Microgrid control method and device based on cloud-side cooperation, and computer equipment

Abstract

The invention relates to the technical field of cloud edge collaboration, and relates to a micro-grid control method and device based on cloud edge collaboration, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: collecting historical operation data of a micro-grid; based on the historical operation data, constructing a prediction model of the operation state of the micro-grid; utilizing the prediction model to predict the future operation state of the micro-grid; based on the future operation state, generating a data acquisition instruction by using a cloud; forwarding the data acquisition instruction through an edge gateway of the micro-grid, and returning a data acquisition result; and based on the data acquisition result, a micro-grid control instruction is generated by using the cloud, and the micro-grid control instruction is forwarded through an edge gateway. By adopting the method, the data processing efficiency and accuracy of the automatic control system of the micro-grid can be improved, and the efficient and stable operation of the micro-grid is ensured.

Description

Technical Field

[0001] The present application relates to the technical field of cloud-edge collaboration, and particularly to a microgrid control method, device, computer device, computer-readable storage medium, and computer program product based on cloud-edge collaboration. Background Art

[0002] With the wide application of renewable energy, the microgrid, as an efficient and flexible power supply and consumption system, has become increasingly important. A microgrid consists of distributed power sources, electrical loads, and an energy management system, etc., and can achieve a basic balance of internal power and electricity, and can be connected to the large power grid or operate independently according to needs. However, traditional microgrid automatic control methods mainly rely on stand-alone information technology and centralized management, with low data processing efficiency and difficulty in meeting the analysis and calculation requirements of massive data in microgrid operation.

[0003] To solve this problem, cloud-edge collaboration technology has been introduced into microgrid automatic control. The edge device collects and preliminarily processes the real-time operation status data of the microgrid, and then transmits the data to the cloud for further analysis and optimization. However, there are deficiencies in generating data collection instructions in traditional technologies, resulting in overly broad or inaccurate instructions, which are likely to collect a large amount of redundant data, increasing the data storage and processing burden and affecting the accuracy and efficiency of data analysis. In addition, the omission of data collection instructions may lead to the lack of key data, unable to comprehensively reflect the operation status of the microgrid, thus affecting subsequent analysis and decision-making.

[0004] Therefore, there is an urgent need for a microgrid control method, device, computer device, computer-readable storage medium, and computer program product based on cloud-edge collaboration, which can improve the data processing efficiency and accuracy of the microgrid automatic control system and ensure the efficient and stable operation of the microgrid. Summary of the Invention

[0005] Based on this, it is necessary to provide a microgrid control method, device, computer device, computer-readable storage medium, and computer program product based on cloud-edge collaboration for the above technical problems, which can improve the data processing efficiency and accuracy of the microgrid automatic control system and ensure the efficient and stable operation of the microgrid.

[0006] In a first aspect, the present application provides a microgrid control method based on cloud-edge collaboration, including:

[0007] Collect the historical operation data of the microgrid;

[0008] Based on the historical operation data, construct a prediction model for the operation status of the microgrid;

[0009] Use the prediction model to predict the future operation status of the microgrid;

[0010] Generate a data acquisition instruction using the cloud based on the future operating state;

[0011] Forward the data acquisition instruction through the edge gateway of the microgrid and return the data acquisition result;

[0012] Generate a microgrid control instruction using the cloud based on the data acquisition result and forward the microgrid control instruction through the edge gateway.

[0013] In one embodiment, the building of the prediction model for the operating state of the microgrid based on historical operating data includes:

[0014] Analyze the correlation between the data in the historical operating data to obtain an analysis result;

[0015] Clean the historical operating data based on the analysis result;

[0016] Build a prediction model for the operating state of the microgrid based on the screened historical operating data.

[0017] In one embodiment, the cleaning of the historical operating data based on the analysis result includes:

[0018] Obtain the degree of association between the data in the historical operating data based on the analysis result;

[0019] Remove the data with an association degree lower than a preset threshold from the historical operating data.

[0020] In one embodiment, the obtaining of the degree of association between the data in the historical operating data based on the analysis result includes:

[0021] Use the calculation formula of the Pearson correlation coefficient to calculate the correlation coefficients between the data in the historical operating data respectively, and the correlation coefficient is used to characterize the degree of association between the data; wherein, the historical operating data includes solar power generation, the load demand value of the microgrid, and voltage fluctuation data, and the calculation formula of the Pearson correlation coefficient includes:

[0022]

[0023] where xi and yi are the i-th data points in the two data sets respectively; and are the average values in the two data sets respectively; n is the number of data points.

[0024] In one embodiment, the forwarding of the microgrid control instruction through the edge gateway includes:

[0025] Send the microgrid control instruction to the edge cluster platform;

[0026] Forward the microgrid control instruction to the energy management platform through the edge gateway of the microgrid, so that the energy management platform performs control operations on the microgrid based on the microgrid control instruction. The dimensions of the control operations include optimizing the control of the energy distribution, load forecasting, and fault diagnosis of the microgrid.

[0027] In one embodiment, the generating of the microgrid control instruction by using the cloud based on the data acquisition result includes:

[0028] Perform aggregation processing on the data acquisition result and upload it to the cloud;

[0029] Use the cloud to analyze the operation state of the microgrid for the aggregated data acquisition result to obtain an operation state analysis result;

[0030] Generate a microgrid control instruction based on the operation state analysis result.

