Method, system and device for optimizing configuration of wind, solar and storage mobile power supply in complex environment

Abstract

The present invention discloses a method, system and device for optimizing the configuration of wind, photovoltaic and storage mobile power sources in complex environments, and relates to the technical field of power systems. The method includes: configuring a sensor network, performing time-series collection of environmental data, and establishing an environmental data set; using the data set to perform environmental prediction and establish prediction results; performing load demand fitting and establishing calibration requirements; using the calibration requirements to build a configuration model, and establishing a power generation fitting result based on the prediction results; synchronizing the power generation fitting result and the environmental steady-state identifier to the configuration model, performing power supply configuration optimization, and establishing a configuration result; and optimizing the configuration management of wind, photovoltaic and storage power sources based on the configuration results. The method solves the technical problems of resource instability and load power demand fluctuation of wind power generation and photovoltaic power generation systems in complex environments, and achieves the technical effect of improving the power supply continuity and reliability of wind, photovoltaic and storage mobile power systems through real-time collection and prediction of environmental data, and dynamic adjustment of demand fitting and power generation fitting.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method, system and device for optimizing configuration of wind, solar and storage mobile power sources in complex environments. Background Art

[0002] With the development of renewable energy, wind power and solar energy are gaining more and more attention as green and environmentally friendly energy forms. However, wind power generation and photovoltaic power generation have their own limitations in resource utilization. Wind power generation relies on stable wind speed, but is greatly affected by factors such as weather and seasons, and is intermittent and unstable; while solar power generation is affected by light intensity and cannot provide stable power supply all day long, especially on cloudy days or at night when the power generation capacity decreases. In remote areas and some special application scenarios, such as field activities, communication base stations, and islands, traditional power supply is difficult to cover, and the demand for independent power supply systems in these areas is growing. Existing wind power generation and photovoltaic power generation systems are often unable to guarantee stable power supply in complex environments due to problems such as unreasonable equipment configuration, unbalanced resources, and demand fluctuations. Therefore, how to make full use of the complementarity of wind and solar energy to ensure the continuity and reliability of power supply is a major challenge currently faced. Summary of the invention

[0003] The present application provides a method, system and device for optimizing the configuration of wind, solar and storage mobile power sources in complex environments, solving the technical problems of resource instability and load power demand fluctuation of wind power generation and photovoltaic power generation systems in complex environments.

[0004] In view of the above problems, the present application provides a method, system and device for optimizing the configuration of wind, solar and storage mobile power supplies in complex environments.

[0005] The first aspect of the present application provides a method for optimizing the configuration of a wind-solar-storage mobile power supply in a complex environment, the method comprising:

[0006] Configure a sensor network, use the sensor network to perform time series acquisition of environmental data, and establish an environmental data set with a time series identifier; use the environmental data set to perform environmental prediction and establish an environmental time series prediction result, wherein the environmental time series prediction result carries an environmental steady-state identifier; perform demand fitting of load power demand, and establish calibration demand based on the demand fitting result; use the calibration demand to build a dynamic configuration model, and perform power generation fitting of wind power generation and photovoltaic power generation based on the environmental time series prediction result, and establish power generation fitting results; synchronize the power generation fitting results and the environmental steady-state identifier to the dynamic configuration model, perform cost-stability demand power supply configuration optimization, and establish a demand power supply configuration optimization result; perform wind, photovoltaic, and storage mobile power supply optimization configuration management based on the demand power supply configuration optimization result.

[0007] The second aspect of the present application provides a wind, solar, and mobile power supply optimization configuration system in a complex environment, the system comprising:

[0008] A data acquisition module, the data acquisition module is used to configure a sensor network, use the sensor network to perform time-series environmental data acquisition, and establish an environmental data set with a time series identifier; an environmental prediction module, the environmental prediction module is used to use the environmental data set to perform environmental prediction and establish an environmental time series prediction result, wherein the environmental time series prediction result carries an environmental steady-state identifier; a demand fitting module, the demand fitting module is used to perform demand fitting of load power demand, and establish a calibration demand based on the demand fitting result; a power generation fitting module, the power generation fitting module is used to construct a dynamic configuration model using the calibration demand, and perform power generation fitting of wind power generation and photovoltaic power generation respectively based on the environmental time series prediction result, and establish a power generation fitting result; a configuration optimization module, the configuration optimization module is used to synchronize the power generation fitting result and the environmental steady-state identifier to the dynamic configuration model, perform cost-stability demand power supply configuration optimization, and establish a demand power supply configuration optimization result; a configuration management module, the configuration management module is used to perform optimized configuration management of wind, solar and storage mobile power sources based on the demand power supply configuration optimization result.

[0009] According to a third aspect of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0010] Configure a sensor network, use the sensor network to collect environmental data in a time series, and establish an environmental data set with a time series identifier; use the environmental data set to perform environmental predictions and establish environmental time series prediction results, wherein the environmental time series prediction results carry an environmental steady-state identifier; perform demand fitting of load power demand, and establish calibration requirements based on the demand fitting results; use the calibration requirements to build a dynamic configuration model, and perform power generation fitting of wind power generation and photovoltaic power generation based on the environmental time series prediction results, and establish power generation fitting results; synchronize the power generation fitting results and the environmental steady-state identifier to the dynamic configuration model, perform cost-stability demand power supply configuration optimization, and establish demand power supply configuration optimization results; perform wind, solar, and storage mobile power supply optimization configuration management based on the demand power supply configuration optimization results. One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] First, configure the sensor network, use the sensor network to collect environmental data in time series, and establish an environmental data set with a time series identifier; then, use the environmental data set to perform environmental prediction, establish environmental time series prediction results, wherein the environmental time series prediction results carry an environmental steady-state identifier, and perform demand fitting of load power demand, and establish calibration requirements based on the demand fitting results; further, use the calibration requirements to build a dynamic configuration model, and perform power generation fitting of wind power generation and photovoltaic power generation based on the environmental time series prediction results, establish power generation fitting results, and then synchronize the power generation fitting results and the environmental steady-state identifier to the dynamic configuration model, perform cost-stability demand power supply configuration optimization, and establish demand power supply configuration optimization results; finally, perform wind, solar, and storage mobile power supply optimization configuration management based on the demand power supply configuration optimization results. The technical problems of resource instability and load power demand fluctuations of wind power generation and photovoltaic power generation systems in complex environments are solved, and the technical effect of improving the power supply continuity and reliability of wind, solar, and storage mobile power supply systems is achieved through real-time collection and prediction of environmental data, dynamic adjustment of demand fitting and power generation fitting. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 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.

