Method and system for improving power generation prediction accuracy for new energy power stations

Abstract

The present invention discloses a method and system for improving the accuracy of power generation prediction for a new energy power station, and relates to the field of electric power. The method comprises: determining a target new energy power station, obtaining a historical power generation data set of the power station, and obtaining an initial power generation influencing factor; using an initial equipment parameter factor and an initial natural influencing factor to form an initial influencing factor parameter sample set and an initial power generation sample set; constructing an initial power generation predictor; optimizing the initial power generation influencing factor to obtain an optimized power generation influencing factor; constructing an optimized influencing factor parameter sample set and an optimized power generation sample set; optimizing and training the initial power generation predictor to obtain a target power generation predictor; predicting the power generation of the target new energy power station based on the target power generation predictor to obtain a target predicted power generation. The method solves the technical problem of low power generation prediction accuracy in the prior art, and achieves the technical effect of improving the power generation prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the field of electric power, and in particular to a method and system for improving the accuracy of power generation prediction for a new energy power station. Background Art

[0002] As the global demand for renewable energy continues to grow, new energy power stations, as an important source of green energy, are receiving widespread attention. The instability and unpredictability of power generation from new energy power stations, especially solar and wind power stations, has always been a major challenge facing the industry. This not only affects the stable operation of the power grid, but also increases the difficulty of operation and maintenance. Therefore, improving the prediction accuracy of power generation from new energy power stations is crucial for the efficient operation of power stations and the stability of power systems. Power generation from new energy is affected by many factors, including complex factors such as weather conditions, seasonal changes, and equipment status. Existing prediction methods are difficult to fully capture the complex relationships between these influencing factors, resulting in low accuracy of prediction results. Summary of the invention

[0003] The embodiments of the present application provide a method and system for improving the accuracy of power generation prediction for a new energy power station, which solves the technical problem of low power generation prediction accuracy in the prior art.

[0004] In view of the above problems, the embodiments of the present application provide a method and system for improving the accuracy of power generation prediction for a new energy power station.

[0005] In a first aspect of an embodiment of the present application, a method for improving the accuracy of power generation prediction for a new energy power station is provided, the method comprising:

[0006] Determine a target new energy power station, obtain a historical power generation data set of the target new energy power station, and obtain an initial power generation impact factor according to the historical power generation data set of the power station, wherein the initial power generation impact factor includes an initial equipment parameter factor and an initial natural impact factor;

[0007] Based on the historical power generation data set of the power station, using the initial equipment parameter factors and the initial natural impact factors, an initial impact factor parameter sample set and an initial power generation sample set are formed;

[0008] Based on the initial influencing factor parameter sample set and the initial power generation sample set, construct an initial power generation predictor;

[0009] Optimizing the initial power generation influencing factors to obtain optimized power generation influencing factors, wherein the optimized power generation influencing factors include optimized equipment parameter factors and optimized natural influencing factors;

[0010] Based on the historical power generation data set of the power station and in combination with the optimized power generation influencing factors, construct an optimized influencing factor parameter sample set and an optimized power generation sample set;

[0011] According to the optimized influencing factor parameter sample set and the optimized power generation sample set, the initial power generation predictor is optimized and trained to obtain a target power generation predictor;

[0012] Based on the target power generation predictor, the power generation of the target new energy power station is predicted to obtain the target predicted power generation.

[0013] According to a second aspect of an embodiment of the present application, a system for improving the accuracy of power generation prediction for a new energy power station is provided, the system comprising:

[0014] A data acquisition module, the data acquisition module is used to determine a target new energy power station, obtain a historical power generation data set of the target new energy power station, and obtain an initial power generation impact factor according to the historical power generation data set of the power station, wherein the initial power generation impact factor includes an initial equipment parameter factor and an initial natural impact factor;

[0015] A sample set construction module, the sample set construction module is used to construct an initial influencing factor parameter sample set and an initial power generation sample set based on the historical power generation data set of the power station and using the initial equipment parameter factors and the initial natural influencing factors;

