SA-GAN-based power market new energy joint prediction method, system and device, and storage medium

Abstract

The invention belongs to the technical field of new energy prediction, and discloses a power market new energy joint prediction method and system based on SA-GAN, and the method comprises the steps: obtaining the historical data of a power market; respectively adding the attention mechanism into a generator network and a discriminator network in the generative adversarial network, and establishing an attention-generative adversarial prediction model; inputting historical data of the electricity market into the attention-generative adversarial prediction model for training, and continuously optimizing parameters of the attention-generative adversarial prediction model through adversarial learning of a generator and a discriminator; and performing joint prediction by using the trained and optimized attention-generative adversarial prediction model to obtain new energy future power generation data. According to the method, the limitation of a traditional method on complex and nonlinear data processing is effectively solved, joint prediction of multivariable data is realized, interaction among variables is fully considered, and a more comprehensive and accurate prediction result is generated.

Description

Technical Field

[0001] The present invention relates to the field of new energy prediction technology, and in particular to a SA-GAN-based new energy joint prediction method and system for the power market. Background Art

[0002] With the development of the global energy internet, the operation mechanism of the power market has become increasingly complex. The behavior of market participants and the uncertainty of renewable energy generation have increased the difficulty of power system operation. The amount of renewable energy generation in the power market is a key parameter for power system dispatch and market operation. Accurate prediction of these data is essential to ensure the stable operation and economic benefits of the power system. Traditional power market forecasting methods are mostly based on statistics and time series analysis, such as the autoregressive moving average model (ARIMA) and the generalized autoregressive conditional heteroskedasticity model (GARCH). These methods perform well when dealing with linear relationships and stable time series, but their forecasting accuracy and adaptability are often insufficient when faced with nonlinear and highly volatile data in the power market. In addition, traditional methods can usually only handle single-variable forecasts, and it is difficult to consider the mutual influence of multiple variables at the same time, which limits the improvement of forecasting results.

[0003] With the improvement of computing power and the increase of data volume, deep learning technology has been widely used in renewable energy forecasting in the power market. Neural network-based forecasting methods, such as long short-term memory networks (LSTM) and convolutional neural networks (CNN), can capture complex nonlinear relationships in data and have achieved good results in single-variable forecasting. However, most of these methods focus on single-variable forecasting and it is difficult to achieve joint forecasting of multivariable renewable energy data such as wind and light, resulting in limited comprehensiveness and accuracy of forecasting results. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a new energy joint prediction method for the power market based on SA-GAN to solve the problem of insufficient joint prediction accuracy of renewable energy power generation in the power market.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for joint prediction of new energy in the power market based on SA-GAN, comprising:

[0008] Obtain historical electricity market data and pre-process it;

[0009] The attention mechanism is added to the generator network and the discriminator network in the generative adversarial network respectively to establish an attention-generative adversarial prediction model;

[0010] Inputting the electricity market historical data into the attention-generation adversarial prediction model for training, and continuously optimizing the parameters of the attention-generation adversarial prediction model through adversarial learning between the generator and the discriminator;

[0011] The historical data of the electricity market is jointly predicted using the trained and optimized attention-generation adversarial prediction model to obtain future power generation data of new energy.

[0012] As a preferred solution of the SA-GAN-based power market new energy joint prediction method described in the present invention, the generator network that adds the attention mechanism to the generative adversarial network includes:

[0013] The generator network adopts a deep residual network structure, combined with a self-attention layer and a fully connected layer, and introduces a dynamic weight adjustment mechanism to adaptively adjust the depth and width of the deep residual network structure according to the distribution characteristics of historical data in the power market;

[0014] The number of self-attention layer heads of the generator network is set to 8, the dimension of the attention head is set to 64, the number of fully connected layers is set to 3, the number of neurons in each layer is set to 256, 128 and 64, and the activation function is ReLU.

