Improved power operation state real-time monitoring system

Abstract

The invention discloses an improved power operation state real-time monitoring system. The system belongs to the technical field of power system monitoring and comprises a power sensing layer, a data processing platform layer, a user application layer and the like. The electric power data acquisition sensing layer is responsible for data acquisition, deploys various intelligent sensors and monitoring equipment including a voltage sensor, a current sensor, a power factor sensor and a frequency sensor, monitors operation parameters and environmental conditions of power distribution facilities in real time, and performs data acquisition through an embedded microcontroller cooperating with the sensors; the application layer displays a monitoring result and realizes remote control and alarm notification, and a control command sent by a user through the application layer is transmitted to the sensing layer for execution through the network layer and the platform layer; and the data processing platform layer receives the data from the network layer, stores, processes and intelligently analyzes the data, and analyzes the data by using an improved grey wolf optimization algorithm so as to improve the monitoring precision.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system monitoring, and relates to aspects such as real-time monitoring of power operation status, data processing and analysis, remote control, and fault diagnosis; specifically, it relates to a real-time monitoring system for power operation status using an improved grey wolf algorithm; that is, a real-time monitoring system for power operation status using an improved grey wolf algorithm. Background Art

[0002] As the scale of power systems continues to expand and power equipment becomes increasingly complex, traditional power monitoring methods can no longer meet the requirements for real-time, comprehensive, and accurate monitoring of power systems. Therefore, there is an urgent need for a method that can collect, process, and analyze power operation status data in real time and analyze the data to improve monitoring accuracy. The following is the current status of this technology:

[0003] Data collection and monitoring: Traditional power system monitoring relies on various sensors and monitoring equipment, including voltage sensors, current sensors, etc., to collect operating parameters and environmental conditions of power facilities. These devices transmit data to the central monitoring system through wired or wireless communication. As the complexity and scale of power systems increase, the requirements for the accuracy and real-time performance of data collection are also getting higher and higher.

[0004] Data processing and analysis: Traditional monitoring systems use simple data storage and analysis methods, including threshold alarms and simple statistical analysis. These methods are inefficient in processing large amounts of data and have difficulty discovering potential failure modes and abnormal behaviors.

[0005] Remote control and user interaction: Traditional monitoring systems mostly provide basic data display and simple control functions. The user interface is relatively simple and lacks intuitiveness and interactivity.

[0006] Algorithm optimization: Traditional optimization algorithms have problems such as slow convergence and easy falling into local optimality when processing complex power system data.

[0007] Environmental adaptability: With the continuous changes in the operating environment of the power system, such as fluctuations in grid load and changes in weather conditions, higher requirements are placed on the environmental adaptability of the monitoring system, which needs to better adapt to different operating conditions. Summary of the invention

[0008] In view of the above problems, the purpose of the present invention is to provide an improved real-time monitoring system for power operation status, aiming to obtain more accurate data through an improved grey wolf algorithm, introducing an environmental adaptability mechanism and dynamically adjusting the search range.

[0009] The technical solution of the present invention is: the improved real-time monitoring system for electric power operation status described in the present invention comprises an electric power data acquisition perception layer, a data processing platform layer and a user application layer;

[0010] One side of the power data acquisition and perception layer is connected to one side of the data processing platform layer via the network layer for data transmission;

[0011] The data processing platform layer is connected to the power data acquisition layer and the user application layer respectively to receive data and transmit data processing results, and respond to user adjustment instructions;

[0012] The user application layer is connected to the data processing platform layer and the power data acquisition perception layer respectively, and is used to display data processing results and issue execution instructions respectively.

[0013] Furthermore, the power data acquisition perception layer is responsible for data acquisition, including the deployment of various intelligent sensors and monitoring equipment, including voltage sensors, current sensors, power factor sensors, and frequency sensors, to monitor the operating parameters and environmental conditions of the distribution facilities in real time, and configure corresponding communication parameters according to the communication protocol of the sensor and the microcontroller, including mode, direction, data size, polarity, clock phase, and baud rate, and collect data through the cooperation of the two.