[0016] A construction module, the construction module is used to construct an initial power generation predictor based on the initial influencing factor parameter sample set and the initial power generation sample set;

[0017] An optimization module, the optimization module is used to optimize the initial power generation influencing factors to obtain optimized power generation influencing factors, wherein the optimized power generation influencing factors include optimized equipment parameter factors and optimized natural influencing factors;

[0018] A sample set optimization module, the sample set optimization module is used to construct an optimized influencing factor parameter sample set and an optimized power generation sample set based on the power station historical power generation data set and the optimized power generation influencing factor;

[0019] A training module, the training module is used to optimize the initial power generation predictor according to the optimized influencing factor parameter sample set and the optimized power generation sample set to obtain a target power generation predictor;

[0020] A prediction module is used to predict the power generation of the target new energy power station based on the target power generation predictor to obtain the target predicted power generation.

[0021] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0022] First, the target new energy power station is determined, and its historical power generation data set is obtained. According to the historical data set, the initial power generation influencing factors are extracted, including the initial equipment parameter factors and the initial natural influencing factors. Based on the historical power generation data set, the initial influencing factor parameter sample set and the initial power generation sample set are established in combination with the initial equipment parameter factors and the initial natural influencing factors. Using these sample sets, an initial power generation predictor is constructed. Subsequently, the initial power generation influencing factors are optimized to obtain optimized power generation influencing factors, including optimized equipment parameter factors and optimized natural influencing factors. Combined with the historical power generation data set and the optimized influencing factors, an optimized influencing factor parameter sample set and an optimized power generation sample set are constructed. According to the optimized influencing factor parameter sample set and the optimized power generation sample set, the initial power generation predictor is optimized and trained to form a target power generation predictor. Finally, the target power generation predictor is used to predict the power generation of the target new energy power station to obtain the target predicted power generation. The technical problem of low power generation prediction accuracy in the prior art is solved, and the technical effect of improving the power generation prediction accuracy is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 A schematic flow chart of a method for improving the accuracy of power generation prediction for a new energy power station provided in an embodiment of the present application;

[0025] Figure 2 A schematic diagram of the structure of a system for improving the accuracy of power generation prediction in a new energy power station provided in an embodiment of the present application.

[0026] Explanation of the reference numerals: data acquisition module 11, sample set construction module 12, construction module 13, optimization module 14, sample set optimization module 15, training module 16, prediction module 17. DETAILED DESCRIPTION

[0027] The embodiments of the present application solve the technical problem of low power generation prediction accuracy in the prior art by providing a method and system for improving power generation prediction accuracy for a new energy power station.

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0029] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0030] Embodiment 1

[0031] like Figure 1 As shown, the embodiment of the present application provides a method for improving the accuracy of power generation prediction for a new energy power station, wherein the method includes:

[0032] Determine a target new energy power station, obtain a historical power generation data set of the target new energy power station, and obtain an initial power generation impact factor according to the historical power generation data set of the power station, wherein the initial power generation impact factor includes an initial equipment parameter factor and an initial natural impact factor;

[0033] The historical power generation data set of the power plant is obtained from the system of the target new energy power plant. The historical power generation data set of the power plant contains the power generation records of the power plant in the past period of time, which is the basis for analyzing the performance of the power plant and predicting future power generation. After obtaining the historical power generation data set of the power plant, it is necessary to extract and analyze the initial power generation influencing factors from it. The initial power generation influencing factors include the initial equipment parameter factors and the initial natural influencing factors. The initial equipment parameter factors refer to the parameters related to the power plant equipment, which can directly affect the power generation efficiency of the power plant; the initial natural influencing factors refer to the factors related to the natural environmental conditions, which also have a significant impact on the power generation of the power plant.