[0031] In a second aspect, the present application also provides a microgrid control device based on cloud-edge collaboration, including:

[0032] A data acquisition module for acquiring the historical operation data of the microgrid;

[0033] A model construction module for constructing a prediction model of the operation state of the microgrid based on the historical operation data;

[0034] A control module for predicting the future operation state of the microgrid by using the prediction model;

[0035] The control module is further configured to generate a data acquisition instruction by using the cloud based on the future operation state;

[0036] The control module is further configured to forward the data acquisition instruction through the edge gateway of the microgrid and return the data acquisition result;

[0037] The control module is further configured to generate a microgrid control instruction by using the cloud based on the data acquisition result and forward the microgrid control instruction through the edge gateway.

[0038] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Acquire the historical operation data of the microgrid;

[0040] Construct a prediction model of the operation state of the microgrid based on the historical operation data;

[0041] Using the prediction model, predict the future operating state of the microgrid;

[0042] Based on the future operating state, generate data collection instructions using the cloud;

[0043] Forward the data collection instructions through the edge gateway of the microgrid and return the data collection results;

[0044] Based on the data collection results, generate microgrid control instructions using the cloud and forward the microgrid control instructions through the edge gateway.

[0045] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0046] Collect historical operating data of the microgrid;

[0047] Based on the historical operating data, construct a prediction model for the operating state of the microgrid;

[0048] Using the prediction model, predict the future operating state of the microgrid;

[0049] Based on the future operating state, generate data collection instructions using the cloud;

[0050] Forward the data collection instructions through the edge gateway of the microgrid and return the data collection results;

[0051] Based on the data collection results, generate microgrid control instructions using the cloud and forward the microgrid control instructions through the edge gateway.

[0052] In a fifth aspect, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0053] Collect historical operating data of the microgrid;

[0054] Based on the historical operating data, construct a prediction model for the operating state of the microgrid;

[0055] Using the prediction model, predict the future operating state of the microgrid;

[0056] Based on the future operating state, generate data collection instructions using the cloud;

[0057] Forward the data collection instructions through the edge gateway of the microgrid and return the data collection results;

[0058] Based on the data collection results, generate microgrid control instructions using the cloud and forward the microgrid control instructions through the edge gateway.

[0059] The above microgrid control method, device, computer equipment, computer-readable storage medium and computer program product based on cloud-edge collaboration. The edge device performs preliminary data collection and processing on the real-time operation status of the microgrid, can quickly screen out key data, and reduce the amount of data transmitted to the cloud. The prediction model constructed based on historical operation data can accurately predict the future operation status of the microgrid, and the cloud generates more targeted data collection instructions accordingly. Compared with traditional broad instructions, such instructions can accurately point to the data points that need attention, avoid collecting a large amount of irrelevant data, and improve the efficiency of data processing. Perform correlation analysis on historical operation data, eliminate irrelevant data, and retain strongly positively correlated, strongly negatively correlated and low-correlated data. This can ensure that the data used for model training and subsequent analysis is closely related to the operation status of the microgrid, thereby improving the accuracy of data analysis. Predict the future operation status of the microgrid through the model and generate data collection instructions accordingly, which can more comprehensively cover the key operation data points of the microgrid and reduce data collection omissions. Because the prediction model is learned based on a large amount of historical data, it can identify various factors affecting the operation status of the microgrid, and thus take these factors into account when generating instructions to ensure that the collected data can comprehensively reflect the operation status of the microgrid. The cloud generates microgrid control instructions based on accurate data collection results and forwards them to the energy management platform of the microgrid in a timely manner through the edge gateway. These control instructions can perform precise energy distribution, load scheduling and equipment control according to the actual operation status and predicted future status of the microgrid, thereby improving the operation efficiency and stability of the microgrid.

[0060] In summary, the cloud-edge collaboration architecture enables the microgrid to achieve real-time interaction between the cloud and the edge. The edge device can quickly respond to the real-time changes of the microgrid, perform preliminary processing and control, while the cloud provides more powerful computing capabilities and global optimization strategies. This collaborative control method can timely respond to various emergencies in the microgrid, such as equipment failures, weather changes, etc., to ensure the stable operation of the microgrid. Description of the Drawings

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0062] Figure 1 It is an application environment diagram of the microgrid control method based on cloud-edge collaboration in an embodiment;

[0063] Figure 2Schematic flowchart of a microgrid control method based on cloud-edge collaboration in an embodiment;

[0064] Figure 3 Schematic flowchart of a microgrid control method based on cloud-edge collaboration in another embodiment;

[0065] Figure 4 Block diagram of the structure of a microgrid control device based on cloud-edge collaboration in an embodiment;

[0066] Figure 5 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0067] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] The microgrid control method based on cloud-edge collaboration provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 where the terminal 102 communicates with the server 104 through a network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or on other network servers.

[0069] The server 104 collects the historical operation data of the microgrid through the terminal 102; the server 104 constructs a prediction model for the operation state of the microgrid based on the historical operation data; uses the prediction model to predict the future operation state of the microgrid; based on the future operation state, generates a data collection instruction by the cloud; forwards the data collection instruction through the edge gateway of the microgrid and returns the data collection result; based on the data collection result, generates a microgrid control instruction by the cloud and forwards the microgrid control instruction through the edge gateway.

[0070] Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0071] In an exemplary embodiment, as Figure 2 shown, a microgrid control method based on cloud-edge collaboration is provided. Taking the server in Figure 1 as an example for illustration, the method includes the following steps S202 to S212. Among them:

[0072] Step S202: Collect historical operation data of the microgrid.

[0073] Specifically, the data acquisition channels include:

[0074] Internal devices of the microgrid: including operation data of distributed power sources (such as solar panels, wind turbines, energy storage batteries, etc.), such as the power generation of solar panels, the power generation power of wind turbines, the charge and discharge status of energy storage batteries, etc. These devices are the core part of the microgrid energy supply, and their operation data can reflect the energy generation situation of the microgrid.

