Configuration method of wind-solar hybrid power system based on intelligent algorithm

Abstract

The present invention relates to the technical field of complementary energy data analysis, and in particular to a method for configuring a wind-solar complementary power supply system based on an intelligent algorithm. The method comprises the following steps: collecting wind-solar environment perception data, wind-solar complementary equipment physical parameters, and wind-solar complementary equipment distribution data; analyzing wind-solar environment perception trend prediction data based on wind-solar complementary equipment perception data; performing wind-solar complementary equipment simulation operation test according to the wind-solar complementary equipment physical parameters, and designing a wind-solar complementary equipment automation control engine through the test results; transmitting wind-solar environment perception trend prediction data and corresponding wind-solar complementary equipment distribution data to the wind-solar complementary equipment automation control engine to analyze the wind-solar complementary equipment automation control parameters; and performing intelligent control operations of wind-solar complementary equipment on the wind-solar complementary power supply system through the wind-solar complementary equipment automation control parameters. The present invention realizes efficient and intelligent wind-solar complementary energy collection.

Description

Technical Field

[0001] The present invention relates to the technical field of complementary energy data analysis, and in particular to a wind-solar complementary power supply system configuration method based on an intelligent algorithm. Background Art

[0002] With the continuous growth of global energy demand and the increasing awareness of environmental protection, the development and utilization of clean energy has become an important direction in the current energy field. Wind power generation and photovoltaic power generation, as two major renewable energy sources, are green, environmentally friendly and rich in resources. Due to the uneven temporal and spatial distribution and intermittent characteristics of wind and solar energy, power generation systems that only use wind or solar energy have certain limitations in terms of power supply stability and energy utilization efficiency. In order to overcome the above problems, wind-solar complementary power generation systems have been widely studied and applied. By combining the power generation characteristics of wind and solar energy, the wind-solar complementary system has achieved energy complementarity and optimization to a certain extent, and improved the stability of energy supply. With the rapid development of Internet of Things technology and intelligent algorithms, new technical means have been provided for the intelligent upgrade of wind-solar complementary power supply systems. Through the real-time collection of environmental data by Internet of Things sensors, and the use of intelligent algorithms to model, predict and optimize the complex and changeable wind and solar environment, the operating efficiency and energy utilization rate of the wind-solar complementary system can be effectively improved. However, the configuration method of traditional wind-solar complementary power supply system mainly relies on empirical models and static parameter design, or the effect of the configuration of wind-solar complementary power supply system is poor, and it is impossible to accurately model, predict and optimize the complex and changeable wind-solar environment. It lacks dynamic perception and real-time optimization capabilities, and it is difficult to adapt to complex environmental changes and diverse application scenario requirements. Summary of the invention

[0003] Based on this, the present invention provides a wind-solar complementary power supply system configuration method based on an intelligent algorithm to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a wind-solar hybrid power system configuration method based on an intelligent algorithm comprises the following steps:

[0005] Step S1: using the Internet of Things sensor to collect the wind and solar environment perception data of the wind and solar complementary power supply analysis area to generate wind and solar environment perception data; performing wind and solar environment perception global aggregation feature analysis based on the wind and solar environment perception data to generate wind and solar environment perception global aggregation feature data;

[0006] Step S2: Design a conditional probability distribution model of the wind environment perception trend based on the Gaussian process regression model and the wind environment perception global aggregation feature data to generate a wind environment perception trend analysis model; perform real-time data monitoring and processing based on the wind environment perception data to generate real-time wind environment perception data; and transmit the real-time wind environment perception data to the wind environment perception trend analysis model to perform wind environment perception trend prediction processing to generate wind environment perception trend prediction data;

[0007] Step S3: Obtain the physical parameters of the wind-solar complementary equipment and the distribution data of the wind-solar complementary equipment in the wind-solar complementary power supply analysis area; perform model simulation and control processing according to the physical parameters of the wind-solar complementary equipment to generate model simulation and control data; use the preset wind-solar complementary resource test set and the model simulation and control data to perform a wind-solar complementary equipment simulation operation test to generate wind-solar complementary equipment simulation operation test data; perform wind-solar complementary state game optimization of the power conversion rate data based on the wind-solar complementary equipment simulation operation test data to generate wind-solar complementary optimized state conversion rate data; design a wind-solar complementary equipment automation control engine according to the wind-solar complementary optimized state conversion rate data and the corresponding model simulation and control data;

[0008] Step S4: Transmit the wind-solar environment perception trend prediction data and the corresponding wind-solar complementary equipment distribution data to the wind-solar complementary equipment automation control engine to perform environmental perception automation control parameter analysis of the wind-solar complementary equipment, and generate wind-solar complementary equipment automation control parameters; perform intelligent control operations of the wind-solar complementary equipment on the wind-solar complementary power supply system through the wind-solar complementary equipment automation control parameters, wherein the wind-solar complementary power supply system is an equipment terminal that drives and controls the wind-solar complementary equipment in the wind-solar complementary power supply analysis area.

[0009] Further, step S1 includes the following steps:

[0010] Step S11: using the Internet of Things sensor to collect the wind and solar environment perception data of the wind and solar complementary power supply analysis area, and generate wind and solar environment perception data;

[0011] Step S12: performing time series data and spatial data analysis according to the scenery environment perception data, and generating scenery environment perception time series data and scenery environment perception spatial data respectively;

[0012] Step S13: designing a scenery environment perception global aggregation convolution layer based on scenery environment perception time series data and scenery environment perception spatial data;

[0013] Step S14: performing scenery environment perception global aggregation feature analysis according to the scenery environment perception global aggregation convolution layer to generate scenery environment perception global aggregation feature data.

[0014] Further, step S13 includes the following steps:

[0015] Step S131: constructing a scenery environment perception time series feature convolution layer based on the scenery environment perception time series data;

[0016] Step S132: constructing a scenery environment perception spatial feature convolution layer based on the scenery environment perception spatial data;

[0017] Step S133: analyzing the temporal and spatial mapping relationship of scenery environment perception according to the scenery environment perception spatial feature convolution layer and the scenery environment perception temporal feature convolution layer, and generating a scenery environment perception spatiotemporal mapping relationship;

[0018] Step S134: Design a spatiotemporal global aggregation convolution layer for scenery environment perception by using the scenery environment perception spatiotemporal mapping relationship for the scenery environment perception spatial feature convolution layer and the scenery environment perception temporal feature convolution layer, and generate a scenery environment perception global aggregation convolution layer.

[0019] Further, step S131 includes the following steps:

[0020] According to the wind and solar environment perception time series data, short-term time series cycle and long-term time series cycle analysis of wind and solar environment perception are performed to generate short-term time series cycle wind and solar environment perception data and long-term time series cycle wind and solar environment perception data respectively;

[0021] Based on the short-term wind and solar environment perception data and the long-term wind and solar environment perception data, a time sliding window of the wind and solar environment perception time series data is designed. According to the time sliding window, the wind and solar environment perception time series data are subjected to wind and solar environment perception time series convolution kernel parameter analysis to establish the wind and solar environment perception time series convolution kernel. Finally, the wind and solar environment perception time series feature convolution layer is constructed through the wind and solar environment perception time series convolution kernel.

[0022] Further, step S132 includes the following steps:

[0023] Performing scenery environment perception spatial distribution analysis processing on scenery environment perception spatial data to generate scenery environment perception spatial distribution analysis data;

[0024] Performing spatial specificity analysis of scenery environment perception based on the spatial distribution analysis data of scenery environment perception to generate spatial specificity data of scenery environment perception;

[0025] According to the spatial specificity data of scenery environment perception, a spatial specificity region division window of scenery environment perception spatial data is designed, and according to the spatial specificity region division window, scenery environment perception spatial convolution kernel parameter analysis is performed on the scenery environment perception spatial data to establish the scenery environment perception spatial convolution kernel, and then the scenery environment perception spatial feature convolution layer is constructed through the scenery environment perception spatial convolution kernel.

[0026] Further, step S2 includes the following steps:

[0027] Step S21: performing frequency domain feature data conversion processing on the scenery environment perception global aggregate feature data to generate scenery environment perception global aggregate frequency domain feature data;

[0028] Step S22: Designing a conditional probability distribution model of the wind and solar environment perception trend for the wind and solar environment perception global aggregated frequency domain feature data based on the Gaussian process regression model, and generating a wind and solar environment perception trend analysis model;

[0029] Step S23: Perform real-time data monitoring and processing according to the wind and solar environment perception data to generate real-time wind and solar environment perception data; and transmit the real-time wind and solar environment perception data to the wind and solar environment perception trend analysis model to perform wind and solar environment perception trend prediction processing to generate wind and solar environment perception trend prediction data.

[0030] Further, step S3 includes the following steps:

[0031] Step S31: obtaining physical parameters of wind-solar complementary equipment and distribution data of wind-solar complementary equipment in the wind-solar complementary power supply analysis area;

[0032] Step S32: Performing physical modeling processing on the wind-solar complementary equipment according to the physical parameters of the wind-solar complementary equipment to generate a physical model of the wind-solar complementary equipment;

[0033] Step S33: performing model simulation control processing according to the physical model of the wind-solar complementary equipment to generate model simulation control data;

[0034] Step S34: using a preset wind-solar complementary resource test set to perform a wind-solar complementary equipment simulation operation test on the model simulation control data to generate wind-solar complementary equipment simulation operation test data;

[0035] Step S35: performing a wind-solar complementary state analysis of the simulated operation test data of the wind-solar complementary equipment to generate test wind-solar complementary state data;

[0036] Step S36: performing fuzzy processing on the wind-solar complementary state according to the wind-solar complementary state test data to generate fuzzy data on the wind-solar complementary state;

[0037] Step S37: Performing a test wind-solar complementary power conversion rate analysis according to the wind-solar complementary equipment simulation operation test data, and generating test wind-solar complementary power conversion rate data;

[0038] Step S38: Based on the test wind-solar complementary power conversion rate data and the test wind-solar complementary state fuzzification data, the power conversion rate data of the wind-solar complementary state game optimization is performed to generate wind-solar complementary optimized state conversion rate data;

[0039] Step S39: Designing a wind-solar complementary equipment automation control engine according to the wind-solar complementary optimization state conversion rate data and the corresponding model simulation control data.

[0040] Further, step S36 includes the following steps:

[0041] Step S361: performing wind and photovoltaic complementary state evaluation processing on the test wind-solar complementary state data according to the preset wind-solar complementary state evaluation decision to generate test wind-solar complementary state evaluation data;

[0042] Step S362: designing a test wind-solar complementary state quantitative evaluation set according to the test wind-solar complementary state evaluation data;

[0043] Step S363: Perform fuzzy analysis on the test wind-solar complementary state through the test wind-solar complementary state quantitative evaluation set to generate fuzzy data on the test wind-solar complementary state.

[0044] Further, step S38 includes the following steps:

[0045] Step S381: Based on the test wind-solar complementary power conversion rate data, the test wind-solar complementary state fuzzy data is analyzed for the power conversion rate of the test wind-solar complementary state, and the test wind-solar complementary state power conversion rate data is generated, wherein the test wind-solar complementary state power conversion rate data includes the test wind complementary state power conversion rate data and the corresponding test photovoltaic power complementary conversion rate data;

[0046] Step S382: performing a test wind-solar complementary state collaborative feature analysis according to the test wind-solar complementary state power conversion rate data, and generating test wind-solar complementary state collaborative feature data;

[0047] Step S383: Design a wind-solar complementary conversion constraint decision based on the test wind-solar complementary state collaborative feature data and the selection of the optimized test wind-solar complementary state power conversion rate data, and perform wind and photovoltaic complementary state game optimization processing on the test wind complementary state power conversion rate data and the corresponding test photovoltaic power complementary conversion rate data through the wind-solar complementary conversion constraint decision to generate wind-solar complementary optimized state conversion rate data.