[0034] Based on the historical power generation data set of the power station, using the initial equipment parameter factors and the initial natural impact factors, an initial impact factor parameter sample set and an initial power generation sample set are formed;

[0035] In order to form the initial influencing factor parameter sample set, specific values ​​related to the initial equipment parameter factors and initial natural influencing factors can be extracted from the historical power generation data set. For example, for equipment parameter factors, the efficiency value of solar panels, the rated power of wind turbines, etc. will be extracted; for natural influencing factors, the average wind speed and solar radiation intensity in the corresponding time period will be extracted. The initial power generation sample set is a collection of actual power generation data corresponding to the initial influencing factor parameter sample set. In other words, for each extracted influencing factor parameter combination, the corresponding power generation record needs to be found.

[0036] Based on the initial influencing factor parameter sample set and the initial power generation sample set, construct an initial power generation predictor;

[0037] An initial power generation predictor is constructed based on the initial influencing factor parameter sample set and the initial power generation sample set. The initial power generation predictor will be able to learn the factors that affect power generation based on the historical data of the power station, and predict future power generation accordingly. Specifically, the initial influencing factor parameter sample set and the initial power generation sample set are divided into training sets and test sets according to a certain ratio, and a prediction model suitable for power generation prediction is selected, such as linear regression, decision tree, random forest, neural network, etc. The selected prediction model is trained using the training set data so that it can learn the relationship between the influencing factors and power generation. The performance of the model is evaluated using the test set data, such as the mean square error to evaluate the accuracy of the prediction results. The model is adjusted and optimized according to the evaluation results until it meets expectations.

[0038] Optimizing the initial power generation influencing factors to obtain optimized power generation influencing factors, wherein the optimized power generation influencing factors include optimized equipment parameter factors and optimized natural influencing factors;

[0039] After constructing the initial power generation predictor, in order to improve the accuracy of the prediction, it is necessary to optimize the initial power generation influencing factors to obtain the optimized power generation influencing factors.

[0040] Furthermore, optimizing the initial power generation influencing factors to obtain optimized power generation influencing factors includes:

[0041] Interacting with the target new energy power station, and building a power station simulation model of the target new energy power station based on the interaction result;

[0042] Extracting the historical power generation data set of the power plant, training a power plant simulation model based on the historical power generation data set of the power plant, fitting the operating performance of the target new energy power plant, and obtaining an influencing factor analyzer;

[0043] The input end of the impact factor analyzer is the initial power generation impact factor, and the output end is the power generation of the power station;

[0044] The optimized power generation influencing factor is obtained based on the influencing factor analyzer.

[0045] Interact with the target new energy power station, and build a power station simulation model of the target new energy power station based on the interaction results. The model includes the characteristics of the new energy equipment, environmental factors, operating parameters, etc., so as to simulate the power generation of the power station. Extract the power generation data set from the historical records of the target new energy power station, including the influencing factor parameters and the corresponding power generation, as training data for training the influencing factor analyzer. Using the trained influencing factor analyzer, input the initial power generation influencing factor into the influencing factor analyzer to obtain the optimized power generation influencing factor.

[0046] Furthermore, obtaining the optimized power generation influencing factors based on the influencing factor analyzer includes:

[0047] Based on the historical power generation data set of the power station, assigning the initial power generation impact factor with the median value of the impact factor, and initializing the impact factor analyzer according to the assignment result;

[0048] Traversing the initial power generation influencing factors, determining a first initial power generation influencing factor, and locking the remaining initial power generation influencing factors except the first initial power generation influencing factor in an influencing factor analyzer;

[0049] Starting the influencing factor analyzer, performing parameter interval disturbance on the first initial power generation influencing factor, and obtaining the power generation variation range;

[0050] Setting a variation range threshold, and when the power generation variation range is greater than or equal to the variation range threshold, identifying the first initial power generation influencing factor as the optimized power generation influencing factor;

[0051] The remaining initial power generation influencing factors are subjected to disturbance analysis in turn to obtain the optimized power generation influencing factors.