[0015] As a preferred solution of the SA-GAN-based power market new energy joint prediction method described in the present invention, the discriminator network in which the attention mechanism is added to the generative adversarial network includes:

[0016] The discriminator network includes multi-scale convolutional layers and self-attention layers to capture micro- and macro-patterns of historical power market data through multi-scale feature extraction;

[0017] The number of heads of the self-attention layer of the discriminator network is set to 8, the dimension of the attention head is set to 64, the convolution kernel size of the convolution layer is set to 3×3, and the number of convolution kernels is set to 32, 64, and 128.

[0018] As a preferred solution of the SA-GAN-based power market new energy joint prediction method of the present invention, wherein: inputting the power market historical data into the attention-generation adversarial prediction model for training includes:

[0019] Initialize the parameters of the generator and the discriminator. In each training iteration, use the historical data of the electricity market to train the discriminator network so that the discriminator network can distinguish the historical data of the electricity market from the data samples generated by the generator network.

[0020] After training the discriminator network with the historical data of the electricity market, the data samples generated by the generator network are input into the discriminator network together with the historical data of the electricity market, and the parameters of the generator network are updated according to the recognition results of the discriminator network.

[0021] As a preferred solution of the SA-GAN-based power market new energy joint forecasting method described in the present invention, it also includes:

[0022] During the training process of the attention-generation adversarial prediction model, an adaptive learning rate adjustment strategy is adopted, and the quantum heuristic algorithm is combined to optimize the parameters of the attention-generation adversarial prediction model;

[0023] The introduction of sparse connections reduces the complexity of the attention-generation adversarial prediction model and improves the generalization ability.

[0024] As a preferred solution of the SA-GAN-based power market new energy joint prediction method described in the present invention, the future power generation data of new energy includes:

[0025] The predicted future power generation data of new energy is evaluated, and the mean square error and mean absolute error indicators are used to evaluate the performance of the attention-generative adversarial prediction model. According to the evaluation results, the attention-generative adversarial prediction model is optimized and adjusted.

[0026] As a preferred solution of the SA-GAN-based power market new energy joint prediction method described in the present invention, the optimization and adjustment of the attention-generation adversarial prediction model includes:

[0027] Analyze the error distribution in the future power generation data of new energy and obtain the error analysis results;

[0028] According to the error analysis results, adjusting the structure and parameters of the attention-generation adversarial prediction model to reduce the prediction error;

[0029] The adjustment method is a trial-and-error method, which uses the trial-and-error method to try possible combinations multiple times to obtain the optimal adjustment solution for the attention-generation adversarial prediction model;

[0030] The adjusted attention-generation adversarial prediction model is retrained until the prediction results reach the expected accuracy.

[0031] In a second aspect, the present invention provides a system for joint prediction of new energy in the power market based on SA-GAN, comprising:

[0032] A data acquisition module is used to acquire and preprocess the historical data of the electricity market; a model prediction module is used to add the attention mechanism to the generator network and the discriminator network in the generative adversarial network respectively, and establish an attention-generation adversarial prediction model; an optimization module is used to input the historical data of the electricity market into the attention-generation adversarial prediction model for training, and continuously optimize the parameters of the attention-generation adversarial prediction model through adversarial learning of the generator and the discriminator; a joint prediction module is used to jointly predict the historical data of the electricity market using the attention-generation adversarial prediction model after training and optimization, so as to obtain future power generation data of new energy.

[0033] In a third aspect, the present invention provides an electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the SA-GAN-based electricity market new energy joint prediction method are implemented.

[0034] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the SA-GAN-based new energy joint forecasting method for the electricity market.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. The present invention significantly improves the prediction accuracy of renewable energy data in the power market by introducing the self-attention mechanism. The self-attention mechanism can capture the global characteristics and long-distance dependencies of the data in the prediction model, so that the model not only focuses on local features, but also understands the intrinsic connection of the entire data sequence. This mechanism effectively solves the limitations of traditional methods in processing complex and nonlinear data. Especially in the power market, data such as renewable energy generation usually has significant temporal and spatial correlations. The self-attention mechanism can capture these correlations more accurately and improve the overall prediction performance of the model.