[0075] Power consumption load side: Record the load demand data of each electrical device in the microgrid, such as the power consumption and power of each user during different time periods. Through these data, the energy consumption situation of the microgrid and the load fluctuation law can be understood.

[0076] Energy management system: This system monitors and manages the overall operation of the microgrid, and the recorded data covers system operation parameters such as voltage, current, frequency, power factor, etc. These parameters can reflect whether the operation state of the microgrid is stable and whether there are abnormal situations.

[0077] The historical operation data includes:

[0078] Energy generation data: such as solar power generation, wind speed and wind direction data (for wind power generation), the charge and discharge status of energy storage batteries, etc. These data reflect the power generation situation of renewable energy in the microgrid and the energy storage and release of energy storage devices, and are an important basis for the microgrid energy supply.

[0079] System operation data: including voltage fluctuation data, current harmonic data, system frequency stability, etc. These data are used to evaluate the power quality and operation stability of the microgrid, and are crucial for ensuring the safe and reliable operation of the microgrid.

[0080] Load demand data: Records the electricity demand of each user in the microgrid during different time periods, such as the production electricity load of industrial users and the daily electricity load of residential users. By analyzing the load demand data, the load change trend of the microgrid can be predicted, providing a reference for the reasonable allocation and scheduling of energy.

[0081] The time span of the data includes:

[0082] Short-term historical data: It may include data of the recent days, weeks or months. These data can reflect the recent operating status and trends of the microgrid, and are of great significance for short-term operation optimization and fault diagnosis. For example, by analyzing the recent solar power generation data, it can be judged whether the solar power generation equipment is operating normally and the impact of weather conditions on the power generation.

[0083] Long-term historical data: It covers data of several months, years or even longer. Long-term historical data helps to analyze the long-term operating characteristics of the microgrid, such as seasonal load changes, the impact of equipment aging on performance, etc. By analyzing the long-term data, it can provide a basis for the planning, equipment update and technology upgrade of the microgrid.

[0084] Step S204, based on the historical operation data, construct a prediction model for the operating state of the microgrid.

[0085] Specifically, extract the features useful for prediction from the historical operation data. For example, extract the daily, weekly and monthly periodic features from the time series data; extract the equipment operating status (such as normal, faulty, maintenance) from the distributed power source data as features.

[0086] Select the features highly correlated with the operating state of the microgrid and remove the redundant features. Methods such as correlation analysis and feature importance evaluation can be used to determine which features have a significant impact on the prediction targets (such as future power generation, load demand, voltage stability, etc.). For example, it is found that temperature and light intensity are highly correlated with solar power generation, while less correlated with wind power generation, so these two features are mainly considered when predicting solar power generation.

[0087] Then, select a suitable model according to the characteristics of the microgrid operating state and the prediction target. For time series prediction (such as power generation or load demand in the next few hours), deep learning models such as recurrent neural network (RNN), long short-term memory network (LSTM) or gated recurrent unit (GRU) can be used. These models can capture the long-term dependencies in the time series data. For classification problems (such as equipment fault prediction), models such as support vector machine (SVM), decision tree or random forest can be used. In this embodiment, the preferred prediction model is a recurrent neural network model.

[0088] Design the structure and parameters of the model. For example, when using the LSTM model to predict the future operating state of the microgrid, it is necessary to determine the number of layers of the LSTM layer, the number of neurons in each layer, the activation function, etc. The design of the model architecture should take into account the complexity of the data and the difficulty of the prediction task to achieve better prediction results.

[0089] Partition the dataset: Divide the historical operation data into a training set, a validation set, and a test set. Usually, it can be partitioned according to the ratio of 70% (training set), 15% (validation set), and 15% (test set). The training set is used for model training, the validation set is used to adjust the hyperparameters of the model and prevent overfitting, and the test set is used to evaluate the final performance of the model. Use the training set data to train the model. During the training process, adjust the parameters of the model through an optimization algorithm (such as gradient descent) to minimize the error between the predicted value and the actual value. For example, when training a model for predicting the load demand of a microgrid, by continuously adjusting the model parameters, the mean square error between the predicted load and the actual load of the model for the training set data gradually decreases.

[0090] Selection of evaluation metrics: Select appropriate evaluation metrics according to the prediction task. For regression problems (such as power generation, load demand prediction), common evaluation metrics include mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), etc.; for classification problems (such as equipment fault prediction), common evaluation metrics include accuracy, recall rate, F1 score, etc.

[0091] Model optimization: Optimize the model according to the results of the evaluation metrics. If the model performs poorly on the validation set, it may be necessary to adjust the model architecture, hyperparameters, or adopt regularization methods to prevent overfitting. For example, if it is found that the RMSE of the model on the validation set is high, the model can be optimized by increasing the number of neurons in the hidden layer or adjusting the learning rate.

[0092] Step S206, use the prediction model to predict the future operating state of the microgrid.

[0093] Specifically, collect the current operating data in real time from various sensors and devices of the microgrid, including parameters such as the output power of distributed power sources, the state of charge of energy storage systems, the current demand of electrical loads, the voltage and current of the power grid, etc.

[0094] Combine the historical operation data to provide richer context information for the prediction model. For example, if the prediction model needs to consider seasonal or periodic factors, data from the same past time period can be supplemented.

[0095] Load the trained prediction model. According to the requirements of the model, construct a feature vector from the input data. For example, if the model requires time series features, data from the past few time points can be used as feature inputs. Input the constructed feature vector into the prediction model, and the model calculates through internal algorithms and parameters to output the future operating state of the microgrid. For example, predict the power generation, load demand, voltage level, etc. at future time points.

