a plurality of sub-region weather actual measurement data, wherein the sub-region weather actual measurement data have time marks;
obtaining a plurality of weather error data according to the weather forecast record and the sub-region weather actual measurement data, wherein the weather forecast record and the sub-region weather actual measurement data have the same time mark;
constructing a weather total error distribution of the target area by combining a plurality of weather error data, and adding the weather total error distribution to the first weather predictor;
Collecting real-time meteorological environment observation data of a plurality of subareas, inputting the data into the first meteorological predictor, and acquiring real-time meteorological prediction data of the target area by combining the total meteorological error distribution;
According to the real-time weather forecast data, carrying out power generation conversion through the new energy power generation device, and obtaining forecast power;
The dividing the target area according to the area dividing factor to obtain a plurality of target subareas includes:
obtaining a region division factor sequence according to the weights of the terrain factors and the altitude factors in the region division factors;
extracting the region division factor sequence, and dividing the target region for multiple times to obtain a plurality of target subregions;
based on big data, acquiring actual geographic data of the target subareas, and adjusting a plurality of the target subareas;
The monitoring training of the meteorological environment observation records of a plurality of subareas to obtain a plurality of meteorological actual measurement branches and adding the branches to a first meteorological predictor to obtain a plurality of subarea meteorological actual measurement data comprises the following steps:
the observation parameters of the meteorological environment observation records of the plurality of subareas comprise sunlight intensity of light energy, light energy collection time, wind level of the wind energy and wind energy collection time;
Training a plurality of light energy influence weather channels of a plurality of weather actual measurement branches according to the sunlight intensity and the light energy collection time of a plurality of light energy, and acquiring a plurality of light energy actual measurement data if a plurality of light energy actual measurement accuracy meets a plurality of calibration light energy accuracy;
Taking wind levels and wind energy collection time of a plurality of wind energies as training data, performing supervision training on a plurality of wind energy influence meteorological channels of a plurality of meteorological actual measurement branches, and acquiring a plurality of wind energy prediction data if a plurality of wind energy actual measurement accuracy rates meet a plurality of calibration wind energy accuracy rates;
And combining the plurality of the light energy actual measurement data and the plurality of the wind energy actual measurement data to obtain a plurality of the sub-region weather actual measurement data.
2. The method of claim 1, wherein the obtaining a plurality of weather error data from the weather forecast record and the sub-region weather measured data, the weather forecast record and the sub-region weather measured data having the same time identification, comprises:
extracting a first sub-region weather environment observation record according to the plurality of sub-region weather environment observation records, inputting a first weather branch to obtain first sub-region weather measured data, and simultaneously providing the time mark;
Extracting a first weather forecast record according to a plurality of weather forecast records and having the time identifier;
And when the time marks of the first sub-region weather actually measured data and the first weather forecast record are the same, comparing the first sub-region weather actually measured data with the first weather forecast record to obtain the weather error data.
3. The method of claim 1, wherein said combining a plurality of said weather error data constructs a weather total error profile for said target area and adds to said first weather predictor, the method comprising:
Arranging position nodes in the target area according to meteorological error data of a plurality of target subareas;
Connecting the position nodes to establish an error data network, wherein the meteorological error data in the error data network are increased and decreased in the same proportion;
and constructing the weather total error distribution of the target area according to the error data network.
4. The method of claim 3, wherein the acquiring sub-region real-time weather environmental observation data, inputting the first weather predictor, and combining the weather total error distribution, acquiring real-time weather prediction data of the target region, the method comprising:
a plurality of meteorological sensors are arranged in a plurality of target subareas, and a plurality of subarea real-time meteorological environment observation data of the target subareas are collected;
Inputting the real-time meteorological environment observation data of a plurality of subareas into the first meteorological predictor to obtain a plurality of real-time meteorological prediction data of a plurality of target subareas;
And matching a plurality of position nodes of the real-time weather forecast data according to the weather total error distribution in the first weather forecast device, and combining to obtain the real-time weather forecast data of the target area.