[0048] Further, step S4 includes the following steps:

[0049] Step S41: transmitting the wind-solar environment perception trend prediction data to the wind-solar complementary equipment distribution data to map the wind-solar environment perception trend prediction data of the equipment, and generating the equipment wind-solar environment perception trend prediction data;

[0050] Step S42: transmitting the equipment wind-solar environment perception trend prediction data to the wind-solar complementary equipment automation control engine to analyze the environment perception automation control parameters of each wind-solar complementary equipment, and generate the wind-solar complementary equipment automation control parameters;

[0051] Step S43: executing a drive control program configuration operation on the wind-solar complementary power supply system through the wind-solar complementary equipment automatic control parameters, and executing the intelligent control operation of the wind-solar complementary equipment through the configured wind-solar complementary power supply system.

[0052] The beneficial effect of the present application is that the use of IoT sensors to collect data from the analysis area of ​​wind-solar complementary power sources can significantly improve the comprehensiveness and real-time nature of data acquisition. The sensor deployment covers the key locations of the analysis area to obtain wind and solar environment perception data in multiple dimensions, including wind speed, wind direction, light intensity, temperature and humidity. The collected wind and solar environment perception data is analyzed in time series and space. Time series analysis captures the dynamic laws of wind and solar environment changes over time, which helps to predict short-term and long-term trends; spatial analysis reveals the spatial distribution characteristics of wind and solar resources in the region, providing guidance for the reasonable layout of equipment and resource allocation. By constructing a wind and solar environment perception time series feature convolution layer, the features of the time dimension are efficiently extracted from the time series data, the trends and laws of wind and solar environment changes over time are captured, and the periodic patterns, mutation points and long-term change trends in the data can be automatically identified. Constructing a spatial feature convolution layer based on wind and solar environment perception spatial data helps to deeply explore the characteristics of the environment in spatial distribution, identify local features and global patterns in spatial data, and reveal the distribution laws and correlations of resources such as wind speed and light in different regions. By analyzing the mapping relationship between the temporal feature convolution layer and the spatial feature convolution layer of wind and solar environment perception, the dynamic coupling characteristics between time and space dimensions are deeply explored to improve the global perception of the dynamic changes of wind and solar resources. The spatial and temporal feature convolution layers are designed with a global aggregation convolution layer based on the time-space mapping relationship, which integrates the key features of the time and space dimensions and realizes the unified expression of multi-dimensional information. The global aggregation convolution layer improves the system's ability to predict the global trend of wind and solar resources, and highly summarizes the dynamic change mode and global trend of the wind and solar environment in the region, enhancing the overall perception of the complex wind and solar environment. By converting the global aggregation feature data of wind and solar environment perception into frequency domain feature data, the hidden frequency patterns and periodic features are extracted from the time domain signal, and the regular fluctuations in resource changes, such as high-frequency disturbances and low-frequency trends of wind speed and light intensity, are effectively identified. The conditional dependence of various wind and solar source characteristics is comprehensively considered through the Gaussian process regression model, so as to accurately evaluate the resource distribution trend under different environmental conditions. The real-time wind and solar environment perception data is generated through real-time data monitoring and processing, and is predicted in combination with the trend analysis model to achieve the ability to respond to dynamic environmental changes in real time. Transmit real-time data to the trend analysis model to provide real-time support for the operation decision-making of the wind-solar complementary system, optimize the response speed and efficiency of the system, and ensure the maximum utilization of resources and the stability of equipment operation. By obtaining the physical parameters and distribution data of the equipment in the wind-solar complementary power supply analysis area, the actual operation status and layout information of the wind-solar complementary equipment can be fully grasped. Physical modeling is performed according to the physical parameters of the equipment to truly simulate the working status and performance of the equipment under different environmental conditions. It can not only reflect the regularity of equipment operation, but also identify its potential bottlenecks and optimization space, providing a reliable theoretical basis for subsequent simulation and control strategies.Using physical models for simulation control processing, the dynamic response of wind-solar complementary equipment under various working conditions is predicted in a virtual environment, potential operating problems are identified, and the effectiveness of optimization strategies is verified. The equipment simulation operation test of the simulation control data is carried out through the preset wind-solar complementary resource test set, which can verify the accuracy of the model simulation results and the actual adaptability of the equipment, and provide a basis for optimizing equipment performance and adjusting control strategies. The state analysis of the simulation operation test data is carried out to understand the operating characteristics of wind-solar complementary equipment and its behavior patterns under different environmental conditions, identify bottlenecks and anomalies in equipment operation, and provide quantitative reference for equipment performance optimization. The test state data is fuzzified to simplify complex state characteristics into an operable fuzzy logic form. This processing method improves the ability to express the state characteristics of the equipment, especially in the face of uncertainty and nonlinear conditions in the form of wind and photovoltaic sources. The power conversion rate analysis of the simulation operation test data is carried out to evaluate the energy utilization efficiency and optimization potential of the equipment, providing a quantitative basis for improving resource utilization and reducing energy consumption. Based on the power conversion rate data and state fuzzification data, game optimization is carried out to effectively balance the operating status of wind power and photovoltaic equipment, improve the overall power conversion efficiency of the system, and the game optimization method ensures that each device works together under complex environmental conditions to achieve the optimization of energy utilization efficiency. According to the optimized state conversion rate data and simulation control data, the automatic control engine is designed to realize the intelligent control of wind-solar complementary equipment, and the control strategy can be dynamically adjusted according to the real-time environmental changes and equipment status to improve the intelligence level of the system. The wind-solar environment perception trend prediction data is mapped with the wind-solar complementary equipment distribution data to ensure that the prediction information matches the actual equipment operating environment and distribution, and improve the applicability and accuracy of the wind-solar photovoltaic source prediction data corresponding to each wind-solar complementary equipment. The equipment wind-solar environment perception trend prediction data is transmitted to the automatic control engine and parameter analysis is performed, which can generate specific control parameters according to the actual operation requirements of the equipment, dynamically adapt to environmental changes, ensure the stability and efficiency of equipment operation, and provide key technical support for the realization of intelligent control. The generated automatic control parameters are used to execute the drive control program configuration of the wind-solar complementary power supply system, and implement intelligent control operations to realize the fully automated operation and management of the wind-solar complementary equipment, effectively improving the operating efficiency and resource utilization of the equipment, while reducing the errors caused by human intervention. It can respond to environmental changes in real time and optimize equipment performance, enhancing the overall operation of the wind-solar complementary power supply system to maximize power conversion.

[0053] Therefore, the configuration method of the wind-solar complementary power supply system based on intelligent algorithm of the present invention accurately models and predicts the complex and changeable wind-solar environment, so as to accurately analyze the wind and photovoltaic energy trends corresponding to each wind-solar complementary device in the wind-solar complementary power supply analysis area, and feed back the analysis results to the wind-solar complementary power supply system. The wind-solar complementary power supply system dynamically perceives and automatically controls and adjusts each wind-solar complementary device through intelligent algorithm, so that the wind-solar complementary device with dynamic perception and adjustment can maximize the reception of wind and photovoltaic corresponding energy data and convert them into power supply, thereby ensuring the maximization of energy utilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic flow chart of the steps of a method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to the present invention;

[0055] Figure 2 for Figure 1 Detailed implementation steps of step S1 in FIG.

[0056] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0059] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0060] It should be understood that although the terms "first", "second", etc. are used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly a second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0061] To achieve this, please refer to Figures 1 to 3 The present invention provides a configuration method for a wind-solar hybrid power system based on an intelligent algorithm. In the embodiments of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the steps of the wind-solar complementary power system configuration method based on the intelligent algorithm of the present invention, and the wind-solar complementary power system configuration method based on the intelligent algorithm includes the following steps:

[0062] Step S1: using the Internet of Things sensor to collect the wind and solar environment perception data of the wind and solar complementary power supply analysis area to generate wind and solar environment perception data; performing wind and solar environment perception global aggregation feature analysis based on the wind and solar environment perception data to generate wind and solar environment perception global aggregation feature data;

[0063] In an embodiment of the present invention, IoT sensors are arranged to cover the wind-solar complementary power supply analysis area, and the types of sensors include wind speed sensors, light sensors, temperature and humidity sensors, and atmospheric pressure sensors. These sensors are arranged according to a predetermined density and position to ensure comprehensive monitoring of the wind and solar environment in the area. Each sensor collects corresponding environmental data at a certain sampling frequency (for example, sampling once per second). The collected data include but are not limited to environmental parameters such as wind speed, light intensity, temperature, humidity, and air pressure. All sensors transmit the data to the central data processing platform in real time. During the data transmission process, the data transmission rate must ensure real-time and accuracy to avoid data loss or delay, so as to form complete wind and solar environment perception data. The collected wind and solar environment perception data is sorted in chronological order to form wind and solar environment perception time series data. For the data collected by each sensor, data segmentation is performed within a fixed time interval to form a data sequence within a period of time. For example, the wind speed sensor collects wind speed data once per second to form a time series sequence of one data point per second. After a period of time, these data points will be summarized as a set of wind speed time series data. Then, spatial data analysis is performed for the data collected by sensors at different positions within the same time range. Spatial data analysis divides and groups sensor data from different geographical locations by location to generate spatial data for wind and solar environment perception. At this time, the generation of spatial data not only considers the physical location, but also reasonably classifies it according to the distance between sensors and the distribution of the region to ensure that the spatial data can accurately reflect the spatial characteristics of the wind and solar complementary area. Based on the time series data and spatial data of wind and solar environment perception, a global aggregation convolution layer for wind and solar environment perception is designed. The purpose of this convolution layer is to fuse time series data and spatial data to extract high-level information with global characteristics. The time series data convolution layer will convolve the data based on the convolution kernel to identify the periodic change characteristics in the data. The convolution kernel size of the time series convolution layer will be set to be determined according to the time interval of the data, for example, every 10 minutes is a time step. The spatial data convolution layer will convolve the data based on the spatial distribution. The size and step size of the convolution kernel are set according to the distribution of the equipment and the area of ​​the region to ensure that important patterns in the spatial distribution can be captured. Combining the processing results of the temporal convolution layer and the spatial convolution layer, they are aggregated in a weighted manner, and finally a global aggregation convolution layer that integrates temporal and spatial features is designed. The features extracted by the convolution layer are processed using the fully connected layer to obtain the global aggregation feature data of the landscape environment.