[0096] The results output by the prediction model are usually one or more values or states interpretable by artificial intelligence. For example, the predicted solar power generation for the next hour is 150 kW, the load demand is 200 kW, and the voltage fluctuation is within the normal range. The prediction results are presented to the operator or system in an intuitive manner. For example, the changing trends of future power generation and load demand are displayed through a graph to help the operator quickly understand the operating status of the microgrid.

[0097] Step S208, based on the future operating status, generate data collection instructions using the cloud.

[0098] Specifically, first, the future operating status of the microgrid obtained through the prediction model (such as power generation, load demand, voltage fluctuation, etc. in the next few hours) is input into the cloud system. These prediction results are obtained through a complex machine learning model based on historical operating data and real-time data, and can provide forward-looking information on the future operation of the microgrid. The cloud system conducts a detailed analysis of these future operating statuses, identifies key operating parameters and potential operating risks. For example, if the prediction shows that the load demand will increase significantly at a certain future moment while the power generation may be insufficient, the cloud system will mark this risk point.

[0099] According to the analysis results of the future operating status, the cloud system generates specific data collection instructions. These instructions are designed to collect data that has a direct impact on the future operating status or can help further optimize the operation. For example, if an increase in load demand is predicted, the cloud may generate an instruction to require the edge device to increase the monitoring frequency of the state of charge of the energy storage system, or to collect the real-time output power data of distributed power sources more frequently.

[0100] As a preferred solution, that is, the generation of data collection instructions can also be based on another method. Specifically, the prediction results are directly processed on the edge device or the field controller to generate data collection instructions. This method can reduce the dependence on the cloud system, reduce the network transmission delay, and improve the real-time performance and response speed of the system. However, when processing data on the edge device or the field controller, obviously these devices need to have certain computing power and processing capabilities.

[0101] The generated data collection instructions include not only what data to collect, but also detailed parameters such as the collection frequency and time window. For example, the instruction may require collecting the state of charge of the energy storage system every 5 minutes during peak load periods, and every 30 minutes at other times.

[0102] Step S210, forward the data collection instructions through the edge gateway of the microgrid and return the data collection results.

[0103] Specifically, the edge gateway can convert the instruction format from the cloud into a format that edge devices can understand. It is an intermediate node in the microgrid that connects edge devices (such as sensors, controllers, distributed power sources, etc.) and the cloud. It is responsible for forwarding the data collection instructions generated by the cloud to the edge devices and uploading the data results collected by the edge devices back to the cloud.

[0104] The edge gateway receives data collection instructions from the cloud. These instructions contain detailed information such as the data types to be collected, collection frequencies, time windows, etc. For example, the instruction may require collecting the state of charge of the energy storage system every 5 minutes. The edge gateway parses the received instructions to ensure that the instruction format and content are correct. If the instruction format is incorrect or the content is incomplete, the edge gateway can request the cloud to resend the instruction or make corrections. After parsing, the edge gateway forwards the instructions to the corresponding edge devices, and these devices perform data collection according to the instruction requirements. For example, forwarding the instruction to collect the state of charge to the controller of the energy storage system.

[0105] After receiving the instructions, the edge devices collect the target data from the microgrid according to the instruction requirements. For example, the controller of the energy storage system measures the state of charge every 5 minutes according to the instruction and temporarily stores the data.

[0106] The edge gateway aggregates the data collected by multiple edge devices. For example, aggregating the state of charge data of multiple energy storage systems into a data packet. The aggregated data is uploaded back to the cloud through the edge gateway. The uploaded data format usually meets the requirements of the cloud so that the cloud can directly perform further analysis and processing.

[0107] Step S212, based on the data collection results, generate microgrid control instructions using the cloud and forward the microgrid control instructions through the edge gateway.

[0108] Specifically, the cloud receives the data collection results uploaded from the edge gateway. These results include the real-time operation data of each device in the microgrid, such as the output power of distributed power sources, the state of charge of energy storage systems, the demand of electrical loads, parameters such as voltage and current. The cloud verifies the uploaded data to ensure the integrity and accuracy of the data. If data loss or anomalies are found, the cloud can request the edge gateway to resend the data or complete the data. Integrate the data from different edge devices to form a comprehensive view of the microgrid operation status. For example, integrating the state of charge data of multiple energy storage systems and the power generation data of distributed power sources for comprehensive analysis.

[0109] The cloud conducts a detailed analysis of the aggregated data to evaluate the current operation status and future trends of the microgrid. For example, analyzing whether the current power generation meets the load demand, whether the energy storage system is in a healthy state, and whether the voltage and current are within the normal range.

[0110] Based on the analysis results, the cloud generates control instructions for the microgrid. These instructions are aimed at optimizing the operation of the microgrid to ensure the stability and economy of power supply. For example:

[0111] Power generation control: If an increase in future load demand is predicted, the cloud can generate instructions to require distributed power sources to increase their output power.

[0112] Energy storage control: If the state of charge of the energy storage system is high and the current power generation is excessive, the cloud can generate instructions to require the energy storage system to charge; conversely, if the load demand is high and the power generation is insufficient, instructions can be generated to require the energy storage system to discharge.

[0113] Load management: If the load demand exceeds the power generation capacity, the cloud can generate instructions for demand response management, such as adjusting the operating time of non-critical loads.

[0114] Voltage and frequency control: If the voltage or frequency deviates from the normal range, the cloud can generate instructions to adjust the operating state of reactive power equipment, such as switching capacitor banks or adjusting transformer tap positions.

