New energy power transmission state monitoring method and system based on artificial intelligence algorithm

Abstract

The invention provides a new energy power transmission state monitoring method and system based on an artificial intelligence algorithm, and belongs to the technical field of power system automation. The method comprises the following steps: collecting power transmission data in real time through a plurality of sensors deployed in a new energy power transmission network; inputting the power transmission data collected by each sensor into a pre-trained artificial intelligence model to perform feature extraction and mode recognition in sequence so as to analyze the operation state of the new energy power transmission network and obtain an analysis result; dynamically adjusting model parameters of the pre-trained artificial intelligence model according to an analysis result; and performing multiple rounds of optimization on the dynamically adjusted artificial intelligence model until the verification result of the prediction accuracy of the latest artificial intelligence model is optimal, and performing operation state analysis on the new energy power transmission network by using the corresponding latest artificial intelligence model. The purpose of accurately monitoring and predicting the state of the power transmission system is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and specifically to a new energy power transmission status monitoring method based on an artificial intelligence algorithm, a new energy power transmission status monitoring system based on an artificial intelligence algorithm, a machine-readable storage medium and an electronic device. Background Art

[0002] At present, when applying artificial intelligence algorithms to the monitoring of renewable energy power transmission status, there is a problem of how to ensure that artificial intelligence algorithms can accurately monitor and predict the status of the power transmission system in a complex and changeable renewable energy power transmission environment. Due to the intermittent and uncertain characteristics of renewable energy power generation (such as wind and solar energy), it poses a great challenge to the stable operation of the power system. In addition, the power transmission network itself is a highly complex system with multiple nonlinear relationships and interactions within it.

[0003] Therefore, it is very difficult to develop an algorithm that can maintain high accuracy and robustness in a complex and changeable renewable energy power transmission environment. It can be seen that how to ensure that artificial intelligence algorithms can achieve accurate state assessment and fault prediction in a complex and changeable renewable energy power transmission environment is an urgent problem to be solved. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for monitoring the status of renewable energy power transmission based on an artificial intelligence algorithm, so as to at least solve the above-mentioned problem of how to ensure that the artificial intelligence algorithm can achieve accurate status assessment and fault prediction in a complex and changeable renewable energy power transmission environment.

[0005] In order to achieve the above-mentioned object, the first aspect of the present invention provides a new energy power transmission status monitoring method based on artificial intelligence algorithm, comprising:

[0006] Collect power transmission data in real time through multiple sensors pre-deployed in the new energy power transmission network;

[0007] The power transmission data collected by each sensor is input into the pre-trained artificial intelligence model to perform feature extraction and pattern recognition in turn to analyze the operating status of the new energy power transmission network and obtain analysis results;

[0008] According to the analysis results, the model parameters of the pre-trained artificial intelligence model are dynamically adjusted;

[0009] The dynamically adjusted artificial intelligence model is optimized for multiple rounds until the verification result of the prediction accuracy of the latest artificial intelligence model reaches the optimal value, and the corresponding latest artificial intelligence model is used to analyze the operating status of the new energy power transmission network.

[0010] Optionally, the deployment rules of the above sensors include:

[0011] Determine a sensor deployment plan based on historical operation data of the new energy power transmission network; wherein the sensor deployment plan includes sensor type, sensor deployment location and data collection frequency of each deployed sensor;

[0012] The collection rules for power transmission data include:

[0013] Based on the data collection frequency of each sensor, a data collection instruction is sent to each sensor, so that each sensor collects power transmission data according to the corresponding data collection frequency;

[0014] The collected power transmission data is preprocessed; wherein the preprocessing includes at least filtering processing and denoising processing.

[0015] Optionally, the power transmission data collected by each sensor is input into a pre-trained artificial intelligence model for feature extraction and pattern recognition, including:

[0016] Adjust the input layer parameters of the pre-trained artificial intelligence model based on the statistical characteristics of the power transmission data;

[0017] Extract key features from power transmission data using an AI model with adjusted input layer parameters;

[0018] Classify and identify key features in the extracted power transmission data.

[0019] Optionally, the statistical characteristic information of the power transmission data includes the average value μ and variance σ of the power transmission data. 2 ;

[0020] The above-mentioned adjustment of the input layer parameters of the pre-trained artificial intelligence model based on the statistical characteristic information of the power transmission data includes:

[0021] Calculate the mean μ and variance σ of power transmission data 2 ;

[0022] When the variance of power transmission data σ 2 When it is greater than the preset variance threshold T, the weight parameters of each input layer of the artificial intelligence model are adjusted;

[0023] Recalculate the input feature vector of the artificial intelligence model based on the adjusted weight parameters of each input layer of the artificial intelligence model;

[0024] The recalculated input feature vector of the artificial intelligence model is input into the artificial intelligence model to determine the input layer parameters of the adjusted artificial intelligence model.

[0025] Optionally, the above-mentioned recalculation of the input feature vector of the artificial intelligence model based on the weight parameters of each input layer of the adjusted artificial intelligence model includes:

[0026] Normalize the weight parameters of each input layer of the adjusted artificial intelligence model;

[0027] Based on the normalized weight parameters, calculate the importance coefficient of each feature of the artificial intelligence model;

[0028] The features of the artificial intelligence model whose importance coefficients are greater than a preset coefficient threshold η are taken as key features, an input feature vector containing the key features is constructed, and the input feature vector is input into the artificial intelligence model.

[0029] Optionally, the features of the artificial intelligence model whose importance coefficient is greater than a preset coefficient threshold η are taken as key features, and an input feature vector containing the key features is constructed, including:

[0030] Screen out all key features whose importance coefficient is greater than the preset coefficient threshold η;

[0031] The key features are sorted from high to low according to their importance coefficients, and an input feature vector containing the sorted key features is constructed.

[0032] Optionally, the above-mentioned pattern recognition process includes an abnormal pattern recognition process, the analysis result includes a result of the abnormal pattern recognition process, and the result of the abnormal pattern recognition process includes a result of determining that an abnormal pattern exists and a result of determining that an abnormal pattern does not exist;

[0033] Based on the analysis results, the model parameters of the pre-trained AI model are dynamically adjusted, including:

[0034] Determine the adjustment direction of model parameters based on the results of the abnormal pattern recognition process;

[0035] The model parameters are updated according to the adjustment direction, and a dynamically adjusted artificial intelligence model is obtained based on the updated model parameters.