[0013] Figure 1 A schematic flow chart of a method for optimizing configuration of a wind, solar, and storage mobile power supply in a complex environment provided by an embodiment of the present application;

[0014] Figure 2 This is a schematic diagram of the structure of a wind, solar, and mobile power supply optimization configuration system in a complex environment provided by an embodiment of the present application.

[0015] Explanation of the reference numerals: data collection module 11 , environment prediction module 12 , demand fitting module 13 , power generation fitting module 14 , configuration optimization module 15 , configuration management module 16 . DETAILED DESCRIPTION

[0016] The present application solves the technical problems of resource instability and load power demand fluctuation of wind power generation and photovoltaic power generation systems in complex environments by providing a method system and equipment for optimizing the configuration of wind, solar and storage mobile power sources in complex environments.

[0017] 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.

[0018] It should be noted that the terms "including" and "having" 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.

[0019] Embodiment 1, as Figure 1 As shown, the present application provides a method for optimizing the configuration of wind, solar and storage mobile power supplies in a complex environment, wherein the method includes:

[0020] Configure the sensor network, use the sensor network to collect environmental data in time series, and establish an environmental data set with time series identification.

[0021] In one embodiment, configuring a sensor network means arranging a variety of environmental sensors in the target area to collect real-time data related to the environment, such as wind speed, light intensity, temperature, humidity, etc. Through these sensors, the system terminal can continuously monitor and record changes in environmental conditions. Each environmental sensor will be assigned a time series identifier, which means that each data record will be marked with an accurate timestamp, thereby forming an environmental data set containing a time series identifier. These data can reflect the dynamic characteristics of the environment changing over time, and provide accurate real-time basis for subsequent environmental prediction, demand fitting, etc.

[0022] The environmental data set is used to perform environmental prediction and establish an environmental time series prediction result, wherein the environmental time series prediction result carries an environmental steady state mark.

[0023] In one embodiment, the system terminal uses the collected environmental data set to perform environmental prediction, analyzes the periodic characteristics of the environmental data set and the environmental data set through the self-attention mechanism, and predicts changes in environmental conditions in a period of time in the future. In this process, an environmental time series prediction result is generated. This environmental time series prediction result refers to the future environmental change trend based on the periodic characteristics and the environmental data set, and also includes an environmental steady-state mark based on the prediction confidence of the prediction result and the fluctuation of the prediction result. The steady-state mark is a judgment on whether the environment has entered a stable state. It indicates whether the environmental conditions are in a stable state at a specific moment, or whether they are about to change significantly. The steady-state mark helps to identify the stable or unstable period of the environment, thereby providing a decision-making basis for subsequent power configuration optimization, ensuring that the wind, solar and storage systems can adjust their strategies according to environmental changes.

[0024] Furthermore, the using the environmental data set to perform environmental prediction and establish environmental time series prediction results includes:

[0025] The time series position information of each data unit is established based on the time series identifier of the environmental data set; the time series position information is used to perform adaptive time series clustering of the environmental data set to establish an adaptive time series clustering result; a dynamic expansion factor is configured based on the adaptive time series clustering result, and the dynamic expansion factor and the time series position information are used to perform dilated causal convolution of the environmental data set to extract the periodic features of the environmental data set; the self-attention mechanism is activated to perform attention optimization based on the periodic features and the environmental data set, and environmental development prediction is performed based on the attention optimization result to establish an environmental time series prediction result.

[0026] Preferably, the system terminal uses the time series identifier in the environmental data set to assign a corresponding time series position information to each data unit (such as environmental parameters such as wind speed and light intensity recorded each time). These position information provide a time series context for subsequent analysis and help understand the change pattern of environmental data over time; then, the environmental data set is adaptively time series clustered using the obtained time series position information. During the clustering process, due to the dimensional differences of various features in the environmental data (such as wind speed, light, etc.), the system terminal performs standardization on the data. Common standardization methods include Z-score standardization, which converts the value of each feature into a standard normal distribution (with a mean of 0 and a standard deviation of 1) to obtain a standard environmental data set to ensure that each feature has equal importance during clustering; for each pair of data points, their distance is calculated using the Euclidean distance, and a distance matrix is ​​constructed based on the calculated distance between each pair of data points. Each element in this matrix represents the similarity distance between two data points; then, the maximum distance ε of the neighborhood of a point is defined. ε can be set according to the k-distance graph method, indicating the maximum distance between two data points. Only points with a distance less than ε are clustered. will be regarded as neighbors, and then define the minimum number of points MinPts required in the neighborhood. MinPts can be set according to the dimension of the data, indicating that if there are enough points in the neighborhood of a point, it is a core point; after determining ε and MinPts, traverse the distance matrix to determine the category of each data point. If there are at least MinPts points (including itself) in its neighborhood, the point is a core point. If it is adjacent to a core point but there are less than MinPts data points in its neighborhood, the point is a boundary point. If it does not belong to the neighborhood of any core point and does not have enough neighbors, then the point is a boundary point. If a point is a boundary point, it is a noise point. After determining the category, the system terminal starts from an unvisited point. If the point is a core point, it and the points in the neighborhood are classified into a cluster according to its neighborhood. If the point is a boundary point, it is added to the cluster where the nearest core point is located. If the point is a noise point, it will not be classified into any cluster. This process continues until all points have been visited and classified as clusters or noise. In this way, the environmental data is divided into multiple clusters to form an adaptive time series clustering result. Each cluster represents an environmental state with a similar change pattern over a period of time.