[0115] The cloud formats the generated control instructions into a format that the edge devices can understand and sends them through the edge gateway. For example, converting the control instructions into a specific communication protocol and data format. The edge gateway receives the control instructions sent by the cloud and forwards them to the corresponding edge devices or platforms. For example, forwarding the power generation control instructions to the controller of the distributed power source and forwarding the energy storage control instructions to the management system of the energy storage system.

[0116] After receiving the control instructions, the edge devices perform the corresponding operations and feedback the execution results to the edge gateway. The edge gateway then uploads the execution results back to the cloud to form a closed-loop control. For example, after receiving the instruction to increase the output power, the distributed power source controller adjusts the operating parameters of the power generation equipment and uploads the adjusted output power data back to the cloud.

[0117] In the above-mentioned microgrid control method based on cloud-edge collaboration, the edge device performs preliminary data collection and processing on the real-time operating status of the microgrid, which can quickly filter out key data and reduce the amount of data transmitted to the cloud. This not only reduces the delay in data transmission, but also reduces the processing burden of the cloud and improves the overall data processing efficiency. The prediction model built based on historical operating data can accurately predict the future operating status of the microgrid, and the cloud generates more targeted data collection instructions based on this. Compared with traditional broad instructions, this instruction can accurately point to the data points that need to be paid attention to, avoid collecting a large amount of irrelevant data, and further improve the efficiency of data processing. Predicting the future operating status of the microgrid through the model and generating data collection instructions based on this can more comprehensively cover the key operating data points of the microgrid and reduce the omission of data collection. This helps to ensure that the collected data can fully reflect the operating status of the microgrid and provide more complete and accurate data support for subsequent analysis and decision-making. The cloud generates microgrid control instructions based on accurate data collection results and forwards them to the energy management platform of the microgrid in a timely manner through the edge gateway. These control instructions can accurately distribute energy, dispatch loads, and control equipment according to the actual operating status and predicted future status of the microgrid, thereby improving the operating efficiency and stability of the microgrid. The cloud-edge collaborative architecture enables the microgrid to achieve real-time interaction between the cloud and the edge. Edge devices can quickly respond to real-time changes in the microgrid and perform preliminary processing and control, while the cloud provides more powerful computing power and global optimization strategies. This collaborative control method can respond to various emergencies in the microgrid in a timely manner, such as equipment failures, weather changes, etc., to ensure the stable operation of the microgrid.

[0118] In an exemplary embodiment, Figure 3 As shown in the figure, based on the historical operation data, a prediction model of the microgrid operation status is constructed, including:

[0119] Step S302, analyzing the correlation between each data in the historical operation data to obtain an analysis result;

[0120] Step S304, based on the analysis results, cleaning the historical operation data;

[0121] Step S306: construct a prediction model for the operation status of the microgrid based on the filtered historical operation data.

[0122] Specifically, perform a correlation analysis on these historical operation data with the aim of finding the internal relationships between different data. For example, analyze the correlation between solar power generation and weather conditions (such as light intensity, temperature), or analyze the correlation between electricity load and time (such as hours, seasons). Through the correlation analysis, obtain the correlation results between each pair of data, and these results will be used for subsequent data cleaning and model construction. For example, it is found that solar power generation is highly correlated with light intensity and has no significant correlation with wind speed.

[0123] According to the results of the correlation analysis, clean and process the historical operation data. The purpose of the cleaning process is to remove irrelevant data, outliers, and noise, and retain high-quality data useful for prediction. Eliminate data that has no significant correlation with the operation state of the microgrid. For example, if the analysis results show that there is no correlation between wind speed and solar power generation, the wind speed data can be eliminated to reduce data redundancy. Identify and process outliers in the data. Outliers may be caused by sensor failures, data recording errors, etc. Statistical methods (such as Z-score, IQR) can be used to identify outliers and correct or delete them. For missing data, interpolation methods (such as linear interpolation, K-nearest neighbor interpolation) or statistical values based on other data (such as mean, median) can be used to fill in the missing data to ensure the integrity of the data.

[0124] Select features that have a significant impact on the prediction target (such as future power generation, load demand, voltage stability, etc.) from the cleaned data. For example, select light intensity and temperature as features for predicting solar power generation. Select a suitable prediction model according to the nature of the prediction task. For time series prediction (such as power generation or load demand in the next few hours), deep learning models such as recurrent neural network (RNN), long short-term memory network (LSTM), or gated recurrent unit (GRU) can be used. For classification problems (such as equipment failure prediction), models such as support vector machine (SVM), decision tree, or random forest can be used.

[0125] Use the filtered historical operation data to train the selected model. During the training process, adjust the parameters of the model through optimization algorithms (such as gradient descent) to minimize the error between the predicted value and the actual value. For example, use the mean squared error (MSE) as the loss function and adjust the parameters of the LSTM model through the backpropagation algorithm.

[0126] In this embodiment, through correlation analysis and data cleaning, high-quality data useful for prediction is retained, and irrelevant data and noise are removed, thereby improving the training effect and prediction accuracy of the model. Eliminating irrelevant data reduces data redundancy, eases the burden of data storage and processing, and improves data processing efficiency. Based on real-time data and prediction results, the parameters and structure of the model can be dynamically adjusted to ensure that the model is always in an optimal state and adapts to the real-time changes of the microgrid.

[0127] In an exemplary embodiment, based on the analysis results, the historical operation data is cleaned, including:

[0128] Based on the analysis results, obtain the degree of association between the data in the historical operation data;

[0129] Eliminate the data with an association degree lower than the preset threshold from the historical operation data.