5. The method of claim 1, wherein after the generating conversion by the new energy generating device is performed according to the real-time weather prediction data and the predicted generated power is obtained, the method further comprises:
Extracting power generation conversion power thresholds of a plurality of new energy power generation devices, and judging whether a plurality of actually measured power generation conversion powers for obtaining a plurality of predicted power generation powers meet a plurality of power generation conversion power thresholds according to a plurality of real-time weather prediction data;
if the measured power conversion powers are met, obtaining a plurality of predicted power generation powers;
And if the actually measured power conversion power is not satisfied, detecting equipment faults of the new energy power generation devices.
6. Power plant power generation control system based on regional new energy power generation prediction, characterized in that the system comprises:
The weather forecast record acquisition module is used for acquiring weather forecast records of the target area, wherein the weather forecast records have time marks, and the weather forecast records are acquired through weather forecast points;
The system comprises a plurality of target subarea acquisition modules, a first air image prediction point and a second air image prediction point, wherein the plurality of target subarea acquisition modules are used for dividing the target area according to area division factors to obtain a plurality of target subareas, each target subarea generates electricity through a new energy power generation device, and the first air image prediction point of the first target subarea is provided with a first air image predictor;
The monitoring training module is used for monitoring and training a plurality of sub-region weather environment observation records to obtain a plurality of weather actual measurement branches and adding the branches to the first weather predictor to obtain a plurality of sub-region weather actual measurement data, wherein the sub-region weather actual measurement data are provided with time marks;
the weather error data acquisition module is used for acquiring a plurality of weather error data according to the weather prediction record and the sub-region weather actual measurement data, and the weather prediction record and the sub-region weather actual measurement data have the same time mark;
A first weather predictor adding module for constructing a weather total error distribution of the target area in combination with a plurality of the weather error data and adding to the first weather predictor;
The real-time weather forecast data acquisition module is used for acquiring a plurality of sub-region real-time weather environment observation data, inputting the data into the first weather forecast, and acquiring real-time weather forecast data of the target region by combining the weather total error distribution;
the prediction power generation power acquisition module is used for carrying out power generation conversion through the new energy power generation device according to real-time weather prediction data and acquiring prediction power;
the actual geographic data acquisition module is used for acquiring a region division factor sequence according to the weights of the terrain factors and the altitude factors in the region division factors; extracting the region division factor sequence, and dividing the target region for multiple times to obtain a plurality of target subregions; based on big data, acquiring actual geographic data of the target subareas, and adjusting a plurality of the target subareas;
the meteorological actual measurement data acquisition module is used for observing observation parameters of the meteorological environment observation records of the plurality of subareas, wherein the observation parameters comprise sunlight intensity of light energy, light energy acquisition time, wind level of the wind energy and wind energy acquisition time; training a plurality of light energy influence weather channels of a plurality of weather actual measurement branches according to the sunlight intensity and the light energy collection time of a plurality of light energy, and acquiring a plurality of light energy actual measurement data if a plurality of light energy actual measurement accuracy meets a plurality of calibration light energy accuracy; taking wind levels and wind energy collection time of a plurality of wind energies as training data, performing supervision training on a plurality of wind energy influence meteorological channels of a plurality of meteorological actual measurement branches, and acquiring a plurality of wind energy prediction data if a plurality of wind energy actual measurement accuracy rates meet a plurality of calibration wind energy accuracy rates; and combining the plurality of the light energy actual measurement data and the plurality of the wind energy actual measurement data to obtain a plurality of the sub-region weather actual measurement data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311443439.7A CN117713039B (en) | 2023-11-01 | 2023-11-01 | Power plant power generation control method based on regional new energy power generation prediction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311443439.7A CN117713039B (en) | 2023-11-01 | 2023-11-01 | Power plant power generation control method based on regional new energy power generation prediction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117713039A CN117713039A (en) | 2024-03-15 |