[0064] Step S2: Design a conditional probability distribution model of the wind environment perception trend based on the Gaussian process regression model and the wind environment perception global aggregation feature data to generate a wind environment perception trend analysis model; perform real-time data monitoring and processing based on the wind environment perception data to generate real-time wind environment perception data; and transmit the real-time wind environment perception data to the wind environment perception trend analysis model to perform wind environment perception trend prediction processing to generate wind environment perception trend prediction data;

[0065] In the embodiment of the present invention, the fast Fourier transform (FFT) algorithm is used to perform frequency domain feature conversion on the global aggregated feature data of wind and solar environment perception, and the feature data such as wind speed and light intensity in the time domain are decomposed into different frequency components as processing logic to identify the spectrum characteristics of the medium-term, short-term and long-term change trends of the wind and solar environment in different spaces. The generated global aggregated frequency domain feature data of wind and solar environment perception includes the time series frequency information of wind power and photovoltaic power in different spaces. Based on the Gaussian process regression model, the conditional probability distribution model of the wind and solar environment perception trend is designed for the global aggregated frequency domain feature data of wind and solar environment perception, and the Gaussian process regression model (Gaussian Process Regression, GPR) is used to design the conditional probability distribution model. First, feature engineering is performed on the frequency domain feature data, and the low-frequency features and high-frequency features are weightedly combined to generate an input feature vector; secondly, the feature vector is input into the Gaussian process regression model, and the correlation between the feature components is calculated based on its built-in kernel function; finally, the parameters of the conditional probability distribution function are determined through model training, and a wind and solar environment perception trend analysis model reflecting the trends of wind speed, light intensity, etc. is generated. The wind and solar environment perception data is collected in real time using IoT sensors, and the real-time data monitoring and processing is performed through the data preprocessing module, including data cleaning, outlier removal, normalization, etc., to ensure the accuracy and consistency of the real-time data. The generated real-time wind and solar environment perception data is stored by timestamp and sent to the wind and solar environment perception trend analysis model in real time through a data transmission protocol (such as MQTT or HTTP). Subsequently, the trend analysis model receives the real-time data input and calculates the future trend of wind speed and light intensity under the current environmental conditions based on the conditional probability distribution function. The trend prediction results are output in the form of time series, including short-term predictions and long-term predictions. For example, in a wind and solar resource area, through real-time monitoring, it is found that the current wind speed is high and is on an upward trend. The analysis model predicts that the wind speed will continue to increase in the next 2 hours, while the light intensity will decrease due to dense clouds. The generated wind and solar environment perception trend prediction data provides a real-time decision-making basis for the operation optimization of wind and solar complementary equipment.

[0066] Step S3: Obtain the physical parameters of the wind-solar complementary equipment and the distribution data of the wind-solar complementary equipment in the wind-solar complementary power supply analysis area; perform model simulation and control processing according to the physical parameters of the wind-solar complementary equipment to generate model simulation and control data; use the preset wind-solar complementary resource test set and the model simulation and control data to perform a wind-solar complementary equipment simulation operation test to generate wind-solar complementary equipment simulation operation test data; perform wind-solar complementary state game optimization of the power conversion rate data based on the wind-solar complementary equipment simulation operation test data to generate wind-solar complementary optimized state conversion rate data; design a wind-solar complementary equipment automation control engine according to the wind-solar complementary optimized state conversion rate data and the corresponding model simulation and control data;

[0067] In the embodiment of the present invention, the physical parameters and distribution data of all wind-solar complementary devices in the wind-solar complementary power supply analysis area are collected by deploying Internet of Things devices, storing wind-solar complementary device construction parameters in the database, and using the GIS geographic information system. The physical parameters of the wind-solar complementary device are used, and the physical parameters of the wind-solar complementary device mainly include four parts: wind power generation module, solar photovoltaic module, energy storage system, and intelligent control unit. The physical modeling of the equipment is performed by multi-physics field simulation tools, and mathematical models and correlation models of wind turbines and photovoltaic modules are established respectively. The physical modeling process of the wind turbine adopts aerodynamic theory, and based on the blade element momentum theory (BEM), the correlation equation between wind speed, blade angle and power output is constructed; the photovoltaic module constructs the nonlinear relationship between light intensity, ambient temperature and current-voltage (IV) curve according to the five-parameter model of the photovoltaic cell. In the modeling process, the physical parameters of the equipment, such as the influence of blade length on wind capture area and the influence of the number of series and parallel photovoltaic modules on output characteristics, are quantified one by one to form an accurate simulation model of the equipment. The physical model of the wind-solar complementary equipment is imported into the simulation environment, and the dynamic simulation process is executed. The dynamic simulation process imitates the operation of the actual wind-solar complementary equipment. By comparing the actual operation characteristics and the simulation characteristics, the accuracy of the model is verified and its parameter settings are optimized, and the model simulation control data is generated, including the control adjustment information of the wind power components and photovoltaic components in each posture and the corresponding status information. Based on the wind-solar complementary resource test set, the previously established wind-solar complementary equipment physical model and the corresponding model simulation control data are comprehensively tested. The wind-solar resource data included in the test set include the time series fluctuation data of wind speed, the all-day distribution curve of light intensity, the ambient temperature change curve, and the long-term weather change trend simulation. By inputting the test set into the simulation model one by one, the response behavior of the wind-solar complementary equipment under various environmental change conditions is observed. The simulation operation test content includes the operation stability of wind turbines under low wind speed and high wind speed limit conditions, the output power change characteristics of photovoltaic equipment under strong light and low light conditions, and the power output stability of the coordinated operation between wind-solar complementary equipment. The generated test data includes the power output curve of the equipment, the equipment response time, the output fluctuation amplitude, the heating condition, etc. Using the data generated by the simulation test, the operating status of the wind-solar complementary equipment is quantitatively evaluated through the set analysis indicators. The analysis indicators include the power coefficient, speed stability, and vibration state of the wind turbine; the photoelectric conversion efficiency, output power fluctuation coefficient, and hot spot generation of the photovoltaic equipment; as well as the wind-solar power smoothing effect, voltage fluctuation characteristics, and power load adaptation capability of the overall system. Based on these indicators, the performance characteristics of the equipment are aggregated and analyzed through big data processing technology to generate wind-solar complementary state analysis results. The multi-dimensional state information in the test wind-solar complementary state data is fuzzy processed in order to map the continuous state data to a specific fuzzy set through the fuzzy membership function, which is convenient for subsequent system optimization.Fuzzy processing first sets a fuzzy membership function for each analysis indicator to generate a fuzzy data set containing the states of all devices under test resource conditions. According to the simulation operation test data of wind-solar complementary equipment, the equipment conversion rate analysis is carried out to evaluate the wind-photovoltaic power conversion efficiency of the equipment under different environmental conditions, and the input energy and output power of wind turbines and photovoltaic equipment are calculated. The conversion rate is obtained by comparing the input wind power and photovoltaic power and the output power of the equipment. The equipment conversion rate data includes the wind power conversion rate of wind turbines, the photovoltaic conversion rate of photovoltaic equipment, and the conversion efficiency data of the comprehensive wind-solar complementary system. According to the test wind-solar complementary power conversion rate data and the test wind-solar complementary state fuzzy data, the game optimization algorithm is applied to optimize the state of the wind-solar complementary system, and the conversion rate data of the equipment and its fuzzy state data are combined to establish a game optimization model of the wind-solar complementary system. Through the analysis of the equipment state, the operation strategy of each equipment (such as wind turbines and photovoltaic systems) is determined to optimize the energy conversion rate of the overall system. In the game model, wind turbines and photovoltaic devices adjust their power distribution according to different environmental conditions (such as wind speed, light intensity, etc.) to avoid over-reliance on a single device. The optimized conversion rate data is obtained through the game optimization algorithm. The optimized conversion rate data finally generated will include the optimized conversion rate of wind-solar complementary equipment and the corresponding comprehensive conversion rate data of the wind-solar complementary system. Based on the wind-solar complementary optimized state conversion rate data and the corresponding model simulation control data, the automatic control engine of the wind-solar complementary equipment is designed and implemented, and the optimized conversion rate data of the wind-solar complementary system is used to set the target parameters for the automatic control engine. The automatic control engine adjusts the operation strategy of the equipment in real time according to these target parameters, dynamically allocates the workload of wind turbines and photovoltaic equipment through the control algorithm, and optimizes the energy demand of the power grid and the output of the equipment. For example, in the case of low wind speed, the automatic control system will increase the power generation ratio of photovoltaic panels, such as adjusting the angle of photovoltaic panels to receive the photovoltaic ratio more efficiently, reducing the workload of wind turbines, and improving the overall system efficiency; in the case of high wind speed, the system will give priority to using wind turbines to generate electricity, such as adjusting the air inlet to reduce the output of the photovoltaic system. The output of the control engine will include real-time equipment adjustment instructions and equipment status information, ensuring that the wind-solar hybrid power system is always in the optimal operating state and improving the energy efficiency and reliability of the system.

[0068] Step S4: Transmit the wind-solar environment perception trend prediction data and the corresponding wind-solar complementary equipment distribution data to the wind-solar complementary equipment automation control engine to perform environmental perception automation control parameter analysis of the wind-solar complementary equipment, and generate wind-solar complementary equipment automation control parameters; perform intelligent control operations of the wind-solar complementary equipment on the wind-solar complementary power supply system through the wind-solar complementary equipment automation control parameters, wherein the wind-solar complementary power supply system is an equipment terminal that drives and controls the wind-solar complementary equipment in the wind-solar complementary power supply analysis area.

[0069] In an embodiment of the present invention, the data processed by the wind and solar environment perception trend prediction (such as the future trend prediction of wind and photovoltaic power generation equipment) is mapped with the distribution data of each device in the wind and solar complementary power supply system. By combining the wind and solar environment perception trend prediction data with the spatial position and operating capacity of the equipment, the performance of each device in the future period of time is predicted, and the generated equipment wind and solar environment perception trend prediction data includes the future power generation prediction capacity of each device and the association information with the surrounding environment. The equipment wind and solar environment perception trend prediction data is input into the wind and solar complementary equipment automatic control engine for further processing. According to the future environmental change trend of each device, the optimized control parameters of each device under the current and future environmental conditions are analyzed. The automatic control engine will analyze the optimal operating parameters of each device according to the wind and photovoltaic power generation capacity of each device, the geographical environment where the device is located, the predicted wind and solar environment data, and the physical parameters of the device (such as the speed range of the wind turbine, the maximum output power of the photovoltaic panel, etc.). For example, if the system predicts that the wind is strong and the light is weak in the next hour, the control engine may analyze that the wind power generation equipment provides more power and reduces the output of the photovoltaic power generation equipment. The analysis results of the automatic control parameters may include the power adjustment range of the equipment, the adjustment of the operating state, the load matching, etc., and finally generate the control parameters of the wind-solar complementary equipment, which will be used to drive the next step of equipment operation optimization. Based on the automatic control parameters of the wind-solar complementary equipment, the entire wind-solar complementary power supply system is configured through the drive control program. During the configuration process, the control parameters of each device are loaded into the system, and the operating state of each wind-solar complementary equipment is adjusted according to the preset optimization strategy. The wind-solar complementary power supply system is a device terminal that drives and controls the wind-solar complementary equipment in the wind-solar complementary power supply analysis area, such as a computer device that automatically controls and adjusts the wind turbine and photovoltaic panel of the wind-solar complementary equipment through the PCL control component and the automatic control parameters of the wind-solar complementary equipment. The control program will intelligently adjust the wind and photovoltaic equipment according to the automatic control parameters of the equipment. For example, when the system predicts that the wind is strong and the light is insufficient in a certain period of time in the future, the program will instruct the wind power generation equipment to output more power, and the output power of the photovoltaic equipment will be weakened according to the actual environment. At this time, the intelligent control operation of the wind-solar complementary power supply system will ensure that the system maintains the best performance under different environmental conditions and maximizes the energy utilization of the entire power supply system. The operation of the drive control program configuration also includes equipment start and stop, power regulation, load distribution, etc., to ensure that the wind-solar hybrid power system maintains efficient and stable operation under real-time environmental conditions. This intelligent control mechanism helps to optimize power output in the complementary operation of wind and photovoltaic power generation equipment, while reducing resource waste and the probability of failure.