[0036] Optionally, during multiple rounds of optimization of the dynamically adjusted artificial intelligence model, each time the dynamic adjustment of the artificial intelligence model is completed, it is necessary to perform a prediction accuracy verification of the corresponding artificial intelligence model; wherein,

[0037] The rules for validating the predictive accuracy of the AI ​​model include:

[0038] The power transmission data collected by each sensor is input into the dynamically adjusted artificial intelligence model to re-perform feature extraction and pattern recognition;

[0039] Based on the results of re-feature extraction and pattern recognition, verify whether the prediction accuracy of the dynamically adjusted artificial intelligence model is higher than the prediction accuracy of the pre-trained artificial intelligence model that has not been dynamically adjusted.

[0040] Optionally, the power transmission data collected by each sensor is input into a pre-trained artificial intelligence model to perform feature extraction and pattern recognition in sequence to analyze the operating status of the new energy power transmission network, including:

[0041] Extracting feature vectors associated with voltage and / or current from power transmission data, and inputting the feature vectors into a pre-trained artificial intelligence model for preliminary analysis;

[0042] Based on the preliminary analysis results, determine whether there are any unusual patterns;

[0043] When it is determined that an abnormal pattern exists, the abnormal type is identified.

[0044] Optionally, the above-mentioned determination of whether there is an abnormal pattern based on the preliminary analysis results includes:

[0045] Perform statistics on abnormal patterns in the preliminary analysis results, and calculate the probability P of the abnormal pattern appearing based on the statistical results;

[0046] The probability P of the abnormal pattern occurring is compared with the preset probability threshold T1. If the probability P of the abnormal pattern occurring is greater than the preset probability threshold T1, it is determined that the abnormal pattern exists. Otherwise, it is determined that the abnormal pattern does not exist.

[0047] Optionally, the above-mentioned comparing the probability P of the abnormal pattern occurrence with the preset probability threshold T1, if the probability P of the abnormal pattern occurrence is greater than the preset probability threshold T1, then it is determined that the abnormal pattern exists, otherwise, it is determined that the abnormal pattern does not exist, including:

[0048] Calculate the difference ΔP between the probability P of the abnormal mode occurring and the preset probability threshold T1;

[0049] It is determined whether the difference ΔP is greater than zero. If the difference ΔP is greater than zero, it is determined that an abnormal mode exists. Otherwise, it is determined that no abnormal mode exists.

[0050] A second aspect of the present invention provides a new energy power transmission status monitoring system based on an artificial intelligence algorithm, comprising:

[0051] The power transmission data acquisition module is used to collect power transmission data in real time through multiple sensors pre-deployed in the new energy power transmission network;

[0052] The operation status analysis module is used to input the power transmission data collected by each sensor into the pre-trained artificial intelligence model to perform feature extraction and pattern recognition in sequence to analyze the operation status of the new energy power transmission network and obtain analysis results;

[0053] A dynamic adjustment module is used to dynamically adjust the model parameters of the pre-trained artificial intelligence model according to the analysis results;

[0054] The prediction accuracy verification module is used to perform multiple rounds of optimization on the dynamically adjusted artificial intelligence model until the verification result of the prediction accuracy of the latest artificial intelligence model reaches the optimal value, and use the corresponding latest artificial intelligence model to analyze the operating status of the new energy power transmission network.

[0055] In a third aspect of the present invention, a machine-readable storage medium is provided, on which instructions are stored, and when the instructions are executed by a processor, the processor is configured to execute the above-mentioned new energy power transmission status monitoring method based on artificial intelligence algorithm.

[0056] In a fourth aspect of the present invention, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for monitoring the transmission status of new energy power based on artificial intelligence algorithm is implemented.

[0057] Through the above technical solution, a method and system for monitoring the state of new energy power transmission based on artificial intelligence algorithm is provided. Multiple sensors are deployed in the new energy power transmission network to collect power transmission data in real time. According to the power transmission data, a pre-trained artificial intelligence model is used to extract features and recognize patterns to analyze the operating state of the power transmission system (i.e., the new energy power transmission network). According to the analysis results of the artificial intelligence model, the model parameters are dynamically adjusted to adapt to the complex and changeable power transmission environment to improve the monitoring accuracy. And the prediction accuracy of the artificial intelligence model is regularly verified. The artificial intelligence model is continuously optimized through the feedback mechanism to ensure that the artificial intelligence model accurately monitors and predicts the operating state of the new energy power transmission network in the complex and changeable new energy power transmission environment. It also ensures that the artificial intelligence algorithm can achieve the purpose of accurately monitoring and predicting the state of the power transmission system in the complex and changeable new energy power transmission environment.

[0058] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0060] Figure 1 It is a flow chart of a new energy power transmission status monitoring method based on artificial intelligence algorithm provided by one embodiment of the present invention;

[0061] Figure 2 It is a flow chart of another new energy power transmission status monitoring method based on artificial intelligence algorithm provided by one embodiment of the present invention;

[0062] Figure 3 It is a flow chart of deploying multiple sensors in a new energy power transmission network to collect power transmission data in real time, provided by an embodiment of the present invention;

[0063] Figure 4 It is a flowchart of performing feature extraction and pattern recognition using a pre-trained artificial intelligence model provided by an embodiment of the present invention;

[0064] Figure 5 is a flow chart of adjusting the input layer parameters of a model provided by an embodiment of the present invention;

[0065] Figure 6 is a flow chart of recalculating the input feature vector of the model provided by one embodiment of the present invention;

[0066] Figure 7 is a flow chart for determining key features provided by an embodiment of the present invention;

[0067] Figure 8 A flowchart of an embodiment of the present invention for using a pre-trained artificial intelligence model to perform feature extraction and pattern recognition to analyze the operating status of a power transmission system;

[0068] Fig. 9 is a flow chart for determining whether an abnormal pattern exists provided by an embodiment of the present invention;