[0027] After completing the time series clustering, based on the adaptive time series clustering results, the system terminal configures a dynamic expansion factor. The expansion factor is a parameter used to adjust data expansion or expansion to strengthen the relationship between different time periods. This expansion factor can be flexibly adjusted according to the size of the time series clustering; after obtaining the dynamic expansion factor, the system terminal uses the expansion factor and the time series position information to perform expansion causal convolution, that is, in each convolution layer, the receptive field is expanded by the expansion factor, and the causal relationship in time is maintained through causal convolution. The characteristic of causal convolution is that each convolution operation only depends on the current and past time series data, ensuring that no future data is involved in the prediction, which is for data with time series position information. The dilated convolution is particularly important for data collection, ensuring that the causal law of time is followed during the convolution process. The dilated convolution expands the receptive field through the dynamic dilation factor, so that the network can capture the periodic features of long-term dependence without increasing the amount of calculation. The dynamic dilation factor adjusts the span of the convolution operation according to the periodicity of the data, so that the convolution layer can adaptively learn the periodic pattern in the time series data; after the convolution operation is completed, the convolution result obtained will contain the periodic features in the time series. The output of the dilated causal convolution reflects the changing law of environmental data in different time periods. For example, through the convolution operation, seasonal fluctuations, day and night temperature differences, wind speed changes and other periodic features can be captured, providing an important basis for environmental prediction.

[0028] After obtaining the periodic characteristics of the environmental data set, the self-attention mechanism is activated. The self-attention mechanism helps the environmental prediction model focus on the key parts related to the current prediction in the time series data by learning the associations between different time steps. During the training process of the environmental prediction model, the model will automatically adjust the weight of each time step through the self-attention mechanism to optimize the learning effect of the model. Specifically, the system terminal screens the historical environmental data based on the periodic characteristics and the environmental data set to obtain the historical environmental data that meets the deviation threshold and the corresponding historical periodic characteristics. Subsequently, the correlation and weight between each time step are calculated through the self-attention mechanism, that is, the model learns which features and time points in the environmental data are most important for the prediction of the current time step through the query, key, and value method. The data of each time step will be mapped through the three vectors of query, key, and value, and the attention score is obtained by calculating the inner product of the query and the key. Softmax normalization obtains weights, and based on these attention weights, the input historical environmental data and the corresponding historical periodic features are weighted and summed to obtain the optimized feature representation of the time step; through the self-attention mechanism, the model optimizes the features according to the weighted results of the periodic features, so that those features that are most important for prediction are strengthened, and other less important features are reduced in weight; afterwards, the model obtains the prediction results through forward propagation during the training process, compares them with the subsequent environmental data of the current input historical environmental data, calculates the loss value, and then adjusts the weights through back propagation to learn to pay attention to periodic features and environmental data, and effectively optimize the prediction ability of environmental change patterns; the trained environmental prediction model predicts the periodic features and environmental data sets weighted by the self-attention mechanism to obtain environmental time series prediction results, which can describe the trend of environmental changes and provide decision support for the subsequent optimization configuration of wind, solar, storage and mobile power sources.

[0029] Furthermore, configuring a dynamic expansion factor based on the adaptive time series clustering result includes:

[0030] Obtain the cluster identifier of the adaptive time series clustering result, perform identifier distribution analysis of the adaptive time series clustering result based on the cluster identifier, and construct a basic factor setting coefficient based on the identifier distribution analysis result; obtain the cluster size of the adaptive time series clustering result, and establish a dynamic expansion factor for each adaptive time series clustering result based on the cluster size and the basic factor setting coefficient.

[0031] Optionally, after performing adaptive time series clustering, each data point will be assigned a cluster identifier, which indicates which cluster the data point belongs to. For example, cluster 1 may include data points with similar wind speed change patterns, and cluster 2 may include data points with similar light intensity changes. The system terminal traverses the adaptive time series clustering results to obtain the identifier of the cluster to which each data point belongs. Subsequently, based on these cluster identifiers, the number of different clusters in the clustering results and the size of each cluster (i.e., the number of cluster points in the cluster) are counted to understand the distribution of each identifier, and the size of the cluster corresponding to each identifier is then calculated by ratio between the distance between the two farthest points in the cluster to obtain the cluster density of the cluster. The above process is repeated to obtain the cluster density of each cluster, and these clusters are grouped together. The class density is added to the identification distribution analysis result, which will be used to establish the basic factor setting coefficient to quantify the importance of each cluster in subsequent operations; then, the dynamic expansion factor of the cluster is obtained by multiplying the logarithm of the cluster size with the corresponding basic factor setting coefficient. For larger clusters, the expansion factor will also be larger, because these clusters represent more common environmental patterns and require a wider receptive field to capture their characteristics. For smaller clusters, the expansion factor will also be smaller to capture local features more finely; repeat the above process to obtain the dynamic expansion factor of each cluster, which will be used in the dilated causal convolution. The convolution operation is adjusted by controlling the size of the receptive field so that the periodic characteristics of each cluster can be fully extracted.

[0032] Furthermore, the method further comprises:

[0033] Perform a forecast back-tracking call on the environmental development forecast to establish a forecast confidence level; perform an environmental fluctuation analysis on the environmental time series forecast results to establish an environmental fluctuation analysis result; perform forecast impact compensation on the environmental fluctuation analysis result based on the forecast confidence level, and construct an environmental steady-state identification based on the forecast impact compensation.

[0034] Optionally, after the environmental prediction model completes the environmental development prediction, the system terminal performs a backtracking of the same length of time according to the predicted time length to obtain a backtracking environmental data set. This data is a benchmark for comparing the difference between the model prediction and the actual result, so as to comprehensively evaluate the accuracy of the model prediction; then, the backtracking environmental data set is calculated with the environmental time series prediction result for absolute difference to obtain the error value of each data point, and then the mean of these error values ​​is calculated, and the inverse calculation is added to 1 to obtain the prediction confidence of the environmental time series prediction result; then, the system terminal performs an environmental fluctuation analysis on the environmental time series prediction result to calculate the environmental time series prediction confidence. The standard deviation and mean of the sequence prediction results are calculated, and then the calculated standard deviation and mean are ratioed to obtain the environmental fluctuation coefficient, and it is used as the environmental fluctuation analysis result. The larger the result, the more severe the fluctuation. Then, the system terminal compensates the environmental fluctuation analysis result for the prediction impact based on the prediction confidence, that is, multiplying the environmental fluctuation analysis result with the difference between 1 and the prediction confidence as the environmental steady-state mark, which is used to indicate whether it is in a stable state during the prediction period. If the compensation result is small, it means that the prediction confidence is high and the fluctuation is small, and the environment is in a steady state. If the compensation result is large, it means that the prediction uncertainty is high and the environment may be in a non-steady state.