[0070] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0071] Step S11: using the Internet of Things sensor to collect the wind and solar environment perception data of the wind and solar complementary power supply analysis area, and generate wind and solar environment perception data;

[0072] In an embodiment of the present invention, IoT sensors are arranged to cover the wind-solar complementary power supply analysis area, and the types of sensors include wind speed sensors, light sensors, temperature and humidity sensors, and atmospheric pressure sensors. These sensors are arranged according to a predetermined density and position to ensure comprehensive monitoring of the wind and solar environment in the area. Each sensor collects corresponding environmental data at a certain sampling frequency (for example, once per second). The collected data includes but is not limited to environmental parameters such as wind speed, light intensity, temperature, humidity, and air pressure. All sensors transmit the data to the central data processing platform in real time. During the data transmission process, the data transmission rate must ensure real-time and accuracy to avoid data loss or delay, thereby forming complete wind and solar environment perception data.

[0073] Step S12: performing time series data and spatial data analysis according to the scenery environment perception data, and generating scenery environment perception time series data and scenery environment perception spatial data respectively;

[0074] In an embodiment of the present invention, the collected wind and solar environment perception data are sorted in chronological order to form wind and solar environment perception time series data. For the data collected by each sensor, data segmentation is performed within a fixed time interval to form a data sequence within a period of time. For example, the wind speed sensor collects wind speed data once per second to form a time series sequence of one data point per second. After a period of time, these data points will be summarized into a set of wind speed time series data. Then, spatial data analysis is performed on the data collected by sensors at different locations within the same time range. Spatial data analysis divides and groups sensor data from different geographical locations by location to generate wind and solar environment perception spatial data. At this point, the generation of spatial data not only takes into account the physical location, but also performs reasonable classification according to the distance between sensors and the distribution of regions to ensure that the spatial data can accurately reflect the spatial characteristics of the wind and solar complementary area.

[0075] Step S13: designing a scenery environment perception global aggregation convolution layer based on scenery environment perception time series data and scenery environment perception spatial data;

[0076] In the embodiment of the present invention, the collected time series data of wind and solar environment perception is used and input into the time series feature convolution layer for processing. The construction of the time series feature convolution layer needs to determine the size and step size of the convolution kernel according to factors such as the frequency of wind and solar data collection and time span, and perform nonlinear processing on the output through an activation function (such as ReLU) to generate wind and solar environment perception time series features. The wind and solar environment perception spatial data is gridded according to geographical regions, and the entire wind and solar complementary power supply analysis area is divided into several sub-regions. Through a two-dimensional convolution operation, a wind and solar environment perception spatial feature convolution layer is constructed. The convolution layer processes the entire grid area through a sliding convolution kernel to extract the spatial features between the regions, including wind speed gradient distribution, light intensity difference, etc. The output spatial features are used for subsequent time-space mapping relationship analysis. The correlation between the time series features and the spatial features is analyzed, and the time series features are weighted on the time axis to identify the historical time points that contribute the most to the current moment, and the spatial feature matrix is ​​weighted according to the importance of the region to highlight the impact of key areas. For example, in the wind speed prediction task, the spatiotemporal mapping relationship will focus on the distribution of areas with higher wind speeds and their changing trends over time. The spatiotemporal mapping relationship matrix of wind and solar environment perception is generated by matrix multiplication, which describes the mapping relationship between different temporal and spatial features and provides a basis for the design of the global aggregation convolution layer. The spatiotemporal mapping relationship matrix is ​​used to jointly process the temporal features and spatial features of wind and solar environment perception, and the spatiotemporal mapping relationship matrix is ​​used to adjust the weights of the temporal features so that the features at different time points are strengthened or suppressed according to their importance. The spatial features are similarly weighted to highlight the key areas in the spatial features. The adjusted temporal features and spatial features are further fused through multiple convolutional layers to design the global aggregation convolution layer of wind and solar environment perception.

[0077] Step S14: performing scenery environment perception global aggregation feature analysis according to the scenery environment perception global aggregation convolution layer to generate scenery environment perception global aggregation feature data.

[0078] In an embodiment of the present invention, the features extracted from the global aggregation convolution layer are further analyzed. The core of this process is to identify and extract key features such as long-term trends, periodic changes, and emergencies in the wind and solar environment. In order to ensure the accuracy of the aggregated features, the deep neural network algorithm is applied to further process the spatiotemporal features output by the convolution layer, and the features extracted by the convolution layer are processed using a fully connected layer to obtain global aggregated feature data of the wind and solar environment, and the change patterns of the time series data and spatial data are further modeled to generate stable aggregated features with strong predictive capabilities. These aggregated features can effectively reflect the overall environmental change trend of the wind and solar complementary power supply analysis area, and provide basic data support for subsequent wind and solar environment perception trend analysis and optimization.

[0079] Further, step S13 includes the following steps:

[0080] Step S131: constructing a scenery environment perception time series feature convolution layer based on the scenery environment perception time series data;

[0081] In an embodiment of the present invention, the collected time series data of wind and light environment perception is used and input into the time series feature convolution layer for processing. The construction of the time series feature convolution layer needs to determine the size and step size of the convolution kernel according to factors such as the collection frequency and time span of the wind and light data. For example, for high-frequency collection data such as wind speed and light intensity, the size of the convolution kernel can be set to a time span of 1 hour to capture the hourly change pattern, and the step size is set to 15 minutes to ensure sufficient time resolution. Through one-dimensional convolution operation, the convolution layer can effectively extract periodic change characteristics in the time series data, such as the light cycle of day and night, seasonal wind speed changes, etc. At the same time, in order to avoid data loss, the input data is expanded using boundary filling technology to keep the output size consistent. Finally, the output is nonlinearly processed by an activation function (such as ReLU) to generate wind and light environment perception time series features.

[0082] Step S132: constructing a scenery environment perception spatial feature convolution layer based on the scenery environment perception spatial data;

[0083] In an embodiment of the present invention, the spatial data of wind and solar environment perception is gridded according to geographical areas, and the entire wind and solar complementary power supply analysis area is divided into several sub-areas, and the data of each sub-area is represented as a characteristic value of a grid point, such as physical quantities such as wind speed and light intensity. A wind and solar environment perception spatial feature convolution layer is constructed through a two-dimensional convolution operation. The size of the convolution kernel is set according to the regional distribution range, for example, it is set to 3×3 grid points to capture the correlation between local areas. The convolution layer processes the entire grid area by sliding the convolution kernel, thereby extracting the spatial features between each area, including wind speed gradient distribution, light intensity difference, etc. In addition, through a pooling layer (such as maximum pooling or average pooling), the spatial features are further downsampled to reduce redundant information and enhance the feature expression capability. The spatial features finally output are used for subsequent spatiotemporal mapping relationship analysis.

[0084] Step S133: analyzing the temporal and spatial mapping relationship of scenery environment perception according to the scenery environment perception spatial feature convolution layer and the scenery environment perception temporal feature convolution layer, and generating a scenery environment perception spatiotemporal mapping relationship;

[0085] In an embodiment of the present invention, the feature matrix output from the temporal feature convolution layer and the spatial feature convolution layer is input into the spatiotemporal mapping module. This module adopts the spatiotemporal attention mechanism to analyze the correlation between temporal features and spatial features. First, the temporal features are weighted on the time axis to identify the historical time points that contribute the most to the current moment; at the same time, the spatial feature matrix is ​​weighted according to the importance of the region to highlight the impact of key areas. For example, in the wind speed prediction task, the spatiotemporal mapping relationship will focus on the distribution of areas with higher wind speeds and their changing trends over time. The fusion of temporal weights and spatial weights is achieved through matrix multiplication to generate a spatiotemporal mapping relationship matrix for wind and light environment perception. The matrix describes the mapping relationship between different temporal and spatial features, providing a basis for the design of the global aggregation convolution layer.

[0086] Step S134: Design a spatiotemporal global aggregation convolution layer for scenery environment perception by using the scenery environment perception spatiotemporal mapping relationship for the scenery environment perception spatial feature convolution layer and the scenery environment perception temporal feature convolution layer, and generate a scenery environment perception global aggregation convolution layer.

[0087] In an embodiment of the present invention, the temporal features and spatial features of wind and solar environment perception are jointly processed according to the spatiotemporal mapping relationship matrix, and a global aggregation convolution layer for wind and solar environment perception is designed. First, the spatiotemporal mapping relationship matrix is ​​used to adjust the weights of the temporal features so that the features at different time points are strengthened or suppressed according to their importance; then, a similar weighted processing is performed on the spatial features to highlight the key areas in the spatial features. Next, the adjusted temporal features and spatial features are further fused through multiple convolutional layers, and a spatiotemporal global aggregation convolution layer for wind and solar environment perception is designed based on the fused features to reflect the environmental change trends in time and space of the entire wind-solar complementary power supply analysis area, including the long-term light intensity distribution trend, the law of wind speed changes between regions, etc. Finally, the aggregated global trend data is output through the fully connected layer to provide the core input for the subsequent prediction of wind and solar environment perception trends.

[0088] Further, step S131 includes the following steps:

[0089] According to the wind and solar environment perception time series data, short-term time series cycle and long-term time series cycle analysis of wind and solar environment perception are performed to generate short-term time series cycle wind and solar environment perception data and long-term time series cycle wind and solar environment perception data respectively;

[0090] In an embodiment of the present invention, the time series data of wind and light environment perception is analyzed in time periodicity to divide it into short time series period and long time series period. The short time series period can be set as a data period at the hour level, such as the hourly changes of wind speed and light intensity; while the long time series period can be set as a daily or seasonal period, such as the daily and monthly change trends. The short time series period data can start with the details of the wind speed and light changes, and use 1 hour as a unit to extract the frequency characteristics of wind speed and light intensity; the long time series period data captures the trend changes on a longer time scale by calculating the daily average wind speed and light intensity. For example, by dividing the wind speed data by hour, short time series period data is obtained, where the hourly data represents the wind speed changes of the day. For the long time series period data, the daily wind speed and light data are summarized by month, the monthly average wind speed and light intensity are calculated, and the long-term seasonal change characteristics are extracted. At this time, the short-term period data can capture the daily wind speed and light intensity fluctuations, while the long-term period data provides the global trend of seasonal or annual changes.

[0091] Based on the short-term wind and solar environment perception data and the long-term wind and solar environment perception data, a time sliding window of the wind and solar environment perception time series data is designed. According to the time sliding window, the wind and solar environment perception time series data are subjected to wind and solar environment perception time series convolution kernel parameter analysis to establish the wind and solar environment perception time series convolution kernel. Finally, the wind and solar environment perception time series feature convolution layer is constructed through the wind and solar environment perception time series convolution kernel.