[0069] Fig.10 is a flow chart based on the comparison between the probability P and the preset probability threshold T1 provided by one embodiment of the present invention;

[0070] Fig.11 is a flowchart for determining whether the difference ΔP is greater than zero, provided by an embodiment of the present invention;

[0071] Fig.12 is a flow chart of updating model parameters based on the results of an abnormal pattern recognition process provided by an embodiment of the present invention;

[0072] Fig.13 It is a block diagram of a new energy power transmission status monitoring system based on artificial intelligence algorithm provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0073] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0074] Figure 1 This is a flow chart of a method for monitoring the transmission status of new energy power based on an artificial intelligence algorithm provided by an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a new energy power transmission status monitoring method based on an artificial intelligence algorithm, comprising:

[0075] S110: Collect power transmission data in real time through multiple sensors pre-deployed in the new energy power transmission network;

[0076] S120: inputting the power transmission data collected by each sensor into the pre-trained artificial intelligence model to perform feature extraction and pattern recognition in sequence, so as to analyze the operation status of the new energy power transmission network and obtain analysis results;

[0077] S130: Dynamically adjust the model parameters of the pre-trained artificial intelligence model according to the analysis results;

[0078] S140: Perform multiple rounds of optimization on the dynamically adjusted artificial intelligence model until the verification result of the prediction accuracy of the latest artificial intelligence model reaches the optimal value, and use the corresponding latest artificial intelligence model to analyze the operating status of the new energy power transmission network.

[0079] Specifically, the method deploys multiple sensors in the new energy power transmission network to collect power transmission data in real time, and uses a pre-trained artificial intelligence model to extract features and recognize patterns based on the power transmission data to analyze the operating status of the power transmission system (i.e., the new energy power transmission network). According to the analysis results of the artificial intelligence model, the model parameters are dynamically adjusted to adapt to the complex and changeable power transmission environment and improve the monitoring accuracy. The prediction accuracy of the artificial intelligence model is verified regularly. The artificial intelligence model is continuously optimized through the feedback mechanism to ensure that the artificial intelligence model accurately monitors and predicts the operating status of the new energy power transmission network in the complex and changeable new energy power transmission environment. This also ensures that the artificial intelligence algorithm can achieve the purpose of accurately monitoring and predicting the status of the power transmission system in the complex and changeable new energy power transmission environment.

[0080] Please refer to Figure 2, Figure 2 It is a flowchart of another new energy power transmission status monitoring method based on artificial intelligence algorithm provided by an embodiment of the present invention. The actual use process steps of the new energy power transmission status monitoring method based on artificial intelligence algorithm are as follows:

[0081] S101: Power transmission data is collected in real time by deploying multiple high-precision sensors at key nodes of the new energy power transmission network. In order to ensure that various status information in the power transmission process can be fully captured, these sensors are carefully arranged at different locations of the network, including but not limited to key links such as power stations, substations, transmission lines, and distribution networks. For example, in a wind farm, in addition to installing sensors near the wind turbines to monitor environmental factors such as wind speed, temperature, and humidity, current and voltage sensors are installed at key points of the transmission lines, and vibration sensors are installed in the substations to monitor the health of the equipment. These sensors can not only provide real-time data streams, but also transmit data to the central processing unit wirelessly or wired for further analysis and processing. In this way, it can be ensured that the acquired data is both comprehensive and timely, laying a solid foundation for the subsequent application of artificial intelligence algorithms.

[0082] S102: By using the pre-trained artificial intelligence model to extract features and recognize patterns on the collected power transmission data, the operating status of the power transmission system is analyzed. At this stage, it is necessary to first select a suitable artificial intelligence model, such as a convolutional neural network CNN, a recurrent neural network RNN ​​or a long short-term memory network LSTM, etc. These models can automatically learn and extract important feature information in the power transmission process after being trained with a large amount of historical data. For example, the LSTM model can capture the changing trend of power load from time series data, while CNN is good at extracting features from image data, such as detecting overheating of power equipment by analyzing infrared thermal images. By analyzing these features, the model can identify the normal operating mode and abnormal mode of the power system, so as to detect potential problems in time. In addition, the model can be fine-tuned in combination with expert knowledge to make it more suitable for the needs of actual application scenarios. Through this series of operations, not only the accuracy of monitoring can be improved, but also the false alarm rate can be reduced to ensure the stable operation of the power system.

[0083] S103: Improve monitoring accuracy by dynamically adjusting model parameters according to the analysis results of the artificial intelligence model to adapt to the complex and changeable power transmission environment. Since the new energy power transmission environment is affected by many factors, such as weather changes, grid load fluctuations, etc., it is necessary to continuously adjust the model parameters to cope with these changes. For example, during high temperatures in summer, electricity demand may surge, and this change can be adapted more quickly by increasing the learning rate of the model; while under low temperature conditions in winter, the learning rate may need to be reduced to avoid overfitting the current low load state. In addition, an online learning mechanism can be introduced so that the model can continuously learn new data samples during operation, so as to better adapt to new situations that may arise in the future. In this way, high monitoring accuracy can be maintained even in complex environments.

[0084] S104: By regularly verifying the prediction accuracy of the artificial intelligence model and continuously optimizing the model through a feedback mechanism, ensure that it accurately monitors and predicts the system status in a complex and changeable renewable energy power transmission environment. In order to ensure the long-term effectiveness of the model, its performance indicators, such as accuracy and recall, need to be regularly evaluated and compared with the actual power transmission situation. For example, a comprehensive performance evaluation can be set up every quarter, and a rapid evaluation can be performed immediately after each major event, such as a large-scale power outage caused by a natural disaster. If the model is found to perform poorly, measures need to be taken to optimize it, which may include retraining the model, adjusting hyperparameters, or introducing new feature variables. In addition, a closed-loop feedback system can be established to incorporate user feedback information into the process of model improvement, which can not only improve the robustness of the model, but also enhance its adaptability in the face of unknown challenges.

[0085] Through the above steps, the problem of "how to ensure that artificial intelligence algorithms can accurately monitor and predict system status in a complex and changeable renewable energy power transmission environment" can be effectively solved. This method can not only improve the safety and reliability of the power system, but also promote the effective use of renewable energy, laying the foundation for building a more intelligent and efficient energy system.