[0014] Furthermore, the user application layer helps users view data that has been accurately processed by the data processing platform layer through the user interface, including real-time monitoring information, historical data, and analysis reports; users provide feedback on the monitoring results, and these feedbacks are used to optimize the performance of the monitoring system; users issue control instructions based on the monitoring results, including adjusting device parameters, starting or stopping certain devices; the control instructions issued by the user are transmitted to the power data acquisition perception layer through the network layer, and the embedded microcontroller executes these instructions to achieve remote control of the power system.

[0015] Furthermore, the data processing platform layer manages data through a database, and stores the data received from the perception layer in the database to facilitate subsequent processing and analysis; the monitoring software reads data from the database for further intelligent analysis; the improved Gray Wolf optimization algorithm is used to analyze the data to improve monitoring accuracy, identify abnormal patterns, and perform fault diagnosis; then, based on the analysis results of the improved Gray Wolf optimization algorithm, it is determined whether the state of the power system is normal; if the result is abnormal, the system will trigger an alarm mechanism and transmit the fault diagnosis result to the user application layer; if the result is normal, the system will transmit the processed data to the user application layer for the user to view and further analyze.

[0016] Furthermore, the data processing platform layer is a method for optimizing the parameters of the real-time monitoring system of the power operation status based on the improved grey wolf optimization algorithm, and the specific steps are as follows:

[0017] Step (1): Initialize the wolf pack, including the positions of alpha (α), beta (β), and delta (δ) wolves;

[0018] Step (2): Evaluate the fitness of each wolf;

[0019] Step (3): Update the positions of α, β, and δ;

[0020] Step (4): Update the position of each wolf in the wolf pack;

[0021] Step (5): Check the termination condition, reaching the maximum number of iterations or the system reaching the preset accuracy standard.

[0022] Furthermore, in steps (1)-(3), the wolf pack is initialized, including the positions of α, β, δ and other wolves, the fitness of each wolf is evaluated, and the positions of α, β, δ are updated; the specific process is as follows:

[0023] Assume that the wolf pack consists of N wolves, and the position of each wolf is X i Randomly initialize in the search space as follows:

[0024] X i =X min +rand()·(X max -X min )

[0025] In the formula, the position X of each wolf is i are the power system parameters, including the initial values ​​of voltage, current, power factor and frequency; rand() is a random number generation function, X min and X max are the minimum and maximum values ​​of these parameter ranges, respectively;

[0026] After initialization, the algorithm evaluates the fitness F of each wolf based on its position in the pack. i , which is related to the objective function of the optimization problem; the algorithm determines the positions of α, β, and δ wolves in the wolf pack according to their fitness, representing the optimal, suboptimal, and third-optimal solutions currently found;

[0027] Calculated according to power system parameters, it is defined by the inverse of monitoring accuracy; as follows:

[0028]

[0029] In the formula, F i The operating efficiency and stability of the power system are related. Error (Xi) is the total error of the system under the current parameter settings, including voltage deviation and frequency deviation. The operating efficiency and stability of the power system are related.i It is inversely proportional to the total error Error(Xi) of the system under the current parameter settings. The smaller the total error of the system under the current parameter settings, the higher the correlation between the operating efficiency and stability of the power system, and the higher the accuracy of the monitored data;

[0030] F α =min(F i ),F β =min(F i ,i≠α),F δ =min(F i ,i≠α,β)

[0031] According to the correlation between the operating efficiency and stability of the power system, a more accurate parameter configuration is selected as α, β, and δ, and the system is guided on how to adjust the power system parameters to improve the accuracy of the system data.

[0032] Furthermore, in steps (4)-(5), the position of each wolf in the wolf pack is updated and the termination condition is checked, such as reaching the maximum number of iterations or the fitness meets the requirements; the specific process is as follows:

[0033] Update the position of each wolf, C adj , C is the coefficient vector, t is the current iteration number, and T is the maximum iteration number; as follows:

[0034]

[0035] X i =X α -C adj ·(C1·X α -X i )+C adj ·(C2·X β -X i )+C adj ·(C3·X δ -X i )

[0036] In the formula, C adj , C1, C2, and C3 are adjustment coefficients to update power system parameters; A affects the adjustment of power system parameters, C1, C2, and C3 control the power system parameters to more accurate voltage, current, power factor, and frequency;