[0092] In an embodiment of the present invention, a time series sliding window is constructed according to the generated short-term time series periodic data and long-term time series periodic data. In a specific implementation, the time series sliding window is used to extract local features in the time series data, and is particularly suitable for capturing short-term and long-term change patterns. First, the length of the sliding window is set. The short-term window length can be set to 24 hours, and the long-term window length can be set to 7 days or 1 month. The step size of the window sliding can be set to 1 hour to ensure that the features can smoothly transition from one time point to the next time point. On the short-term wind and light environment perception data, the window sliding obtains the local change characteristics of wind speed and light within 24 hours by taking every 24 hours as a window. For long-term periodic data, the design of the sliding window will be adjusted according to the monthly or seasonal data, such as sliding the window once a month, so as to capture the trend within a longer period. The data in the sliding window is characterized by local convolution calculation to obtain dynamic change information in different time periods. Based on the data in the time series sliding window, the time series convolution kernel parameters are analyzed, and the size of the convolution kernel needs to be selected according to the frequency distribution of the characteristics of the wind and light environment perception data (such as wind speed, light intensity, etc.). For example, within a 24-hour sliding window, a convolution kernel length of 3 to 5 can be used to extract local trends within several consecutive time points. In a window of 7 days or longer, the size of the convolution kernel should be increased accordingly, such as using a convolution kernel of 7 to 14 to capture trend changes in a long period. For wind speed data, the convolution kernel will process wind speed changes by weighted processing, filter out random noise and extract regular fluctuations. For example, the convolution kernel calculates the average wind speed and change trend over the past few hours, and then identifies the pattern of periodic fluctuations in wind speed. For light intensity data, a similar method is used to extract the fluctuation characteristics of sunshine intensity through the convolution kernel, thereby helping the subsequent wind-solar hybrid power system configuration to provide accurate environmental prediction data. The wind-solar environment perception time series feature convolution layer is constructed through the parameter analysis results of the wind-solar environment perception time series convolution kernel. The wind-solar environment perception time series feature convolution layer extracts the local time characteristics of the time series data through convolution operations with short-term and long-term data. For example, the designed convolution kernel is used to perform convolution processing on the time series data, and local time features such as short-term changes in wind speed or light intensity, periodic fluctuations, etc. are extracted in the convolution layer. The output of this convolution layer will become the time series feature data of wind and solar environment perception, which is used to reflect the changing characteristics of the environment within a specific time window, especially the comprehensive reflection of short-term and long-term periodic changes. These extracted time series feature data can provide support for subsequent spatiotemporal mapping analysis, help identify the regularity of time series changes, and provide data support for equipment scheduling and energy conversion efficiency optimization in the configuration of wind and solar complementary power supply systems.

[0093] Further, step S132 includes the following steps:

[0094] Performing scenery environment perception spatial distribution analysis processing on scenery environment perception spatial data to generate scenery environment perception spatial distribution analysis data;

[0095] In an embodiment of the present invention, the spatial distribution analysis processing of the wind and solar environment perception spatial data requires clarifying the geographical distribution characteristics of the data and extracting the geographical spatial factors that affect the distribution of wind and solar complementary resources, such as terrain, altitude, wind field intensity, solar radiation, etc. The analysis area is divided into grid units, for example, one unit per 10 square kilometers, and the data of each unit is statistically analyzed, including indicators such as wind speed, wind direction, sunshine duration and light intensity. By calculating the mean and variance of wind power and photovoltaic distribution in each unit, spatial distribution analysis data is generated. For example, in a certain wind and solar resource analysis area, the collected wind speed data presents different distribution characteristics in mountainous and plain areas. Through analytical processing, the generated wind and solar environment perception spatial distribution analysis data clearly points out that the wind speed in the mountains is higher than that in the plains, and the solar radiation intensity is more concentrated in the plains. These data can provide a reliable basis for subsequent spatial specificity analysis.

[0096] Performing spatial specificity analysis of scenery environment perception based on the spatial distribution analysis data of scenery environment perception to generate spatial specificity data of scenery environment perception;

[0097] In an embodiment of the present invention, the spatial specificity is analyzed according to the spatial distribution analysis data, and the spatial distribution analysis data is grouped using a clustering algorithm (for example, based on k-means or DBSCAN) to find areas with significant differences. For example, wind speed and light intensity are used as clustering factors to perform spatial specificity clustering on the analysis data. The generated spatial specificity data can reflect the differences in wind and solar resources in each region, such as which areas have strong wind speeds but weak light, and which areas have both evenly distributed. For example, the clustering results of a certain analysis area show that the northern region belongs to a high wind speed and low light specific area, and the southern plains belong to a high light and low wind speed specific area. These specific data can guide the layout of wind and solar complementary equipment in different areas and the adjustment of operating parameters.

[0098] According to the spatial specificity data of scenery environment perception, a spatial specificity region division window of scenery environment perception spatial data is designed, and according to the spatial specificity region division window, scenery environment perception spatial convolution kernel parameter analysis is performed on the scenery environment perception spatial data to establish the scenery environment perception spatial convolution kernel, and then the scenery environment perception spatial feature convolution layer is constructed through the scenery environment perception spatial convolution kernel.

[0099] In an embodiment of the present invention, a spatial specific region division window is designed according to spatial specific data, including setting different regional division standards according to the distribution pattern of specific data, such as using geographical boundaries or numerical boundaries to determine the scope of each specific region. The size of the window can be adjusted according to the distribution density of wind and light resources, for example, a smaller division window (such as 1 square kilometer) is used in areas with large wind speed changes, and a larger division window (such as 10 square kilometers) is used in areas with relatively uniform wind speeds. For example, in a region, smaller window units are divided in the northern mountainous high wind speed area to capture the local characteristics of wind speed changes; while the southern plain area is divided into larger window units to simplify the complexity of data processing due to the small wind speed changes. By dividing the window, the spatial specific region can be refined and segmented, laying the foundation for the subsequent convolution kernel parameter analysis. According to the divided spatial specific region window, the landscape environment perception spatial convolution kernel is designed. The parameter design of the convolution kernel is based on the change amplitude and direction of the distribution of wind speed and illumination characteristics in the region. In a larger window, a larger convolution kernel (such as 5×5 unit) is used to capture global features; in a smaller window, a smaller convolution kernel (such as 3×3 unit) is used to capture local features. The weights of the convolution kernels are optimized through data regression analysis to ensure that they can extract the main features in the area. For example, in high wind speed areas, a 5×5 convolution kernel is used to capture the overall trend of wind speed changes, and the weights are adjusted through regression analysis to be sensitive to wind speed changes. In high light areas, a 3×3 convolution kernel is used to extract local differences in light intensity, and the convolution kernel weights are tuned to highlight the characteristics of areas with strong light. Using the wind and light environment perception spatial convolution kernel, a wind and light environment perception spatial feature convolution layer is constructed, and convolution operations are performed on the wind and light environment perception spatial data. The convolution kernel slides over the entire spatial data to extract the characteristic patterns of spatial distribution. For example, the wind speed-light intensity joint distribution data of a specific area is output through the spatial feature convolution layer to identify the resource advantages of different areas. The constructed spatial feature convolution layer can output the characteristics of high wind speed areas and high light areas in matrix form, and mark the high and low resource distribution respectively. These spatial features will provide key data support for the subsequent global aggregation convolution layer design and equipment optimization configuration.

[0100] Further, step S2 includes the following steps:

[0101] Step S21: performing frequency domain feature data conversion processing on the scenery environment perception global aggregate feature data to generate scenery environment perception global aggregate frequency domain feature data;

[0102] In the embodiment of the present invention, the fast Fourier transform (FFT) algorithm is used to perform frequency domain feature conversion on the global aggregated feature data of the wind and solar environment perception, and the feature data such as wind speed and light intensity in the time domain are decomposed into different frequency components as processing logic to identify the spectrum characteristics of the medium-term, short-term and long-term change trends of the wind and solar environment in different spaces. For wind speed data, it is decomposed into low-frequency (long-term wind speed change trend) and high-frequency (short-term fluctuation characteristics) components through FFT analysis; for light intensity data, the main frequency of the day and night periodic changes and the high-frequency interference caused by abnormal weather can be identified through frequency domain conversion, and the generated wind and solar environment perception global aggregated frequency domain feature data includes the time series frequency information of wind and photovoltaic in different spaces. For example, in a certain wind and solar resource area, after performing frequency domain analysis on the wind speed data through FFT, it is found that the time period corresponding to the main frequency is 24 hours (day and night cycle), and the high-frequency component reflects the severity of wind speed fluctuations in a short time. These frequency domain features provide a basis for accurately predicting the trend of wind and solar resources.

[0103] Step S22: Designing a conditional probability distribution model of the wind and solar environment perception trend for the wind and solar environment perception global aggregated frequency domain feature data based on the Gaussian process regression model, and generating a wind and solar environment perception trend analysis model;

[0104] In an embodiment of the present invention, a Gaussian Process Regression (GPR) model is used to design a conditional probability distribution model based on the global aggregated frequency domain feature data of wind and solar environment perception. First, feature engineering is performed on the frequency domain feature data, and the low-frequency features and high-frequency features are weighted and combined to generate an input feature vector; secondly, the feature vector is input into the Gaussian process regression model, and the correlation between the feature components is calculated based on its built-in kernel function; finally, the parameters of the conditional probability distribution function are determined through model training to generate a wind and solar environment perception trend analysis model that reflects trends such as wind speed and light intensity. For example, for a certain wind and solar resource area, the trained Gaussian process regression model shows that the wind speed signal with a higher weight of the low-frequency component has a strong periodicity, while the high-frequency component of the light intensity is significantly affected by weather factors. The generated conditional probability distribution model can describe the probability of future changes in wind and solar resources under specific environmental conditions.

[0105] Step S23: Perform real-time data monitoring and processing according to the wind and solar environment perception data to generate real-time wind and solar environment perception data; and transmit the real-time wind and solar environment perception data to the wind and solar environment perception trend analysis model to perform wind and solar environment perception trend prediction processing to generate wind and solar environment perception trend prediction data.

[0106] In an embodiment of the present invention, the Internet of Things sensor is used to collect wind and solar environment perception data in real time, and the data preprocessing module is used to perform real-time data monitoring and processing, including data cleaning, outlier removal, normalization processing, etc., to ensure the accuracy and consistency of the real-time data. The generated real-time wind and solar environment perception data is stored by timestamp and sent to the wind and solar environment perception trend analysis model in real time through a data transmission protocol (such as MQTT or HTTP). Subsequently, the trend analysis model receives the real-time data input and calculates the future trend of wind speed and light intensity under the current environmental conditions based on the conditional probability distribution function. The trend prediction results are output in the form of a time series, including short-term predictions and long-term predictions. For example, in a wind and solar resource area, through real-time monitoring, it is found that the current wind speed is high and is on an upward trend. The analysis model predicts that the wind speed will continue to increase in the next 2 hours, while the light intensity will be weakened due to dense clouds. The generated wind and solar environment perception trend prediction data provides a real-time decision-making basis for the operation optimization of wind and solar complementary equipment.

[0107] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S3 in the embodiment, step S3 includes the following steps:

[0108] Step S31: obtaining physical parameters of wind-solar complementary equipment and distribution data of wind-solar complementary equipment in the wind-solar complementary power supply analysis area;

[0109] In an embodiment of the present invention, the physical parameters and distribution data of all wind-solar complementary equipment in the wind-solar complementary power supply analysis area are collected by deploying Internet of Things devices, storing wind-solar complementary equipment construction parameters in the database, and using the GIS geographic information system. The physical parameters of the equipment include but are not limited to the rated power, speed range, blade length, rated wind speed, and wind utilization coefficient of the wind turbine; the photoelectric conversion efficiency, open circuit voltage, short circuit current, and maximum power point characteristics of the photovoltaic equipment. The distribution data is obtained through on-site surveys, satellite image analysis, and the coordinate database of the equipment management system to obtain the geographical location of each device, the spacing between devices, the altitude, and the geographical azimuth. In the specific implementation process, for example, in a certain wind-solar complementary area, the distribution images of wind turbines and photovoltaic equipment are accurately obtained through drone aerial photography combined with geographic data analysis methods, and the equipment numbers and their physical parameters are marked to provide basic data support for subsequent physical modeling.