[0086] Please refer to Figure 3 , Figure 3 The flowchart of deploying multiple sensors in a new energy power transmission network to collect power transmission data in real time is provided by an embodiment of the present invention. The specific steps of deploying multiple sensors in a new energy power transmission network to collect power transmission data in real time are as follows:

[0087] S201: Select the appropriate sensor type and determine its deployment location: According to the characteristics of the power transmission network and monitoring requirements, select the sensor type that can accurately measure key parameters such as current, voltage, and temperature. For example, you can choose a Hall effect sensor to measure current and a fiber optic temperature sensor to monitor cable temperature. At the same time, based on the layout of the power line and the importance of key nodes, determine the best deployment location for the sensor to ensure that the key links of power transmission can be fully covered.

[0088] S202: Install sensors and configure data collection frequency: Install sensors at selected locations and reasonably set data collection frequency according to the operating characteristics of the power transmission system and the requirements of monitoring accuracy. For example, for high-voltage transmission lines, a higher collection frequency can be set, such as once per second, so as to capture abnormal situations in a timely manner; while for low-voltage distribution networks, the collection frequency can be appropriately reduced according to actual needs, such as once per minute.

[0089] S203: Start the sensor to collect data and transmit the data to the central processing unit wirelessly or wired: After completing the installation and configuration of the sensor, start the sensor to start data collection. The collected data can be transmitted to the central processing unit through a wireless communication module such as Wi-Fi, 4G / 5G network or a wired connection such as optical fiber or Ethernet cable. For example, low-power Bluetooth technology is used to send sensor data to a nearby gateway device, and then the gateway device uploads the data to the cloud server through the 4G network.

[0090] S204: Preprocessing the collected raw data: In order to improve the accuracy and efficiency of data analysis, the collected raw data needs to be preprocessed. This includes but is not limited to filtering to remove noise interference, data smoothing, and outlier detection. For example, a digital filter such as a Kalman filter can be used to reduce random noise in the signal to ensure the reliability of subsequent analysis results.

[0091] Please refer to Figure 4 , Figure 4 This is a flowchart of feature extraction and pattern recognition using a pre-trained artificial intelligence model provided by an embodiment of the present invention. The specific steps of the new energy power transmission status monitoring method based on artificial intelligence algorithm are as follows:

[0092] S301: By collecting power transmission data and inputting it into a pre-trained artificial intelligence model: First, various data are collected from the power transmission system in real time or periodically, which may include factors such as current, voltage, power, etc. Then, these raw data are input into a pre-trained artificial intelligence model. The artificial intelligence model can be a deep learning network or other machine learning model, which is designed to process specific types of data from the power system.

[0093] S302: Adjust the model input layer parameters to match the statistical characteristics of the power transmission data: Before the artificial intelligence model receives data, it is necessary to adjust the input layer parameters of the artificial intelligence model according to the statistical characteristics of the power transmission data, such as mean value, variance, etc. This step ensures that the artificial intelligence model can understand the input data more accurately and can effectively extract meaningful features. For example, if the voltage fluctuations in the data set are large, the model may need to be adjusted to better capture such changes.

[0094] S303: Extract key features from power transmission data through artificial intelligence models: The adjusted artificial intelligence model begins to process the input data and extract key features from it. These features may include but are not limited to abnormal detection indicators, equipment health indicators, etc. This process depends on the internal structure and algorithm of the model. For example, convolutional neural network CNN can be used to identify patterns in images, while recurrent neural network RNN ​​is suitable for the analysis of time series data.

[0095] S304: Classify and identify the extracted features by applying pattern recognition technology: Finally, the extracted key features are further analyzed and classified using pattern recognition technology. This can be done by using clustering algorithms, support vector machines (SVMs), decision trees and other technologies to identify different states or potential problems in the power transmission system. For example, it can be determined whether there is a fault or abnormality by comparing the features under normal operation with the currently extracted features.

[0096] Please refer to Figure 5 , Figure 5 The flowchart of adjusting the input layer parameters of the model provided by an embodiment of the present invention is as follows:

[0097] S401: Determine whether the weight parameters of the model input layer need to be adjusted by calculating the statistical characteristics of the power transmission data. First, collect the power transmission data within a certain time window and calculate the mean μ and variance σ of these data. 2 These statistical characteristics can reflect the central tendency and fluctuation of power transmission data, and thus help determine the stability and reliability of the data. 2 If it is greater than the preset threshold T, it is considered that the current data has large volatility, which may affect the accuracy of the artificial intelligence model, so the weight parameters of the model input layer need to be adjusted.

[0098] S402: Adjust the weight parameters of the model input layer to adapt to the changes in the power transmission data. When it is detected that the variance of the power transmission data exceeds the preset threshold T, the method adjusts the weight parameters of the model input layer according to a specific rule or algorithm. For example, an adaptive learning rate method can be used to dynamically adjust the weight, or the weight can be adjusted proportionally according to the size of the variance to ensure that the artificial intelligence model can better capture the changing trend in the data. The adjusted weight parameters will be used in subsequent data processing.

[0099] S403: Recalculate the input feature vector of the artificial intelligence model based on the adjusted weight parameters. After adjusting the weight parameters of the model input layer, the input feature vector needs to be recalculated. This step ensures that the artificial intelligence model can accurately reflect the latest power transmission data status. Specifically, the adjusted weight parameters can be used to perform weighted summation with the new power transmission data to obtain an updated feature vector.

[0100] S404: Input the calculated feature vector of the artificial intelligence model into the model for further processing. Finally, the new feature vector obtained through the above steps is used as input to continue the subsequent processing flow of the model, such as feature extraction, classification or prediction. In this way, the performance and accuracy of the model can be guaranteed even when there are large fluctuations in the power transmission data.

[0101] Through the above steps, the robustness and adaptability of the renewable energy power transmission status monitoring system based on artificial intelligence algorithm can be effectively improved.