[0037] Update the speed of the wolf pack V i , increase the global search capability of the algorithm, as follows:

[0038] V i =w·V i +A·(X α -X i)+B·(X β -X i )+C·(X δ -X i ))

[0039] Where, speed V i is the rate of parameter adjustment, the system responds quickly and adjusts its parameters to adapt to grid changes; w is the inertia weight, B is another coefficient vector;

[0040] F i <F α , then X α =X i

[0041] If the new parameter configuration provides better performance, these parameters become the new alpha (α);

[0042] t ≥ T or F α ≤threshold

[0043] If the maximum number of iterations T is reached or the system reaches the preset accuracy standard, accurate data is obtained and the iteration stops.

[0044] Furthermore, the gray wolf optimization algorithm is improved by introducing an environmental adaptability mechanism and dynamically adjusting the search range to obtain more accurate data. The specific process is as follows:

[0045] After each iteration, an environmental adaptability assessment step is added. This step will evaluate the relationship between the current power grid operation status and environmental changes, and adjust the wolf pack's search strategy according to these changes; by introducing an environmental adaptability coefficient, the coefficient is dynamically adjusted according to the degree of matching between the power grid operation status and environmental changes, so as to guide the wolf pack to search for the optimal solution more effectively.

[0046] The calculation formula of environmental adaptability coefficient EAC is as follows:

[0047]

[0048] In the formula, E current Indicates the current power grid operation efficiency, E avg Represents the average historical grid operation efficiency, S current Indicates the current grid stability, S avg Represents the historical average value of grid stability;

[0049]

[0050] In the formula, E i is the voltage value of the ith monitoring point, E ref is the reference voltage value, EAC jis the frequency value of the jth monitoring point, EAC ref is the reference frequency value, n and m are the number of voltage and frequency monitoring points respectively. T is the time range of historical data, Ecurrent(t) is the current grid operation efficiency at time t, I i is the current value of the ith monitoring point, I ref is the reference current value, P j is the power factor value of the jth monitoring point, P ref is the reference power factor value, n and m are the number of current and power factor monitoring points, respectively, T is the time range of historical data, S current (t) is the current grid stability at time t;

[0051] The adjustment formula of the search range SR is as follows:

[0052]

[0053] In the formula, SR represents the search range, SR base represents the basic search range, EAC represents the environmental adaptability coefficient, C adj represents the adjustment factor;

[0054]

[0055] Where n and m are the number of voltage and frequency monitoring points, respectively, and p and q are the number of current and power factor monitoring points, respectively;

[0056] According to the environmental adaptability coefficient, the search range SR of the wolf pack is dynamically adjusted; when the environmental adaptability coefficient EAC is high, the search range SR is narrowed to conduct a more detailed search; when the environmental adaptability coefficient EAC is low, the search range SR is expanded to increase the globality of the search.

[0057] Furthermore, the improved gray wolf optimization algorithm is used to monitor the operation status of the power operation status real-time monitoring system, and improve the monitoring accuracy of voltage, current, power factor and frequency. The specific steps are as follows:

[0058] Step 1: Power system parameters, including initial values ​​of voltage, current, power factor and frequency;

[0059] Step 2: Evaluate the operational efficiency and stability of the power system;

[0060] Step 3: Update α, β, δ;

[0061] Step 4: Update the position of each wolf in the wolf pack;

[0062] Step 5: Check the termination condition;

[0063] If Fi <F α , then X α =X i ,The system has not reached the preset accuracy standard, and continues to iterate;

[0064] If t ≥ T or F α ≤threshold, the maximum number of iterations is reached or the system reaches the preset accuracy standard, and the iteration is terminated.