[0052] The initial power generation influencing factors are optimized to obtain optimized power generation influencing factors. Specifically, the initial power generation influencing factors are assigned using the median of the influencing factors in the historical power generation data set of the power plant, and the influencing factor analyzer is initialized according to the assignment results. An initial power generation influencing factor is selected as the first initial power generation influencing factor, and it is locked in the influencing factor analyzer, and the remaining influencing factors remain unchanged. The locked first initial power generation influencing factor is subjected to parameter interval perturbation, and the variation range of power generation is obtained by gradually changing the parameter value. A variation range threshold is set to determine whether the first initial power generation influencing factor has a significant impact on power generation. When the power generation variation range is greater than or equal to the threshold, the first initial power generation influencing factor is identified as the optimized power generation influencing factor. Similar perturbation analysis is performed on other initial power generation influencing factors in turn to obtain the optimized power generation influencing factor.

[0053] Based on the historical power generation data set of the power station and in combination with the optimized power generation influencing factors, construct an optimized influencing factor parameter sample set and an optimized power generation sample set;

[0054] The influencing factor parameters in the historical power generation data set are combined with the optimized power generation influencing factors to construct a new data set as the optimized influencing factor parameter sample set. The power generation data corresponding to the optimized influencing factor parameter sample set are extracted from the historical power generation data set to form the optimized power generation sample set.

[0055] Furthermore, based on the power plant historical power generation data set and in combination with the optimized power generation influencing factors, an optimized influencing factor parameter sample set and an optimized power generation sample set are constructed, including:

[0056] Filter the power station historical power generation data set based on the optimized power generation influencing factor to construct an optimized influencing factor parameter sample set;

[0057] The optimization influencing factor parameter sample set includes a plurality of optimization influencing factor parameter samples, each of which has specific parameters of each optimization power generation influencing factor;

[0058] Based on the power plant historical power generation data set, sample power generation is respectively identified for the multiple optimization influencing factor parameter samples to obtain an optimized power generation sample set, wherein each optimization influencing factor parameter sample has a corresponding sample power generation.

[0059] Using the optimized power generation influencing factors as filtering conditions, data related to these influencing factors are screened out from the power plant's historical power generation data set. Based on the screened historical power generation data set, specific parameter samples are constructed for each optimized power generation influencing factor, and these parameter samples will reflect different combinations of influencing factors. For each constructed optimized influencing factor parameter sample, the corresponding sample power generation is calculated using the corresponding data in the historical power generation data set to form an optimized power generation sample set.

[0060] According to the optimized influencing factor parameter sample set and the optimized power generation sample set, the initial power generation predictor is optimized and trained to obtain a target power generation predictor;

[0061] The optimized influencing factor parameter sample set and the optimized power generation sample set are integrated into a training data set, and the integrated data set is divided into a training set and a validation set for model training and evaluation. The initial power generation predictor is optimized and trained using the training set, and the trained initial power generation predictor is validated using the validation set to evaluate its prediction performance. Based on the validation results, the model parameters are adjusted to optimize the performance. After the model training and evaluation are completed, the target power generation predictor will be obtained.

[0062] Based on the target power generation predictor, the power generation of the target new energy power station is predicted to obtain the target predicted power generation.

[0063] The trained target power generation predictor is used to predict the power generation of the target new energy power station, thereby obtaining the target predicted power generation.

[0064] Furthermore, before predicting the power generation of the target new energy power station based on the target power generation predictor, the method includes:

[0065] Constructing a power generation evaluation space based on the optimized influencing factor parameter sample set and the optimized power generation sample set;

[0066] According to the optimized natural impact factor, environmental information of the target new energy power station is collected to obtain an optimized natural impact factor value;

[0067] Mapping the optimized natural impact factor value in the power generation evaluation space, optimizing the power generation, and obtaining the optimal power generation;

[0068] Obtaining optimal equipment parameters in the power generation evaluation space using the optimal power generation as optimized equipment parameter factor values;

[0069] The target new energy power station is reset according to the optimized equipment parameter factor value, and a power generation forecast is performed according to the reset target new energy power station.

