Renewable energy access intelligent power distribution cabinet

Abstract

The invention relates to an intelligent power distribution cabinet with renewable energy access, which takes specific time as a step length, and monitors and collects real-time weather environment data of a local weather forecast in a future time sequence; extracting main features of the real-time weather environment data by adopting a principal component analysis method; establishing a Bayesian network model with the main characteristics of weather environment data as father nodes and the power generation condition of the power distribution cabinet as child nodes through historical data, inputting the real-time weather environment data into the Bayesian network model, and predicting the current power generation condition of the power distribution cabinet; and controlling the power supply mode of the power distribution cabinet according to the current power generation condition of the power distribution cabinet. The problem that the energy utilization efficiency is reduced due to the fact that the control strategy of the power distribution cabinet is difficult to optimize according to the change of weather environment factors in the prior art is solved. The future power generation condition is predicted in combination with weather forecast, the power supply mode of the power distribution cabinet is optimized in advance, and the control effect of the power distribution cabinet is improved.

Description

Technical Field

[0001] The invention belongs to the technical field of power distribution cabinets and relates to an intelligent power distribution cabinet for accessing renewable energy. Background Art

[0002] Under the dual pressures of energy crisis and environmental protection, traditional energy is facing difficulties, while renewable energy technologies such as solar energy, wind energy, hydropower, geothermal energy, and biomass energy are constantly developing. At the same time, the rise of smart grid technology provides technical support for the access of renewable energy. In this context, smart grids can efficiently access renewable energy, realize intelligent monitoring and management of electricity, fault diagnosis and protection, and energy optimization and management. It has broad application prospects in distributed energy systems, smart buildings, industrial parks, and power supply in remote areas, providing an effective solution for achieving a sustainable energy future.

[0003] As a key component of the smart grid, the smart distribution cabinet bears the important responsibility of distributing, controlling and protecting electricity in the distribution link. However, the power generation of renewable energy will fluctuate with changes in external factors such as the environment and weather, making the power generation of the distribution cabinet connected to renewable energy unstable, which in turn has a negative impact on the efficiency of electric energy utilization. Therefore, the existing technology urgently needs to adjust the energy inflow according to the changes in external factors and optimize the control strategy of the distribution cabinet to improve the efficiency of energy utilization. Summary of the invention

[0004] In order to solve the above-mentioned problems existing in the prior art, the present invention provides an intelligent distribution cabinet for renewable energy access, which aims to establish an artificial intelligence model between weather and environmental factors and renewable energy power generation through big data of historical periods, and then obtain weather and environmental data of future time series through local weather forecasts and input them into the artificial intelligence model to predict the power generation of the distribution cabinet in the future, and formulate a control strategy for the distribution cabinet according to the power generation to improve energy utilization efficiency.

[0005] The purpose of the present invention can be achieved through the following technical solutions: The present application provides an intelligent power distribution cabinet for renewable energy access, including a monitoring and collection module, an intelligent prediction module and an optimization control module, wherein the monitoring and collection module, the intelligent prediction module and the optimization control module are communicatively connected, wherein: The monitoring and collection module is used to monitor and collect the real-time weather environment data of the local weather forecast for a period of time in the future with a specific time step; the principal component analysis method is used to extract the main features of the real-time weather environment data; The intelligent prediction module is used to build an artificial intelligence model by collecting weather and environmental data in historical periods and data on power generation of renewable energy distribution cabinets, input the real-time weather and environmental data into the artificial intelligence model, and predict the current power generation of the distribution cabinet; the artificial intelligence model is configured as a Bayesian network model with the main features of the weather and environmental data as the parent node and the power generation of the distribution cabinet as the child node; The optimization control module is used to control the power supply mode of the distribution cabinet according to the current power generation situation of the distribution cabinet.

[0006] Furthermore, the weather environment data includes temperature, humidity, wind speed, light intensity and rainfall.

[0007] Furthermore, the weather forecast is obtained through the China Meteorological Data Network, commercial meteorological data API, weather stations, official weather forecast websites or weather forecast applications.

[0008] Furthermore, the power generation data includes power generation, power generation, power generation stability index and power generation efficiency; wherein: The power generation refers to the total amount of electricity generated by the smart power distribution cabinet connected to the renewable energy in a specific time period; The power generation refers to the power generation energy per unit time; The power generation stability index is used to measure the stability of power generation and is determined by the standard deviation or coefficient of variation of power generation or power generation over a period of time; The power generation efficiency refers to the ratio of renewable energy converted into electrical energy, and is calculated by the ratio of actual power generation to theoretical maximum power generation.