[0102] Please refer to Figure 6 , Figure 6 The flowchart of recalculating the input feature vector of the model provided by one embodiment of the present invention. In the new energy power transmission state monitoring method based on artificial intelligence algorithm, the specific steps of recalculating the input feature vector of the artificial intelligence model according to the adjusted weight parameters are as follows:

[0103] S501: First, the adjusted weight parameters are normalized. This process ensures that all weight parameters are on the same scale, thereby avoiding that certain features are given too much importance due to differences in numerical values. Normalization can be achieved in many ways, such as min-max normalization, which maps each weight parameter to a value between 0 and 1, with the formula: w'_i = frac{w_i-minw}{maxw-minw}, where w_i is the original weight parameter, w'_i is the normalized weight parameter, maxw and minw are the maximum and minimum values ​​of all weight parameters, respectively.

[0104] S502: Next, based on the normalized weight parameter, calculate the importance coefficient of each feature. This step is completed by multiplying the normalized weight parameter with the corresponding feature value, and the result obtained reflects the degree of influence of each feature on the model prediction result. The calculation of the importance coefficient can be expressed as: c_i = w'_i cdot f_i, where c_i represents the importance coefficient of the i-th feature, w'_i is the normalized weight parameter, f_i is the original value of the i-th feature, and cdot is the dot product symbol.

[0105] S503: Then, when the importance coefficient is greater than a preset coefficient threshold η, the feature is considered a key feature. The selection of the preset coefficient threshold η depends on the specific application scenario and requirements, and usually a suitable value needs to be determined through experiments. For example, in power transmission status monitoring, if the preset coefficient threshold η is set to 0.8, only those features with an importance coefficient greater than 0.8 will be considered key features.

[0106] S504: Finally, a new feature vector containing key features is constructed and input into the model. This step involves filtering out those marked as key features from the original feature vector and forming a new feature vector. The new feature vector not only contains the most valuable information for model prediction, but also reduces unnecessary computational burden and improves the efficiency and accuracy of the artificial intelligence model. For example, assuming that the original feature vector contains 10 features, after the above steps, only 5 features may be retained as key features, which will be used in subsequent model training or prediction processes.

[0107] Please refer to Figure 7 , Figure 7 The flowchart of determining key features provided by an embodiment of the present invention is as follows:

[0108] S601: Screening key features: First, calculate the importance coefficients of all features extracted from the new energy power transmission system. The importance coefficient can be a weight value or other evaluation index obtained through the machine learning model training process. If the importance coefficient of a feature is greater than a preset threshold η, it is considered a key feature. This process ensures that only those features that have a significant impact on the power transmission state are retained.

[0109] S602: Sorting key features: Once all key features with importance coefficients greater than η are identified, these features need to be sorted. The basis for sorting can be the size of the importance coefficient, that is, the features with higher importance coefficients are ranked first. This step helps to determine which features are more important in subsequent analysis and can optimize the structure of the new feature vector.

[0110] S603: Construct a new feature vector (i.e., an input feature vector containing the sorted key features): Based on the sorting results, a new feature vector is constructed, which contains the key features arranged in order. This new feature vector not only reduces the dimension of the original data set, but also ensures that the model can focus on the most relevant signals, thereby improving prediction accuracy and efficiency.

[0111] S604: Input the new feature vector to the artificial intelligence model: Finally, the constructed new feature vector is input into the artificial intelligence model for monitoring the state of renewable energy power transmission. The artificial intelligence model will use these key features to perform further data analysis, pattern recognition or prediction tasks to achieve effective monitoring of the power transmission system.

[0112] For example, in practical applications, assume that a random forest model has been trained to evaluate the importance coefficient of each feature. Assuming that the threshold η is set to 0.5, the importance coefficients of all features can be calculated, and the features above 0.5 can be selected as key features. Then, these key features are sorted from high to low according to the importance coefficient, and a new feature vector is constructed. Finally, this new feature vector is input into another prediction model such as a support vector machine to achieve effective monitoring of the transmission status of renewable energy power.

[0113] Please refer to Figure 8 , Figure 8 This is a flowchart of an embodiment of the present invention that uses a pre-trained artificial intelligence model to perform feature extraction and pattern recognition to analyze the operating status of a power transmission system. The specific steps of the new energy power transmission status monitoring method based on artificial intelligence algorithm are as follows:

[0114] S701: By collecting real-time data during power transmission, including but not limited to key parameters such as voltage and current, the method first pre-processes these raw data, such as filtering and normalization, to ensure the quality and consistency of the data. Subsequently, a specific data mining technique or machine learning algorithm is used to extract feature vectors closely related to voltage and current from these pre-processed data. This process aims to convert complex power transmission data into a form that is easy to analyze, so that it can be processed by subsequent artificial intelligence models.

[0115] S702: The extracted feature vector is used as input and sent to a pre-trained artificial intelligence model for preliminary analysis. The artificial intelligence model here can be a deep neural network such as a convolutional neural network CNN or a recurrent neural network RNN, a support vector machine SVM or other machine learning models suitable for processing time series data. The artificial intelligence model has learned a large number of data samples under normal and abnormal power transmission states during the training phase, so it can quickly determine whether the operating status of the current power transmission system is normal based on the input feature vector.

[0116] S703: Based on the preliminary analysis results of the artificial intelligence model, automatically determine whether there is an abnormal pattern. If the model detects an abnormal pattern, that is, the output result shows that the current power transmission state deviates from the normal range, then proceed to the next step; if no abnormality is detected, continue to monitor new data and repeat the above process.

[0117] S704: Once the abnormal pattern is confirmed, the specific abnormal type will be further identified. This step may involve more detailed feature analysis or use of models optimized for anomaly detection to determine the specific cause of the anomaly, such as overload, short circuit, equipment failure, etc. In this way, not only can problems in the power transmission system be discovered in a timely manner, but targeted solutions can also be provided, thereby effectively improving the stability and safety of the power transmission system.

[0118] Please refer to Fig. 9 , Fig. 9 The flowchart of determining whether there is an abnormal mode provided by an embodiment of the present invention. The specific steps of determining whether there is an abnormal mode in the new energy power transmission status monitoring method based on artificial intelligence algorithm are as follows:

[0119] S801: Calculate the probability P of abnormal mode occurrence by statistically processing the preliminary analysis results. This process usually involves analyzing the data output by the artificial intelligence model, identifying data points that deviate from the normal operating state, and estimating the probability P of abnormal mode occurrence based on the number and distribution of these data points.