[0035] Perform demand fitting of load power demand and establish calibration demand based on the demand fitting result.

[0036] In one embodiment, demand fitting refers to using historical load power consumption data to predict future power demand through a suitable mathematical model, with the goal of finding the relationship between past power demand and factors such as time and seasonal fluctuations, and using this relationship to predict future demand; the system terminal first collects historical load power consumption data, which includes daily and hourly power consumption, as well as external factors related to power demand such as temperature, date, and holidays, and then divides the historical load power consumption data into a training set and a validation set. The training set is used to train the demand fitting model, and the validation set is used to evaluate the prediction performance of the demand fitting model. During the training process, the model will learn the seasonal fluctuations in the historical data. The system terminal first selects the appropriate seasonal cycle according to business needs. Common seasonal cycles include 7 days (weekly), 30 days or 31 days (monthly), 24 hours (daily), etc., and then selects the appropriate AR (autoregression), I (difference) and MA (moving average) orders through the autocorrelation function (ACF) and partial autocorrelation function (PACF) diagrams, and determines the orders of the seasonal autoregression (SAR), seasonal difference (SI) and seasonal moving average (SMA) parts. Subsequently, these parameters are used to build a demand fitting model and fit the training set. The model The training process includes initializing weights and parameters, inputting sample sets and performing forward propagation. Through forward propagation, the model will calculate the predicted value of each time step based on historical data. These predicted values ​​are calculated based on the current parameters of the model. The difference (error) between the predicted value and the true value is calculated by the mean square error (MSE) or the root mean square error (RMSE). The smaller the error, the stronger the predictive ability of the model. After each forward propagation, the calculated loss value will be adjusted through back propagation, and the contribution of each layer's weight to the loss function is calculated layer by layer. Through back propagation, the model will adjust its parameters (such as autoregressive coefficients, differential coefficients, etc.) to minimize the loss value. Usually, the model is used. Gradient descent or Ada optimizer is used to optimize these parameters. The training process will continue to iterate until the model loss reaches the preset threshold or the maximum number of iterations. After training, the model is evaluated using the validation set. By comparing the predicted results in the validation set with the actual results, the accuracy of the model in load demand forecasting is evaluated. If the model performs well on the validation set, it means that the training has been completed and the model has good forecasting ability. If the accuracy rate does not meet expectations, it is necessary to adjust the model's hyperparameters (such as learning rate, seasonal cycle, AR, MA order, etc.) to further optimize the model. After training, the optimized demand fitting model can predict future load power demand.Afterwards, the trained model can predict the load demand based on the time variables (such as future dates, hours, etc.) input by the system terminal and related external factors (such as weather forecasts, holidays, etc.), obtain the demand fitting result, and use this demand fitting result as the calibration demand to provide strong data support for the system's designated scheduling. ;

[0037] A dynamic configuration model is constructed using the calibration requirements, and power generation fitting of wind power generation and photovoltaic power generation is performed based on the environmental time series prediction results to establish power generation fitting results.

[0038] In one embodiment, the system terminal screens historical power generation data based on the calibration demand, that is, screens out historical environmental time series information and historical power generation information (including wind power generation capacity and photovoltaic power generation capacity) with similar demand (the absolute difference of the demand satisfies the difference constraint); then, a long short-term memory network is used to build a power generation fitting unit of the dynamic configuration model, and then through the same forward propagation, loss calculation, back propagation, parameter update and other steps as mentioned above, the historical environmental time series information and historical power generation information are used to train the power generation fitting unit, so that it gradually learns the mapping relationship between different environmental information and power generation information; then, the system terminal inputs the environmental time series prediction results into the power generation fitting unit of the dynamic configuration model for power generation fitting, calculates the power generation output values ​​of wind power generation and photovoltaic power generation, and integrates them through the output layer of the power generation fitting unit, and outputs them in the form of power generation fitting results, which will serve as the basis for subsequent demand power supply configuration optimization to ensure that the user's load requirements can be stably and reliably met under different environmental conditions.

[0039] The power generation fitting result and the environmental steady-state identifier are synchronized to a dynamic configuration model, and a cost-stability demand power supply configuration optimization is performed to establish a demand power supply configuration optimization result.

[0040] In one embodiment, after obtaining the power generation fitting result, the system terminal synchronizes the power generation fitting result and the environmental steady-state identification to the dynamic configuration model, performs independent power supply authentication through the independent power supply authentication unit of the dynamic configuration model, and performs joint power supply scheme fitting through the joint power supply analysis unit of the dynamic configuration model, and then respectively calculates the fitness of the output results of the two units, and based on these fitness, performs demand power supply configuration optimization, thereby obtaining a demand power supply configuration optimization result to ensure that under given environmental conditions, the load demand can be met and the cost and stability of power supply are optimized.

[0041] Furthermore, synchronizing the power generation fitting result and the environmental steady-state identifier to a dynamic configuration model, performing cost-stability demand power supply configuration optimization, and establishing a demand power supply configuration optimization result includes:

[0042] The independent power supply authentication unit of the dynamic configuration model is called to execute independent power supply authentication based on the power generation fitting result and the environmental steady-state identification, and establish an authentication result; if the authentication result is a passed authentication result, a cost-stability fitness analysis is performed based on the authentication result, a first fitness analysis result is established, and an additional cost constraint for joint power supply is created; the joint power supply analysis unit of the dynamic configuration model is called to execute a joint power supply scheme fitting based on the power generation fitting result and the environmental steady-state identification, and a cost-stability fitness analysis is performed through the additional cost constraint to establish a second fitness analysis result; and the demand power supply configuration is optimized according to the first fitness analysis result and the second fitness analysis result to establish a demand power supply configuration optimization result.