[0130] Specifically, first, perform a correlation analysis on the historical operation data to calculate the correlation coefficients between the data. The correlation coefficient can quantify the linear relationship between the data. Commonly used ones include the Pearson correlation coefficient, Spearman rank correlation coefficient, etc. The value range of the Pearson correlation coefficient is between -1 and 1. A value close to 1 indicates a strong positive correlation, close to -1 indicates a strong negative correlation, and close to 0 indicates no correlation. Set a correlation threshold, such as 0.3. This threshold is used to determine whether the correlation between the data is strong enough to decide whether to retain the data. According to the calculated correlation coefficients, eliminate the data with a correlation coefficient lower than the preset threshold from the historical operation data.

[0131] In this embodiment, by eliminating the data with low correlation, data redundancy is reduced, and the purity and quality of the data are improved. This helps to improve the efficiency and accuracy of model training. The data with low correlation may contain noise. Eliminating this data can reduce the impact of noise on model training and improve the generalization ability of the model. Retaining the data with high correlation ensures that the model can learn the features that have a significant impact on the prediction target, thereby improving the prediction performance of the model.

[0132] In an exemplary embodiment, based on the analysis results, obtaining the degree of association between the data in the historical operation data includes:

[0133] Using the calculation formula of the Pearson correlation coefficient, calculate the correlation coefficients between the data in the historical operation data respectively. The correlation coefficient is used to characterize the degree of association between the data. Among them, the historical operation data includes solar power generation, the load demand value of the microgrid, and voltage fluctuation data. The calculation formula of the Pearson correlation coefficient includes:

[0134]

[0135] Among them, xi and yi are the i-th data points in the two data sets respectively; and are the average values ​​in the two data sets respectively; n is the number of data points.

[0136] Specifically, the Pearson correlation coefficient is a statistical measure used to measure the linear correlation between two continuous variables. Its value range is between -1 and 1, where:

[0137] 1 indicates a perfect positive correlation, that is, when one variable increases, the other variable also increases;

[0138] -1 indicates a perfect negative correlation, that is, when one variable increases, the other variable decreases;

[0139] 0 means no correlation, that is, there is no linear relationship between the two variables.

[0140] Assume that there are three data sets: XX (solar power generation), YY (microgrid load demand value) and ZZ (voltage fluctuation data). It is necessary to calculate the Pearson correlation coefficient between each pair of data sets.

[0141] Strong positive correlation: If the correlation coefficient is close to 1, it means that there is a strong positive correlation between the two data sets. For example, r(XY)≈1, which means that there is a strong positive correlation between the solar power generation and the load demand value of the microgrid.

[0142] Strong negative correlation: If the correlation coefficient is close to -1, it indicates that there is a strong negative correlation between the two data sets. For example, if r(XZ) ≈ -1, it indicates that there is a strong negative correlation between the solar power generation and voltage fluctuation data.

[0143] No correlation: If the correlation coefficient is close to 0, it means that there is no linear correlation between the two data sets. For example, if r(YZ)≈0, it means that there is no linear correlation between the load demand value and the voltage fluctuation data of the microgrid.

[0144] In this embodiment, the historical operation data can be cleaned according to the calculated correlation coefficient, and the data with low correlation can be eliminated and the data with high correlation can be retained to improve the data quality and provide a solid foundation for subsequent model construction and training.

[0145] In an exemplary embodiment, forwarding a microgrid control instruction through an edge gateway includes:

[0146] Send microgrid control instructions to the edge cluster platform;

[0147] The edge gateway of the microgrid forwards the microgrid control instructions to the energy management platform, enabling the energy management platform to perform control operations on the microgrid based on the microgrid control instructions. The dimensions of the control operations include optimizing the control of energy distribution, load forecasting, and fault diagnosis of the microgrid.

[0148] Specifically, the cloud formats the generated control instructions into a format that the edge cluster platform can understand and sends them to the edge cluster platform through the network. The formatting process ensures the integrity and consistency of the instructions during transmission. The edge gateway, as an intermediate node connecting the cloud and edge devices in the microgrid, receives the control instructions from the cloud. The edge gateway has protocol conversion and data preprocessing functions and can convert the instruction format from the cloud into a format that edge devices can understand. The edge gateway parses the received control instructions to ensure that the instruction format and content are correct. If the instruction format is incorrect or the content is incomplete, the edge gateway can request the cloud to resend the instruction or make corrections.

[0149] After parsing, the edge gateway forwards the control instructions to the energy management platform of the microgrid. The energy management platform is the local control center of the microgrid and is responsible for performing specific control operations. The energy management platform receives the control instructions forwarded by the edge gateway and further parses and validates them to ensure the feasibility and security of the instructions. According to the control instructions, the energy management platform performs specific control operations, and the dimensions of these operations include: adjusting the output power of distributed power sources and optimizing the energy distribution in the microgrid. For example, according to the load demand and power generation capacity, reasonably allocate the output of solar energy, wind energy, and energy storage systems.

[0150] Among them, for the energy distribution of the microgrid: it is required that the solar power generation system increases the output power when the sunlight is sufficient, and the energy storage system charges during the low load period and discharges during the high load period.

[0151] Load forecasting: According to the load forecasting, adjust the operation time of non-critical loads to ensure the balance of power supply.

[0152] Fault diagnosis: Monitor voltage and current parameters, identify potential equipment failures, and give early warnings or automatically switch to standby equipment in a timely manner.

[0153] These control instructions are forwarded to the energy management platform through the edge gateway. The energy management platform performs specific control operations according to the instructions, optimizes the operation status of the microgrid, and ensures the stability and economy of power supply.

[0154] Based on historical data and real-time data, predict future load demands and conduct load management in advance. For example, through demand response management, adjust the operating time of non-critical loads to ensure the balance of power supply. Monitor the operating status of the microgrid, identify potential fault risks, and perform fault diagnosis and handling in a timely manner. For example, by monitoring voltage, current, and equipment status parameters, identify equipment faults and give early warnings or automatically switch to standby equipment.

[0155] In this embodiment, through the collaborative work of the edge gateway and the energy management platform, the microgrid can quickly respond to the control instructions generated by the cloud and achieve real-time control. This helps to cope with various emergencies in the microgrid, such as equipment failures and load fluctuations, and ensures the stable operation of the microgrid. Based on the prediction model and data acquisition results on the cloud, the control instructions can optimize the energy distribution, load management, and fault diagnosis of the microgrid, improving the operating efficiency and reliability of the microgrid. For example, by optimizing energy distribution, reduce energy waste and improve energy utilization efficiency. The distributed architecture of the edge gateway and the energy management platform enables the microgrid to achieve the combination of local autonomy and global optimization. Edge devices can perform preliminary control operations, while the cloud provides global optimization strategies to ensure the efficient operation of the microgrid under different operating conditions.

[0156] In an exemplary embodiment, based on the data acquisition results, generate microgrid control instructions using the cloud, including:

[0157] Perform aggregation processing on the data acquisition results and upload them to the cloud;

[0158] Use the cloud to perform an analysis of the operating status of the microgrid on the aggregated data acquisition results to obtain the operating status analysis results;

[0159] Generate microgrid control instructions based on the operating status analysis results.

[0160] Specifically, edge devices (such as sensors and controllers) collect real-time operating data from the microgrid, including parameters such as the output power of distributed power sources, the state of charge of energy storage systems, the demand of electrical loads, voltage, current, and frequency. Edge devices or edge gateways perform preprocessing on the collected data, such as data cleaning, removing outliers, formatting, etc., to ensure the quality and consistency of the data.

[0161] Perform aggregation processing on the preprocessed data to form a comprehensive data packet. For example, summarize the power generation data of multiple distributed power sources or summarize the electricity consumption data of multiple load users. Aggregation processing can reduce the data transmission volume and improve the data transmission efficiency. The aggregated data is uploaded to the cloud through the edge gateway. The format of the uploaded data usually conforms to the requirements of the cloud so that the cloud can directly perform further analysis and processing.

[0162] The cloud receives the aggregated data uploaded from the edge gateway and verifies it to ensure the integrity and accuracy of the data. The cloud conducts a detailed analysis of the aggregated data to evaluate the current operating status and future trends of the microgrid. The analysis content includes:

[0163] Energy distribution: Analyze whether the power generation of distributed power sources meets the load demand and whether the state of charge of the energy storage system is reasonable.

[0164] Load management: Predict future load demands, evaluate whether the load distribution is balanced, and whether there is a risk of overload.

[0165] Voltage and frequency: Monitor whether the voltage and frequency are within the normal range and whether there is a risk of fluctuation.

[0166] Equipment status: Evaluate the operating status of equipment and identify potential failure risks.

[0167] Through the analysis, the cloud generates the analysis results of the operating status of the microgrid, which include the current operating status, future predicted status, and potential risk points. For example, the analysis results show that the current power generation is sufficient, but the future load demand will increase, and the energy storage system needs to be charged in advance. The cloud conducts a fault analysis on the aggregated data to identify potential fault points in the microgrid. For example, by monitoring the operating parameters (such as temperature, current, voltage) and historical data of equipment, it is identified whether the equipment is abnormal. Based on the operating status analysis results and the operating status analysis results, the cloud generates microgrid control instructions. These instructions are aimed at optimizing the operating status of the microgrid to ensure the stability and economy of power supply. The control instructions may include:

[0168] Power generation control: Adjust the output power of distributed power sources to ensure that the power generation meets the load demand.

[0169] Energy storage control: Control the charge and discharge of the energy storage system to optimize energy storage and release.

[0170] Load management: Adjust the operating time of non-critical loads to ensure the balance of power supply.

[0171] Fault handling: Isolate the identified faulty equipment or switch to standby equipment to ensure the stable operation of the system.

[0172] Instruction optimization: The cloud can use an expert system to optimize the generated control instructions to ensure the effectiveness and safety of the instructions. For example, the expert system can check whether the instructions will cause equipment overload or voltage over-limit and put forward improvement suggestions.

[0173] In this embodiment, through real-time analysis and control instruction generation in the cloud, the microgrid can quickly respond to changes in the operating state and achieve real-time control. This helps to cope with various emergencies in the microgrid, such as equipment failures, load fluctuations, etc., and ensures the stable operation of the microgrid. Based on detailed operating state analysis and fault analysis, the control instructions can optimize the energy distribution, load management, and fault handling of the microgrid, improving the operating efficiency and reliability of the microgrid.

[0174] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps in other steps.

[0175] Based on the same inventive concept, an embodiment of the present application also provides a cloud-edge collaborative microgrid control device for implementing the above-mentioned cloud-edge collaborative microgrid control method. The solution provided by this device to solve problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the following cloud-edge collaborative microgrid control device can refer to the limitations on the cloud-edge collaborative microgrid control method in the above text, and will not be repeated here.

[0176] In an exemplary embodiment, as Figure 4 shown, a cloud-edge collaborative microgrid control device is provided, including:

[0177] A data acquisition module 402, configured to acquire historical operation data of the microgrid;

[0178] A model construction module 404, configured to construct a prediction model of the microgrid operating state based on the historical operation data;

[0179] A control module 406, configured to use the prediction model to predict the future operating state of the microgrid;

[0180] The control module 406 is further configured to generate a data acquisition instruction using the cloud based on the future operating state;

[0181] The control module 406 is further configured to forward the data acquisition instruction through the edge gateway of the microgrid and return the data acquisition result;

[0182] The control module 406 is further configured to generate a microgrid control instruction by using the cloud based on the data acquisition result, and forward the microgrid control instruction through the edge gateway.