[0120] S802: Compare the calculated probability P with a preset threshold value T1 (i.e., preset probability threshold value T1). This step is to quantify the judgment criteria, that is, to compare the probability of the occurrence of the abnormal mode with a pre-defined threshold value (i.e., preset probability threshold value T1) to determine whether further action is needed. If the probability P is greater than the threshold value T1, it is considered that there is an abnormal mode in the current power transmission state; conversely, if the probability P is less than or equal to the threshold value T1, it is considered that there is no abnormal mode in the current state.

[0121] S803: Make a determination based on the result of the above comparison. If P is greater than T1, it is determined that an abnormal mode exists, and it may be necessary to trigger an alarm mechanism or take other measures to further diagnose the problem and prevent the occurrence of potential faults; if P is less than or equal to T1, it is determined that there is no abnormal mode, and the power transmission state can be regarded as normal, and no special measures need to be taken immediately.

[0122] In this way, the method can effectively use artificial intelligence algorithms to monitor the status of renewable energy power transmission in real time and detect potential problems in a timely manner, thereby improving the stability and security of the power system.

[0123] Please refer to Fig.10 , Fig.10 This is a flowchart based on the comparison between probability P and preset probability threshold T1 provided by an embodiment of the present invention. In the new energy power transmission status monitoring method based on artificial intelligence algorithm, the specific steps of comparing probability P with preset threshold T1 are as follows:

[0124] S901: Evaluate the abnormality of the current power transmission state by calculating the difference ΔP between the probability P and the preset threshold T1. This calculation can be completed by a simple subtraction operation, that is, ΔP = P-T1. The purpose here is to quantify the gap between the probability P and the threshold T1 to determine whether there is an abnormal situation beyond the normal range.

[0125] S902: Determine whether there is an abnormal mode by comparing the relationship between ΔP and zero. If the calculated ΔP is greater than zero, this indicates that the actual detected probability P is higher than the preset threshold T1, which means that the current power transmission state may deviate from the normal operating range and there is a high possibility of an abnormal mode. At this time, the system will trigger the corresponding alarm mechanism or take further diagnostic measures.

[0126] S903: If the calculated ΔP is less than or equal to zero, the current power transmission state is considered to be within the normal range and there is no abnormal mode. This means that the actual detected probability P does not exceed the preset threshold T1, and the system can continue to monitor without taking immediate action. In this case, the system may continue to monitor the power transmission state and re-evaluate regularly to ensure the stability and safety of the system.

[0127] Through the above steps, artificial intelligence algorithms can be effectively used to monitor the new energy power transmission status in real time and detect anomalies, thereby improving the reliability and efficiency of the power system.

[0128] Please refer to Fig.11 , Fig.11This is a flowchart for judging whether the difference ΔP is greater than zero provided by an embodiment of the present invention. The specific steps of judging whether ΔP is greater than zero and executing the abnormal pattern recognition process based on the artificial intelligence algorithm in the new energy power transmission status monitoring method are as follows:

[0129] S1001: Determine the working status of the system by monitoring and calculating the difference ΔP between the actual power and the expected power of the new energy power transmission system within a specific time interval. If the monitored ΔP is greater than zero, it means that the actual power exceeds the expected power, which may indicate an abnormality in the system, such as overload or equipment failure. At this time, the system needs to further analyze to determine the specific type of abnormality.

[0130] S1002: If ΔP is indeed greater than zero, the abnormal pattern recognition process is started. This process can use a pre-trained machine learning model, such as a support vector machine (SVM), a neural network, or other classification algorithms, to analyze the current operating data to identify the specific cause of the abnormal increase in ΔP. For example, the correlation between historical data and current data can be analyzed to identify whether the abnormality is caused by changes in external environmental factors or internal equipment failures.

[0131] S1003: If ΔP is less than or equal to zero, the system is considered to be in normal working condition and no abnormal pattern recognition process needs to be performed. This means that the actual power is consistent with the expected power or lower than expected, and the system does not need to take additional measures to deal with potential abnormal situations.

[0132] S1004: Regardless of the value of ΔP, the system automatically updates the model parameters used for prediction and monitoring based on the results of the abnormal pattern recognition process. This update mechanism helps improve the model's ability to identify similar abnormal situations in the future, thereby enhancing the accuracy and reliability of the entire monitoring system.

[0133] Through the above steps, the present invention can effectively monitor the operating status of the new energy power transmission system, and promptly discover and handle abnormal situations to ensure the safety and stability of power transmission.

[0134] Please refer to Fig.12 , Fig.12 This is a flowchart of updating model parameters based on the results of the abnormal pattern recognition process provided by an embodiment of the present invention. The specific steps of updating model parameters in the new energy power transmission status monitoring method based on artificial intelligence algorithm are as follows:

[0135] S1101: Analyze the results of the abnormal pattern recognition process - In this step, the system first conducts an in-depth analysis of the results of the abnormal pattern recognition process. This step aims to understand the performance of the current model when processing a specific type of data and identify the cases where the model fails to accurately identify abnormal patterns. By analyzing these results, the direction of model parameter adjustment can be determined, that is, which parameters need to be modified and how to modify them to improve the accuracy of the model.

[0136] S1102: Update model parameters according to adjustment direction - Once the adjustment direction of the model parameters is determined, the model parameters need to be updated according to these guidelines. This usually involves adjusting the weights, bias terms or other hyperparameters in the neural network. For example, if the model is found to be too sensitive to certain types of anomalies, the weight value of the relevant layer may need to be reduced; conversely, if the model is not sensitive enough to certain anomalies, the weight value may need to be increased. In this way, the model can be gradually optimized to better adapt to the actual application scenario.

[0137] S1103: Re-perform feature extraction and pattern recognition based on updated model parameters - After updating the model parameters, the feature extraction and pattern recognition process needs to be re-performed using the new model parameters. This means that the data from the power transmission system will be processed again to verify whether the model can more accurately identify abnormal patterns after being adjusted. This process may involve using the same training and test set data, or introducing new data sets to further evaluate the generalization ability of the model.

[0138] S1104: Verify whether the performance of the updated model has improved - The last step is to evaluate the performance of the updated model. This is usually done by comparing the performance of the new and old models on the same test set. If the updated model shows higher accuracy, recall or other performance indicators in identifying abnormal patterns, the model is considered to have been effectively improved. If the performance has not improved significantly or even decreased, it is necessary to return to S1101, re-analyze the results of the abnormal pattern recognition process, and adjust the model parameters based on the new findings.

[0139] In actual operation, when this device is used, multiple sensors are first deployed at key nodes of the new energy power transmission network. These sensors can collect various data in the power transmission process in real time, such as current, voltage, temperature and other key indicators. These data are then transmitted to the central processing unit, where the pre-trained artificial intelligence model comes into play. The model uses deep learning technology to extract features and recognize patterns on the collected data, so that it can analyze the current operating status of the power transmission system and identify potential problems or abnormal situations. In order to ensure that the model can adapt to the complex and changing power transmission environment and maintain high monitoring accuracy, the system will dynamically adjust the model parameters according to the analysis results of the model. This means that as time and environment change, the model can optimize itself to better reflect the actual situation. In addition, in order to further improve the accuracy and reliability of the model, the system will regularly verify the prediction accuracy of the model and continuously optimize the model through a feedback mechanism. For example, if the model predicts that there may be a risk of overload in a certain area, but the actual overload does not occur, the system will feed this information back to the model for subsequent training and adjustment to reduce errors in future predictions. The whole process is a closed-loop control system, in which sensors, artificial intelligence models and feedback mechanisms work closely together to ensure effective monitoring of the transmission status of renewable energy power. This method based on artificial intelligence algorithms not only improves monitoring efficiency, but also enhances the system's adaptive and predictive capabilities, which is of great significance for ensuring the stable operation of renewable energy power systems.

[0140] Fig.13 FIG. 1 is a block diagram of a new energy power transmission status monitoring system based on an artificial intelligence algorithm provided by an embodiment of the present invention. Fig.13 As shown, the embodiment of the present invention provides a new energy power transmission status monitoring system based on artificial intelligence algorithm, including:

[0141] The power transmission data acquisition module is used to collect power transmission data in real time through multiple sensors pre-deployed in the new energy power transmission network;

[0142] The operation status analysis module is used to input the power transmission data collected by each sensor into the pre-trained artificial intelligence model to perform feature extraction and pattern recognition in sequence to analyze the operation status of the new energy power transmission network and obtain analysis results;

[0143] A dynamic adjustment module is used to dynamically adjust the model parameters of the pre-trained artificial intelligence model according to the analysis results;

[0144] The prediction accuracy verification module is used to perform multiple rounds of optimization on the dynamically adjusted artificial intelligence model until the verification result of the prediction accuracy of the latest artificial intelligence model reaches the optimal value, and use the corresponding latest artificial intelligence model to analyze the operating status of the new energy power transmission network.

[0145] Specifically, the system deploys multiple sensors in the new energy power transmission network to collect power transmission data in real time. Based on the power transmission data, the system uses a pre-trained artificial intelligence model to extract features and recognize patterns to analyze the operating status of the power transmission system (i.e., the new energy power transmission network). According to the analysis results of the artificial intelligence model, the model parameters are dynamically adjusted to adapt to the complex and changeable power transmission environment and improve the monitoring accuracy. The prediction accuracy of the artificial intelligence model is verified regularly. The artificial intelligence model is continuously optimized through the feedback mechanism to ensure that the artificial intelligence model accurately monitors and predicts the operating status of the new energy power transmission network in the complex and changeable new energy power transmission environment. This ensures that the artificial intelligence algorithm can achieve the purpose of accurately monitoring and predicting the status of the power transmission system in the complex and changeable new energy power transmission environment.

[0146] The optional implementation modes of the embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above implementation modes. Within the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical scheme of the embodiments of the present invention, and these simple modifications all belong to the protection scope of the embodiments of the present invention.

[0147] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0148] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including a number of instructions to enable a single-chip microcomputer, a chip or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0149] In addition, various implementation modes of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed by the embodiments of the present invention.

Claims

1. A new energy power transmission status monitoring method based on artificial intelligence algorithm, characterized in that: include: Collect power transmission data in real time through multiple sensors pre-deployed in the new energy power transmission network; The power transmission data collected by each sensor is input into the pre-trained artificial intelligence model to perform feature extraction and pattern recognition in turn to analyze the operating status of the new energy power transmission network and obtain analysis results; According to the analysis results, dynamically adjust the model parameters of the pre-trained artificial intelligence model; The dynamically adjusted artificial intelligence model is optimized in multiple rounds until the verification result of the prediction accuracy of the latest artificial intelligence model reaches the optimal value, and the corresponding latest artificial intelligence model is used to analyze the operating status of the new energy power transmission network.

2. The method for monitoring the transmission status of renewable energy power based on artificial intelligence algorithm according to claim 1 is characterized in that: The deployment rules of the sensor include: Determine a sensor deployment plan based on historical operation data of the new energy power transmission network; wherein the sensor deployment plan includes sensor type, sensor deployment location and data collection frequency of each deployed sensor; The collection rules of the power transmission data include: Based on the data collection frequency of each sensor, a data collection instruction is sent to each sensor, so that each sensor collects power transmission data according to the corresponding data collection frequency; The collected power transmission data is preprocessed; wherein the preprocessing includes at least filtering and denoising.

3. The method for monitoring the transmission status of renewable energy power based on artificial intelligence algorithm according to claim 1 is characterized in that: The power transmission data collected by each sensor is input into the pre-trained artificial intelligence model for feature extraction and pattern recognition, including: Adjust the input layer parameters of the pre-trained artificial intelligence model based on the statistical characteristics of the power transmission data; Extract key features from power transmission data using an AI model with adjusted input layer parameters; Classify and identify key features in the extracted power transmission data.

4. The method for monitoring the transmission status of new energy power based on artificial intelligence algorithm according to claim 3 is characterized in that: The statistical characteristic information of the power transmission data includes the average value μ and the variance σ of the power transmission data. 2 ; The step of adjusting the input layer parameters of the pre-trained artificial intelligence model based on the statistical characteristic information of the power transmission data includes: Calculate the mean μ and variance σ of power transmission data 2 ; When the variance of power transmission data σ 2 When it is greater than the preset variance threshold T, the weight parameters of each input layer of the artificial intelligence model are adjusted; Recalculate the input feature vector of the artificial intelligence model based on the adjusted weight parameters of each input layer of the artificial intelligence model; The recalculated input feature vector of the artificial intelligence model is input into the artificial intelligence model to determine the input layer parameters of the adjusted artificial intelligence model.

5. The method for monitoring the transmission status of new energy power based on artificial intelligence algorithm according to claim 4 is characterized in that: The step of recalculating the input feature vector of the artificial intelligence model based on the adjusted weight parameters of each input layer of the artificial intelligence model includes: Normalize the weight parameters of each input layer of the adjusted artificial intelligence model; Based on the normalized weight parameters, calculate the importance coefficient of each feature of the artificial intelligence model; The features of the artificial intelligence model whose importance coefficients are greater than a preset coefficient threshold η are taken as key features, an input feature vector containing the key features is constructed, and the input feature vector is input into the artificial intelligence model.

6. The method for monitoring the transmission status of renewable energy power based on artificial intelligence algorithm according to claim 5 is characterized in that: The feature of the artificial intelligence model whose importance coefficient is greater than the preset coefficient threshold η is taken as the key feature, and an input feature vector containing the key feature is constructed, including: Screen out all key features whose importance coefficient is greater than the preset coefficient threshold η; The key features are sorted from high to low according to their importance coefficients, and an input feature vector containing the sorted key features is constructed.

7. The method for monitoring the transmission status of renewable energy power based on artificial intelligence algorithm according to claim 1 is characterized in that: The pattern recognition process includes an abnormal pattern recognition process, the analysis result includes a result of the abnormal pattern recognition process, and the result of the abnormal pattern recognition process includes a result of determining that an abnormal pattern exists and a result of determining that an abnormal pattern does not exist; According to the analysis results, the model parameters of the pre-trained artificial intelligence model are dynamically adjusted, including: Determine the adjustment direction of model parameters based on the results of the abnormal pattern recognition process; The model parameters are updated according to the adjustment direction, and a dynamically adjusted artificial intelligence model is obtained based on the updated model parameters.

8. The method for monitoring the transmission status of renewable energy power based on artificial intelligence algorithm according to claim 1 is characterized in that: During multiple rounds of optimization of the dynamically adjusted artificial intelligence model, each time the dynamic adjustment of the artificial intelligence model is completed, it is necessary to perform a prediction accuracy verification of the corresponding artificial intelligence model; The rules for validating the predictive accuracy of the AI ​​model include: The power transmission data collected by each sensor is input into the dynamically adjusted artificial intelligence model to re-perform feature extraction and pattern recognition; Based on the results of re-feature extraction and pattern recognition, verify whether the prediction accuracy of the dynamically adjusted artificial intelligence model is higher than the prediction accuracy of the pre-trained artificial intelligence model that has not been dynamically adjusted.

9. The method for monitoring the transmission status of renewable energy power based on artificial intelligence algorithm according to claim 1 is characterized in that: The power transmission data collected by each sensor is input into the pre-trained artificial intelligence model to perform feature extraction and pattern recognition in sequence to analyze the operating status of the new energy power transmission network, including: Extracting feature vectors associated with voltage and / or current from the power transmission data, and inputting the feature vectors into a pre-trained artificial intelligence model for preliminary analysis; Based on the preliminary analysis results, determine whether there are any unusual patterns; When it is determined that an abnormal pattern exists, the abnormal type is identified.

10. The method for monitoring the transmission status of new energy power based on artificial intelligence algorithm according to claim 9 is characterized in that: Determining whether there is an abnormal pattern based on the preliminary analysis results includes: Perform statistics on abnormal patterns in the preliminary analysis results, and calculate the probability P of the abnormal pattern appearing based on the statistical results; The probability P of the abnormal pattern occurring is compared with the preset probability threshold T1. If the probability P of the abnormal pattern occurring is greater than the preset probability threshold T1, it is determined that the abnormal pattern exists. Otherwise, it is determined that the abnormal pattern does not exist.

11. The method for monitoring the transmission status of renewable energy power based on artificial intelligence algorithm according to claim 10, characterized in that: The comparing the probability P of the abnormal pattern to be present with the preset probability threshold T1, if the probability P of the abnormal pattern to be present is greater than the preset probability threshold T1, it is determined that the abnormal pattern exists, otherwise, it is determined that the abnormal pattern does not exist, including: Calculate the difference ΔP between the probability P of the abnormal mode occurring and the preset probability threshold T1; It is determined whether the difference ΔP is greater than zero. If the difference ΔP is greater than zero, it is determined that an abnormal mode exists. Otherwise, it is determined that no abnormal mode exists.

12. A new energy power transmission status monitoring system based on artificial intelligence algorithm, characterized in that: include: The power transmission data acquisition module is used to collect power transmission data in real time through multiple sensors pre-deployed in the new energy power transmission network; The operation status analysis module is used to input the power transmission data collected by each sensor into the pre-trained artificial intelligence model to perform feature extraction and pattern recognition in sequence to analyze the operation status of the new energy power transmission network and obtain analysis results; A dynamic adjustment module, used to dynamically adjust the model parameters of the pre-trained artificial intelligence model according to the analysis results; The prediction accuracy verification module is used to perform multiple rounds of optimization on the dynamically adjusted artificial intelligence model until the verification result of the prediction accuracy of the latest artificial intelligence model reaches the optimal value, and use the corresponding latest artificial intelligence model to analyze the operating status of the new energy power transmission network.

13. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the new energy power transmission status monitoring method based on artificial intelligence algorithm as described in any one of claims 1 to 11.

14. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for monitoring the transmission status of new energy power based on artificial intelligence algorithm as described in any one of claims 1 to 11 is implemented.

Images