[0043] Preferably, after obtaining the power generation fitting result, the system terminal inputs the power generation fitting result and the environmental steady-state identifier into the dynamic configuration model. The dynamic configuration model calls the independent power supply authentication unit in the dynamic configuration model to perform independent power supply authentication based on the power generation fitting result and the environmental steady-state identifier. The purpose of this authentication is to verify whether the current power generation configuration (i.e., the output of wind power generation and photovoltaic power generation) is sufficient to support the load demand. In the independent power supply authentication unit, the system terminal compares the environmental steady-state identifier with the environmental steady-state threshold inside the unit. If the environmental steady-state identifier is greater than or equal to the environmental steady-state threshold, it means that the current environmental area is stable and will not cause drastic fluctuations in power generation capacity. The power generation fitting result is relatively accurate. Otherwise, it means that the current environmental area may fluctuate, which will cause the power generation capacity to decrease or increase. At this time, the system terminal will adjust the power generation fitting result downward, that is, multiply the power generation fitting result and the ratio of the environmental steady-state identifier to the environmental steady-state threshold to obtain the power generation fitting adjustment result. If the total output of the power generation fitting result or the power generation fitting adjustment result is greater than or equal to the calibration demand, it means that the load demand can be met and the authentication result is passed. Otherwise, the demand cannot be met and the authentication result is failed.

[0044] When the independent power supply certification is passed, the system terminal will conduct a cost-stability fitness analysis. The purpose of this analysis is to evaluate the adaptability of the current power generation fitting results in terms of cost and stability, and generate the first fitness analysis result. Specifically, the system terminal will obtain the wind power generation capacity and photovoltaic power generation capacity from the power generation fitting results, and multiply the wind power generation capacity by the wind power unit cost to obtain the wind power generation cost, multiply the photovoltaic power generation capacity by the photovoltaic unit cost to obtain the photovoltaic power generation cost, multiply the energy storage charge and discharge capacity by the energy storage unit cost to obtain the energy storage charge and discharge cost, and then perform weighted addition on these costs to obtain the cost index; then, add the wind power generation capacity and the photovoltaic power generation capacity to obtain the total power generation, and calculate the ratio of this total power generation to the calibrated demand to obtain the load demand. Matching degree, calculate the ratio of the environmental steady-state identifier and the environmental steady-state threshold to obtain the environmental matching degree, and then calculate the average of the load demand matching degree and the environmental matching degree to obtain the stability index; then, standardize the cost index based on the maximum cost upper limit, and use the weight set by actual demand to weight the standardized cost index and stability index to sum them, and then use 1 to subtract the sum result to obtain the first fitness analysis result; in addition, an additional cost constraint for joint power supply is created, that is, the maximum additional cost that can be received, such as the charging and discharging costs of energy storage and the electricity procurement costs of the power grid, is included in the cost index, with the cost index as the lower limit and the sum of the cost index and the maximum additional cost as the upper limit, to construct the additional cost constraint for joint power supply, ensuring that the total operating cost is controlled while meeting the load demand.

[0045] After obtaining the additional cost constraints of joint power supply, the system terminal will call the joint power supply analysis unit in the dynamic configuration model to perform the joint power supply scheme fitting based on the power generation fitting results and the environmental steady-state identification. At this stage, the combined use of wind power generation, photovoltaic power generation, energy storage charging and discharging, and external power grids will be considered to meet the load demand. In this process, the system terminal will randomly allocate electricity based on the calibration demand, and set the required electricity for wind power generation, photovoltaic power generation, energy storage charging and discharging, and external power grids, and calculate the joint cost index in the same way as above. The cost of the external power grid is obtained by multiplying the power grid electricity price by the power that the external power grid needs to provide. If the joint cost index meets the additional cost constraints, the joint stability index is calculated in the same way. Otherwise, the electricity is redistributed. Subsequently, the standardized joint cost index and joint stability index are weighted by the joint weight calculation set according to the actual demand to obtain the second fitness analysis result.

[0046] After completing the power supply scheme fitting, the system terminal optimizes the demand power supply configuration according to the first fitness analysis result and the second fitness analysis result, and takes the power supply configuration corresponding to the largest fitness analysis result as the power supply configuration scheme; repeat the above process until the maximum number of iterations is reached, and output the current power supply configuration scheme as the demand power supply configuration optimization result to ensure that it can meet the load demand under different environmental conditions, optimize the cost and improve stability.

[0047] Furthermore, the method further comprises:

[0048] A mapping verification window is established according to the optimization result of the demand power supply configuration; power generation verification is performed in the mapping verification window to generate a power generation verification result; a wind-solar balance factor is generated using the power generation verification result, and configuration reconstruction of the demand power supply configuration optimization result is performed based on the wind-solar balance factor.

[0049] Preferably, after obtaining the optimal result of the demand power supply configuration, the system terminal establishes a mapping verification window (such as 1 hour, one day, etc.); after establishing the mapping verification window, the power generation verification is performed according to the actual power generation capacity and load demand in the window. The purpose of the power generation verification is to confirm whether the power generation capacity under given environmental conditions is sufficient to meet the load demand and ensure stability. In this process, the system terminal will count the actual power generation in the mapping verification window, and calculate the ratio of this actual power generation to the calibration demand to obtain the power generation verification result. If the power generation verification result is close to 1, it means that the power generation and load demand are well matched. If the demand matching degree is lower than 1, it means that the power generation is insufficient and the configuration needs to be adjusted; then, the sum of the wind power generation capacity and the photovoltaic power generation capacity is used to calculate the ratio with the total power generation to obtain the wind-solar balance factor. If the wind-solar balance factor is low (that is, the proportion of grid power is high), it will tend to increase the proportion of wind and photovoltaic power generation and reduce dependence on the external grid. If the wind-solar balance factor is high, the energy storage system can be charged to ensure that renewable energy can be efficiently used when there is excess power generation. In this way, the configuration reconstruction of the optimal result of the demand power supply configuration is completed to ensure the stability and economy of the power supply.

[0050] Based on the optimization result of the required power supply configuration, the wind, solar and storage mobile power supply is optimized and managed.

[0051] In one embodiment, the system terminal dynamically adjusts the output of wind power generation, photovoltaic power generation, energy storage system and external power grid by executing the optimization result of the demand power supply configuration, and realizes the optimized configuration management of wind, photovoltaic and energy storage mobile power sources, so that energy utilization can be maximized, cost can be minimized, and power supply is highly stable while meeting load demand.

[0052] Furthermore, the method further comprises:

[0053] Supply hidden dangers are identified according to the demand fitting results and the power generation fitting results, and hidden danger nodes are established, wherein the hidden danger nodes are marked with risk values; a time series backtracking demand is constructed based on the hidden danger nodes, and a dynamic configuration model is updated using the time series backtracking demand, and a demand power supply configuration optimization result is re-established according to the updated dynamic configuration model; and demand power supply and energy storage management are performed using the re-established demand power supply configuration optimization result.