[0065] The beneficial effects of the present invention are as follows: 1. By introducing the improved gray wolf optimization algorithm, the system can significantly improve the monitoring accuracy of the power operation status, effectively identify abnormal modes and perform fault diagnosis, and improve the operation efficiency and stability of the power system; 2. The system uses strong environmental adaptability to dynamically adjust the search range and optimization strategy according to the power grid operation status and environmental changes, ensuring that efficient monitoring capabilities are maintained under complex and changeable operating conditions; in addition, the data processing platform layer of the system manages data through a database to achieve efficient storage and intelligent analysis of real-time monitoring information, historical data and analysis reports, providing users with comprehensive and accurate data support, while supporting users to issue control instructions through the interface to achieve remote control and operation, greatly improving user experience and system interactivity; 3. The system fully considers the complexity and scale of the power system in design, and effectively solves the deficiencies of traditional monitoring methods in data collection, processing and analysis through the improvement of the optimization algorithm and the collaborative work of the multi-layer architecture, providing new technical means for intelligent monitoring of the power system, and has broad application prospects and important practical significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is the overall operation block diagram of the present invention. DETAILED DESCRIPTION

[0067] The specific technical scheme of the present invention is further described in detail below with reference to specific examples.

[0068] As shown in the figure, a method for real-time monitoring of system parameters using improved power operation status according to the present invention comprises the following steps:

[0069] Step 1: Power system parameters, including initial values ​​of voltage, current, power factor and frequency;

[0070] Step 2: Evaluate the operational efficiency and stability of the power system;

[0071] Step 3: Update α, β, δ;

[0072] Step 4: Update the position of each wolf in the wolf pack;

[0073] Step 5: Introduce environmental adaptability mechanism and dynamically adjust the search range;

[0074] Step 6: Check the termination condition;

[0075] If F i <F α , then X α =X i ,The system has not reached the preset accuracy standard, and continues to iterate;

[0076] If t ≥ T or F α ≤threshold, the maximum number of iterations is reached or the system reaches the preset accuracy standard, and the iteration is terminated.

[0077] Furthermore, the real-time monitoring optimization model of the power operation status is specifically as follows:

[0078] Assume that the wolf pack consists of N wolves, and the position of each wolf is X i Randomly initialize in the search space as follows:

[0079] X i =X min +rand()·(X max -X min )

[0080] In the formula, the position X of each wolf is i are the power system parameters, including the initial values ​​of voltage, current, power factor and frequency, rand() is a random number generation function, X min and X max are the minimum and maximum values ​​of these parameter ranges, respectively;

[0081] After initialization, the algorithm evaluates the fitness F of each wolf based on its position in the pack. i , which is related to the objective function of the optimization problem; the algorithm determines the positions of α, β, and δ wolves in the wolf pack according to their fitness, representing the optimal, suboptimal, and third-optimal solutions currently found;

[0082] According to the calculation of power system parameters, it is defined by the inverse of monitoring accuracy, as follows;

[0083]

[0084] In the formula, F i The operating efficiency and stability of the power system are related. Error (Xi) is the total error of the system under the current parameter settings, including voltage deviation and frequency deviation. iIt is inversely proportional to the total error Error(Xi) of the system under the current parameter settings. The smaller the total error of the system under the current parameter settings, the higher the correlation between the operating efficiency and stability of the power system, and the higher the accuracy of the monitored data;

[0085] F α =min(F i ),F β =min(F i ,i≠α),F δ =min(F i ,i≠α,β)

[0086] According to the correlation between the operating efficiency and stability of the power system, more accurate parameter configurations are selected as α, β, and δ, and the system is guided on how to adjust the power system parameters to improve the accuracy of system data;

[0087] Update the position of each wolf, C adj , C is the coefficient vector, t is the current iteration number, and T is the maximum iteration number; as follows:

[0088]

[0089] X i =X α -C adj ·(C1·X α -X i )+C adj ·(C2·X β -X i )+C adj ·(C3·X δ -X i )

[0090] In the formula, C adj , C1, C2, and C3 are adjustment coefficients, which update the power system parameters. A affects the adjustment of power system parameters. C1, C2, and C3 control the power system parameters to adjust to more accurate voltage, current, power factor, and frequency;

[0091] Update the speed of the wolf pack V i , increase the global search capability of the algorithm; as follows:

[0092] V i =w·V i +A·(X α -X i )+B·(X β -X i )+C·(X δ -X i ))

[0093] Where, speed Vi is the rate of parameter adjustment, the system responds quickly and adjusts its parameters to adapt to grid changes; w is the inertia weight, B is another coefficient vector;