| CN117713039B true CN117713039B (en) | 2024-06-14 |
Family
ID=90143114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311443439.7A Active CN117713039B (en) | 2023-11-01 | 2023-11-01 | Power plant power generation control method based on regional new energy power generation prediction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117713039B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705771A (en) * | 2019-09-26 | 2020-01-17 | 国家电网公司华北分部 | Method and device for predicting and optimizing power generation power of new energy of regional power grid |
| CN116739152A (en) * | 2023-05-24 | 2023-09-12 | 阳光电源（上海）有限公司 | New energy power prediction model construction method and new energy power prediction method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950780A (en) * | 2020-07-31 | 2020-11-17 | 许继集团有限公司 | Wind power plant short-term power prediction method |
| CN113570126A (en) * | 2021-07-15 | 2021-10-29 | 远景智能国际私人投资有限公司 | Method, device and system for predicting power generation power of photovoltaic power station |
| CN113937763B (en) * | 2021-10-14 | 2023-09-26 | 远景智能国际私人投资有限公司 | Wind power prediction method, device, equipment and storage medium |
| CN115907268A (en) * | 2022-10-14 | 2023-04-04 | 国网河南省电力公司 | Integrated forecast meteorological resource integrated management method and system |
| CN116865236A (en) * | 2023-05-17 | 2023-10-10 | 山东国电投能源营销有限公司 | Medium-and-long-term power generation capacity prediction method and system based on new energy power generation |
-
2023
- 2023-11-01 CN CN202311443439.7A patent/CN117713039B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110705771A (en) * | 2019-09-26 | 2020-01-17 | 国家电网公司华北分部 | Method and device for predicting and optimizing power generation power of new energy of regional power grid |
| CN116739152A (en) * | 2023-05-24 | 2023-09-12 | 阳光电源（上海）有限公司 | New energy power prediction model construction method and new energy power prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117713039A (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dong et al. | Wind power day-ahead prediction with cluster analysis of NWP | |
| CN102934312B (en) | Energy production system and control thereof | |
| CN102411729B (en) | Wind power prediction method based on adaptive linear logic network | |
| CN113496311A (en) | Photovoltaic power station generated power prediction method and system | |
| Qing | Statistical analysis of wind energy characteristics in Santiago island, Cape Verde | |
| CN117036104B (en) | Intelligent electricity utilization method and system based on electric power Internet of things | |
| CN113988273A (en) | Ice disaster environment active power distribution network situation early warning and evaluation method based on deep learning | |
| CN117318111B (en) | Weather prediction-based dynamic adjustment method and system for light energy storage source | |
| KR102488667B1 (en) | System of predicting photovoltaic power generation using machine learning | |
| US20240054267A1 (en) | Method for planning a layout of a renewable energy site | |
| KR20210066642A (en) | Consulting system through big data based prediction of solar power generation | |
| CN117013527A (en) | Distributed photovoltaic power generation power prediction method | |
| CN112884601A (en) | Electric power system operation risk assessment method based on weather regionalization strategy | |
| Cabezon et al. | Comparison of methods for power curve modelling | |
| CN117669960A (en) | New energy power prediction method based on multivariable meteorological factors | |
| CN117713039B (en) | Power plant power generation control method based on regional new energy power generation prediction | |
| KR102488668B1 (en) | System and method of predicting photovoltaic power generation using machine learning | |
| CN115907268A (en) | Integrated forecast meteorological resource integrated management method and system | |
| CN112761896B (en) | Calculation method, device and computer equipment for improving prediction accuracy of power generation amount of wind power station | |
| KR102497736B1 (en) | System for generating energy for smart farms and method for building the same | |
| KR102264786B1 (en) | Method of selecting optimized wind farm model by using artificial neural network | |
| Cho et al. | Application of Parallel ANN-PSO to Hourly Solar PV Estimation | |
| Buonanno et al. | Combined Machine Learning and weather models for photovoltaic production forecasting in microgrid systems | |
| Özkan et al. | Verification of a real-time wind power monitoring and forecast system for Turkey | |
| CN118174277A (en) | Error analysis and correction-based medium-and-long-term wind-driven photovoltaic output prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |