Distributed new energy security management method, device, equipment and medium integrated with VPDN wireless channel

Abstract

The present invention discloses a distributed new energy safety management and control method, device, equipment and medium for an integrated VPDN wireless channel, and relates to the technical field of distributed new energy safety management and control, including setting a plurality of groups of different threshold values ​​of wireless channel signal strength; analyzing the security event prediction abnormal data and security management stable data of the distributed new energy safety management of the wireless channel under different threshold values; and constructing a distributed new energy safety management and control effect evaluation model based on a convolutional neural network; and constructing a security management and control effect-threshold value change curve; performing data analysis on the security management and control effect-threshold value change curve to obtain an optimized threshold value, and applying it to the distributed new energy safety management and control of the wireless channel; the present application solves the problem that the threshold value of the wireless channel signal strength is not effectively evaluated, thereby resulting in an unstable effect of the distributed new energy safety management and control method of the wireless channel.

Description

Technical Field

[0001] The present invention relates to the field of distributed new energy security management and control technology, and more specifically, to a distributed new energy security management and control method, device, equipment and medium integrating a VPDN wireless channel. Background Art

[0002] "Distributed renewable energy" refers to distributed energy systems including wind energy, solar energy, etc. These systems are widely distributed and usually rely on the Internet and wireless communications to achieve interconnection and coordination. It is suitable for distributed renewable energy networks rather than centralized traditional energy systems. This system has decentralized power generation points and management centers, which is suitable for regional renewable energy management needs.

[0003] For example, the invention patent announcement with announcement number: CN110969367B announces a method for analyzing the distribution of distributed renewable energy power, including collecting data on output power, power consumption, power transmission, input power, and power generated by light and / or wind power sources related to each node in the regional distribution network in real time according to the step length, and calculating the residual power capacity of each node in real time according to the data; determining the power flow direction of the lines connecting each node; calculating the input or output power of the lines connecting each node; and determining the power distribution of the entire regional distribution network according to the residual power capacity of each node, the input power of the input line, and the output power of the output line. The application of the present invention can analyze the distribution of distributed renewable energy power in the regional distribution network in real time, and provide technical support for the optimal configuration of the distributed renewable energy distribution network.

[0004] For example, the invention patent with announcement number CN118313495A announces an Al data modeling method based on distributed new energy power prediction, including obtaining distributed new energy structure data in an interactive manner; obtaining environmental information based on the data; and performing preprocessing to obtain a power response feature set through correlation analysis; extracting sample power characteristic records; constructing a distributed energy power prediction network, using sample records for training and evaluation, and obtaining network performance parameters; if it meets the preset performance parameter constraints, it is stored as a distributed energy power prediction model for power prediction. This application solves the technical problem of poor performance of distributed energy power prediction models due to data sparsity, nonlinearity and uncertainty by extracting distributed environmental information and performing correlation analysis, thereby ensuring the accuracy and reliability of the prediction results.

[0005] The above disclosed technical solutions have at least the following technical problems: in long-distance wireless data transmission, signal strength is an important indicator for measuring signal quality; the threshold value sets the minimum signal strength for whether the wireless channel can maintain stable transmission;

[0006] If the threshold value is set too high, the system will often experience signal interruptions in areas with weak signals, affecting the continuity and reliability of remote data. If the threshold value is set too low, the system may still attempt to transmit when the signal is extremely weak, resulting in data transmission loss or increased error rate, thus affecting data reliability.

[0007] However, the existing distributed new energy safety management method for wireless channels does not effectively evaluate the threshold value of the wireless channel signal strength, which leads to unstable effect of the distributed new energy safety management method for wireless channels. In view of the above problems, the present invention proposes a solution. Summary of the invention

[0008] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a distributed new energy safety management and control method, device, equipment and medium for an integrated VPDN wireless channel, which analyzes and evaluates the threshold value to solve the problem that the existing distributed new energy safety management and control method for wireless channels does not effectively evaluate the threshold value of the wireless channel signal strength, thereby causing the distributed new energy safety management and control method for wireless channels to be unstable.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] The invention discloses a distributed new energy safety control method integrating VPDN wireless channels, comprising the following steps: setting several groups of different threshold values ​​of wireless channel signal strength based on a random perturbation method according to a preset basic threshold value of wireless channel signal strength; analyzing the security event prediction abnormal data and security control stable data of the distributed new energy safety control of the wireless channels under different threshold values; constructing a distributed new energy safety control effect evaluation model based on a convolutional neural network according to the security event prediction abnormal data and security control stable data; constructing a security control effect-threshold value change curve according to the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values; performing data analysis on the security control effect-threshold value change curve to obtain an optimized threshold value, and applying it to the distributed new energy safety control of the wireless channel.

[0011] In a preferred embodiment, the basic threshold value sets several groups of different threshold values ​​of wireless channel signal strength based on the random perturbation method, specifically: determining the basic threshold value range, setting the normal distribution parameters for the specific dBm value of the signal strength as the mean of the random perturbation; setting the random perturbation parameters, the random perturbation parameters include the perturbation intensity and the number of perturbations, and generating several different signal strength values ​​by introducing the standard deviation and performing several perturbations; applying the random perturbation function, applying a preset distributed perturbation deviation to the basic threshold value, and obtaining the threshold values ​​of different wireless channel signal strengths under several different signal strengths.

[0012] In a preferred embodiment, the security incident prediction anomaly data includes a security incident prediction anomaly coefficient; the specific method for obtaining the security incident prediction anomaly coefficient is as follows: obtain the data of security incident warning when the security control value is performed under different threshold values, and perform feature clustering to obtain a cluster set; obtain the respective proportions of cluster types; calculate and evaluate the weights of each security warning cluster based on a support vector machine combined with the respective proportions of cluster types; obtain the average value between each security warning cluster; calculate the square of the deviation of each security warning cluster based on the weight of each security warning cluster and the average value between each security warning cluster, and add the squares of the deviations of each security warning cluster to obtain the security incident prediction anomaly coefficient.

[0013] In a preferred embodiment, the safety management and control stability data includes a system maintenance stability coefficient and a real-time monitoring accuracy fluctuation coefficient; the specific method for obtaining the system maintenance stability coefficient is as follows: obtaining the voltage fluctuation and current fluctuation during the safety management of distributed new energy under different threshold values; preprocessing the obtained voltage and current fluctuations, and establishing a fluctuation assessment model based on the voltage fluctuation and current fluctuation; and establishing a fluctuation vector group based on the processed voltage fluctuation and current fluctuation labels, performing observation updates on the fluctuation assessment model based on the stable observation model, and calculating the system maintenance stability coefficient according to the updated fluctuation vector.

[0014] In a preferred embodiment, the specific method for obtaining the real-time monitoring accuracy fluctuation coefficient is as follows: obtain in real time the monitoring response rate and the monitoring disconnection duration corresponding to the distributed new energy safety management and control under each different threshold value, and number the monitoring response rate and the monitoring disconnection duration corresponding to the distributed new energy safety management and control under each different threshold value; calculate the monitoring accuracy standard deviation and the monitoring accuracy average value through the monitoring response rate and the monitoring disconnection duration corresponding to the distributed new energy safety management and control under each different threshold value; calculate the monitoring accuracy variation coefficient based on the monitoring accuracy standard deviation and the monitoring accuracy average value; calculate the real-time monitoring accuracy fluctuation coefficient based on the monitoring accuracy variation coefficient.

[0015] In a preferred embodiment, the safety control effect-threshold value change curve is constructed according to the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values, specifically: obtaining the output safety control effect evaluation coefficient under different threshold values ​​from the distributed new energy safety control effect evaluation model; establishing a rectangular coordinate system, setting the horizontal axis to the line threshold value, and the vertical axis to the safety control effect evaluation coefficient; marking the safety control effect evaluation coefficient corresponding to each threshold value on the rectangular coordinate system to form data points; connecting the data points to form a safety control effect-threshold value change curve graph.

[0016] In a preferred embodiment, the safety control effect-threshold value change curve is subjected to data analysis to obtain an optimized threshold value, and the threshold value is applied to the distributed new energy safety control of the wireless channel. Specifically, the peak values ​​of several safety control effect-threshold value change curves are obtained, and the corresponding data points are quadratically differentiated for each highest safety control effect evaluation coefficient, and the threshold value corresponding to the data point whose quadratic derivative is close to 0 is taken as the optimal threshold value, and it is applied to the distributed new energy safety control of the wireless channel.

[0017] A device for a distributed new energy safety management method integrating a VPDN wireless channel, characterized in that it includes a threshold value setting module, a data analysis module, a model construction module, a curve construction module and a threshold value selection module, and there is a connection between the modules; the threshold value setting module is used to set a plurality of groups of different threshold values ​​of wireless channel signal strength based on a random perturbation method according to a preset basic threshold value of the wireless channel signal strength; the data analysis module is used to analyze the security event prediction abnormal data and the security control stable data of the distributed new energy safety management of the wireless channel under each different threshold value; the model construction module is used to construct a distributed new energy safety management effect evaluation model based on a convolutional neural network according to the security event prediction abnormal data and the security control stable data; the curve construction module is used to construct a security control effect-threshold value change curve according to the output of a plurality of distributed new energy safety management effect evaluation models and the corresponding threshold value; the threshold value selection module is used to perform data analysis on the security control effect-threshold value change curve to obtain an optimized threshold value, and apply it to the distributed new energy safety management of the wireless channel.

[0018] An electronic device, characterized in that the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a distributed new energy security management and control method for an integrated VPDN wireless channel.

[0019] A computer-readable storage medium stores a computer program, wherein the computer program is executed by a processor to implement a distributed new energy security management and control method for an integrated VPDN wireless channel.

[0020] The technical effects and advantages of the distributed new energy security management method, device, equipment and medium integrated with VPDN wireless channel of the present invention are as follows:

[0021] 1. The present invention sets the threshold value of wireless signal strength through the random perturbation method by integrating the distributed new energy safety management method of VPDN wireless channel, which significantly improves the safety and stability of the system under different signal conditions. Its technical effects are mainly reflected in the following aspects: First, by quantitatively evaluating the abnormal coefficient of security event prediction and the system maintenance stability coefficient, the signal strength threshold can be scientifically and rationally optimized to ensure the accuracy of early warning and the effectiveness of equipment maintenance; secondly, the method flexibly adjusts the threshold value, provides rich experimental data support, facilitates the subsequent construction of neural network models, and improves the response speed and protection level of the system; finally, the analysis of the system maintenance stability coefficient helps to reduce maintenance costs, optimize the workload of operation and maintenance personnel, and enhance the reliability of the overall system, thereby promoting the safe and efficient operation of distributed new energy systems.

[0022] 2. The present invention can effectively integrate the safety event prediction anomaly coefficient, system maintenance stability coefficient and real-time monitoring accuracy fluctuation coefficient through the distributed new energy safety management and control effect evaluation model constructed based on convolutional neural network to generate a comprehensive safety management and control effect evaluation coefficient. This model improves the real-time monitoring and prediction capabilities of safety management, optimizes the threshold setting by constructing a safety management and control effect-threshold value change curve, and realizes accurate safety management. At the same time, this method reduces the need for human intervention, improves the degree of automation, and significantly enhances the safety and reliability of the new energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a structural schematic diagram of the distributed new energy safety management and control method integrating VPDN wireless channels of the present invention.

[0024] Figure 2 It is a structural schematic diagram of a distributed new energy safety management and control device integrating a VPDN wireless channel of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] Embodiment 1, Figure 1 The invention provides a distributed new energy security management and control method integrating a VPDN wireless channel, comprising the following steps:

[0027] S1, setting a plurality of different groups of threshold values ​​of wireless channel signal strengths based on a random perturbation method according to a preset basic threshold value of wireless channel signal strengths.

[0028] In this embodiment, the basic threshold value sets several groups of different wireless channel signal strength threshold values ​​based on the random perturbation method, specifically:

[0029] Determine the basic threshold value range, set the normal distribution parameters for the specific dBm value of the signal strength as the mean of the random disturbance;

[0030] Set random perturbation parameters, which include perturbation intensity and perturbation times. By introducing standard deviation and performing perturbations several times, several different signal strength values ​​are generated.

[0031] A random perturbation function is applied to apply a preset distributed perturbation deviation to the basic threshold value, and threshold values ​​of different wireless channel signal strengths under a plurality of different signal strengths are obtained.

[0032] It should be noted that an initial and relatively reasonable basic threshold value of wireless signal strength is determined based on system requirements and environmental characteristics. This basic threshold value is usually set based on the basic characteristics of the wireless channel and the location, distance, interference conditions and other factors of the distributed new energy equipment, and may be derived from previous experience data or experimental data.

[0033] The random perturbation method is used to adjust the basic threshold value in order to generate a series of different threshold value combinations. The core of the random perturbation method is to generate several groups of slightly different threshold values ​​by adding random variables to the basic threshold value. For example, assuming that the basic threshold value is a specific RSSI value (such as -70 dBm), a random perturbation within the range of ±X dBm can be performed based on this value to generate multiple different threshold value combinations. The selection of these perturbation values ​​can be appropriately adjusted according to the actual situation of the system, such as taking a certain normal distribution random number to ensure that the generated threshold value covers a wide range of strengths.

[0034] After setting several groups of different threshold values, the impact of different threshold value combinations on the signal can better understand the operating performance of the distributed new energy system under different signal conditions. For example, a lower signal strength threshold may lead to more transmission signal loss or false alarms, while a higher signal strength threshold may cause some nodes to lose connection. This method ensures that the optimal configuration of the signal strength threshold value can be found by adjusting the threshold value during the experiment or simulation stage to optimize the effectiveness of security management and control.

[0035] This method of gradually changing the threshold value can not only more flexibly analyze the impact of signal strength on system security and stability, but also provide important experimental data support for the subsequent construction of neural network models and optimization of threshold values.

[0036] S2, analyzes the security event prediction abnormal data and security control stable data of distributed new energy security management of wireless channels under different threshold values.

[0037] The security event prediction abnormal data includes a security event prediction abnormal coefficient;

[0038] The security control stability data includes the system maintenance stability coefficient and the real-time monitoring accuracy fluctuation coefficient;

[0039] The safety event prediction anomaly coefficient is used to measure the early warning capability and accident prevention effect of the distributed new energy safety management and control system under different RSSI threshold conditions. Its role is to evaluate the system's safety warning responsiveness under a specific signal strength threshold and the accuracy of preventing potential accidents. When the RSSI threshold is too high, the system may cause the device to be disconnected from the main control center due to insufficient signal, and thus fail to transmit key safety data. Specifically, when the environmental sensor cannot upload data due to poor signal, the main control center may not be able to obtain environmental information about potential risks such as lightning strikes, fires or storms in time, making it difficult for the system to make early warnings and responses, which may cause small-scale risks to evolve into more serious safety incidents and increase the safety risks of the overall system. On the contrary, if the RSSI threshold is too low, the system may transmit data under noise or interference, thereby affecting the accuracy of the early warning. For example, a too low threshold may cause more errors in data transmission, causing the system to generate false alarms. In this case, the safety event prediction anomaly coefficient will increase, reflecting that the system has generated more false alarms under this threshold, which may interfere with the operation and maintenance team, causing them to mistake it for a false alarm when a real risk comes, thereby increasing the possibility of an accident.

[0040] Analyzing the abnormal coefficient of security event prediction has the following advantages in solving the problem that the existing distributed new energy safety management method of wireless channels does not effectively evaluate the threshold value of wireless channel signal strength, resulting in unstable effects of the distributed new energy safety management method of wireless channels:

[0041] Quantitative evaluation of threshold impact: The security event prediction anomaly coefficient provides a quantitative method that can clearly show the impact of different RSSI thresholds on the warning effect. By analyzing the anomaly coefficient, the change in warning capability under different signal strengths can be accurately identified, making the threshold setting more scientific and reasonable.

[0042] Improve warning accuracy: This factor helps identify false alarms and missed alarms caused by improper threshold value settings. By selecting the most suitable threshold value range, false warnings caused by signal fluctuations can be reduced, making warning information more reliable, which helps to improve the overall safety management and control of distributed new energy systems.

[0043] Optimize threshold adjustment strategy: When building and optimizing the signal strength threshold adjustment strategy, the security event prediction anomaly coefficient is used as a key indicator to guide the system to dynamically adjust the threshold. Based on its feedback data, the system can automatically adjust the threshold under different environments and conditions to ensure that the occurrence of security incidents is minimized while ensuring system stability.

[0044] Enhance the response speed to potential risks: Through the combined analysis of threshold values ​​and warning anomaly coefficients, the system can identify possible safety hazards in advance and respond in a timely manner when the signal is insufficient or too strong, avoiding warning failures caused by signal strength fluctuations, thereby improving the response capability and protection level of distributed new energy systems in complex environments.

[0045] In summary, the anomaly coefficient of security event prediction is crucial for analyzing the optimal threshold value.

[0046] The specific method for obtaining the security event prediction anomaly coefficient is as follows:

[0047] Obtain the data of security event warnings when performing security control values ​​under different thresholds, and perform feature clustering to obtain a cluster set; obtain the respective proportions of cluster types;

[0048] The weight of each safety warning cluster is evaluated based on the support vector machine combined with the respective proportions of cluster types;

[0049] Get the average value between each security warning cluster;

[0050] The square deviation of each security warning cluster is calculated according to the weight of each security warning cluster and the average value between each security warning cluster, and the square deviation of each security warning cluster is added to obtain the security event prediction anomaly coefficient.

[0051] Among them, the weight of each security warning cluster The specific calculation formula is as follows:

[0052]

[0053] The specific calculation formula for the average value between each security warning cluster is as follows

[0054]

[0055] The specific calculation formula for the abnormal coefficient of security event prediction is as follows:

[0056]

[0057] In the formula, is the occurrence ratio of cluster z, and are cluster labels, is the difference between the safe cluster c and cluster z, is the average value between security warning clusters, Predict the total number of clusters for security events, Predict anomaly coefficients for security events.

[0058] The system maintenance stability coefficient is used to measure the performance of the distributed new energy safety management and control system in terms of maintenance frequency and stability under different RSSI threshold conditions. Its main function is to evaluate whether the system can achieve reliable remote monitoring and periodic maintenance under the set signal strength threshold to ensure the long-term stability of the system and control maintenance costs. When the RSSI threshold is too high, some device nodes may be frequently disconnected under low signal strength conditions, making it impossible for the system to upload device operation status data in time, and it is difficult for operation and maintenance personnel to obtain real-time device health status, affecting the arrangement of preventive maintenance. This will extend the maintenance cycle of the system, increase the possibility and uncertainty of equipment failure, and lead to an increase in the difficulty and cost of overall system maintenance. Conversely, when the RSSI threshold is too low, forced data transmission under poor signal quality may lead to a large number of transmission errors and retransmission events, increase the load of the communication link, and accelerate the wear of the device hardware, thereby affecting the performance stability of the system. Frequent data transmission retries will not only shorten the maintenance cycle of the equipment, but also increase the maintenance frequency, thereby increasing the long-term maintenance cost and resource investment of the system. Therefore, by reasonably setting the RSSI threshold and analyzing the system maintenance stability coefficient, the maintenance cycle and stability can be optimized, so that the distributed new energy system can maintain an efficient and stable operation state under reasonable resource consumption.

[0059] Analyzing the system maintenance stability coefficient has the following advantages in solving the problem that the existing distributed new energy safety management and control methods for wireless channels do not effectively evaluate the threshold value of the wireless channel signal strength, resulting in the unstable effect of the distributed new energy safety management and control methods for wireless channels:

[0060] Improve the scientific nature of maintenance plans: Through the analysis of the system maintenance stability coefficient, the equipment maintenance requirements under different RSSI thresholds can be quantitatively evaluated, making the maintenance plan more scientific and reasonable. The system can adjust the maintenance cycle in real time based on the data to ensure that the equipment operates in the best condition and reduce maintenance delays caused by improper signal strength.

[0061] Reduce maintenance costs: Effectively evaluating the system maintenance stability coefficient helps identify the impact of signal strength on equipment maintenance cycles. When the threshold value is set appropriately, unnecessary maintenance can be minimized, avoiding high maintenance costs caused by frequent retransmissions and equipment wear, thereby improving resource utilization.

[0062] Optimize the workload of operation and maintenance personnel: By analyzing the system maintenance stability coefficient, operation and maintenance personnel can timely grasp the health status of equipment and conduct more effective remote monitoring. This will reduce the frequency of emergency response of operation and maintenance personnel in the event of equipment failure, thereby reducing workload and improving work efficiency.

[0063] Enhance system stability: The system maintenance stability coefficient provides a clear performance indicator for the distributed new energy security management and control of wireless channels, enabling the system to adjust the signal strength threshold in a dynamic environment in a timely manner, reduce the uncertainty caused by signal fluctuations, and thus improve the stability and reliability of the overall system.

[0064] Promote intelligent maintenance decisions: Introducing the system maintenance stability coefficient into the safety management and control method can provide data support for intelligent maintenance decisions, optimize the maintenance strategy through machine learning or algorithm models, achieve predictive maintenance, reduce the risk of equipment failure, and improve the long-term operation safety of the system.

[0065] In summary, the system maintenance stability factor is crucial for analyzing the optimal threshold value.

[0066] The specific method for obtaining the system maintenance stability coefficient is as follows:

[0067] Obtain voltage and current fluctuations during distributed renewable energy safety management and control under different threshold values;

[0068] Preprocessing the acquired voltage and current fluctuations, and establishing a fluctuation assessment model based on the voltage fluctuations and the current fluctuations;

[0069] A fluctuation vector group is established based on the processed voltage fluctuation and current fluctuation labels, the fluctuation assessment model is updated based on the observation of the stable observation model, and the system maintenance stability coefficient is calculated based on the updated fluctuation vectors;

[0070] The volatility assessment model is specifically:

[0071]

[0072] The stable observation model is specifically:

[0073]

[0074] The specific calculation formula of the system maintenance stability coefficient is:

[0075]

[0076] In the formula, is the wave vector in the wave vector group, k is the number of the wave vector, is the process noise, is the control vector, is the updated fluctuation vector, To measure noise, is the system maintenance stability coefficient, and n is the total amount of recorded voltage fluctuation and current fluctuation.

[0077] The real-time monitoring accuracy fluctuation coefficient is used to evaluate the real-time monitoring effect of the distributed new energy safety management method under different wireless channel signal strength threshold conditions. The main focus of this coefficient is the accuracy of the system in data transmission and the fault response speed, reflecting the real-time control ability of the main control center over the operation status of each node. When the RSSI threshold is set too high, the system may not be able to transmit data under low signal strength, resulting in some remote or complex new energy nodes (such as long-distance wind turbines or photovoltaic panels in mountainous areas) unable to stably connect to the main control center. This will create a "blind spot", making it impossible for the main control center to obtain the operating status data (such as voltage, power output and frequency) of these nodes in real time, thereby reducing the coverage of the overall monitoring system, failing to identify local anomalies or faults in time, and increasing the safety risks of the system. Conversely, when the RSSI threshold is set too low, the system still allows data transmission even under poor signal quality, which may cause errors or incompleteness in the transmitted data, especially in bad weather or signal interference, the accuracy of the data will be significantly affected. The main control center may receive distorted information, making it difficult for operation and maintenance personnel to judge the true status of each node, thereby reducing the accuracy of real-time monitoring. In addition, fault response speed is also an important component of the real-time monitoring accuracy fluctuation coefficient. In distributed new energy systems, sudden faults (such as inverter failure, overheating, or abnormal power generation) need to be reported and handled quickly. If the RSSI threshold is too high, the fault information may not be transmitted to the main control center in time due to insufficient signal strength, which will extend the response time, causing the fault to further deteriorate and increase the risk of equipment damage, and even trigger chain failures of other nodes. If the RSSI threshold is too low, although the data can still be transmitted, the frequent retransmission when the signal is weak will occupy a lot of bandwidth and resources, prolong the transmission time of the fault information, and make it difficult for the main control center to quickly obtain the truly critical fault information, thereby affecting the timely response to priority events.

[0078] Analyzing the real-time monitoring accuracy fluctuation coefficient has the following advantages in solving the problem that the existing distributed new energy safety management and control methods for wireless channels do not effectively evaluate the threshold value of the wireless channel signal strength, resulting in the unstable effect of the distributed new energy safety management and control methods for wireless channels:

[0079] Improve assessment accuracy: By introducing the real-time monitoring accuracy fluctuation coefficient, the impact of the signal strength threshold on the accuracy of monitoring data can be quantified. This quantification enables the system to evaluate the reliability of data in real time, ensure the accuracy of monitoring information, and avoid data distortion caused by improper threshold setting.

[0080] Optimize threshold settings: Real-time monitoring accuracy fluctuation coefficient provides a dynamic evaluation mechanism that can adjust thresholds under different environments and conditions. By analyzing the fluctuation of monitoring data, the wireless channel signal strength threshold can be optimized for different scenarios (such as weather changes, device types, etc.) to ensure the stability and reliability of data transmission.

[0081] Enhanced fault early warning capability: Real-time monitoring of the accuracy fluctuation coefficient can promptly reflect changes in system status, helping to quickly identify and handle potential fault information. If the accuracy of the monitoring data decreases, the system can quickly issue an alarm, prompting the operation and maintenance personnel to take timely intervention measures to reduce the risk of accidents.

[0082] Reduced operation and maintenance costs: By accurately evaluating and optimizing the signal strength threshold of the wireless channel, the additional operation and maintenance costs caused by false alarms and missed alarms can be reduced. The introduction of real-time monitoring accuracy fluctuation coefficient allows the operation and maintenance team to focus more on real security risks instead of wasting time and resources on insignificant alarms.

[0083] Improve system stability: In the distributed new energy safety management and control of wireless channels, the improvement of monitoring accuracy directly affects the stability of the entire system. Real-time monitoring of the accuracy fluctuation coefficient can help identify unstable factors in data transmission, and prompt the system to optimize data processing and transmission processes, ensure smooth communication between nodes, and thus improve the anti-interference ability of the entire system.

[0084] Data-driven decision support: Real-time monitoring of accuracy fluctuation coefficients can provide data-based feedback to decision makers, enabling them to make more scientific adjustments and decisions. This data-driven approach helps build a more intelligent and efficient distributed new energy safety management and control system and improve the comprehensive management level of the system.

[0085] Through the above advantages, the real-time monitoring accuracy fluctuation coefficient can effectively make up for the shortcomings of the existing wireless channel distributed new energy security management and control methods in the signal strength threshold value evaluation, thereby improving the safety and stability of the system.

[0086] The specific method for obtaining the real-time monitoring accuracy fluctuation coefficient is as follows:

[0087] Obtain in real time the monitoring response rate and monitoring disconnection duration corresponding to the distributed new energy safety management and control under different threshold values, and number the monitoring response rate and monitoring disconnection duration corresponding to the distributed new energy safety management and control under different threshold values;

[0088] The standard deviation and average value of monitoring accuracy are calculated by the corresponding monitoring response rate and monitoring disconnection duration during distributed new energy safety management and control under different threshold values;

[0089] Calculate the coefficient of variation of monitoring accuracy based on the standard deviation of monitoring accuracy and the mean value of monitoring accuracy;

[0090] The real-time monitoring accuracy fluctuation coefficient is calculated based on the monitoring accuracy variation coefficient.

[0091] The specific calculation formula of the monitoring accuracy standard deviation is as follows:

[0092]

[0093] The specific calculation formula of the monitoring accuracy average value is as follows:

[0094]

[0095] The specific calculation formula of the real-time monitoring accuracy fluctuation coefficient is as follows:

[0096]

[0097] In the formula, To monitor the accuracy standard deviation, To monitor the accuracy average, The total number of numbers for monitoring response rate and monitoring disconnection duration. The number for monitoring the response rate and the duration of the disconnection. To monitor the response rate, To monitor the duration of disconnection, To monitor the accuracy fluctuation coefficient in real time.

[0098] This embodiment uses a distributed new energy security management method that integrates VPDN wireless channels to set the threshold value of wireless signal strength through a random perturbation method, which significantly improves the security and stability of the system under different signal conditions. Its technical effects are mainly reflected in the following aspects: First, by quantitatively evaluating the abnormal coefficient of security event prediction and the system maintenance stability coefficient, it can scientifically and rationally optimize the signal strength threshold to ensure the accuracy of early warning and the effectiveness of equipment maintenance; secondly, this method flexibly adjusts the threshold value and provides rich experimental data support, which is convenient for the subsequent construction of neural network models and improves the response speed and protection level of the system; finally, the analysis of the system maintenance stability coefficient helps to reduce maintenance costs, optimize the workload of operation and maintenance personnel, and enhance the reliability of the overall system, thereby promoting the safe and efficient operation of distributed new energy systems.

[0099] Embodiment 2, S3, builds a distributed new energy safety management and control effect evaluation model based on a convolutional neural network according to the safety event prediction abnormal data and safety management and control stable data.

[0100] The distributed new energy safety control effect evaluation model is constructed based on the convolutional neural network according to the abnormal data predicted by the safety incident and the stable data of the safety control, specifically:

[0101] The obtained safety event prediction anomaly coefficient, system maintenance stability coefficient and real-time monitoring accuracy fluctuation coefficient are used to construct a line distributed new energy safety management and control effect evaluation model to generate a safety management and control effect evaluation coefficient;

[0102] The specific calculation formula of the safety control effect evaluation coefficient is as follows:

[0103]

[0104] In the formula, is the safety control effect evaluation coefficient, is the preset proportional coefficient of the security event prediction anomaly coefficient, is the preset proportionality factor of the system maintenance stability factor, is the preset proportionality factor for real-time monitoring accuracy fluctuation coefficient, and , Predict anomaly coefficients for security events, Maintains stability factor for the system, To monitor the accuracy fluctuation coefficient in real time.

[0105] S4, constructs a safety control effect-threshold value change curve based on the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values.

[0106] The safety control effect-threshold value change curve is constructed according to the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values, specifically:

[0107] Obtain the output safety control effect evaluation coefficient under different threshold values ​​from the distributed new energy safety control effect evaluation model;

[0108] Establish a rectangular coordinate system, set the horizontal axis to the line threshold value, and the vertical axis to the safety control effect evaluation coefficient;

[0109] Mark the safety control effect evaluation coefficient corresponding to each threshold value on the rectangular coordinate system to form a data point;

[0110] Connect data points to form a security control effect - threshold value change curve.

[0111] S5, conduct data analysis on the safety control effect-threshold value change curve to obtain the optimized threshold value, and apply it to the distributed new energy safety control of the wireless channel.

[0112] The data analysis of the safety control effect-threshold value change curve is performed to obtain the optimized threshold value, and the threshold value is applied to the distributed new energy safety control of the wireless channel, specifically:

[0113] Obtain the peak values ​​of several safety control effect-threshold value change curves, perform secondary derivatives on the corresponding data points for each highest safety control effect evaluation coefficient, take the threshold value corresponding to the data point whose secondary derivative is close to 0 as the optimal threshold value, and apply it to the distributed new energy safety control of wireless channels.

[0114] This implementation uses a distributed new energy safety management and control effect evaluation model based on a convolutional neural network to effectively integrate the safety event prediction anomaly coefficient, system maintenance stability coefficient, and real-time monitoring accuracy fluctuation coefficient to generate a comprehensive safety management and control effect evaluation coefficient. This model improves the real-time monitoring and prediction capabilities of safety management, optimizes threshold settings by constructing a safety management and control effect-threshold value change curve, and achieves accurate safety management. At the same time, this method reduces the need for human intervention, improves the degree of automation, and significantly enhances the safety and reliability of new energy systems.

[0115] Embodiment 3, Figure 2 What is displayed is a device for a distributed new energy safety management and control method integrating a VPDN wireless channel, which is characterized by comprising a threshold value setting module, a data analysis module, a model building module, a curve building module and a threshold value selection module, and there are connections between the modules;

[0116] A threshold value setting module, used to set a plurality of different threshold values ​​of wireless channel signal strengths based on a random perturbation method according to a preset basic threshold value of wireless channel signal strength;

[0117] A data analysis module is used to analyze the security event prediction abnormal data and security control stability data of distributed new energy security control of wireless channels under different threshold values;

[0118] Model building module, used to build a distributed new energy safety control effect evaluation model based on convolutional neural network according to the abnormal data predicted by security events and the stable data of safety control;

[0119] A curve construction module is used to construct a safety control effect-threshold value change curve based on the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values;

[0120] The threshold value selection module is used to perform data analysis on the security control effect - threshold value change curve, obtain the optimized threshold value, and apply it to the distributed new energy security control of the wireless channel.

[0121] The present application also provides an electronic device, characterized in that the electronic device comprises:

[0122] at least one processor; and,

[0123] a memory communicatively connected to the at least one processor; wherein,

[0124] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a distributed new energy security management and control method for an integrated VPDN wireless channel.

[0125] The present application also provides a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement a distributed new energy security management and control method for an integrated VPDN wireless channel.

[0126] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0127] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0128] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0129] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0130] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0131] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A distributed new energy security management and control method integrating VPDN wireless channels, characterized in that: The steps include: According to the preset basic threshold value of the wireless channel signal strength, a plurality of different threshold values ​​of the wireless channel signal strength are set based on the random perturbation method; Analyze the security event prediction abnormal data and security control stable data of distributed new energy security control of wireless channels under different threshold values; According to the abnormal data predicted by security events and the stable data of security control, a distributed new energy security control effect evaluation model is built based on convolutional neural network; According to the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values, a safety control effect-threshold value change curve is constructed; Data analysis is performed on the safety control effect - threshold value change curve to obtain the optimized threshold value, which is then applied to the distributed new energy safety control of wireless channels.

2. According to claim 1, the distributed new energy security management and control method of integrated VPDN wireless channel is characterized in that: The basic threshold value sets several groups of different wireless channel signal strength threshold values ​​based on the random perturbation method, specifically: Determine the basic threshold range, set the normal distribution parameters for the specific dBm value of the signal strength as the mean of the random disturbance; Set random perturbation parameters, which include perturbation intensity and perturbation times. By introducing standard deviation and performing perturbations several times, several different signal strength values ​​are generated. A random perturbation function is applied to apply a preset distributed perturbation deviation to the basic threshold value, and threshold values ​​of different wireless channel signal strengths under a plurality of different signal strengths are obtained.

3. The distributed new energy security management and control method of integrated VPDN wireless channel according to claim 2 is characterized in that: The security event prediction abnormal data includes a security event prediction abnormal coefficient; the specific method for obtaining the security event prediction abnormal coefficient is as follows: Obtain the data of security event warnings when performing security control values ​​under different thresholds, and perform feature clustering to obtain a cluster set; obtain the respective proportions of cluster types; The weight of each safety warning cluster is evaluated based on the support vector machine combined with the respective proportions of cluster types; Get the average value between each security warning cluster; The square deviation of each security warning cluster is calculated according to the weight of each security warning cluster and the average value between each security warning cluster, and the square deviation of each security warning cluster is added to obtain the security event prediction anomaly coefficient.

4. The distributed new energy security management and control method of integrated VPDN wireless channel according to claim 3 is characterized in that: The security control stability data includes the system maintenance stability coefficient and the real-time monitoring accuracy fluctuation coefficient; the specific method for obtaining the system maintenance stability coefficient is as follows: Obtain voltage and current fluctuations during distributed renewable energy safety management and control under different threshold values; Preprocessing the acquired voltage and current fluctuations, and establishing a fluctuation assessment model based on the voltage fluctuations and the current fluctuations; A fluctuation vector group is established based on the processed voltage fluctuation and current fluctuation labels, the fluctuation assessment model is updated based on the observation of the stable observation model, and the system maintenance stability coefficient is calculated according to the updated fluctuation vectors.

5. According to claim 4, the distributed new energy security management and control method of integrated VPDN wireless channel is characterized in that: The specific method for obtaining the real-time monitoring accuracy fluctuation coefficient is as follows: Obtain in real time the monitoring response rate and monitoring disconnection duration corresponding to the distributed new energy safety management and control under different threshold values, and number the monitoring response rate and monitoring disconnection duration corresponding to the distributed new energy safety management and control under different threshold values; The standard deviation and average value of monitoring accuracy are calculated by the corresponding monitoring response rate and monitoring disconnection duration during distributed new energy safety management and control under different threshold values; Calculate the coefficient of variation of monitoring accuracy based on the standard deviation of monitoring accuracy and the mean value of monitoring accuracy; The real-time monitoring accuracy fluctuation coefficient is calculated based on the monitoring accuracy variation coefficient.

6. The distributed new energy security management and control method of integrated VPDN wireless channel according to claim 5 is characterized in that: The safety control effect-threshold value change curve is constructed according to the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values, specifically: Obtain the output safety control effect evaluation coefficient under different threshold values ​​from the distributed new energy safety control effect evaluation model; Establish a rectangular coordinate system, set the horizontal axis to the line threshold value, and the vertical axis to the safety control effect evaluation coefficient; Mark the safety control effect evaluation coefficient corresponding to each threshold value on the rectangular coordinate system to form a data point; Connect data points to form a security control effect - threshold value change curve.

7. The distributed new energy security management and control method of integrated VPDN wireless channel according to claim 6 is characterized in that: The data analysis of the safety control effect-threshold value change curve is performed to obtain the optimized threshold value, and the threshold value is applied to the distributed new energy safety control of the wireless channel, specifically: Obtain the peak values ​​of several safety control effect-threshold value change curves, perform secondary derivatives on the corresponding data points for each highest safety control effect evaluation coefficient, take the threshold value corresponding to the data point whose secondary derivative is close to 0 as the optimal threshold value, and apply it to the distributed new energy safety control of wireless channels.

8. A device using the distributed new energy security management and control method of the integrated VPDN wireless channel as described in any one of claims 1 to 7, characterized in that: It includes a threshold value setting module, a data analysis module, a model building module, a curve building module and a threshold value selection module, and there are connections between the modules; A threshold value setting module, used to set a plurality of different groups of threshold values ​​of wireless channel signal strength based on a random perturbation method according to a preset basic threshold value of wireless channel signal strength; A data analysis module is used to analyze the security event prediction abnormal data and security control stability data of distributed new energy security control of wireless channels under different threshold values; Model building module, used to build a distributed new energy safety control effect evaluation model based on convolutional neural network according to the abnormal data predicted by security events and the stable data of safety control; A curve construction module is used to construct a safety control effect-threshold value change curve based on the outputs of several distributed new energy safety control effect evaluation models and the corresponding threshold values; The threshold value selection module is used to perform data analysis on the security control effect - threshold value change curve, obtain the optimized threshold value, and apply it to the distributed new energy security control of the wireless channel.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the distributed new energy security management and control method of the integrated VPDN wireless channel as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the distributed new energy security management and control method for an integrated VPDN wireless channel as described in any one of claims 1 to 7.

Images