[0094] F i <F α , then X α =X i

[0095] If the new parameter configuration provides better performance, these parameters become the new alpha (α);

[0096] t ≥ T or F α ≤threshold

[0097] If the maximum number of iterations T is reached or the system reaches the preset accuracy standard, accurate data is obtained and the iteration stops;

[0098] After each iteration, an environmental adaptability assessment step is added; this step will evaluate the relationship between the current power grid operation status and environmental changes, and adjust the wolf pack's search strategy according to these changes; by introducing an environmental adaptability coefficient, the coefficient is dynamically adjusted according to the degree of matching between the power grid operation status and environmental changes, so as to guide the wolf pack to search for the optimal solution more effectively;

[0099] The calculation formula of environmental adaptability coefficient EAC is as follows:

[0100]

[0101] In the formula, E current Indicates the current power grid operation efficiency, E avg Represents the average historical grid operation efficiency, S current Indicates the current grid stability, S avg Represents the historical average value of grid stability;

[0102]

[0103] In the formula, E i is the voltage value of the ith monitoring point, E ref is the reference voltage value, EAC j is the frequency value of the jth monitoring point, EAC ref is the reference frequency value, n and m are the number of voltage and frequency monitoring points, respectively, T is the time range of historical data, Ecurrent(t) is the current grid operation efficiency at time t, I i is the current value of the ith monitoring point, I ref is the reference current value, P j is the power factor value of the jth monitoring point, P refis the reference power factor value, n and m are the number of current and power factor monitoring points, respectively, T is the time range of historical data, S current (t) is the current grid stability at time t;

[0104] The adjustment formula of the search range SR is as follows:

[0105]

[0106] In the formula, SR represents the search range, SR base represents the basic search range, EAC represents the environmental adaptability coefficient, C adj represents the adjustment factor;

[0107]

[0108] Where n and m are the number of voltage and frequency monitoring points, respectively, and p and q are the number of current and power factor monitoring points, respectively;

[0109] According to the environmental adaptability coefficient, the search range SR of the wolf pack is dynamically adjusted; when the environmental adaptability coefficient EAC is high, the search range SR is narrowed to conduct a more detailed search; when the environmental adaptability coefficient EAC is low, the search range SR is expanded to increase the globality of the search;

[0110] One side of the power data acquisition perception layer is connected to the other side of the data processing platform layer via the network layer for data transmission; it is responsible for data acquisition, including the deployment of various intelligent sensors and monitoring equipment, real-time monitoring of the operating parameters and environmental conditions of the distribution facilities, and configuring the corresponding communication parameters according to the communication protocol of the sensor and the microcontroller, including mode, direction, data size, polarity, clock phase, and baud rate, and data acquisition is carried out through the cooperation of the two.

[0111] The user application layer is connected to the data processing platform layer and the power data acquisition perception layer, respectively, to display the data processing results and issue execution instructions; the user issues control instructions based on the monitoring results, and the issued control instructions are transmitted to the power data acquisition perception layer through the network layer. The embedded microcontroller executes these instructions to realize remote control of the power system.

[0112] The data processing platform layer is connected to the power data acquisition layer and the user application layer to receive data and transmit data processing results. The improved gray wolf optimization algorithm is used to analyze the data, improve monitoring accuracy, identify abnormal patterns, and perform fault diagnosis. The improved gray wolf optimization algorithm is used to determine whether the power system is normal based on the analysis results, and respond to the user's adjustment instructions.

[0113] The Grey Wolf Optimization Algorithm, which introduces an environmental adaptability mechanism and dynamically adjusts the search range, is used to train the real-time monitoring optimization model for power operation status to obtain the most accurate monitoring data.

[0114] Furthermore, the real-time monitoring optimization model of the power operation status is specifically as follows:

[0115] Assume that the wolf pack consists of N wolves, and the position of each wolf is X i Randomly initialize in the search space as follows:

[0116] X i =X min +rand()·(X max -X min )

[0117] In the formula, the position X of each wolf is i are the power system parameters, including the initial values ​​of voltage, current, power factor and frequency, rand() is a random number generation function, X min and X max are the minimum and maximum values ​​of these parameter ranges, respectively;

[0118] After initialization, the algorithm evaluates the fitness F of each wolf based on its position in the pack. i , which is related to the objective function of the optimization problem; the algorithm determines the positions of α, β, and δ wolves in the wolf pack based on their fitness, representing the optimal, suboptimal, and third-optimal solutions currently found.

[0119] Calculated according to power system parameters, it is defined by the inverse of monitoring accuracy, as follows:

[0120]

[0121] In the formula, F i The operating efficiency and stability of the power system are related. Error (Xi) is the total error of the system under the current parameter settings, including voltage deviation and frequency deviation. The operating efficiency and stability of the power system are related. i It is inversely proportional to the total error Error(Xi) of the system under the current parameter settings. The smaller the total error of the system under the current parameter settings, the higher the correlation between the operating efficiency and stability of the power system, and the higher the accuracy of the monitored data;

[0122] F α =min(F i ),F β =min(F i ,i≠α),F δ =min(F i ,i≠α,β)

[0123] According to the correlation between the operating efficiency and stability of the power system, more accurate parameter configurations are selected as α, β, and δ, and the system is guided on how to adjust the power system parameters to improve the accuracy of system data;

[0124] Update the position of each wolf, C adj , C is the coefficient vector, t is the current iteration number, and T is the maximum iteration number; as follows:

[0125]

[0126] X i =X α -C adj ·(C1·X α -X i )+C adj ·(C2·X β -X i )+C adj ·(C3·X δ -X i )

[0127] In the formula, C adj , C1, C2, and C3 are adjustment coefficients, which update the power system parameters. A affects the adjustment of power system parameters. C1, C2, and C3 control the power system parameters to adjust to more accurate voltage, current, power factor, and frequency;

[0128] Update the speed of the wolf pack V i , increase the global search capability of the algorithm, as follows:

[0129] V i =w·V i +A·(X α -X i )+B·(X β -X i )+C·(X δ -X i ))

[0130] Where, speed V i is the rate of parameter adjustment, the system responds quickly and adjusts its parameters to adapt to grid changes; w is the inertia weight, B is another coefficient vector;

[0131] F i <F α , then X α =X i

[0132] If the new parameter configuration provides better performance, these parameters become the new alpha (α);

[0133] t ≥ T or Fα ≤threshold

[0134] If the maximum number of iterations T is reached or the system reaches the preset accuracy standard, accurate data is obtained and the iteration stops;

[0135] After each iteration, an environmental adaptability assessment step is added; this step will evaluate the relationship between the current power grid operation status and environmental changes, and adjust the wolf pack's search strategy according to these changes; by introducing an environmental adaptability coefficient, the coefficient is dynamically adjusted according to the degree of matching between the power grid operation status and environmental changes, so as to guide the wolf pack to search for the optimal solution more effectively;

[0136] The calculation formula of environmental adaptability coefficient EAC is as follows:

[0137]

[0138] In the formula, E current Indicates the current power grid operation efficiency, E avg Represents the average historical grid operation efficiency, S current Indicates the current grid stability, S avg Represents the historical average value of grid stability;

[0139]

[0140] In the formula, E i is the voltage value of the ith monitoring point, E ref is the reference voltage value, EAC j is the frequency value of the jth monitoring point, EAC ref is the reference frequency value, n and m are the number of voltage and frequency monitoring points respectively. T is the time range of historical data, Ecurrent(t) is the current grid operation efficiency at time t, I i is the current value of the ith monitoring point, I ref is the reference current value, P j is the power factor value of the jth monitoring point, P ref is the reference power factor value, n and m are the number of current and power factor monitoring points respectively; T is the time range of historical data, S current (t) is the current grid stability at time t.

[0141] The adjustment formula of the search range SR is as follows:

[0142]

[0143] In the formula, SR represents the search range, SR base represents the basic search range, EAC represents the environmental adaptability coefficient, C adjrepresents the adjustment factor;

[0144]

[0145] Where n and m are the number of voltage and frequency monitoring points, respectively, and p and q are the number of current and power factor monitoring points, respectively;

[0146] According to the environmental adaptability coefficient, the search range SR of the wolf pack is dynamically adjusted; when the environmental adaptability coefficient EAC is high, the search range SR is narrowed to conduct a more detailed search; when the environmental adaptability coefficient EAC is low, the search range SR is expanded to increase the globality of the search.