[0054] Preferably, the demand fitting result represents the predicted value of the load demand in different time periods, which can reflect the fluctuation and change of the load demand. The power generation fitting result represents the power generation capacity under the current environmental conditions, covering the output of wind power generation and photovoltaic power generation. In the actual operation process, there may be a matching problem between the load demand and the power generation capacity. For example, if the power generation capacity is insufficient to meet the load demand, resulting in power shortage, or if the power generation is excessive and the load demand is low, it may cause a waste of resources. For this reason, the system terminal compares the demand fitting result with the power generation fitting result to identify potential power supply risks. When the demand fitting result is greater than the power generation fitting result, it indicates that the load demand may not be met and a power supply shortage may occur. When the power generation fitting result is greater than the demand fitting result, it indicates that the power generation capacity exceeds the load demand, and there may be hidden dangers of resource waste or insufficient energy storage. Therefore, the system terminal establishes hidden danger nodes at the time corresponding to the occurrence of these hidden dangers. The hidden danger nodes represent the power supply risks that may occur at a certain point in time or under a certain specific state. The hidden danger nodes are usually accompanied by a risk value logo to measure the severity of the hidden danger. The risk value logo is determined based on the absolute difference between the demand fitting result and the power generation fitting result. After determining the hidden danger node, the system terminal analyzes the matching degree of historical load demand and power generation capacity, identifies the potential time periods of power shortage or surplus, and converts the load of these time periods into The demand is used as a retrospective demand, and then the load demand forecast is dynamically adjusted and updated according to the retrospective demand and potential danger nodes to respond to future load fluctuations. If the retrospective demand shows that there is a power shortage in certain time periods, the power generation configuration should be adjusted in advance for these time periods or the energy storage discharge should be increased. If the retrospective demand shows excess power generation, it may be necessary to reduce the energy storage charging or adjust the power generation ratio in a timely manner; according to the analysis results of the retrospective demand, the system terminal updates the dynamic configuration model. The dynamic configuration model is a key tool for optimizing power generation configuration, energy storage strategy and external power grid power procurement. Through the analysis of the retrospective demand, the dynamic configuration model is adjusted, for example, according to the updated demand The fitting results and power generation fitting results are used to readjust the output ratio of wind power generation and photovoltaic power generation to ensure that power generation matches load demand. According to the changes in the back-tracking demand, the charging and discharging strategy of the energy storage system is adjusted to balance the insufficient or excessive power generation. If the demand increases, the energy storage system will be required to charge in advance. If the demand decreases, the energy storage system can discharge to meet the load. After the dynamic configuration model is updated, the system terminal will establish the time penalty fitness for time storage loss and the stability penalty fitness for demand adaptation, and based on these penalty fitnesses, the demand power supply configuration optimization result is re-established through the updated dynamic configuration model to ensure the smooth supply of load demand and avoid unnecessary energy waste.

[0055] Furthermore, re-establishing the optimal result of the required power supply configuration according to the updated dynamic configuration model includes:

[0056] Establish time penalty fitness for time storage loss and stability penalty fitness for demand adaptation; when performing additional adaptation optimization for timing backtracking requirements, perform adaptation penalty analysis based on the time penalty fitness and the stability penalty fitness, and re-establish the demand power supply configuration optimization result based on the adaptation penalty analysis result.

[0057] Optionally, based on the time penalty fitness and stability penalty fitness, the system terminal performs an adaptive penalty analysis to optimize the load demand and power generation configuration to ensure the best balance between response time and system stability. First, the establishment of the time penalty fitness takes into account the charging and discharging response time of the energy storage system. If the power generation cannot meet the load demand, the response time of the energy storage system becomes particularly critical. If the response time of the energy storage system exceeds the preset threshold, a time penalty will be incurred, increasing the risk. At this time, the system terminal will adjust the charging and discharging strategy of the energy storage system according to the time penalty fitness. The time penalty fitness can further introduce a weight coefficient by calculating the difference between the actual response time and the expected response time to reflect the impact of the penalty on the optimization target. At the same time, the stability penalty fitness will evaluate the matching degree between the power generation and the load demand, especially when the environmental fluctuations are large. If the power generation cannot match the load demand, it will face stability. The stability penalty fitness calculates the ratio of power generation to demand, and generates a penalty based on the deviation between this ratio and the target matching degree. If the power generation is insufficient or excessive, the stability penalty fitness will increase, and the system terminal will adjust the proportion of wind and solar power generation according to this penalty or balance the power supply through the energy storage system; in the adaptation penalty analysis, the time penalty fitness and the stability penalty fitness are combined to form a comprehensive fitness function, and the weight coefficient will adjust their influence in the total fitness. By optimizing this fitness function, the system terminal can achieve a balance between time response and load adaptation, thereby determining the optimal configuration of wind power, photovoltaic power generation and energy storage systems; according to the results of the adaptation penalty analysis, the system terminal will re-establish the demand power supply configuration optimization result to meet the load demand, reduce time and stability penalties, and ensure that under various environmental conditions, the power supply can stably and economically meet the demand.

[0058] In summary, the embodiments of the present application have at least the following technical effects:

[0059] First, configure the sensor network, use the sensor network to collect environmental data in time series, and establish an environmental data set with a time series identifier; then, use the environmental data set to perform environmental prediction, establish environmental time series prediction results, wherein the environmental time series prediction results carry an environmental steady-state identifier, and perform demand fitting of load power demand, and establish calibration requirements based on the demand fitting results; further, use the calibration requirements to build a dynamic configuration model, and perform power generation fitting of wind power generation and photovoltaic power generation based on the environmental time series prediction results, establish power generation fitting results, and then synchronize the power generation fitting results and the environmental steady-state identifier to the dynamic configuration model, perform cost-stability demand power supply configuration optimization, and establish demand power supply configuration optimization results; finally, perform wind, solar, and storage mobile power supply optimization configuration management based on the demand power supply configuration optimization results. The technical problems of resource instability and load power demand fluctuations of wind power generation and photovoltaic power generation systems in complex environments are solved, and the technical effect of improving the power supply continuity and reliability of wind, solar, and storage mobile power supply systems is achieved through real-time collection and prediction of environmental data, dynamic adjustment of demand fitting and power generation fitting.