[0009] Furthermore, the artificial intelligence model is configured as a Bayesian network model, including the following construction steps: S1. Determine the variable parameters in the Bayesian network according to the numerical range of the weather environment data and the power generation data of the renewable energy distribution cabinet; S2. Construct the structure of the Bayesian network based on the dependency relationship between variables; S3, determine the conditional probability distribution between each variable parameter and construct a conditional probability table; S4. After the Bayesian network model is built, use cross-validation, accuracy or recall to evaluate and optimize the Bayesian network.

[0010] Furthermore, in step S1, a cluster analysis method is also used to determine the variable parameters, and the cluster analysis method is configured as a K-means method, a Ward clustering method or a SVM method.

[0011] Furthermore, in step S2, the structure of the Bayesian network is constructed according to the dependency relationship between the variables, and the dependency relationship between the variables is specifically determined through expert knowledge, data analysis model or machine learning algorithm.

[0012] Furthermore, the power supply mode includes a pure renewable energy power supply mode, a hybrid power supply mode, an energy storage auxiliary power supply mode and a backup power supply mode, wherein: In the pure renewable energy power supply mode, the intelligent distribution cabinet only relies on the electricity generated by renewable energy to power the load, and does not connect to traditional energy; In the hybrid power supply mode, renewable energy and traditional energy are used to supply power to the load at the same time, and the ratio of renewable energy to traditional energy is dynamically adjusted according to the real-time power generation situation and load demand; The energy storage auxiliary power supply mode stores excess electric energy in the energy storage device when the renewable energy power generation is sufficient; when the renewable energy power generation is unstable or cannot meet the load demand within a specific time period, the energy storage device releases electric energy to supply power to the load; In the backup power supply mode, when both renewable energy and traditional energy fail to supply electricity normally, the backup power supply is started to supply power to the load.

[0013] Furthermore, the optimization control module includes a receiving module, a matching module and an execution module, wherein: The receiving module is used to receive the current power generation status of the power distribution cabinet and generate a control signal; The matching module is used to match the corresponding power supply mode according to the control signal; The execution module is used to supply power to the load according to the matched power supply mode.

[0014] Furthermore, the optimization control module also uses visualization tools to display the power supply status of the distribution cabinet, which includes changes in weather and environmental data, future power generation forecasts, power supply mode recommendations and current load demand conditions.

[0015] Beneficial effects of the present invention: (1) Monitor and collect the real-time weather environment data of the local weather forecast for a certain period of time in the future with a specific time as the step length; use the principal component analysis method to extract the main features of the real-time weather environment data; build an artificial intelligence model by collecting the main features of weather environment data in the historical period and the power generation data of the renewable energy distribution cabinet, input the real-time weather environment data into the artificial intelligence model, and predict the current power generation of the distribution cabinet; control the power supply mode of the distribution cabinet according to the current power generation of the distribution cabinet. The present invention solves the problem that it is difficult to optimize the control strategy of the distribution cabinet according to the changes in weather and environmental factors in the prior art, resulting in reduced energy utilization efficiency.

[0016] (2) By establishing an artificial intelligence model between weather and environmental data and the power generation conditions of the distribution cabinet, and combining weather forecasts to predict future power generation conditions, the power supply mode of the distribution cabinet can be optimized in advance, thereby improving the control effect of the distribution cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0018] Figure 1 This is a structural diagram of an intelligent power distribution cabinet for accessing renewable energy in the present invention.

[0019] Figure 2 A flowchart of constructing a Bayesian network model in one embodiment of the present invention.

[0020] Figure 3 It is a structural diagram of an optimization control module in one embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0022] See also Figure 1-Figure 3 The present application provides a smart power distribution cabinet for renewable energy access, including a monitoring and collection module, an intelligent prediction module and an optimization control module, wherein the monitoring and collection module, the intelligent prediction module and the optimization control module are communicatively connected, wherein: The monitoring and collection module is used to monitor and collect the real-time weather environment data of the local weather forecast for a period of time in the future with a specific time step; the principal component analysis method is used to extract the main features of the real-time weather environment data; In this embodiment, the monitoring and collection module works with a specific time step, which means that it can monitor the weather environment data of the local weather forecast for a period of time in the future in an orderly manner according to the preset time interval. This specific time step can be adjusted according to actual needs to ensure that the dynamic changes of the weather environment are captured as accurately as possible without wasting too many resources. The weather environment data covers many important aspects. Among them, temperature data is crucial, and different temperature ranges will affect the performance of renewable energy equipment. For example, at higher temperatures, the efficiency of some solar panels may be affected to a certain extent; and for some devices that use temperature difference to generate electricity, changes in temperature are more directly related to the amount of power generated.

[0023] Humidity data cannot be ignored either: higher humidity may cause the insulation performance of the equipment to decline, increasing the risk of equipment failure; at the same time, humidity will also affect the thermal conductivity of the air, thereby affecting the heat dissipation effect, indirectly affecting the operating efficiency of renewable energy equipment.

[0024] Wind speed data is of decisive significance to wind power generation systems: the size and change trend of wind speed directly determine the output power of wind turbines. By accurately monitoring wind speed, the potential of wind power generation can be better predicted, providing an important basis for the control strategy of intelligent distribution cabinets.

[0025] Light intensity data is a core parameter for solar power generation systems: sufficient light intensity can enable solar panels to generate more electricity, and changes in light intensity will directly affect the fluctuation of solar power generation. Therefore, accurate monitoring of light intensity is crucial to optimizing the operation of solar power generation systems and improving energy efficiency.

[0026] Precipitation data also has some impact: although rainfall itself has little to do with direct energy generation, excessive rainfall may affect the efficiency of solar panels and may also cause damage to some outdoor renewable energy equipment. In addition, rainfall may also affect river water levels, which in turn has an indirect impact on renewable energy forms such as hydropower.

[0027] It should be noted that the weather and environmental data collected present the characteristics of a long time series. This means that over a long period of time, various weather and environmental factors such as temperature, humidity, wind speed, light intensity, rainfall, etc. are continuously monitored and collected, thereby accumulating a large number of data samples. However, a large number of data samples are not entirely beneficial. Although rich data can provide more comprehensive information to a certain extent, there may also be many repeated or highly correlated data parts, which is the so-called data redundancy. For example, in a continuous period of time, the temperature may fluctuate within a small range, and its change trend is relatively stable. In this way, the continuously recorded temperature data may have a large number of similar values. These similar values ​​do not provide much additional valuable information for subsequent analysis and modeling, but may become interference factors.

[0028] When using these data containing a lot of redundancy to build models, such as building an artificial intelligence model for predicting the power generation of distribution cabinets, too much redundant data will make it difficult for the model to accurately grasp key information during the learning process, and it is easy to be misled by those repeated and insubstantial data. This may cause the model to be unable to accurately capture the real and effective relationship between weather and environmental factors and power generation, thereby reducing the accuracy of modeling, resulting in a large deviation between the final predicted power generation of the distribution cabinet and the actual situation.

[0029] In order to solve the problem of reduced modeling accuracy caused by data redundancy, this embodiment introduces the principal component analysis (PCA) method. Principal component analysis is a commonly used multivariate statistical analysis technique. Its core purpose is to convert a data set with multiple variables (in this case, various weather environment data variables) into a new set of variables that are unrelated (or have very low correlation) by performing a linear transformation on the original data, that is, the principal component.

[0030] In the specific operation process, the principal component analysis method will find the main features that can best represent the original data information based on the statistical characteristics of the data such as the variance. For weather and environmental data, it can extract the main features that best reflect the overall weather and environmental conditions and are relatively independent of each other from many data samples such as temperature, humidity, wind speed, etc. that may be redundant.

[0031] For example, PCA analysis may reveal that a new variable (principal component) that combines factors such as temperature, light intensity, and wind speed can largely represent the impact of weather conditions on power generation, while other original data variables that are more highly correlated with it are relatively less important. By extracting the main features in this way, we can effectively reduce data redundancy while retaining key information of weather and environmental data.

[0032] In this way, when the data processed by principal component analysis is used for subsequent modeling work, such as building an artificial intelligence model to predict the power generation of the distribution cabinet, the model can focus more on those key features that really have an important impact on the power generation situation, thereby improving the accuracy of modeling and making the prediction results closer to the actual power generation situation of the distribution cabinet.

[0033] Therefore, further, the weather environment data includes temperature, humidity, wind speed, light intensity and rainfall.

[0034] Furthermore, the weather forecast is obtained by the following method: (1) Use professional meteorological data platforms or APIs: China Meteorological Data Network: This is an official meteorological data platform that provides a wealth of meteorological data resources. According to the "Basic Meteorological Data Open Sharing Catalog" issued by the China Meteorological Administration, there are a variety of shared meteorological data and data service products available for use, but special needs or data outside the shared catalog may require application to the provincial meteorological bureau.

[0035] Commercial weather data API: Some commercial companies provide weather data interface services, such as the AutoNavi weather API. By applying for an API key, you can call the relevant interface to obtain weather forecast information for a specific area. Taking the AutoNavi API as an example, when using it, you need to construct the request URL in the specified format and pass in the corresponding parameters, such as the city code, and then parse the returned JSON format data to extract the required weather environment data, including temperature, humidity, wind speed, light intensity (some areas may not provide it directly, but can be indirectly inferred through information such as cloud cover), rainfall, etc.

[0036] (2) Using meteorological monitoring equipment: Meteorological stations: In some areas, there are professional meteorological stations equipped with various sensors and monitoring instruments, which can collect local meteorological data in real time, including basic weather and environmental data such as temperature, humidity, wind speed, and rainfall. Relevant departments or institutions can establish data connections with meteorological stations to obtain real-time monitoring data, and collect and organize them according to specific time steps.

[0037] Personal weather monitoring devices: For some individuals or small organizations that have specific needs for weather data, small weather monitoring devices, such as home weather stations, can be used. These devices can usually measure basic parameters such as temperature, humidity, and air pressure, and some advanced devices can also measure information such as wind speed. By connecting the device to a computer or mobile device, local weather and environmental data can be obtained and recorded in real time, but the data obtained in this way is relatively small in range and may not be as accurate as professional weather stations.

[0038] (3) Obtain from weather forecast websites or applications: Official weather forecast website: Meteorological departments in various places usually have their own official weather forecast website, which provides weather forecast information for the region. You can use web crawler technology to visit these websites at specific time intervals to grab the required weather and environmental data. However, this method needs to pay attention to complying with relevant laws and regulations and website usage regulations.

[0039] Weather forecast applications: There are many weather forecast applications on the market that obtain real-time weather forecast data by cooperating with meteorological data providers. Some applications provide open interfaces or data export functions that can be used to obtain the required weather environment data.

[0040] The intelligent prediction module is used to build an artificial intelligence model by collecting weather and environmental data in historical periods and data on power generation of renewable energy distribution cabinets, input the real-time weather and environmental data into the artificial intelligence model, and predict the current power generation of the distribution cabinet; the artificial intelligence model is configured as a Bayesian network model with the main features of the weather and environmental data as the parent node and the power generation of the distribution cabinet as the child node; In this embodiment, the intelligent prediction module is first dedicated to collecting weather and environmental data in historical periods and power generation data of renewable energy distribution cabinets. Historical weather and environmental data include information such as temperature, humidity, wind speed, light intensity, and rainfall in different seasons and time periods. The power generation data of renewable energy distribution cabinets covers detailed information such as power generation and power fluctuation at each time node. By sorting and analyzing a large amount of historical data, an accurate artificial intelligence model is constructed.

[0041] This AI model is able to learn the complex relationship between weather and environmental factors and the power generation of the distribution cabinet. For example, when the light intensity is high, the power generation of the solar power generation part will usually increase; when the wind speed is high, the contribution of wind power generation may increase. At the same time, the model will also take into account the combined effects of multiple factors, such as the impact of high humidity and high temperature on equipment performance, and the indirect impact of different rainfall conditions on renewable energy generation.

[0042] When real-time weather and environmental data is input, the intelligent prediction module will quickly pass this data to the built artificial intelligence model. The model will quickly calculate and analyze the input data to predict the current power generation of the distribution cabinet. This prediction can include the estimation of power generation in the future, the trend of power generation, etc. In this way, the intelligent distribution cabinet can understand its own power generation capacity in advance, providing an important basis for formulating reasonable control strategies, thereby effectively improving energy utilization efficiency and ensuring the stable operation of the power system.

[0043] Furthermore, the power generation data is characterized by the following variables: 1. Power generation: This is the variable that most directly reflects the power generation situation. It represents the total amount of electricity generated by the smart distribution cabinet connected to renewable energy in a specific period of time, usually in kilowatt-hours (kWh). By monitoring and recording the power generation at different time points, the overall scale and trend of power generation can be understood.

[0044] 2. Power generation: The power generation represents the power generation energy per unit time, usually in kilowatts (kW). It reflects the intensity of power generation at the current moment and is of great significance for real-time monitoring and control of the operating status of the intelligent distribution cabinet. For example, when the power generation suddenly drops, it may mean that a renewable energy power generation equipment has failed or the weather conditions have changed unfavorably.

[0045] 3. Power generation stability indicators: This indicator is used to measure the stability of power generation. It can be determined by calculating the standard deviation, coefficient of variation and other statistics of power generation or power generation over a period of time. If the power generation stability index is low, it means that the power generation situation fluctuates greatly, and corresponding measures may need to be taken to stabilize power generation, such as adjusting the charging and discharging strategy of energy storage equipment or optimizing the control parameters of the intelligent distribution cabinet.

[0046] 4. Power generation efficiency: Power generation efficiency indicates the ratio of renewable energy converted into electrical energy. It can be calculated by the ratio of actual power generation to theoretical maximum power generation. For example, for solar power generation, the theoretical maximum power generation can be estimated based on the solar radiation intensity and the conversion efficiency of photovoltaic panels. Improving power generation efficiency is one of the important goals of optimizing the performance of intelligent distribution cabinets, which can be achieved by selecting efficient renewable energy power generation equipment, optimizing system configuration and control strategies, etc.

[0047] Furthermore, the artificial intelligence model is configured as a Bayesian network model, including the following construction steps: S1. Determine variable parameters: First, the variable parameters in the Bayesian network are clarified. These variables include but are not limited to weather environmental factors such as temperature, humidity, wind speed, light intensity, rainfall, and power generation of renewable energy distribution cabinets. For each variable, its possible range of values ​​needs to be determined to determine the parameters. For example, the temperature can be divided into different intervals according to actual conditions, such as low temperature, medium temperature, high temperature, etc.; the power generation can be divided according to different power ranges. Cluster analysis methods can also be used for division.

[0048] Furthermore, in step S1, a cluster analysis method is also used to determine the variable parameters, and the cluster analysis method is configured as a K-means method, a Ward clustering method or a SVM method.

[0049] In this embodiment, in the step of constructing the Bayesian network model of the intelligent power distribution cabinet for renewable energy access, step S1 plays a key role in determining the variable parameters using the cluster analysis method. Among them, the K-means method, Ward clustering method and SVM method are configured with their own characteristics.

[0050] The K-means method first randomly selects k data points as the initial cluster centers, distributes them by calculating the distance from the data points to each center, and then recalculates the center and repeats until it is stable. When determining the variable parameters, historical weather and power generation data are used as input, and the data are divided into different clusters. Each cluster represents a specific combination of weather and power generation conditions, and weather factors such as average temperature and average power generation are extracted as variable parameters of the Bayesian network model. Its advantages are that the algorithm is simple and easy to implement, the calculation speed is fast, and it can process large-scale data sets, but the number of clusters must be determined in advance and it is sensitive to the initial center.

[0051] The Ward clustering method is based on variance analysis. The goal is to minimize the sum of the variances within each cluster after clustering. Each time, two clusters with the smallest increase in total variance after merging are selected for merging. When determining the variable parameters, historical data is also used as input to analyze clustering characteristics and extract parameters related to weather and power generation. This method can produce compact and balanced clusters that are suitable for different data distributions, but the computational complexity is high and it is sensitive to outliers.

[0052] The SVM (Support Vector Machine) method can be used for clustering through improvements. For example, One-Class SVM can detect outliers for single-class clustering. When determining variable parameters, first perform outlier detection on weather and power generation data, use normal data as clusters, analyze their characteristics, and extract parameters such as power generation range under normal weather conditions. This method has good processing capabilities for high-dimensional complex data distribution and can effectively detect outliers, but the parameter selection has a large impact and high computational complexity. These clustering analysis methods provide important variable parameter basis for constructing Bayesian network models, which helps to more accurately predict the power generation of renewable energy distribution cabinets and improve energy efficiency.

[0053] S2. Build network structure: The structure of the Bayesian network is constructed based on the relationship between variables. The dependencies between variables can be determined through expert knowledge, data analysis, or machine learning algorithms. For example, light intensity may directly affect solar power generation, and wind speed may be related to wind power generation. When constructing the network structure, graphical tools can be used to intuitively represent the relationship between variables.

[0054] S3. Determine the conditional probability distribution: After determining the network structure, it is necessary to determine the conditional probability distribution of each variable parameter. This can be achieved by performing statistical analysis on the training data. For example, for a given temperature and light intensity, calculate the probability distribution of solar power generation. Methods such as maximum likelihood estimation and Bayesian estimation can be used to determine the parameters.

[0055] S4. Model evaluation and optimization: After building the Bayesian network model, it needs to be evaluated and optimized. The performance of the model can be evaluated using indicators such as cross-validation, accuracy, precision, recall, and F1 value. If the performance of the model is not ideal, the model can be improved by adjusting the network structure, adding variables, optimizing parameters, etc.

[0056] Accuracy is the ratio of the number of samples correctly predicted by the model to the total number of samples, and is one of the most commonly used evaluation indicators; precision measures how many of the positive examples predicted by the model are truly positive examples, and is an important indicator for evaluating the accuracy of model predictions; recall measures the ratio of the number of positive examples that the model can correctly predict to the actual number of positive examples, also known as recall; F1 value is the harmonic mean of precision and recall, which comprehensively considers the accuracy and recall of the model. The higher the F1 value, the better the balance between precision and recall.

[0057] Furthermore, in step S5, the accuracy rate is calculated as follows: , In the formula, ACC represents accuracy; TP represents true positive examples; TN represents true negative examples; FP represents false positive examples; and FN represents false negative examples.

[0058] Furthermore, in step S5, the accuracy is calculated as follows: , Where PPV represents precision, TP represents true positives, and FP represents false positives.

[0059] Furthermore, in step S5, the recall rate is calculated as follows: , Where TRP represents the recall rate; TP represents the true positive examples; and FN represents the false negative examples.

[0060] Furthermore, in step S5, the F1 value is calculated by the formula: , Where, F1 represents the F1 value; PPV represents the precision; TRP represents the recall rate.

[0061] The optimization control module is used to control the power supply mode of the distribution cabinet according to the current power generation situation of the distribution cabinet.

[0062] In this embodiment, the optimization control module closely controls the power supply mode of the power distribution cabinet according to the current power generation situation of the power distribution cabinet. When the intelligent prediction module predicts the current power generation situation of the power distribution cabinet, the optimization control module will immediately receive this information and conduct in-depth analysis. The power supply modes include the following: 1. Pure renewable energy power supply mode: When the power generation of renewable energy is sufficient and stable and can fully meet the load demand connected to the distribution cabinet, the pure renewable energy power supply mode is adopted. In this mode, the intelligent distribution cabinet only relies on the power generated by renewable energy such as solar energy and wind energy to power the load, and does not connect to traditional energy. This mode has the advantages of zero emissions and environmental protection, and can maximize the use of renewable energy and reduce dependence on traditional energy.

[0063] 2. Hybrid power supply mode: When the power generation of renewable energy is not enough to meet all load demands, the hybrid power supply mode is activated. In this mode, renewable energy and traditional energy (such as mains electricity) supply power to the load at the same time. The optimization control module dynamically adjusts the proportion of renewable energy and traditional energy according to the real-time power generation situation and load demand. For example, when the power generation of renewable energy is high, the proportion of traditional energy is reduced; when the power generation of renewable energy is insufficient, the supply of traditional energy is increased to ensure the stable operation of the load.

[0064] 3. Energy storage auxiliary power supply mode: When the power generation of renewable energy is unstable or cannot meet the load demand within a specific time period, the energy storage auxiliary power supply mode comes into play. In this mode, the smart distribution cabinet is connected to energy storage devices, such as battery packs, supercapacitors, etc. When the power generation of renewable energy is sufficient, the excess power is stored in the energy storage device; when the power generation of renewable energy is insufficient, the energy storage device releases power to supply power to the load. This mode can effectively smooth the fluctuations of renewable energy power generation and improve the stability and reliability of the system.

[0065] 4. Backup power supply mode: As an emergency power supply mode, when both renewable energy and traditional energy cannot supply electricity normally, the backup power supply mode is activated. The backup power supply can be a diesel generator, UPS (uninterruptible power supply), etc. This mode ensures that critical loads can still be supplied with electricity in extreme cases, improving the safety and reliability of the system.