Claims

1. An improved real-time monitoring system for power operation status, characterized in that: It includes interconnected power data collection perception layer, user application layer and data processing platform layer; One side of the power data acquisition and perception layer is connected to one side of the data processing platform layer via the network layer for data transmission; The user application layer is connected to the data processing platform layer and the power data acquisition perception layer, respectively, and is used to display data processing results and issue execution instructions; The data processing platform layer is connected to the power data acquisition layer and the user application layer respectively for receiving data and transmitting data processing results, and responding to user adjustment instructions.

2. The improved real-time monitoring system for power operation status according to claim 1 is characterized in that: The power data acquisition perception layer includes a voltage sensor, a current sensor, a power factor sensor, a frequency sensor and an embedded microcontroller; The power data acquisition perception layer monitors the operating parameters and environmental conditions of the distribution facilities in real time. According to the communication protocol of the sensor and the micro-embedded controller, it configures the corresponding communication parameters, including mode, direction, data size, polarity, clock phase, and baud rate, and collects data through the cooperation of the two.

3. The improved real-time monitoring system for power operation status according to claim 1 is characterized in that: The user application layer helps users view the data accurately processed by the data processing platform layer through the user interface, and users provide feedback on the monitoring results; The user issues control instructions based on the monitoring results. The control instructions issued by the user are transmitted to the power data acquisition and perception layer through the network layer, and the embedded microcontroller executes the instructions to realize remote control of the power system.

4. The improved real-time monitoring system for power operation status according to claim 3 is characterized in that: The data includes real-time monitoring information, historical data and analysis reports; The control instructions include adjusting device parameters and starting or stopping certain devices.

5. The improved real-time monitoring system for power operation status according to claim 1 is characterized in that: The data processing platform layer manages data through a database, stores the data received from the perception layer in the database, and the monitoring software reads the data from the database for intelligent analysis; uses the improved Gray Wolf optimization algorithm to analyze the data, identifies abnormal patterns for fault diagnosis; and then determines whether the state of the power system is normal based on the analysis results of the improved Gray Wolf optimization algorithm; If the result is abnormal, the system triggers the alarm mechanism and transmits the fault diagnosis result to the user application layer; if the result is normal, the system transmits the processed data to the user application layer for the user to view and further analyze.

6. The improved real-time monitoring system for electric power operation status according to claim 1 is characterized in that: The data processing platform layer is a method for optimizing the parameters of the real-time monitoring system of the power operation status based on the improved grey wolf optimization algorithm; The specific steps are as follows: Step (1): Initialize the wolf pack, including the positions of alpha (α), beta (β), and delta (δ) wolves; Step (2): Evaluate the fitness of each wolf; Step (3): Update the positions of α, β, and δ; Step (4): Update the position of each wolf in the wolf pack; Step (5): Check the termination condition, reaching the maximum number of iterations or the system reaching the preset accuracy standard.

7. The improved real-time monitoring system for electric power operation status according to claim 6 is characterized in that: In steps (1)-(3), the specific process is as follows: Assume that the wolf pack consists of N wolves, and the position of each wolf is X i Randomly initialize in the search space as follows: X i =X min +rand()·(X max -X min ) In the formula, the position X of each wolf is i are the power system parameters, including the initial values ​​of voltage, current, power factor and frequency; rand() is a random number generation function. min and X max are the minimum and maximum values ​​of the above parameter ranges respectively; After initialization, the algorithm evaluates the fitness F of each wolf according to its position in the pack. i ; The algorithm determines the positions of α, β, and δ wolves in the wolf pack based on their fitness, representing the optimal, second-optimal, and third-optimal solutions currently found; Calculated according to power system parameters, it is defined by the inverse of monitoring accuracy, as follows: In the formula, F i The operating efficiency and stability of the power system are related. Error (Xi) is the total error of the system under the current parameter settings, including voltage deviation and frequency deviation. The operating efficiency and stability of the power system are related. i It is inversely proportional to the total error Error(Xi) of the system under the current parameter settings. The smaller the total error of the system under the current parameter settings, the higher the correlation between the operating efficiency and stability of the power system, and the higher the accuracy of the monitored data; as shown in the following formula: F α =min(F i ),F β =min(F i ,i≠α),F δ =min(F i ,i≠α,β).