[0060] Embodiment 2 is based on the same inventive concept as the method for optimizing the configuration of wind, solar and storage mobile power supplies in complex environments in the above embodiments. Figure 2 As shown, the present application provides a wind, solar, and storage mobile power supply optimization configuration system in a complex environment, wherein the system includes:

[0061] A data acquisition module 11, the data acquisition module 11 is used to configure a sensor network, use the sensor network to perform time series acquisition of environmental data, and establish an environmental data set with a time series identifier; an environmental prediction module 12, the environmental prediction module 12 is used to use the environmental data set to perform environmental prediction and establish an environmental time series prediction result, wherein the environmental time series prediction result has an environmental steady-state identifier; a demand fitting module 13, the demand fitting module 13 is used to perform demand fitting of load power demand, and establish a calibration demand according to the demand fitting result; a power generation fitting module 14, the power generation fitting module 14 is used to build a dynamic configuration model using the calibration demand, and perform power generation fitting of wind power generation and photovoltaic power generation respectively based on the environmental time series prediction result, and establish a power generation fitting result; a configuration optimization module 15, the configuration optimization module 15 is used to synchronize the power generation fitting result and the environmental steady-state identifier to the dynamic configuration model, perform cost-stability demand power supply configuration optimization, and establish a demand power supply configuration optimization result; a configuration management module 16, the configuration management module 16 is used to perform wind, solar and storage mobile power supply optimization configuration management based on the demand power supply configuration optimization result.

[0062] Furthermore, the environment prediction module 12 is also used to execute the following method:

[0063] The time series position information of each data unit is established based on the time series identifier of the environmental data set; the time series position information is used to perform adaptive time series clustering of the environmental data set to establish an adaptive time series clustering result; a dynamic expansion factor is configured based on the adaptive time series clustering result, and the dynamic expansion factor and the time series position information are used to perform dilated causal convolution of the environmental data set to extract the periodic features of the environmental data set; the self-attention mechanism is activated to perform attention optimization based on the periodic features and the environmental data set, and environmental development prediction is performed based on the attention optimization result to establish an environmental time series prediction result.

[0064] Furthermore, the environment prediction module 12 is also used to execute the following method:

[0065] Obtain the cluster identifier of the adaptive time series clustering result, perform identifier distribution analysis of the adaptive time series clustering result based on the cluster identifier, and construct a basic factor setting coefficient based on the identifier distribution analysis result; obtain the cluster size of the adaptive time series clustering result, and establish a dynamic expansion factor for each adaptive time series clustering result based on the cluster size and the basic factor setting coefficient.

[0066] Furthermore, the environment prediction module 12 is also used to execute the following method:

[0067] Perform a forecast back-tracking call on the environmental development forecast to establish a forecast confidence level; perform an environmental fluctuation analysis on the environmental time series forecast results to establish an environmental fluctuation analysis result; perform forecast impact compensation on the environmental fluctuation analysis result based on the forecast confidence level, and construct an environmental steady-state identification based on the forecast impact compensation.

[0068] Furthermore, the configuration optimization module 15 is also used to execute the following method:

[0069] The independent power supply authentication unit of the dynamic configuration model is called to execute independent power supply authentication based on the power generation fitting result and the environmental steady-state identification, and establish an authentication result; if the authentication result is a passed authentication result, a cost-stability fitness analysis is performed based on the authentication result, a first fitness analysis result is established, and an additional cost constraint for joint power supply is created; the joint power supply analysis unit of the dynamic configuration model is called to execute a joint power supply scheme fitting based on the power generation fitting result and the environmental steady-state identification, and a cost-stability fitness analysis is performed through the additional cost constraint to establish a second fitness analysis result; and the demand power supply configuration is optimized according to the first fitness analysis result and the second fitness analysis result to establish a demand power supply configuration optimization result.

[0070] Furthermore, the configuration optimization module 15 is also used to execute the following method:

[0071] A mapping verification window is established according to the optimization result of the demand power supply configuration; power generation verification is performed in the mapping verification window to generate a power generation verification result; a wind-solar balance factor is generated using the power generation verification result, and configuration reconstruction of the demand power supply configuration optimization result is performed based on the wind-solar balance factor.

[0072] Furthermore, the configuration management module 16 is also used to execute the following method:

[0073] Supply hidden dangers are identified according to the demand fitting results and the power generation fitting results, and hidden danger nodes are established, wherein the hidden danger nodes are marked with risk values; a time series backtracking demand is constructed based on the hidden danger nodes, and a dynamic configuration model is updated using the time series backtracking demand, and a demand power supply configuration optimization result is re-established according to the updated dynamic configuration model; and demand power supply and energy storage management are performed using the re-established demand power supply configuration optimization result.

[0074] Furthermore, the configuration management module 16 is also used to execute the following method:

[0075] Establish time penalty fitness for time storage loss and stability penalty fitness for demand adaptation; when performing additional adaptation optimization for timing backtracking requirements, perform adaptation penalty analysis based on the time penalty fitness and the stability penalty fitness, and re-establish the demand power supply configuration optimization result based on the adaptation penalty analysis result.

[0076] Embodiment 3, based on the same inventive concept as the method for optimizing the configuration of wind, solar, and mobile power supplies in a complex environment in the aforementioned embodiment 1, the present application provides an electronic device, which may be a server, comprising a processor, a memory, and a network interface connected via a system bus, wherein the processor of the electronic device is used to provide computing and control capabilities, the memory of the electronic device comprises a non-volatile storage medium and an internal memory, the non-volatile storage medium stores an operating system, a computer program, and a database, the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium, the database of the electronic device is used to store data, the network interface of the electronic device is used to communicate with an external terminal via a network connection, and the computer program is executed by the processor to implement the method for optimizing the configuration of wind, solar, and mobile power supplies in a complex environment.

[0077] 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. The processes depicted in the accompanying 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.

[0078] 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.