[0183] In an exemplary embodiment, the data processing module 408 is configured to analyze the correlation between the data in the historical operation data to obtain an analysis result; and perform cleaning processing on the historical operation data based on the analysis result.

[0184] The model construction module 404 is further configured to construct a prediction model for the operation state of the microgrid based on the screened historical operation data.

[0185] In an exemplary embodiment, the data processing module 408 is further configured to obtain the degree of association between the data in the historical operation data based on the analysis result; and remove the data with the degree of association lower than the preset threshold from the historical operation data.

[0186] In an exemplary embodiment, the data processing module 408 is further configured to calculate the correlation coefficient between the data in the historical operation data respectively by using the calculation formula of the Pearson correlation coefficient, and the correlation coefficient is used to characterize the degree of association between the data; wherein, the historical operation data includes solar power generation, the load demand value of the microgrid, and voltage fluctuation data, and the calculation formula of the Pearson correlation coefficient includes:

[0187]

[0188] wherein xi and yi are the i-th data points in the two data sets respectively; and are the average values in the two data sets respectively; and n is the number of data points.

[0189] In an exemplary embodiment, the control module 406 is further configured to send the microgrid control instruction to the edge cluster platform through the cloud; forward the microgrid control instruction to the energy management platform through the edge gateway of the microgrid, so that the energy management platform performs control operations on the microgrid based on the microgrid control instruction, and the dimensions of the control operations include optimizing the control of the energy distribution, load prediction, and fault diagnosis of the microgrid.

[0190] In an exemplary embodiment, the data processing module 408 is further configured to perform aggregation processing on the data acquisition result, and the control module 406 is further configured to upload the aggregated data acquisition result to the cloud; use the cloud to perform operation state analysis of the microgrid on the aggregated data acquisition result to obtain an operation state analysis result; and generate a microgrid control instruction based on the operation state analysis result.

[0191] Each module in the above-mentioned microgrid control device based on cloud-edge collaboration can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of a computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0192] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the historical operation data of the microgrid. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a microgrid control method based on cloud-edge collaboration.

[0193] Those skilled in the art can understand that Figure 5 the structure shown in

[0194] is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0195] In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of the above method.

[0196] In an embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, it implements the steps of the above method.

[0197] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0198] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0199] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0200] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application should be subject to the appended claims.

Claims

1. A microgrid control method based on cloud-edge collaboration, characterized in that: The method comprises: Collect historical operation data of microgrid; Based on historical operation data, a prediction model for the operation status of the microgrid is constructed; Using the prediction model, the future operation state of the microgrid is predicted; Based on the future operating state, generating data collection instructions using the cloud; Forwarding the data collection instruction through the edge gateway of the microgrid and returning the data collection result; Based on the data collection results, a microgrid control instruction is generated using the cloud, and the microgrid control instruction is forwarded through an edge gateway.

2. The method according to claim 1, characterized in that The method of constructing a prediction model for the operation status of a microgrid based on historical operation data includes: Analyze the correlation between each data in the historical operation data to obtain an analysis result; Based on the analysis result, cleaning the historical operation data; Based on the filtered and processed historical operation data, a prediction model for the operation status of the microgrid is constructed.

3. The method according to claim 2, characterized in that The cleaning process of the historical operation data based on the analysis result includes: Based on the analysis results, obtaining the degree of correlation between each data in the historical operation data; Data with a correlation degree lower than a preset threshold is removed from the historical operation data.

4. The method according to claim 3, characterized in that The step of obtaining the degree of association between each data in the historical operation data based on the analysis result includes: The calculation formula of the Pearson correlation coefficient is used to calculate the correlation coefficients between the data in the historical operation data, and the correlation coefficient is used to characterize the degree of association between the data; wherein the historical operation data includes solar power generation, load demand value of the microgrid and voltage fluctuation data, and the calculation formula of the Pearson correlation coefficient includes: Among them, xi and yi are the i-th data points in the two data sets respectively; and are the average values ​​in the two data sets respectively; n is the number of data points.

5. The method according to claim 1, characterized in that: The forwarding of the microgrid control instruction by the edge gateway includes: Send microgrid control instructions to the edge cluster platform; The microgrid control instructions are forwarded to the energy management platform through the microgrid's edge gateway, so that the energy management platform can control the microgrid based on the microgrid control instructions. The dimensions of the control operation include optimizing the microgrid's energy distribution, load forecasting, and fault diagnosis.

6. The method according to claim 1, characterized in that The method of generating a microgrid control instruction based on the data collection result by using the cloud comprises: Aggregate the data collection results and upload them to the cloud; Use the cloud to analyze the operation status of the microgrid based on the aggregated data collection results to obtain the operation status analysis results; Based on the operating status analysis result, a microgrid control instruction is generated.

7. A microgrid control device based on cloud-edge collaboration, characterized in that: The device comprises: Data acquisition module, used to collect historical operation data of the microgrid; A model building module is used to build a prediction model of the microgrid operation status based on historical operation data; A control module, used to predict the future operation state of the microgrid using the prediction model; The control module is further used to generate data collection instructions using the cloud based on the future operating state; The control module is also used to forward the data collection instruction through the edge gateway of the microgrid and return the data collection result; The control module is also used to generate microgrid control instructions using the cloud based on the data collection results, and forward the microgrid control instructions through the edge gateway.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images