[0066] Furthermore, the optimization control module includes a receiving module, a matching module and an execution module, wherein: The receiving module is used to receive the current power generation status of the power distribution cabinet and generate a control signal; The matching module is used to match the corresponding power supply mode according to the control signal; The execution module is used to supply power to the load according to the matched power supply mode.

[0067] In this embodiment, the receiving module is the starting link of the entire optimization control process and is responsible for receiving the power generation status of the current distribution cabinet. Through close connection with the intelligent prediction module, key data such as power generation, power generation, and power generation stability are obtained in real time. The receiving module will quickly analyze and process these data and generate corresponding control signals according to the preset judgment criteria. This control signal is like an instruction, providing a clear direction for the operation of subsequent modules.

[0068] The matching module starts working after receiving the control signal generated by the receiving module. Its main task is to match the corresponding power supply mode according to the control signal. The matching module stores the correspondence between different power generation conditions and power supply modes. For example, when the control signal indicates that the current renewable energy generation is sufficient, the matching module will quickly identify and select the pure renewable energy power supply mode; when the power generation is not enough to meet the load demand, it will match the hybrid power supply mode or the energy storage auxiliary power supply mode. Through precise matching, it ensures that the selected power supply mode can adapt to the current power generation situation to the greatest extent, realize efficient energy utilization and stable operation of the system.

[0069] The execution module is the last link of the optimization control module and is also the key part of putting the power supply mode into practice. Once the matching power supply mode is determined, the execution module will perform power supply operations according to the mode. If it is a pure renewable energy power supply mode, the execution module will adjust the circuit connection of the distribution cabinet to ensure that the load is powered only by renewable energy; if it is a hybrid power supply mode, the execution module will coordinate the input ratio of renewable energy and traditional energy to meet the load demand; for the energy storage auxiliary power supply mode, the execution module will reasonably control the inflow and outflow of electric energy according to the status of the energy storage device. The efficient operation of the execution module ensures the accurate implementation of the power supply mode and provides a stable and reliable power supply for the load.

[0070] Furthermore, the optimization control module also uses visualization tools to display the power supply status of the distribution cabinet, which includes changes in weather and environmental data, future power generation forecasts, power supply mode recommendations and current load demand conditions.

[0071] In this embodiment, the comprehensive visualization display allows the user to intuitively understand the power supply status of the distribution cabinet, better manage energy and make decisions, and improve energy utilization efficiency and system stability. For the display of changes in weather and environmental data, the visualization tool is presented in the form of dynamic charts or graphs. For example, the temperature can be displayed as a line graph over time, and curves of different colors represent different temperature ranges. Humidity can be represented by a bar graph to intuitively reflect the changes in the humidity of the air. Wind speed can be clearly displayed by combining a wind rose diagram and a wind speed change curve to show the distribution of wind direction and the fluctuations in wind speed. Light intensity can be represented by a graph similar to solar radiation intensity, and the depth of color represents the changes in light intensity. The rainfall can be displayed by a cumulative bar graph to show the changes in the total amount of rainfall over a period of time.

[0072] In terms of future power generation forecasts, the visualization tool presents the forecast curve and data table in combination. The forecast curve shows the trend of power generation in the future, and curves of different colors can represent different types of renewable energy power generation forecasts. The data table lists specific forecast values, including expected power generation and power generation information in different time periods, so that users can understand the future power generation situation at a glance.

[0073] The visualization tool presents power supply mode recommendations in a highlighted and textual manner. Based on current weather and environmental data, future power generation forecasts, and load demand, the system will give corresponding power supply mode recommendations. For example, if renewable energy generation is sufficient and stable, the visualization tool will highlight the "pure renewable energy power supply mode" and provide a brief explanation of why this mode is recommended. If hybrid power supply or energy storage auxiliary power supply is required, it will also be clearly displayed and explained.

[0074] The current load demand is displayed through real-time data and charts. The current power demand of different types of loads can be represented by bar charts, and different load categories can be distinguished by colors. At the same time, the total load demand and the comparison with the current power supply capacity can be displayed numerically, so that users can clearly understand whether the load demand is met and whether the power supply strategy needs to be adjusted.