[0070] Using the optimized influencing factor parameter sample set and the optimized power generation sample set, a power generation evaluation space is constructed to evaluate the power generation performance under different parameter combinations. Environmental information of the target new energy power station is collected to obtain the optimized natural influencing factor values, such as real-time weather conditions, wind speed, light intensity, etc. The optimized natural influencing factor values ​​are mapped to the power generation evaluation space, and the power generation optimization is performed to obtain the optimal power generation under the current environmental conditions. According to the optimal power generation, the optimal equipment parameter combination is determined in the power generation evaluation space as the optimized equipment parameter factor value. According to the optimized equipment parameter factor value, the equipment parameters of the target new energy power station are reset to make it conform to the optimal configuration. According to the reset target new energy power station configuration, the power generation predictor trained previously is used to predict the power generation to obtain the predicted power generation.

[0071] Furthermore, the method further comprises:

[0072] Setting an accuracy monitoring window, extracting the target predicted power generation based on the accuracy monitoring window, and obtaining a predicted power generation list;

[0073] The predicted power generation list includes multiple target predicted power generation, and each of the multiple target predicted power generation has a prediction period identifier;

[0074] Retrieving the actual power generation of the target new energy power station based on the forecast period identifier, and obtaining a list of actual power generation;

[0075] The target power generation amount predictor is optimized based on the predicted power generation amount list and the actual power generation amount list.

[0076] Set an accuracy monitoring window for extracting the target predicted power generation. The accuracy monitoring window can be a time period for monitoring the accuracy of the predicted power generation. Based on the accuracy monitoring window, extract a predicted power generation list containing multiple target predicted power generation and a prediction period identifier. According to the prediction period identifier, retrieve the actual power generation of the target new energy power station, and obtain the actual power generation list for comparison with the predicted power generation. By comparing the predicted power generation list with the actual power generation list, the accuracy and performance of the target power generation predictor can be evaluated. According to the comparison results, optimize the power generation predictor and adjust the model parameters or algorithm to improve its prediction accuracy and reliability.

[0077] Furthermore, optimizing the target power generation predictor based on the predicted power generation list and the actual power generation list includes:

[0078] Pre-set the prediction qualified warning line;

[0079] According to the predicted power generation list and the actual power generation list, obtaining the power generation prediction qualification rate;

[0080] When the power generation prediction qualification rate triggers the prediction qualification warning line, the power generation influencing factor is optimized and updated again, and the optimization target power generation predictor is updated.

[0081] A prediction qualified warning line is set based on the predicted power generation, and re-optimization is performed when the warning line is triggered according to the power generation prediction qualified rate. Specifically, a standard for qualified power generation prediction is set, namely, the prediction qualified warning line. According to the predicted power generation list and the actual power generation list, the power generation prediction qualified rate is calculated, namely, the proportion of the predictions that meet the prediction qualified standard. When the power generation prediction qualified rate triggers the prediction qualified warning line, that is, the qualified rate is lower than the set standard, the re-optimization process can be started. When the power generation prediction qualified rate triggers the prediction qualified warning line, the power generation influencing factors can be optimized again to adapt to the current environmental conditions and improve the prediction accuracy. By updating and optimizing the power generation influencing factors, the target power generation predictor is further updated and optimized to make it more accurately reflect the power generation situation under the current environmental conditions.

[0082] In summary, the embodiments of the present application have at least the following technical effects:

[0083] First, the target new energy power station is determined, and its historical power generation data set is obtained. According to the historical data set, the initial power generation influencing factors are extracted, including the initial equipment parameter factors and the initial natural influencing factors. Based on the historical power generation data set, the initial influencing factor parameter sample set and the initial power generation sample set are established in combination with the initial equipment parameter factors and the initial natural influencing factors. Using these sample sets, an initial power generation predictor is constructed. Subsequently, the initial power generation influencing factors are optimized to obtain optimized power generation influencing factors, including optimized equipment parameter factors and optimized natural influencing factors. Combined with the historical power generation data set and the optimized influencing factors, an optimized influencing factor parameter sample set and an optimized power generation sample set are constructed. According to the optimized influencing factor parameter sample set and the optimized power generation sample set, the initial power generation predictor is optimized and trained to form a target power generation predictor. Finally, the target power generation predictor is used to predict the power generation of the target new energy power station to obtain the target predicted power generation. The technical problem of low power generation prediction accuracy in the prior art is solved, and the technical effect of improving the power generation prediction accuracy is achieved.