8. The improved real-time monitoring system for power operation status according to claim 6 is characterized in that: In steps (4)-(5), the specific process is as follows: Update the position of each wolf, C adj , C is the coefficient vector, t is the current iteration number, and T is the maximum iteration number; X i =X α -C adj ·(C1·X α -X i )+C adj ·(C2·X β -X i )+C adj ·(C3·X δ -X i ) In the formula, C adj , C1, C2, and C3 are adjustment coefficients to update power system parameters; A affects the adjustment of power system parameters, C1, C2, and C3 control the adjustment of power system parameters to voltage, current, power factor, and frequency; Update the speed of the wolf pack V i , increase the global search capability of the algorithm; V i =w·V i +A·(X α -X i )+B·(X β -X i )+C·(X δ -X i )) Where, speed V i is the rate of parameter adjustment; w is the inertia weight, and B is another coefficient vector; F i <F α , then X α =X i If the new parameter configuration provides better performance, these parameters become the new alpha (α); t ≥ T or F α ≤threshold If the maximum number of iterations T is reached or the system reaches the preset accuracy standard, accurate data is obtained and the iteration stops.

9. The improved real-time monitoring system for power operation status according to claim 7 or 8, characterized in that: The gray wolf optimization algorithm is improved by introducing an environmental adaptability mechanism and dynamically adjusting the search range to obtain accurate data. The specific process is as follows: After each iteration, an environmental adaptability assessment step is added; this step will evaluate the relationship between the current power grid operation status and environmental changes, and adjust the wolf pack's search strategy according to these changes; by introducing an environmental adaptability coefficient, the coefficient is dynamically adjusted according to the matching degree between the power grid operation status and environmental changes to guide the wolf pack to search for the optimal solution; The calculation formula of environmental adaptability coefficient EAC is as follows: In the formula, E current Indicates the current power grid operation efficiency, E avg Represents the average historical grid operation efficiency, S current Indicates the current grid stability, S avg Represents the historical average value of grid stability; In the formula, E i is the voltage value of the ith monitoring point, E ref is the reference voltage value, EAC j is the frequency value of the jth monitoring point, EAC ref is the reference frequency value, n and m are the number of voltage and frequency monitoring points, respectively, T is the time range of historical data, Ecurrent(t) is the current grid operation efficiency at time t, I i is the current value of the ith monitoring point, I ref is the reference current value, P j is the power factor value of the jth monitoring point, P ref is the reference power factor value, n and m are the number of current and power factor monitoring points, respectively, T is the time range of historical data, S current (t) is the current grid stability at time t; The search range SR is adjusted by the following formula: In the formula, SR represents the search range, SR base represents the basic search range, EAC represents the environmental adaptability coefficient, C adj represents the adjustment factor; Where n and m are the number of voltage and frequency monitoring points, respectively, and p and q are the number of current and power factor monitoring points, respectively; According to the environmental adaptability coefficient, the search range SR of the wolf pack is dynamically adjusted; when the environmental adaptability coefficient EAC is high, the search range SR is narrowed for searching; when the environmental adaptability coefficient EAC is low, the search range SR is expanded to increase the globality of the search.

10. The improved real-time monitoring system for electric power operation status according to claim 6, characterized in that: The specific steps of the improved gray wolf optimization algorithm are as follows: Step 1: Power system parameters, including initial values ​​of voltage, current, power factor and frequency; Step 2: Evaluate the operational efficiency and stability of the power system; Step 3: Update α, β, δ; Step 4: Update the position of each wolf in the wolf pack; Step 5: Check termination conditions; If F i <F α , then X α =X i ,The system has not reached the preset accuracy standard, and continues to iterate; If t ≥ T or F α ≤threshold, the maximum number of iterations is reached or the system reaches the preset accuracy standard, and the iteration is terminated.

Images