[0037] 2. Traditional prediction methods usually focus on the prediction of a single variable, while ignoring the interactions and influences between different variables. The present invention combines self-attention with generative adversarial networks (SA-GAN) to achieve joint prediction of multivariate data such as different renewable energy power generation. By predicting multiple variables simultaneously, the model can fully consider the relationship between the variables, thereby generating more comprehensive and accurate prediction results. This multivariate joint prediction not only improves the prediction accuracy of a single variable, but also better reflects the comprehensive impact of various factors in the power market, which is conducive to the intelligent dispatch and optimized operation of the power system.

[0038] 3. Generative Adversarial Networks (GAN) can effectively learn and simulate the complex characteristics of data distribution through adversarial training of generators and discriminators. The present invention combines the self-attention mechanism to enable the generator to pay attention to the global information of the data when generating samples, thereby generating samples that are closer to the real data distribution. This method not only improves the performance of the model on training data, but also enhances the generalization ability of the model on unknown data. Specifically, the generative adversarial network continuously adjusts the parameters of the generator and the discriminator so that the generated prediction samples can maintain a high degree of credibility and accuracy in various power market environments, and is suitable for different power market scenarios.

[0039] 4. The data in the electricity market usually has large volatility and uncertainty. When faced with these complex data, traditional prediction methods are prone to large fluctuations in prediction results. The present invention uses the design of a self-attention generative adversarial network to enable the model to converge more stably during the training process, thereby improving the stability of the prediction results. The self-attention mechanism calculates the dependencies between different positions, enabling the model to better handle noise and outliers in the data and reduce prediction errors. In addition, through the adversarial learning of the generator and the discriminator, the model can maintain a high level of robustness when faced with new data, reducing the prediction uncertainty caused by data fluctuations, thereby providing more stable and reliable prediction results for the scheduling and optimization of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0041] Figure 1 It is a schematic diagram of the overall process of the SA-GAN-based new energy joint prediction method for the power market according to an embodiment of the present invention; Figure 2 A schematic diagram of a framework of a SA-GAN-based new energy joint forecasting system for a power market according to an embodiment of the present invention; Figure 3 This is a practical application diagram of a SA-GAN-based new energy joint forecasting method for the power market according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0043] Example 1, reference Figure 1~Figure 2 , which is an embodiment of the present invention, provides a new energy joint prediction method for the power market based on SA-GAN, including:

[0044] S100: Obtain historical electricity market data and perform preprocessing.

[0045] In the embodiment of the present application, the electricity market historical data includes data such as installed capacity, weather conditions, and renewable energy power generation.

[0046] After obtaining the historical data of the electricity market, preprocessing is performed, including data cleaning, missing value filling, data normalization and other operations to ensure the quality and consistency of the data.

[0047] S102: Add the attention mechanism to the generator network and the discriminator network in the generative adversarial network respectively to establish an attention-generative adversarial prediction model.

[0048] Preferably, the generator network adopts a deep residual network structure, combines a self-attention layer and a fully connected layer, and introduces a dynamic weight adjustment mechanism to adaptively adjust the depth and width of the deep residual network structure according to the distribution characteristics of historical data in the electricity market.

[0049] Specifically, the generator network is initialized and the parameters are set as follows: the number of self-attention layer heads of the generator network is set to 8, the dimension of the attention head is set to 64, the number of fully connected layers is set to 3, the number of neurons in each layer is set to 256, 128 and 64, and the activation function is ReLU.

[0050] The deep residual network structure is constructed through residual blocks. Each residual block contains two convolutional layers and passes the input directly to the output through residual connections, thereby retaining the original information and allowing gradient information to flow, thereby alleviating the gradient vanishing problem in deep networks.

[0051] After each residual block of the deep residual network, a self-attention layer is integrated, which assigns weights to each feature by calculating the correlation between the input features, so that the generator can capture and emphasize the features in the data that have a greater impact on the prediction task, thereby improving the model's understanding of the historical data patterns of the electricity market.

[0052] The output of the self-attention layer is then fed into the fully connected layer, which is responsible for mapping the features to a higher or lower dimensional space, performing nonlinear transformations, further refining the features, and providing the final feature representation for the output of the generator network.