[0110] Step S32: Performing physical modeling processing on the wind-solar complementary equipment according to the physical parameters of the wind-solar complementary equipment to generate a physical model of the wind-solar complementary equipment;

[0111] In the embodiment of the present invention, the physical parameters of the wind-solar complementary equipment are used, and the physical parameters of the wind-solar complementary equipment mainly include four parts: wind power generation module: including a micro vertical wind turbine cluster, a controller, etc., for converting wind power into electrical energy. Solar photovoltaic module: composed of photovoltaic panels, movable brackets, inverters, etc., for converting solar energy into electrical energy. Energy storage system: usually includes a battery pack and a battery control system, which is used to store excess electrical energy and may not be used in the grid-connected system. Intelligent control unit: composed of PLC, proximity switch, deflection system, wind speed sensor, light sensor, etc., responsible for the status monitoring, attitude adjustment, data collection and power generation control of the entire system. Working principle: based on the PLC collecting wind speed and wind direction sensor and light sensor data, the priority of photovoltaic power generation and wind power generation is judged. By controlling the solenoid valve to drive the mini cylinder to push the photovoltaic panel, the photovoltaic panel is swung to achieve the multifunctional new energy power generation intelligent control module under strong light conditions during the day to improve the efficiency of photovoltaic power generation; under weak light conditions at night, the air inlet area is increased to improve the power generation efficiency of the micro-fan cluster. The physical modeling of the equipment is carried out through multi-physics simulation tools, and the mathematical models and associated models of wind turbines and photovoltaic modules are established respectively. The physical modeling process of wind turbines adopts aerodynamic theory and builds the associated equation between wind speed, blade angle and power output based on blade element momentum theory (BEM); photovoltaic modules build the nonlinear relationship between light intensity, ambient temperature and current-voltage (IV) curve according to the five-parameter model of photovoltaic cells. In the modeling process, the physical parameters of the equipment, such as the effect of blade length on wind capture area and the effect of the number of series and parallel connections of photovoltaic modules on output characteristics, are quantified one by one to form an accurate simulation model of the equipment. For example, for a wind turbine with a rated power of 2 MW, parameters such as blade length of 45 m and rated wind speed of 10 m / s are input to generate a wind speed-output power curve model; for a set of 250 W monocrystalline silicon photovoltaic panels, the light intensity of 800 W / m² and ambient temperature of 25℃ are input to generate an IV curve with an output current of 7.5 A.

[0112] Step S33: performing model simulation control processing according to the physical model of the wind-solar complementary equipment to generate model simulation control data;

[0113] In an embodiment of the present invention, a physical model of a wind-solar complementary device is imported into a simulation environment, and a dynamic simulation process is executed. The dynamic simulation process imitates the operation of an actual wind-solar complementary device. For example, a model simulation control module is added with PLC, deflection motor, proximity switch, limit switch and other devices. The PLC controller is connected to a wind speed and direction sensor and a light sensor via RS485 communication, and reads climate information in a regular polling manner to provide a control basis for the deflection of the photovoltaic panel. The deflection angle of the photovoltaic component is adjusted in real time to give priority to photovoltaic power generation under strong light conditions and to give priority to wind power generation under strong wind conditions, thereby achieving more efficient energy conversion. In order to simplify the control structure and improve the stability and wind resistance of the system, a PLC is used to control the solenoid valve and the mini cylinder to achieve deflection. The mini cylinder directly pulls the photovoltaic panel, and controls the angle and posture of the photovoltaic panel through the activity of the cylinder. When the solenoid valve is powered on, the cylinder air supply piston is pushed; when the solenoid valve is powered off, the cylinder exhaust piston returns to the initial position, which has the effect of limiting deflection. The simulation process includes real-time monitoring of the equipment response characteristics, such as the speed, power output stability, vibration state and corresponding wind component control parameters of the wind turbine under different wind speed conditions; the output power, voltage fluctuation, hot spot effect and corresponding photovoltaic component control parameters of the photovoltaic component under different light and temperature conditions. By comparing the actual operation characteristics and simulation characteristics, the accuracy of the model is verified and its parameter settings are optimized, and the model simulation control data is generated, including the control adjustment information and corresponding status information of the wind component and photovoltaic component under various postures.

[0114] Step S34: using a preset wind-solar complementary resource test set to perform a wind-solar complementary equipment simulation operation test on the model simulation control data to generate wind-solar complementary equipment simulation operation test data;

[0115] In an embodiment of the present invention, based on the wind-solar complementary resource test set, the previously established physical model of the wind-solar complementary equipment and the corresponding model simulation control data are comprehensively tested. The wind-solar resource data contained in the test set include the time series fluctuation data of wind speed, the all-day distribution curve of light intensity, the ambient temperature change curve, and the long-term weather change trend simulation. By inputting the test set into the simulation model one by one, the response behavior of the wind-solar complementary equipment under various environmental change conditions is observed. The simulation operation test content includes the operation stability of the wind turbine under low wind speed and high wind speed limit conditions, the output power change characteristics of the photovoltaic equipment under strong light and low light conditions, and the power output stability of the coordinated operation between wind-solar complementary equipment. The generated test data includes the power output curve of the equipment, the equipment response time, the output fluctuation amplitude, the heating condition, etc. For example, a test set contains a change curve of the wind speed from 0 m / s to 15 m / s in one day. In the simulation operation test, the gradual change trend of the wind turbine output power from 0 to 2000 kW is recorded, and the output power of the photovoltaic panel at peak light is captured and the power stability is verified.

[0116] Step S35: performing a wind-solar complementary state analysis of the simulated operation test data of the wind-solar complementary equipment to generate test wind-solar complementary state data;

[0117] In the embodiment of the present invention, the data generated by the simulation operation test is used to quantitatively evaluate the operation status of the wind-solar complementary equipment through the set analysis indicators. The analysis indicators include the power coefficient, speed stability, and vibration state of the wind turbine; the photoelectric conversion efficiency, output power fluctuation coefficient, and hot spot generation of the photovoltaic equipment; and the wind-solar power smoothing effect, voltage fluctuation characteristics, and power load adaptation capability of the overall system. Based on these indicators, the performance characteristics of the equipment are aggregated and analyzed through big data processing technology to generate wind-solar complementary state analysis results. For example, under the condition of rapid fluctuation of the test wind speed, the average power coefficient of the wind turbine is 0.42, and the frequency of the vibration state deviating from the safe range value is 5 times; the photoelectric conversion efficiency of the photovoltaic equipment under high temperature conditions is reduced to 15%. According to the analysis results, the equipment operation status is classified into three states: "high efficiency and stability", "mild fluctuation", and "severe fluctuation", which are marked as test status data sets respectively.

[0118] Step S36: performing fuzzy processing on the wind-solar complementary state according to the wind-solar complementary state test data to generate fuzzy data on the wind-solar complementary state;

[0119] In an embodiment of the present invention, the multi-dimensional state information in the test wind-solar complementary state data is fuzzified, with the purpose of mapping the continuous state data to a specific fuzzy set through a fuzzy membership function, so as to facilitate subsequent system optimization. The fuzzy processing first sets a fuzzy membership function for each analysis indicator. For example, the membership function of the power coefficient is a triangular function, which defines the high efficiency range as 0.4 to 0.45, the low efficiency range as 0 to 0.2, and the overload range as above 0.45; the membership function of the photoelectric conversion efficiency defines the high efficiency range as above 17%, the medium efficiency range as 12% to 17%, and the low efficiency range as below 12%. Using fuzzy logic rules, all device state data are classified and assigned membership. The output data of fuzzy processing includes the fuzzy membership set of equipment under different wind and solar resource conditions. For example, the membership of a wind turbine is "high efficiency" 0.8 and "low efficiency" 0.2 at a wind speed of 12 m / s, and the membership is "high efficiency" 0.5 and "low efficiency" 0.5 at a wind speed of 6 m / s. Finally, a fuzzy data set containing the status of all equipment under the test resource conditions is generated.

[0120] Step S37: Performing a test wind-solar complementary power conversion rate analysis according to the wind-solar complementary equipment simulation operation test data, and generating test wind-solar complementary power conversion rate data;

[0121] In an embodiment of the present invention, based on the simulation operation test data of the wind-solar complementary equipment, the equipment conversion rate analysis is performed to evaluate the wind-to-photovoltaic energy conversion efficiency of the equipment under different environmental conditions, the input energy and output power of the wind turbine and the photovoltaic equipment are calculated, and the conversion rate is obtained by comparing the input wind power and photovoltaic power and the output power of the equipment. For example, in a set of test data, when the wind speed is 12 m / s, the input wind power of the wind turbine is 5000 kWh, and the output power is 2000 kWh, then the wind power conversion rate of the wind turbine is 40%. In the same test set, when the light intensity of the photovoltaic equipment is 1000 W / m², the input photovoltaic power is 4000 kWh, the output power is 1000 kWh, and the photovoltaic conversion rate is 25%. The conversion rate data of the equipment includes the wind power conversion rate of the wind turbine, the photovoltaic conversion rate of the photovoltaic equipment, and the comprehensive conversion efficiency data of the wind-solar complementary system, which provide a basis for subsequent optimization and adjustment of equipment operation.

[0122] Step S38: Based on the test wind-solar complementary power conversion rate data and the test wind-solar complementary state fuzzification data, the power conversion rate data of the wind-solar complementary state game optimization is performed to generate wind-solar complementary optimized state conversion rate data;

[0123] In the embodiment of the present invention, the state of the wind-solar complementary system is optimized by applying a game optimization algorithm according to the test wind-solar complementary power conversion rate data and the test wind-solar complementary state fuzzification data, and the conversion rate data of the device is combined with its fuzzified state data to establish a game optimization model of the wind-solar complementary system. By analyzing the state of the device, the operation strategy of each device (such as a wind turbine and a photovoltaic system) is determined so that the energy conversion rate of the overall system is optimized. In the game model, the wind turbine and the photovoltaic device adjust their power distribution according to different environmental conditions (such as wind speed, light intensity, etc.) to avoid over-reliance on a single device. The optimized conversion rate data is obtained by the game optimization algorithm. For example, the wind turbine reduces its output power when the wind speed is low, and the photovoltaic device increases its power generation on sunny days, so as to ensure that the overall wind-solar complementary system can achieve the optimal power output under different environmental conditions. The optimized conversion rate data finally generated will include the optimized wind-solar complementary device conversion rate and the corresponding wind-solar complementary system comprehensive conversion rate data.

[0124] Step S39: Designing a wind-solar complementary equipment automation control engine according to the wind-solar complementary optimization state conversion rate data and the corresponding model simulation control data.