[0084] Embodiment 2

[0085] Based on the same inventive concept as the method for improving the accuracy of power generation prediction for a new energy power station in the aforementioned embodiment, Figure 2 As shown, the present application provides a system for improving the prediction accuracy of power generation of a new energy power station. The system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0086] A data acquisition module 11, the data acquisition module 11 is used to determine a target new energy power station, obtain a historical power generation data set of the target new energy power station, and obtain an initial power generation impact factor according to the historical power generation data set of the power station, wherein the initial power generation impact factor includes an initial equipment parameter factor and an initial natural impact factor;

[0087] A sample set construction module 12, wherein the sample set construction module 12 is used to construct an initial influencing factor parameter sample set and an initial power generation sample set based on the historical power generation data set of the power station and using the initial equipment parameter factors and the initial natural influencing factors;

[0088] A construction module 13, wherein the construction module 13 is used to construct an initial power generation predictor based on the initial influencing factor parameter sample set and the initial power generation sample set;

[0089] An optimization module 14, the optimization module 14 is used to optimize the initial power generation influencing factors to obtain optimized power generation influencing factors, wherein the optimized power generation influencing factors include optimized equipment parameter factors and optimized natural influencing factors;

[0090] A sample set optimization module 15, wherein the sample set optimization module 15 is used to construct an optimized influencing factor parameter sample set and an optimized power generation sample set based on the power station historical power generation data set and in combination with the optimized power generation influencing factor;

[0091] A training module 16, wherein the training module 16 is used to optimize the initial power generation predictor according to the optimized influencing factor parameter sample set and the optimized power generation sample set to obtain a target power generation predictor;

[0092] The prediction module 17 is used to predict the power generation of the target new energy power station based on the target power generation predictor to obtain the target predicted power generation.

[0093] Furthermore, the optimization module 14 is used to execute the following method:

[0094] Interacting with the target new energy power station, and building a power station simulation model of the target new energy power station based on the interaction result;

[0095] Extracting the historical power generation data set of the power plant, training a power plant simulation model based on the historical power generation data set of the power plant, fitting the operating performance of the target new energy power plant, and obtaining an influencing factor analyzer;

[0096] The input end of the impact factor analyzer is the initial power generation impact factor, and the output end is the power generation of the power station;

[0097] The optimized power generation influencing factor is obtained based on the influencing factor analyzer.

[0098] Furthermore, the optimization module 14 is used to execute the following method:

[0099] Based on the historical power generation data set of the power station, assigning the initial power generation impact factor with the median value of the impact factor, and initializing the impact factor analyzer according to the assignment result;

[0100] Traversing the initial power generation influencing factors, determining a first initial power generation influencing factor, and locking the remaining initial power generation influencing factors except the first initial power generation influencing factor in an influencing factor analyzer;

[0101] Starting the influencing factor analyzer, performing parameter interval disturbance on the first initial power generation influencing factor, and obtaining the power generation variation range;

[0102] Setting a variation range threshold, and when the power generation variation range is greater than or equal to the variation range threshold, identifying the first initial power generation influencing factor as the optimized power generation influencing factor;

[0103] The remaining initial power generation influencing factors are subjected to disturbance analysis in turn to obtain the optimized power generation influencing factors.

[0104] Furthermore, the sample set optimization module 15 is used to perform the following method:

[0105] Filter the power station historical power generation data set based on the optimized power generation influencing factor to construct an optimized influencing factor parameter sample set;

[0106] The optimization influencing factor parameter sample set includes a plurality of optimization influencing factor parameter samples, each of which has specific parameters of each optimization power generation influencing factor;

[0107] Based on the power plant historical power generation data set, sample power generation is respectively identified for the multiple optimization influencing factor parameter samples to obtain an optimized power generation sample set, wherein each optimization influencing factor parameter sample has a corresponding sample power generation.