[0053] In an embodiment of the present application, in order to enable the generator network to adaptively adjust according to the distribution characteristics of historical electricity market data, a dynamic weight adjustment mechanism is introduced to adaptively adjust the learning rate, number of network layers, and number of neurons to better adapt to data characteristics and improve prediction performance.

[0054] Preferably, the discriminator network includes multi-scale convolutional layers and self-attention layers to capture micro and macro patterns of historical electricity market data through multi-scale feature extraction.

[0055] In an embodiment of the present application, the number of heads of the self-attention layer of the discriminator network is set to 8, the dimension of the attention head is set to 64, the convolution kernel size of the convolution layer is set to 3×3, and the number of convolution kernels is set to 32, 64 and 128.

[0056] Specifically, the discriminator receives data generated by the generator, processes the data in parallel using multi-scale convolutional layers, and analyzes the data from multiple angles by setting different numbers of convolution kernels 32, 64, and 128 to capture micro and macro patterns; each convolution layer uses a 3×3 convolution kernel, which is specially designed to capture the fine features of the data.

[0057] The self-attention layer then processes the output of the multi-scale convolutional layer. Each self-attention layer contains 8 heads, each with a dimension of 64, to calculate the correlation between features and assign weights. The self-attention layer can identify and emphasize the features that are most critical to the discrimination task, thereby improving the discrimination accuracy; the output of the self-attention layer is input into the fully connected layer for nonlinear transformation to extract the features that are critical to the discrimination decision.

[0058] The discriminator network makes judgments based on the integrated features and outputs a similarity score between the generated data and the real data. The similarity score is used to guide the optimization of the generator network. Through adversarial learning, the parameters of the generator network are continuously adjusted to generate more realistic data samples.

[0059] It should be noted that in the attention-generation adversarial prediction model of the present invention, the design of the discriminator network integrates multi-scale convolutional layers and self-attention layers to enhance the in-depth understanding and prediction capabilities of the historical data of the power market. By adopting multi-scale convolutional layers, the discriminator can process features of different scales in parallel, analyze data from multiple angles using different numbers of convolutional kernels (32, 64, 128), and effectively capture the micro details and macro trends of the historical data of the power market. Each convolutional layer uses a 3×3 convolutional kernel, which is specially designed to capture the fine features of the data and enhance the understanding of complex data structures.

[0060] The integration of self-attention layers further enhances the performance of the discriminator. Each self-attention layer contains 8 heads, each with a dimension of 64. By calculating the correlation between features and assigning weights, the discriminator can identify and emphasize the features that are most critical to the discrimination task, thereby significantly improving the discrimination accuracy. The fully connected layer then performs a nonlinear transformation on the output of the self-attention layer to extract the features that are critical to the discrimination decision.

[0061] In addition, the dynamic weight adjustment mechanism of the discriminator network allows the network to adaptively adjust according to the distribution characteristics of the historical data of the power market, including the learning rate, the number of network layers, the number of neurons, etc., to better adapt to the data characteristics and improve the prediction performance. This design enables the discriminator network to accurately evaluate the similarity between the data samples generated by the generator and the real data, thereby continuously optimizing the parameters of the generator network through adversarial learning and generating more realistic data samples.

[0062] It should also be noted that traditional discriminators cannot fully capture the multi-scale characteristics of data and may have limitations when processing complex data structures; the present invention improves the discriminator's understanding and prediction capabilities of historical electricity market data through the combination of multi-scale convolutional layers and self-attention layers, as well as a dynamic weight adjustment mechanism, thereby improving the accuracy and reliability of renewable energy power generation predictions.

[0063] S104: Input the historical data of the electricity market into the attention-generation adversarial prediction model for training, and continuously optimize the parameters of the attention-generation adversarial prediction model through adversarial learning between the generator and the discriminator.

[0064] Preferably, the parameters of the generator and the discriminator are initialized, and in each training iteration, the discriminator network is trained using the electricity market historical data so that the discriminator network can distinguish between the electricity market historical data and the data samples generated by the generator network.

[0065] In this embodiment of the present application, the number of training rounds is set to 10,000 rounds, and the batch size used in each round is set to 64.

[0066] Preferably, after the discriminator network is trained using the electricity market historical data, the data samples generated by the generator network are input into the discriminator network together with the electricity market historical data, and the parameters of the generator network are updated according to the recognition results of the discriminator network.

[0067] Preferably, during the training process of the attention-generation adversarial prediction model, an adaptive learning rate adjustment strategy is adopted, and a quantum heuristic algorithm is combined to optimize the attention-generation adversarial prediction model parameters.

[0068] In an embodiment of the present application, in order to further optimize the model parameters, a quantum heuristic algorithm is combined to search for a better parameter combination, such as a quantum particle swarm optimization algorithm or a quantum genetic algorithm.

[0069] Quantum-inspired algorithms exploit the parallelism and randomness of quantum computing to quickly find better solutions in a larger search space.

[0070] Specifically, the optimization process is as follows: set the initial learning rate and other hyperparameters; in each round of iteration, use the adaptive learning rate adjustment strategy to update the learning rate and model parameters according to the current gradient information and other training states, including loss value, accuracy, etc.; suspend the adaptive learning rate adjustment in the iteration cycle, and use the quantum heuristic algorithm to perform a global search for the model parameters; use the parameter combination found by the quantum heuristic algorithm as a new starting point, and continue to use the adaptive learning rate adjustment strategy for local optimization.

[0071] In the embodiment of the present application, the search process can be expressed as: , in, is a better parameter combination found by the quantum heuristic algorithm, is the current parameter, is the current learning rate, is the training data.

[0072] The parameter update formula is expressed as: , in, represents the model parameters at the t+1th iteration, Adam represents the update rule of the Adam optimizer, represents the gradient at the tth iteration, represents the learning rate at the tth iteration, is a tuning factor that controls the degree to which the parameter combination found by the quantum heuristic algorithm affects the current parameter update.

[0073] In an embodiment of the present application, when the attention-generation adversarial prediction model is initialized, the learning rate is set to 0.0002, β1 is set to 0.5, and β2 is set to 0.999.

[0074] Preferably, sparse connections are introduced to reduce the complexity of the attention-generation adversarial prediction model and improve the generalization ability.

[0075] In the attention-generation adversarial prediction model, the present invention preferably introduces a strategy of sparse connections, aiming to reduce the complexity of the model and improve the generalization ability; sparse connections make the network structure more streamlined and reduce redundant parameters by setting some connections to zero in the model, thereby reducing computing costs and storage requirements.

[0076] Furthermore, in the generator and the discriminator, the present invention adopts a sparse network layer, and achieves effective control of the complexity of the model by adjusting the connection sparsity of the network layer.

[0077] In the training process of the attention-generation adversarial prediction model, the parameters of the generator and discriminator were first initialized, and the number of training rounds was set to 10,000, with a batch size of 64 used in each round. At the beginning of training, the discriminator network was trained using historical electricity market data so that it could distinguish between historical electricity market data and data samples generated by the generator network. Subsequently, the data samples generated by the generator network were input into the discriminator network together with the historical electricity market data, and the parameters of the generator network were updated according to the recognition results of the discriminator network. In order to further optimize the model parameters, quantum heuristic algorithms, such as quantum particle swarm optimization or quantum genetic algorithm, were combined to search for better parameter combinations.

[0078] In each round of iteration, the learning rate and model parameters are updated using an adaptive learning rate adjustment strategy (such as the Adam optimizer) based on the current gradient information and other training states (such as loss value, accuracy, etc.). In a specific iteration cycle, the adaptive learning rate adjustment is suspended, and a quantum heuristic algorithm is used to perform a global search for the model parameters, and the found parameter combination is used as a new starting point to continue local optimization. Through this process, the parameters of the attention-generation adversarial prediction model are continuously optimized to improve its prediction performance.