[0075] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent power distribution cabinet for renewable energy access, characterized in that: It includes a monitoring and collection module, an intelligent prediction module and an optimization control module, which are communicatively connected to each other, wherein: The monitoring and collection module is used to monitor and collect the real-time weather environment data of the local weather forecast for a period of time in the future with a specific time step; the principal component analysis method is used to extract the main features of the real-time weather environment data; The intelligent prediction module is used to build an artificial intelligence model by collecting weather and environmental data in historical periods and data on power generation of renewable energy distribution cabinets, input the real-time weather and environmental data into the artificial intelligence model, and predict the current power generation of the distribution cabinet; the artificial intelligence model is configured as a Bayesian network model with the main features of the weather and environmental data as the parent node and the power generation of the distribution cabinet as the child node; The optimization control module is used to control the power supply mode of the distribution cabinet according to the current power generation situation of the distribution cabinet.

2. The intelligent power distribution cabinet for renewable energy access according to claim 1, characterized in that: The power generation data includes power generation, power generation, power generation stability index and power generation efficiency; among which: The power generation refers to the total amount of electricity generated by the smart power distribution cabinet connected to the renewable energy in a specific time period; The power generation refers to the power generation energy per unit time; The power generation stability index is used to measure the stability of power generation and is determined by the standard deviation or coefficient of variation of power generation or power generation over a period of time; The power generation efficiency refers to the ratio of renewable energy converted into electrical energy, and is calculated by the ratio of actual power generation to theoretical maximum power generation.

3. The intelligent power distribution cabinet for renewable energy access according to claim 1, characterized in that: The Bayesian network model includes the following construction steps: S1. Determine the variable parameters in the Bayesian network according to the numerical range of the weather environment data and the power generation data of the renewable energy distribution cabinet; S2. Construct the structure of the Bayesian network based on the dependency relationship between variables; S3, determine the conditional probability distribution between each variable parameter and construct a conditional probability table; S4. After the Bayesian network model is built, use cross-validation, accuracy or recall to evaluate and optimize the Bayesian network.

4. The intelligent power distribution cabinet for renewable energy access according to claim 3, characterized in that: In step S1, a cluster analysis method is also used to determine variable parameters, and the cluster analysis method is configured as a K-means method, a Ward clustering method or a SVM method.

5. The intelligent power distribution cabinet for renewable energy access according to claim 3, characterized in that: In step S2, the structure of the Bayesian network is constructed according to the dependency relationship between the variables, and the dependency relationship between the variables is determined specifically through expert knowledge, data analysis model or machine learning algorithm.

6. The intelligent power distribution cabinet for renewable energy access according to claim 1, characterized in that: The power supply mode includes a pure renewable energy power supply mode, a hybrid power supply mode, an energy storage auxiliary power supply mode and a backup power supply mode, wherein: In the pure renewable energy power supply mode, the intelligent distribution cabinet only relies on the electricity generated by renewable energy to power the load, and does not connect to traditional energy; In the hybrid power supply mode, renewable energy and traditional energy are used to supply power to the load at the same time, and the ratio of renewable energy to traditional energy is dynamically adjusted according to the real-time power generation situation and load demand; The energy storage auxiliary power supply mode stores excess electric energy in the energy storage device when the renewable energy power generation is sufficient; when the renewable energy power generation is unstable or cannot meet the load demand within a specific time period, the energy storage device releases electric energy to supply power to the load; In the backup power supply mode, when both renewable energy and traditional energy fail to supply electricity normally, the backup power supply is started to supply power to the load.

7. The intelligent power distribution cabinet for renewable energy access according to claim 1, characterized in that: The optimization control module includes a receiving module, a matching module and an execution module, wherein: The receiving module is used to receive the current power generation status of the power distribution cabinet and generate a control signal; The matching module is used to match the corresponding power supply mode according to the control signal; The execution module is used to supply power to the load according to the matched power supply mode.

8. The intelligent power distribution cabinet for renewable energy access according to claim 1, characterized in that: The optimization control module also uses visualization tools to display the power supply status of the distribution cabinet, which includes changes in weather and environmental data, future power generation forecasts, power supply mode recommendations, and current load demand conditions.

9. The intelligent power distribution cabinet for renewable energy access according to claim 1, characterized in that: The weather environment data includes temperature, humidity, wind speed, light intensity and rainfall.

10. The intelligent power distribution cabinet for renewable energy access according to claim 1, characterized in that: The weather forecast is obtained through the China Meteorological Data Network, commercial meteorological data API, weather stations, official weather forecast websites or weather forecast applications.

Images