[0079] 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 optimizing the configuration of wind, solar and storage mobile power sources in complex environments, characterized in that: The method comprises: Configure the sensor network, use the sensor network to collect environmental data in time series, and establish an environmental data set with time series identification; Using the environmental data set to perform environmental prediction, and establish an environmental time series prediction result, wherein the environmental time series prediction result carries an environmental steady state mark; Perform demand fitting of load power demand and establish calibration demand based on the demand fitting result; A dynamic configuration model is constructed using the calibration requirements, and power generation fitting of wind power generation and photovoltaic power generation is performed respectively based on the environmental time series prediction results to establish power generation fitting results; The power generation fitting result and the environmental steady-state identifier are synchronized to a dynamic configuration model, and a cost-stability demand power supply configuration optimization is performed to establish a demand power supply configuration optimization result; Perform optimized configuration management of wind, solar, and storage mobile power supplies based on the optimization results of the required power supply configuration; The step of using the environmental data set to perform environmental prediction and establish an environmental time series prediction result includes: Establishing time series position information of each data unit based on the time series identifier of the environmental data set; Using the time series location information to perform adaptive time series clustering of the environmental data set, and establishing an adaptive time series clustering result; configuring a dynamic expansion factor based on the adaptive time series clustering result, performing an expansion causal convolution of an environmental data set using the dynamic expansion factor and the time series position information, and extracting periodic features of the environmental data set; Activate the self-attention mechanism, perform attention optimization based on the periodic features and the environmental data set, and make environmental development predictions based on the attention optimization results to establish environmental time series prediction results.

2. The method for optimizing the configuration of wind, solar and mobile power supply in a complex environment as claimed in claim 1, characterized in that: The configuring a dynamic expansion factor based on the adaptive time series clustering result includes: Acquire a cluster identifier of the adaptive time series clustering result, perform identifier distribution analysis of the adaptive time series clustering result according to the cluster identifier, and construct a basic factor setting coefficient based on the identifier distribution analysis result; The cluster size of the adaptive time series clustering result is obtained, and a dynamic expansion factor of each adaptive time series clustering result is established according to the cluster size and the basic factor setting coefficient.

3. The method for optimizing the configuration of wind, solar and storage mobile power sources in complex environments as claimed in claim 1, characterized in that: The method further comprises: Conduct forecast back-testing of environmental development forecasts to establish forecast confidence; Perform environmental fluctuation analysis on the environmental time series prediction results to establish environmental fluctuation analysis results; The environmental fluctuation analysis result is subjected to prediction impact compensation based on the prediction confidence, and an environmental steady-state identification is constructed according to the prediction impact compensation.

4. The method for optimizing the configuration of wind, solar and storage mobile power sources in complex environments as claimed in claim 1, characterized in that: The step of synchronizing the power generation fitting result and the environmental steady-state identifier to a dynamic configuration model, performing cost-stability demand power supply configuration optimization, and establishing a demand power supply configuration optimization result includes: Invoking the independent power supply authentication unit of the dynamic configuration model, performing independent power supply authentication based on the power generation fitting result and the environmental steady-state identification, and establishing an authentication result; If the authentication result is a pass result, performing a cost-stability fitness analysis based on the authentication result, establishing a first fitness analysis result, and creating an additional cost constraint for joint power supply; Calling the joint power supply analysis unit of the dynamic configuration model, executing the joint power supply scheme fitting based on the power generation fitting result and the environmental steady-state identifier, and performing cost-stability fitness analysis through the additional cost constraint to establish a second fitness analysis result; The demand power supply configuration is optimized according to the first fitness analysis result and the second fitness analysis result, and a demand power supply configuration optimization result is established.

5. The method for optimizing the configuration of wind, solar and storage mobile power sources in complex environments as claimed in claim 1, characterized in that: The method further comprises: Identify supply hidden dangers according to the demand fitting result and the power generation fitting result, and establish hidden danger nodes, wherein the hidden danger nodes are marked with risk values; Constructing a timing backtracking requirement based on the potential danger node, and using the timing backtracking requirement to update a dynamic configuration model, and re-establishing a demand power supply configuration optimization result according to the updated dynamic configuration model; The re-established demand power supply configuration optimization results are used to manage demand power supply and energy storage.

6. The method for optimizing the configuration of wind, solar and mobile power supply in complex environments as claimed in claim 5, characterized in that: The re-establishing the optimization result of the required power supply configuration according to the updated dynamic configuration model includes: Establish time penalty fitness for time storage loss and stable penalty fitness for demand adaptation; When performing additional adaptive optimization of timing backtracking requirements, an adaptive penalty analysis is performed based on the time penalty fitness and the stability penalty fitness, and the demand power supply configuration optimization result is re-established according to the adaptive penalty analysis result.

7. The method for optimizing the configuration of wind, solar and storage mobile power sources in complex environments as claimed in claim 1, characterized in that: The method further comprises: Establishing a mapping verification window according to the optimization result of the required power supply configuration; Perform power generation verification in the mapping verification window to generate a power generation verification result; The power generation verification result is used to generate a wind-solar balance factor, and the configuration reconstruction of the demand power supply configuration optimization result is performed based on the wind-solar balance factor.

8. The wind, solar and storage mobile power supply optimization configuration system in complex environments is characterized by: The system is used to implement the steps of the method for optimizing the configuration of wind, solar, and mobile power supplies in a complex environment as described in any one of claims 1 to 7, and comprises: Data collection module: configure the sensor network, use the sensor network to collect environmental data in time series, and establish an environmental data set with time series identification; Environmental prediction module: using the environmental data set to perform environmental prediction and establish an environmental time series prediction result, wherein the environmental time series prediction result carries an environmental steady state mark; Demand fitting module: performs demand fitting of load power demand and establishes calibration demand based on demand fitting results; Power generation fitting module: construct a dynamic configuration model using the calibration requirements, and perform power generation fitting of wind power generation and photovoltaic power generation based on the environmental time series prediction results to establish power generation fitting results; Configuration optimization module: synchronizes the power generation fitting result and the environmental steady-state identifier to the dynamic configuration model, performs cost-stability demand power supply configuration optimization, and establishes demand power supply configuration optimization results; Configuration management module: performs optimized configuration management of wind, solar and storage mobile power sources based on the optimization results of the required power supply configuration.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for optimizing the configuration of wind, solar, and mobile power supplies in a complex environment described in any one of claims 1 to 7 are implemented.

Images