[0125] In the embodiment of the present invention, based on the conversion rate data of the optimized state of wind-solar hybrid and the corresponding model simulation control data, the automatic control engine of the wind-solar hybrid equipment is designed and implemented, and the optimized conversion rate data of the wind-solar hybrid system is used to set the target parameters for the automatic control engine. For example, the optimization target can be the power output of the equipment, the maximization of power generation efficiency or the minimization of energy consumption. The automatic control engine adjusts the operation strategy of the equipment in real time according to these target parameters, dynamically allocates the workload of wind turbines and photovoltaic equipment through control algorithms, and optimizes the energy demand of the power grid and the output of the equipment. For example, under low wind speed conditions, the automatic control system will increase the power generation ratio of photovoltaic panels, such as adjusting the angle of photovoltaic panels to receive the photovoltaic ratio more efficiently, reducing the workload of wind turbines, so as to improve the overall system efficiency; under high wind speed conditions, the system will give priority to using wind turbines to generate electricity, such as adjusting the air inlet to reduce the output of the photovoltaic system. The output of the control engine will include real-time equipment adjustment instructions and equipment status information to ensure that the wind-solar hybrid power supply system is always in the optimal operating state and improve the energy efficiency and reliability of the system.

[0126] Further, step S36 includes the following steps:

[0127] Step S361: performing wind and photovoltaic complementary state evaluation processing on the test wind-solar complementary state data according to the preset wind-solar complementary state evaluation decision to generate test wind-solar complementary state evaluation data;

[0128] In an embodiment of the present invention, the evaluation standard for the complementary state of wind power and photovoltaic power generation of the wind-solar complementary equipment is defined as the overall power conversion efficiency, and the collaborative working state of the wind and photovoltaic systems is evaluated based on environmental data (such as wind speed, light intensity, etc.) and the power generation capacity of the equipment. For example, assuming that in a specific period of time, the wind speed is 12 m / s, the light intensity is 500 W / m², the output power of the wind turbine is 3000 kWh, and the output power of the photovoltaic panel is 1500 kWh. Under this environmental condition, the evaluation decision will judge the working state of the wind-solar complementary equipment based on the set threshold. If both the wind speed and the light can support a higher output power of the equipment, good wind-solar complementary state evaluation data is generated. The evaluation data will include information such as the power generation contribution ratio of wind power and photovoltaic power generation, the balance of the complementary state, etc., as the basis for subsequent processing.

[0129] Step S362: designing a test wind-solar complementary state quantitative evaluation set according to the test wind-solar complementary state evaluation data;

[0130] In an embodiment of the present invention, a quantitative evaluation set is designed based on the evaluation data of the wind-solar complementary state. This set is used to quantitatively analyze and evaluate different wind-solar complementary states and provide numerical results. For example, a series of evaluation dimensions are set, such as the total power generation of the wind-solar complementary system, the output ratio of each device, the energy efficiency ratio, the system stability, etc. According to the evaluation data, the output power of wind power generation and photovoltaic power generation is quantified as the power generation efficiency of the wind-solar complementary system (such as the power generation efficiency of wind power equipment is 50%, and the power generation efficiency of photovoltaic equipment is 60%). In addition, the response speed and stability of the system (such as the adaptability of the equipment to wind speed fluctuations) need to be evaluated. Through these quantitative indicators, a quantitative evaluation set of wind-solar complementary states is formed.

[0131] Step S363: Perform fuzzy analysis on the test wind-solar complementary state through the test wind-solar complementary state quantitative evaluation set to generate fuzzy data on the test wind-solar complementary state.

[0132] In an embodiment of the present invention, a fuzzy analysis of the wind-solar complementary state is performed using a quantitative evaluation set. The fuzzy algorithm converts the quantitative evaluation data into fuzzy data to adapt to the uncertainty and ambiguity in practical applications. For example, in actual tests, the output power of wind-solar equipment fluctuates to a certain extent and cannot be accurately evaluated. In the fuzzification process, numerical data such as the conversion state of wind and photovoltaic power generation efficiency and system stability are converted into fuzzy sets, such as setting the corresponding wind power receiving mode when the lower wind power is converted to the power supply state to an inefficient state. For another example, the stability score of the system is converted into a fuzzy level (such as "good", "general", "poor") according to its fluctuation range, and the generated fuzzy data of the test wind-solar complementary state includes the comprehensive evaluation state of the system, such as the wind power conversion state of the wind power receiving mode under the current environmental conditions, the photovoltaic power conversion state of the photovoltaic receiving mode, stability, etc., which is convenient for optimizing decision-making and control execution in subsequent steps.

[0133] Further, step S38 includes the following steps:

[0134] Step S381: Based on the test wind-solar complementary power conversion rate data, the test wind-solar complementary state fuzzy data is analyzed for the power conversion rate of the test wind-solar complementary state, and the test wind-solar complementary state power conversion rate data is generated, wherein the test wind-solar complementary state power conversion rate data includes the test wind complementary state power conversion rate data and the corresponding test photovoltaic power complementary conversion rate data;

[0135] In an embodiment of the present invention, the fuzzy data of the test wind-solar complementary state is analyzed based on the test wind-solar complementary power conversion rate data, and the conversion rate information is extracted from the wind power and photovoltaic power generation data of the system. The conversion rate of wind-solar complementary equipment refers to the ratio of the actual output power of wind power and photovoltaic power generation equipment to the theoretical maximum output power per unit time. Assuming that in a certain period of time, the theoretical maximum power of the wind power generation equipment is 3000 kWh, and the actual output power is 2500 kWh, the conversion rate of wind power is 83.3%. Similarly, assuming that the theoretical maximum power of the photovoltaic power generation equipment is 2000 kWh, and the actual output power is 1800 kWh, the conversion rate of photovoltaic power is 90%. Combined with the state fuzzy data of the wind-solar complementary equipment (such as the wind power is in the "medium" state and the photovoltaic power is in the "high" state), the power conversion rate data of the wind and photovoltaic complementary state can be generated. These conversion rate data will include the conversion rates of wind power and photovoltaic power, and the comprehensive conversion efficiency of the wind-solar complementary equipment is reflected through the fuzzy calculation results. The generated conversion rate data provides a quantitative basis for subsequent optimization and decision-making.

[0136] Step S382: performing a test wind-solar complementary state collaborative feature analysis according to the test wind-solar complementary state power conversion rate data, and generating test wind-solar complementary state collaborative feature data;

[0137] In an embodiment of the present invention, the generated test wind-solar complementary state power conversion rate data is subjected to collaborative feature analysis. The collaborative features of the wind-solar complementary system reflect the collaborative effect of the wind and photovoltaic power generation equipment at the same time. The focus of collaborative analysis is to identify the complementary advantages of wind and photovoltaic power generation equipment in actual operation and their relationship. For example, assuming that in a certain period of time, the conversion rate of wind power generation equipment is high (such as 85%), while the conversion rate of photovoltaic power generation equipment is low (such as 60%). In this case, the collaborative feature data of the system reflects how the two devices can maximize the overall efficiency of the system through complementarity under specific conditions. In order to achieve quantitative analysis of collaborative features, by calculating the sum of wind and solar power generation, output fluctuations, response time and other dimensions, the degree of mutual promotion between the two is identified, and these collaborative feature data are formalized into quantitative indicators, such as the synergy coefficient of wind and solar equipment, the joint utilization rate of wind and photovoltaic, etc., to further provide data support for the optimization of wind and solar complementary.

[0138] Step S383: Design a wind-solar complementary conversion constraint decision based on the test wind-solar complementary state collaborative feature data and the selection of the optimized test wind-solar complementary state power conversion rate data, and perform wind and photovoltaic complementary state game optimization processing on the test wind complementary state power conversion rate data and the corresponding test photovoltaic power complementary conversion rate data through the wind-solar complementary conversion constraint decision to generate wind-solar complementary optimized state conversion rate data.

[0139] In the embodiment of the present invention, according to the test wind-solar complementary state collaborative characteristic data, combined with the optimized power conversion rate data, the wind-solar complementary conversion constraint decision is designed, and the optimization constraint conditions of the wind and photovoltaic power generation equipment, such as the maximum value of the system power output, and the collaborative optimization requirements between them are determined by analyzing the collaborative efficiency of the wind-solar complementary equipment under different environments. For example, if the system hopes to rely more on wind power generation when the wind is strong, and increase the proportion of photovoltaic power generation when the light is strong, the relevant constraints are designed, such as when the wind power equipment conversion rate reaches a certain threshold, the output ratio of the photovoltaic equipment must be lowered, and the optimal configuration of the wind-solar complementary system is calculated by performing game optimization on these constraints. In the game optimization process, the wind and photovoltaic power generation equipment consider their own optimal operation strategies respectively, and adjust their own behaviors based on the state of the other party until the global optimal state is reached. The optimization result will generate the wind-solar complementary optimized state conversion rate data, specifically including the optimized conversion rate of wind and photovoltaic equipment and the optimal operation strategy of the entire system, which will be used for the subsequent automatic control and state adjustment of the wind-solar complementary equipment.

[0140] Further, step S4 includes the following steps:

[0141] Step S41: transmitting the wind-solar environment perception trend prediction data to the wind-solar complementary equipment distribution data to map the wind-solar environment perception trend prediction data of the equipment, and generating the equipment wind-solar environment perception trend prediction data;

[0142] In an embodiment of the present invention, the data processed by the wind and solar environment perception trend prediction (such as the future trend prediction of wind and photovoltaic power generation equipment) is mapped with the distribution data of each device in the wind and solar complementary power supply system. The wind and solar environment perception trend prediction data includes the prediction of wind and light changes in the future period of time, such as the prediction that the wind speed will continue to increase or the light will reach the maximum value in the next 3 hours. The wind and solar complementary equipment distribution data includes the geographical location, power capacity, technical parameters and other information of each wind power generation and photovoltaic power generation equipment in the wind and solar complementary power supply system. By combining the wind and solar environment perception trend prediction data with the spatial location and operating capacity of the equipment, the performance of each device in the future period of time is predicted. For example, if a certain device is located in an area with strong wind, it will provide higher power output in the future period of time. This process generates the equipment wind and solar environment perception trend prediction data through algorithm mapping, which specifically includes the future power generation prediction capability of each device and its association with the surrounding environment, and provides it to the next control system for further analysis.

[0143] Step S42: transmitting the equipment wind-solar environment perception trend prediction data to the wind-solar complementary equipment automation control engine to analyze the environment perception automation control parameters of each wind-solar complementary equipment, and generate the wind-solar complementary equipment automation control parameters;

[0144] In an embodiment of the present invention, the device wind and solar environment perception trend prediction data is input into the wind and solar complementary device automatic control engine for further processing. According to the future environmental change trend of each device, the optimized control parameters of each device under the current and future environmental conditions are analyzed. The automatic control engine will analyze the optimal operating parameters of each device based on the wind and photovoltaic power generation capacity of each device, the geographical environment where the device is located, the predicted wind and solar environment data, and the physical parameters of the device (such as the speed range of the wind turbine, the maximum output power of the photovoltaic panel, etc.). For example, if the system predicts that the wind is strong and the light is weak in the next hour, the control engine may analyze that the wind power generation equipment provides more electricity and reduces the output of the photovoltaic power generation equipment. The analysis results of the automatic control parameters may include the power adjustment range of the equipment, the operation status adjustment, the load matching, etc., and finally generate the control parameters of the wind and solar complementary equipment. These parameters will be used to drive the next step of equipment operation optimization.