[0079] Through the above training process, the attention-generation adversarial prediction model can make full use of the information in the historical data of the electricity market, and continuously optimize the model parameters through the adversarial learning of the generator and the discriminator, thereby improving the prediction accuracy of the electricity market data. The combination of quantum heuristic algorithm for parameter optimization further improves the search ability and optimization efficiency of the model, enabling the model to quickly find a better parameter combination in a larger search space. In addition, the introduction of sparse connections reduces the complexity of the model and improves the generalization ability of the model, enabling it to better adapt to new data and tasks. Finally, the trained attention-generation adversarial prediction model can accurately predict the changing trend of the electricity market and provide strong support for new energy power generation forecasting, electricity market scheduling, etc.

[0080] S106: Use the trained and optimized attention-generation adversarial prediction model to jointly predict the historical data of the electricity market and obtain future power generation data of new energy.

[0081] Preferably, the predicted future power generation data of new energy is evaluated, and the mean square error and mean absolute error indicators are used to evaluate the performance of the attention-generative adversarial prediction model. According to the evaluation results, the attention-generative adversarial prediction model is optimized and adjusted.

[0082] The formulas for mean square error and average error are expressed as: , , in, is the sample size, is the true value, is the predicted value;

[0083] Preferably, the error distribution in the future power generation data of new energy is analyzed to obtain the error analysis results; according to the error analysis results, the structure and parameters of the attention-generation adversarial prediction model are adjusted to reduce the prediction error.

[0084] Preferably, the adjustment method is a trial-and-error method, which uses the trial-and-error method to try possible combinations multiple times to obtain the optimal adjustment solution for the attention-generation adversarial prediction model.

[0085] The adjusted attention-generation adversarial prediction model is retrained until the prediction results reach the expected accuracy.

[0086] In another possible embodiment, in order to evaluate the performance of the attention-generation adversarial prediction model, R² (coefficient of determination) can be used as an additional evaluation indicator. The R² indicator not only considers the difference between the predicted value and the true value, but also measures the degree of improvement of the model relative to the simple average prediction, thereby providing a deeper insight into the model's prediction ability; at the same time, in addition to the traditional trial and error method, the model adjustment method can also introduce gradient descent-based optimization algorithms, such as Adam, RMSprop, etc. These algorithms can automatically adjust the learning rate according to the performance of the model during training, speed up the convergence speed, and may find better model parameters. The present invention does not strictly limit the specific evaluation indicators and adjustment methods, and encourages flexible selection according to actual needs and data characteristics to achieve the best prediction effect and model performance.

[0087] It should be noted that the present invention realizes the joint prediction of historical data of the electricity market by training the optimized attention-generation adversarial prediction model, effectively obtains the future power generation data of new energy, and provides accurate data support for energy planning and management. By adopting mean square error and mean absolute error as evaluation indicators, the present invention can comprehensively evaluate the performance of the prediction model, and optimize and adjust the model in a targeted manner accordingly, significantly improving the prediction accuracy. Furthermore, through the analysis of the distribution of prediction errors, the present invention can deeply understand the shortcomings of the model performance, and optimize the model structure and parameters through flexible adjustment methods such as trial and error, effectively reducing the prediction error. Finally, after repeated training and adjustment, the present invention ensures that the prediction results reach the expected accuracy, brings better technical effects to the prediction and management of new energy power generation, and improves energy utilization efficiency and economic benefits.

[0088] The above is a schematic scheme of a method for joint prediction of new energy in the power market based on SA-GAN in this embodiment. It should be noted that the technical scheme of the system for joint prediction of new energy in the power market based on SA-GAN and the technical scheme of the method for joint prediction of new energy in the power market based on SA-GAN above belong to the same concept. For the details not described in detail in the technical scheme of the system for joint prediction of new energy in the power market based on SA-GAN in this embodiment, please refer to the description of the technical scheme of the method for joint prediction of new energy in the power market based on SA-GAN above.

[0089] In this embodiment, the SA-GAN-based power market new energy joint prediction system is as follows: Figure 2 As shown, including:

[0090] The data acquisition module 100 is used to acquire historical data of the power market and perform preprocessing.

[0091] The model prediction module 200 is used to add the attention mechanism to the generator network and the discriminator network in the generative adversarial network respectively, and establish an attention-generative adversarial prediction model.

[0092] The optimization module 300 is used to input the historical data of the electricity market into the attention-generation adversarial prediction model for training, and continuously optimize the parameters of the attention-generation adversarial prediction model through adversarial learning between the generator and the discriminator.

[0093] The joint prediction module 400 is used to perform joint prediction on the historical data of the electricity market using the trained and optimized attention-generative adversarial prediction model to obtain future power generation data of new energy.

[0094] This embodiment also provides an electronic device, which is applicable to the case of joint prediction of new energy in the power market based on SA-GAN, including:

[0095] A memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the SA-GAN-based new energy joint prediction method for the power market as proposed in the above embodiment.

[0096] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for jointly predicting new energy in the power market based on SA-GAN as proposed in the above embodiment is implemented.

[0097] The storage medium proposed in this embodiment and the method for implementing the joint prediction of new energy in the power market based on SA-GAN proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0098] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0099] Example 2, reference Figure 3 ,This embodiment provides a new energy joint prediction method for the ,power market based on SA-GAN. In order to verify its beneficial ,effects, the comparison results of several schemes are provided.

[0100] Comprehensive historical data of the power market was collected, covering key information such as installed capacity, weather changes, and renewable energy generation. Through the data cleaning process, outliers and noise were removed, and interpolation or mean filling methods were cleverly used to repair missing values ​​to ensure the integrity and accuracy of the data. Furthermore, the data was normalized to the [0, 1] interval, effectively eliminating the potential impact of different dimensions on data analysis, laying a solid foundation for the construction of subsequent models.

[0101] The self-attention generative adversarial network of the present invention is applied to make predictions, and the performance of different models in the prediction of renewable energy power generation is obtained through comparative experiments with traditional time series prediction methods, such as the ARIMA model and the standard generative adversarial network.

[0102] MSE and MAE are used as preliminary evaluation indicators to comprehensively evaluate the prediction performance of different models; in order to more intuitively show the prediction quality, the calculation method of prediction accuracy is defined, that is, whether the prediction is correct is determined based on whether the relative error between the predicted value and the actual value is within the set threshold. According to the experiment. Compared with traditional time series prediction methods, such as ARIMA model and standard generative adversarial network, the method of the present invention has achieved a significant improvement in the prediction accuracy of photovoltaic power generation, wind power generation and other renewable energy types.

[0103] Specifically, the accuracy of the method in the photovoltaic power generation forecast reached 83.5%, the wind power generation forecast reached 73.8%, and the other energy forecast reached 75.4%, with an average forecast accuracy of 77.6%. This result shows that the method in the present invention effectively improves the ability to understand and predict complex power market data through its unique self-attention mechanism and the combination of generative adversarial networks.

[0104] like Figure 3 As shown in the figure, by predicting the output of new energy in the future, the power sales company can adjust the day-ahead declaration strategy. When the new energy is expected to be large on the operation day, the load declaration should be reduced; when the new energy is expected to be limited on the operation day, the load declaration should be increased; in the range of large fluctuations in the output of new energy, the actual proxy load should be declared. In the medium and long-term market, the yield is expected to increase by 5%, and in the spot market, the yield is expected to increase by 12%.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A new energy joint forecasting method for power market based on SA-GAN, characterized in that: include: Obtain historical electricity market data and pre-process it; The attention mechanism is added to the generator network and the discriminator network in the generative adversarial network respectively to establish an attention-generative adversarial prediction model; Inputting the electricity market historical data into the attention-generation adversarial prediction model for training, and continuously optimizing the parameters of the attention-generation adversarial prediction model through adversarial learning between the generator and the discriminator; The historical data of the electricity market is jointly predicted using the trained and optimized attention-generation adversarial prediction model to obtain future power generation data of new energy.