[0108] Furthermore, the prediction module 17 is used to perform the following method:

[0109] Constructing a power generation evaluation space based on the optimized influencing factor parameter sample set and the optimized power generation sample set;

[0110] According to the optimized natural impact factor, environmental information of the target new energy power station is collected to obtain an optimized natural impact factor value;

[0111] Mapping the optimized natural impact factor value in the power generation evaluation space, optimizing the power generation, and obtaining the optimal power generation;

[0112] Obtaining optimal equipment parameters in the power generation evaluation space using the optimal power generation as optimized equipment parameter factor values;

[0113] The target new energy power station is reset according to the optimized equipment parameter factor value, and a power generation forecast is performed according to the reset target new energy power station.

[0114] Furthermore, the prediction module 17 is used to perform the following method:

[0115] Setting an accuracy monitoring window, extracting the target predicted power generation based on the accuracy monitoring window, and obtaining a predicted power generation list;

[0116] The predicted power generation list includes multiple target predicted power generation, and each of the multiple target predicted power generation has a prediction period identifier;

[0117] Retrieving the actual power generation of the target new energy power station based on the forecast period identifier, and obtaining a list of actual power generation;

[0118] The target power generation amount predictor is optimized based on the predicted power generation amount list and the actual power generation amount list.

[0119] Furthermore, the prediction module 17 is used to perform the following method:

[0120] Pre-set the prediction qualified warning line;

[0121] According to the predicted power generation list and the actual power generation list, obtaining the power generation prediction qualification rate;

[0122] When the power generation prediction qualification rate triggers the prediction qualification warning line, the power generation influencing factor is optimized and updated again, and the optimization target power generation predictor is updated.

[0123] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0124] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0125] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for improving the accuracy of power generation prediction for a new energy power station, characterized in that: The method comprises: Determine a target new energy power station, obtain a historical power generation data set of the target new energy power station, and obtain an initial power generation impact factor according to the historical power generation data set of the power station, wherein the initial power generation impact factor includes an initial equipment parameter factor and an initial natural impact factor; Based on the historical power generation data set of the power station, using the initial equipment parameter factors and the initial natural impact factors, an initial impact factor parameter sample set and an initial power generation sample set are formed; Based on the initial influencing factor parameter sample set and the initial power generation sample set, construct an initial power generation predictor; Optimizing the initial power generation influencing factors to obtain optimized power generation influencing factors, wherein the optimized power generation influencing factors include optimized equipment parameter factors and optimized natural influencing factors; Based on the historical power generation data set of the power station and in combination with the optimized power generation influencing factors, construct an optimized influencing factor parameter sample set and an optimized power generation sample set; According to the optimized influencing factor parameter sample set and the optimized power generation sample set, the initial power generation predictor is optimized and trained to obtain a target power generation predictor; Based on the target power generation predictor, the target new energy power station is predicted to obtain the target predicted power generation; Optimizing the initial power generation influencing factors to obtain optimized power generation influencing factors includes: Interacting with the target new energy power station, and building a power station simulation model of the target new energy power station based on the interaction result; Extracting the historical power generation data set of the power plant, training a power plant simulation model based on the historical power generation data set of the power plant, fitting the operating performance of the target new energy power plant, and obtaining an influencing factor analyzer; The input end of the impact factor analyzer is the initial power generation impact factor, and the output end is the power generation of the power station; Obtaining the optimized power generation influencing factor based on the influencing factor analyzer; Obtaining the optimized power generation influencing factors based on the influencing factor analyzer includes: Based on the historical power generation data set of the power station, assigning the initial power generation impact factor with the median value of the impact factor, and initializing the impact factor analyzer according to the assignment result; Traversing the initial power generation influencing factors, determining a first initial power generation influencing factor, and locking the remaining initial power generation influencing factors except the first initial power generation influencing factor in an influencing factor analyzer; Starting the influencing factor analyzer, performing parameter interval disturbance on the first initial power generation influencing factor, and obtaining the power generation variation range; Setting a variation range threshold, and when the power generation variation range is greater than or equal to the variation range threshold, identifying the first initial power generation influencing factor as the optimized power generation influencing factor; The remaining initial power generation influencing factors are subjected to disturbance analysis in turn to obtain the optimized power generation influencing factors.