[0145] Step S43: executing a drive control program configuration operation on the wind-solar complementary power supply system through the wind-solar complementary equipment automatic control parameters, and executing the intelligent control operation of the wind-solar complementary equipment through the configured wind-solar complementary power supply system.

[0146] In an embodiment of the present invention, the entire wind-solar complementary power supply system is configured through a drive control program based on the automatic control parameters of the wind-solar complementary equipment. During the configuration process, the control parameters of each device are loaded into the system, and the operating state of each wind-solar complementary equipment is adjusted according to the preset optimization strategy. The wind-solar complementary power supply system is a device terminal that drives and controls the wind-solar complementary equipment in the wind-solar complementary power supply analysis area, such as a computer device that automatically controls and adjusts the wind turbine, photovoltaic panel, etc. of the wind-solar complementary equipment through the PCL control component and the automatic control parameters of the wind-solar complementary equipment. The control program will intelligently adjust the wind and photovoltaic equipment according to the automatic control parameters of the equipment. For example, when the system predicts that the wind is strong and the light is insufficient in a certain period of time in the future, the program will instruct the wind power generation equipment to output more power, and the output power of the photovoltaic equipment will be weakened according to the actual environment. At this time, the intelligent control operation of the wind-solar complementary power supply system will ensure that the system maintains the best performance under different environmental conditions and maximizes the energy utilization of the entire power supply system. The operation configured by the drive control program also includes the start and stop of the equipment, power regulation, load distribution, etc., to ensure that the wind-solar complementary power supply system maintains efficient and stable operation under real-time environmental conditions. This intelligent control mechanism helps to optimize power output in the complementary operation of wind and photovoltaic power generation equipment, while reducing resource waste and the probability of failure.

[0147] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0148] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for configuring a wind-solar hybrid power system based on an intelligent algorithm, characterized in that: The following steps are involved: Step S1: using the Internet of Things sensor to collect the wind and solar environment perception data of the wind and solar complementary power supply analysis area to generate wind and solar environment perception data; performing wind and solar environment perception global aggregation feature analysis based on the wind and solar environment perception data to generate wind and solar environment perception global aggregation feature data; Step S2: Design a conditional probability distribution model of the wind environment perception trend based on the Gaussian process regression model and the wind environment perception global aggregation feature data to generate a wind environment perception trend analysis model; perform real-time data monitoring and processing based on the wind environment perception data to generate real-time wind environment perception data; The instant wind and solar environment perception data is transmitted to the wind and solar environment perception trend analysis model for wind and solar environment perception trend prediction processing to generate wind and solar environment perception trend prediction data; Step S3: Obtain the physical parameters of the wind-solar complementary equipment and the distribution data of the wind-solar complementary equipment in the wind-solar complementary power supply analysis area, wherein the physical parameters of the wind-solar complementary equipment include the rated power, speed range, blade length, rated wind speed, wind utilization coefficient of the wind turbine and the photoelectric conversion efficiency, open circuit voltage, short circuit current, and maximum power point characteristics of the photovoltaic equipment; perform model simulation and control processing according to the physical parameters of the wind-solar complementary equipment to generate model simulation and control data; perform wind-solar complementary equipment simulation operation test using the preset wind-solar complementary resource test set and model simulation and control data to generate wind-solar complementary equipment simulation operation test data; Based on the simulation operation test data of wind-solar complementary equipment, the power conversion rate data of wind-solar complementary state game optimization is performed to generate the wind-solar complementary optimized state conversion rate data; Design the wind-solar hybrid equipment automation control engine based on the wind-solar hybrid optimization state conversion rate data and the corresponding model simulation control data; Step S4: transmitting the wind-solar environment perception trend prediction data and the corresponding wind-solar complementary equipment distribution data to the wind-solar complementary equipment automation control engine to analyze the environment perception automation control parameters of the wind-solar complementary equipment and generate the wind-solar complementary equipment automation control parameters; The wind-solar complementary power system performs intelligent control operations of the wind-solar complementary equipment through the automatic control parameters of the wind-solar complementary equipment, wherein the wind-solar complementary power system is an equipment terminal that drives and controls the wind-solar complementary equipment in the wind-solar complementary power analysis area.

2. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using the Internet of Things sensor to collect the wind and solar environment perception data of the wind and solar complementary power supply analysis area, and generate wind and solar environment perception data; Step S12: performing time series data and spatial data analysis according to the scenery environment perception data, and generating scenery environment perception time series data and scenery environment perception spatial data respectively; Step S13: designing a scenery environment perception global aggregation convolution layer based on scenery environment perception time series data and scenery environment perception spatial data; Step S14: performing scenery environment perception global aggregation feature analysis according to the scenery environment perception global aggregation convolution layer to generate scenery environment perception global aggregation feature data.

3. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 2, characterized in that: Step S13 includes the following steps: Step S131: constructing a scenery environment perception time series feature convolution layer based on the scenery environment perception time series data; Step S132: constructing a scenery environment perception spatial feature convolution layer based on the scenery environment perception spatial data; Step S133: analyzing the temporal and spatial mapping relationship of scenery environment perception according to the scenery environment perception spatial feature convolution layer and the scenery environment perception temporal feature convolution layer, and generating a scenery environment perception spatiotemporal mapping relationship; Step S134: Design a spatiotemporal global aggregation convolution layer for scenery environment perception by using the scenery environment perception spatiotemporal mapping relationship for the scenery environment perception spatial feature convolution layer and the scenery environment perception temporal feature convolution layer, and generate a scenery environment perception global aggregation convolution layer.

4. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 3 is characterized in that: Step S131 includes the following steps: According to the wind and solar environment perception time series data, short-term time series cycle and long-term time series cycle analysis of wind and solar environment perception are performed to generate short-term time series cycle wind and solar environment perception data and long-term time series cycle wind and solar environment perception data respectively; Based on the short-term wind and solar environment perception data and the long-term wind and solar environment perception data, a time sliding window of the wind and solar environment perception time series data is designed. According to the time sliding window, the wind and solar environment perception time series data are subjected to a wind and solar environment perception time series convolution kernel parameter analysis to establish a wind and solar environment perception time series convolution kernel. The wind and solar environment perception time series feature convolution layer is constructed through the wind and solar environment perception time series convolution kernel.

5. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 3, characterized in that: Step S132 includes the following steps: Performing scenery environment perception spatial distribution analysis processing on scenery environment perception spatial data to generate scenery environment perception spatial distribution analysis data; Performing spatial specificity analysis of scenery environment perception based on the spatial distribution analysis data of scenery environment perception to generate spatial specificity data of scenery environment perception; According to the spatial specificity data of scenery environment perception, a spatial specificity region division window of scenery environment perception spatial data is designed, and according to the spatial specificity region division window, scenery environment perception spatial convolution kernel parameter analysis is performed on the scenery environment perception spatial data to establish the scenery environment perception spatial convolution kernel, and then the scenery environment perception spatial feature convolution layer is constructed through the scenery environment perception spatial convolution kernel.

6. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing frequency domain feature data conversion processing on the scenery environment perception global aggregate feature data to generate scenery environment perception global aggregate frequency domain feature data; Step S22: Designing a conditional probability distribution model of the wind and solar environment perception trend for the wind and solar environment perception global aggregated frequency domain feature data based on the Gaussian process regression model, and generating a wind and solar environment perception trend analysis model; Step S23: Perform real-time data monitoring and processing according to the wind and solar environment perception data to generate real-time wind and solar environment perception data; and transmit the real-time wind and solar environment perception data to the wind and solar environment perception trend analysis model to perform wind and solar environment perception trend prediction processing to generate wind and solar environment perception trend prediction data.

7. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: obtaining physical parameters of wind-solar complementary equipment and distribution data of wind-solar complementary equipment in the wind-solar complementary power supply analysis area; Step S32: Performing physical modeling processing on the wind-solar complementary equipment according to the physical parameters of the wind-solar complementary equipment to generate a physical model of the wind-solar complementary equipment; Step S33: performing model simulation control processing according to the physical model of the wind-solar complementary equipment to generate model simulation control data; Step S34: using a preset wind-solar complementary resource test set to perform a wind-solar complementary equipment simulation operation test on the model simulation control data to generate wind-solar complementary equipment simulation operation test data; Step S35: performing a wind-solar complementary state analysis of the simulated operation test data of the wind-solar complementary equipment to generate test wind-solar complementary state data; Step S36: performing fuzzy processing on the wind-solar complementary state according to the wind-solar complementary state test data to generate fuzzy data on the wind-solar complementary state; Step S37: Performing a test wind-solar complementary power conversion rate analysis according to the wind-solar complementary equipment simulation operation test data, and generating test wind-solar complementary power conversion rate data; Step S38: Based on the test wind-solar complementary power conversion rate data and the test wind-solar complementary state fuzzification data, the power conversion rate data of the wind-solar complementary state game optimization is performed to generate wind-solar complementary optimized state conversion rate data; Step S39: Designing a wind-solar complementary equipment automation control engine according to the wind-solar complementary optimization state conversion rate data and the corresponding model simulation control data.

8. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 7, characterized in that: Step S36 includes the following steps: Step S361: performing wind and photovoltaic complementary state evaluation processing on the test wind-solar complementary state data according to the preset wind-solar complementary state evaluation decision to generate test wind-solar complementary state evaluation data; Step S362: designing a test wind-solar complementary state quantitative evaluation set according to the test wind-solar complementary state evaluation data; Step S363: Perform fuzzy analysis on the test wind-solar complementary state through the test wind-solar complementary state quantitative evaluation set to generate fuzzy data on the test wind-solar complementary state.

9. The method for configuring a wind-solar complementary power supply system based on an intelligent algorithm according to claim 7, characterized in that: Step S38 includes the following steps: Step S381: Based on the test wind-solar complementary power conversion rate data, the test wind-solar complementary state fuzzy data is analyzed for the power conversion rate of the test wind-solar complementary state, and the test wind-solar complementary state power conversion rate data is generated, wherein the test wind-solar complementary state power conversion rate data includes the test wind complementary state power conversion rate data and the corresponding test photovoltaic power complementary conversion rate data; Step S382: performing a test wind-solar complementary state collaborative feature analysis according to the test wind-solar complementary state power conversion rate data, and generating test wind-solar complementary state collaborative feature data; Step S383: Design a wind-solar complementary conversion constraint decision based on the test wind-solar complementary state collaborative feature data and the selection of the optimized test wind-solar complementary state power conversion rate data, and perform wind and photovoltaic complementary state game optimization processing on the test wind complementary state power conversion rate data and the corresponding test photovoltaic power complementary conversion rate data through the wind-solar complementary conversion constraint decision to generate wind-solar complementary optimized state conversion rate data.

10. The method for configuring a wind-solar hybrid power system based on an intelligent algorithm according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: transmitting the wind-solar environment perception trend prediction data to the wind-solar complementary equipment distribution data to map the wind-solar environment perception trend prediction data of the equipment, and generating the equipment wind-solar environment perception trend prediction data; Step S42: transmitting the equipment wind-solar environment perception trend prediction data to the wind-solar complementary equipment automation control engine to analyze the environment perception automation control parameters of each wind-solar complementary equipment, and generate the wind-solar complementary equipment automation control parameters; Step S43: executing a drive control program configuration operation on the wind-solar complementary power supply system through the wind-solar complementary equipment automatic control parameters, and executing the intelligent control operation of the wind-solar complementary equipment through the configured wind-solar complementary power supply system.

Images