2. The SA-GAN-based new energy joint forecasting method for the power market as claimed in claim 1, characterized in that: The generator network that adds the attention mechanism to the generative adversarial network includes: The generator network adopts a deep residual network structure, combined with a self-attention layer and a fully connected layer, and introduces a dynamic weight adjustment mechanism to adaptively adjust the depth and width of the deep residual network structure according to the distribution characteristics of historical data in the power market; The number of self-attention layer heads of the generator network is set to 8, the dimension of the attention head is set to 64, the number of fully connected layers is set to 3, the number of neurons in each layer is set to 256, 128 and 64, and the activation function is ReLU.

3. The SA-GAN-based new energy joint forecasting method for the power market according to claim 1 or 2, characterized in that: The discriminator network that adds the attention mechanism to the generative adversarial network includes: The discriminator network includes multi-scale convolutional layers and self-attention layers to capture micro- and macro-patterns of historical power market data through multi-scale feature extraction; The number of heads of the self-attention layer of the discriminator network is set to 8, the dimension of the attention head is set to 64, the convolution kernel size of the convolution layer is set to 3×3, and the number of convolution kernels is set to 32, 64, and 128.

4. The SA-GAN-based new energy joint forecasting method for the power market as claimed in claim 3, characterized in that: Inputting the electricity market historical data into the attention-generation adversarial prediction model for training includes: Initialize the parameters of the generator and the discriminator. In each training iteration, use the historical data of the electricity market to train the discriminator network so that the discriminator network can distinguish the historical data of the electricity market from the data samples generated by the generator network. After training the discriminator network with the historical data of the electricity market, the data samples generated by the generator network are input into the discriminator network together with the historical data of the electricity market, and the parameters of the generator network are updated according to the recognition results of the discriminator network.

5. The SA-GAN-based joint forecasting method for new energy in the power market as claimed in claim 4, characterized in that: Also includes: During the training process of the attention-generation adversarial prediction model, an adaptive learning rate adjustment strategy is adopted, and the quantum heuristic algorithm is combined to optimize the parameters of the attention-generation adversarial prediction model; The introduction of sparse connections reduces the complexity of the attention-generation adversarial prediction model and improves the generalization ability.

6. The SA-GAN-based new energy joint forecasting method for the power market as claimed in claim 5, characterized in that: New energy future power generation data include: The predicted future power generation data of new energy is evaluated, and the mean square error and mean absolute error indicators are used to evaluate the performance of the attention-generative adversarial prediction model. According to the evaluation results, the attention-generative adversarial prediction model is optimized and adjusted.

7. The SA-GAN-based new energy joint forecasting method for the power market according to claim 5 or 6, characterized in that: Optimization adjustments to the attention-generation adversarial prediction model include: Analyze the error distribution in the future power generation data of new energy and obtain the error analysis results; According to the error analysis results, adjusting the structure and parameters of the attention-generation adversarial prediction model to reduce the prediction error; The adjustment method is a trial-and-error method, which uses the trial-and-error method to try possible combinations multiple times to obtain the optimal adjustment solution for the attention-generation adversarial prediction model; The adjusted attention-generation adversarial prediction model is retrained until the prediction results reach the expected accuracy.

8. A system for joint prediction of new energy in the power market based on SA-GAN, characterized in that: include: A data acquisition module (100), used for acquiring historical data of the electricity market and performing pre-processing; A model prediction module (200) is used to add the attention mechanism to the generator network and the discriminator network in the generative adversarial network respectively, and establish an attention-generative adversarial prediction model; An optimization module (300) is used to input the electricity market historical data into the attention-generation adversarial prediction model for training, and continuously optimize the parameters of the attention-generation adversarial prediction model through adversarial learning between the generator and the discriminator; The joint prediction module (400) is used to perform joint prediction on the electricity market historical data using the trained and optimized attention-generation adversarial prediction model to obtain future power generation data of new energy.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the SA-GAN-based power market new energy joint prediction method are implemented as claimed in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: Computer executable instructions are stored, and when the computer executable instructions are executed by a processor, the steps of the SA-GAN-based new energy joint prediction method for the power market as described in any one of claims 1-7 are implemented.

Images