2. The method according to claim 1, characterized in that: Based on the historical power generation data set of the power station and in combination with the optimized power generation influencing factors, an optimized influencing factor parameter sample set and an optimized power generation sample set are constructed, including: Filter the power station historical power generation data set based on the optimized power generation influencing factor to construct an optimized influencing factor parameter sample set; The optimization influencing factor parameter sample set includes a plurality of optimization influencing factor parameter samples, each of which has specific parameters of each optimization power generation influencing factor; Based on the power plant historical power generation data set, sample power generation is respectively identified for the multiple optimization influencing factor parameter samples to obtain an optimized power generation sample set, wherein each optimization influencing factor parameter sample has a corresponding sample power generation.

3. The method according to claim 1, characterized in that Before predicting the power generation of the target new energy power station based on the target power generation predictor, the method includes: Constructing a power generation evaluation space based on the optimized influencing factor parameter sample set and the optimized power generation sample set; According to the optimized natural impact factor, environmental information of the target new energy power station is collected to obtain an optimized natural impact factor value; Mapping the optimized natural impact factor value in the power generation evaluation space, optimizing the power generation, and obtaining the optimal power generation; Obtaining optimal equipment parameters in the power generation evaluation space using the optimal power generation as optimized equipment parameter factor values; The target new energy power station is reset according to the optimized equipment parameter factor value, and a power generation forecast is performed according to the reset target new energy power station.

4. The method according to claim 1, characterized in that The method further comprises: Setting an accuracy monitoring window, extracting the target predicted power generation based on the accuracy monitoring window, and obtaining a predicted power generation list; The predicted power generation list includes multiple target predicted power generation, and each of the multiple target predicted power generation has a prediction period identifier; Retrieving the actual power generation of the target new energy power station based on the forecast period identifier, and obtaining a list of actual power generation; The target power generation amount predictor is optimized based on the predicted power generation amount list and the actual power generation amount list.

5. The method according to claim 4, characterized in that Optimizing the target power generation predictor based on the predicted power generation list and the actual power generation list includes: Pre-set the prediction qualified warning line; According to the predicted power generation list and the actual power generation list, obtaining the power generation prediction qualification rate; When the power generation prediction qualification rate triggers the prediction qualification warning line, the power generation influencing factor is optimized and updated again, and the optimization target power generation predictor is updated.

6. A system for improving the prediction accuracy of power generation in a new energy power station, characterized in that: A method for improving the prediction accuracy of power generation for a new energy power station according to any one of claims 1 to 5, the system comprising: A data acquisition module, the data acquisition module is used to determine a target new energy power station, obtain a historical power generation data set of the target new energy power station, and obtain an initial power generation impact factor according to the historical power generation data set of the power station, wherein the initial power generation impact factor includes an initial equipment parameter factor and an initial natural impact factor; A sample set construction module, the sample set construction module is used to construct an initial influencing factor parameter sample set and an initial power generation sample set based on the historical power generation data set of the power station and using the initial equipment parameter factors and the initial natural influencing factors; A construction module, the construction module is used to construct an initial power generation predictor based on the initial influencing factor parameter sample set and the initial power generation sample set; An optimization module, the optimization module is used to optimize the initial power generation influencing factors to obtain optimized power generation influencing factors, wherein the optimized power generation influencing factors include optimized equipment parameter factors and optimized natural influencing factors; A sample set optimization module, the sample set optimization module is used to construct an optimized influencing factor parameter sample set and an optimized power generation sample set based on the power station historical power generation data set and the optimized power generation influencing factor; A training module, the training module is used to optimize the initial power generation predictor according to the optimized influencing factor parameter sample set and the optimized power generation sample set to obtain a target power generation predictor; A prediction module is used to predict the power generation of the target new energy power station based on the target power generation predictor to obtain the target predicted power generation.

Images