Centralized automation strategy optimization method and system based on fuzzy logic

Abstract

The application provides a centralized control automation strategy optimization method and system based on fuzzy logic, which comprises the following steps: firstly, collecting real-time operation state data of power grid operation equipment in a target centralized control area, covering power grid operation parameters and parameter fluctuation ranges; then, performing fuzzy membership processing on the data according to the parameter fluctuation ranges to generate a fuzzy rule set containing multiple fuzzy rules, each fuzzy rule corresponding to parameter dynamic adjustment logic; based on the fuzzy rule set, using fuzzy logic to optimize the current control strategy to generate an optimized control strategy containing control instructions and trigger conditions; then, sending the strategy to the execution equipment according to the trigger conditions and monitoring execution feedback data; verifying the validity of the strategy according to the matching result of the execution feedback data and a preset threshold value, and then dynamically adjusting the optimized control strategy, which can effectively optimize the centralized control automation strategy and improve the power grid operation control effect.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and more specifically, to a method and system for optimizing centralized control automation strategies based on fuzzy logic. Background Technology

[0002] In today's era of continuous development and transformation of power systems, centralized control and automation play a crucial role in ensuring the stable and efficient operation of the power grid. With the increasing scale and complexity of the power grid, as well as the diversified growth of electricity demand, the need to optimize centralized control and automation strategies has become extremely urgent.

[0003] Traditional centralized control automation strategies, when addressing power grid operation-related issues, largely rely on fixed rules for formulating control strategies. These fixed rules are often pre-set based on specific, relatively ideal operating scenarios, lacking the ability to effectively cope with the complex and ever-changing power grid operating parameters. Once the power grid operating conditions change, exceeding the applicability of the pre-set rules, these control strategies become ineffective, unable to flexibly adjust according to the actual situation, resulting in poor control performance and potentially affecting the stable operation of the power grid.

[0004] In the process of optimizing the control strategy, the existing technology has failed to fully consider the interrelationship between various power grid operating parameters and the dynamic changes in the operating environment, so that the optimized control strategy still has certain limitations and cannot meet the precise control requirements under complex power grid operating scenarios. Summary of the Invention

[0005] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for optimizing centralized control automation strategies based on fuzzy logic, the method comprising:

[0006] Collect real-time operating status data of power grid operating equipment within the target centralized control area. The real-time operating status data includes at least one power grid operating parameter and the parameter fluctuation range corresponding to the power grid operating parameter.

[0007] Based on the fluctuation range of the parameters, the real-time operating status data is processed by fuzzy membership to generate a set of fuzzy rules that match the power grid operating parameters. The set of fuzzy rules contains multiple fuzzy rules, and each fuzzy rule corresponds to a dynamic adjustment logic of the power grid operating parameters.

[0008] Based on the set of fuzzy rules, the current control strategy of the target centralized control area is optimized by fuzzy logic to generate an optimized control strategy. The optimized control strategy includes multiple control instructions and the triggering conditions of each control instruction.

[0009] Based on the triggering conditions, the optimized control strategy is sent to the execution devices within the target centralized control area, and the execution feedback data of the execution devices in response to the control commands is monitored.

[0010] Based on the matching results of the execution feedback data and the preset feedback threshold, the effectiveness of the optimized control strategy is verified, and the optimized control strategy is dynamically adjusted according to the verification results.

[0011] In another aspect, embodiments of the present invention also provide a centralized control automation strategy optimization system based on fuzzy logic, including a processor and a machine-readable storage medium connected to the processor. The machine-readable storage medium is used to store programs, instructions, or code, and the processor is used to execute the programs, instructions, or code in the machine-readable storage medium to implement the above-described method.

[0012] Based on the above, this application embodiment collects real-time operating status data of power grid equipment and performs fuzzy membership processing based on parameter fluctuation ranges to generate a fuzzy rule set. This effectively quantifies and analyzes the uncertainty of power grid operating parameters through fuzzy logic, generating dynamic adjustment logic that matches different operating parameters. In the control strategy optimization stage, the current control strategy is optimized using fuzzy logic based on the fuzzy rule set, generating an optimized control strategy containing multiple control commands and their triggering conditions. This achieves intelligent optimization of the control strategy for the centralized control area, comprehensively considering various operating parameters and their dynamic changes. This allows the optimized control strategy to better adapt to the complex operating conditions of the power grid, improving the accuracy and timeliness of the control strategy and effectively avoiding the lag and incompatibility problems that may occur with traditional control strategies. In terms of strategy execution and feedback verification, the optimized control strategy is sent to the execution equipment according to the triggering conditions, and the execution feedback data is monitored in real time. The optimized control strategy is dynamically adjusted based on the matching result of the execution feedback data and the preset feedback threshold, thus forming an adaptive optimization loop. This allows the entire centralized control automation system to continuously adjust and optimize itself according to the actual execution situation. Compared with traditional methods, instead of pre-setting fixed control strategies that cannot be flexibly changed according to actual performance, this method uses real-time feedback verification to ensure that the optimized control strategy remains effective under different power grid operation scenarios. This further enhances the ability of the centralized control automation system to cope with complex and ever-changing power grid operation environments and ensures the stable and efficient operation of the power grid. Attached Figure Description

[0013] Figure 1 This is a schematic diagram of the execution flow of the centralized control automation strategy optimization method based on fuzzy logic provided in the embodiments of the present invention.

[0014] Figure 2This is a schematic diagram of the hardware architecture of the centralized control automation strategy optimization system based on fuzzy logic provided in an embodiment of the present invention. Detailed Implementation

[0015] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 This is a flowchart illustrating a fuzzy logic-based centralized control automation strategy optimization method according to an embodiment of the present invention. The following is a detailed description of this fuzzy logic-based centralized control automation strategy optimization method.

[0016] Step S110: Collect real-time operating status data of power grid operating equipment within the target centralized control area. The real-time operating status data includes at least one power grid operating parameter and the parameter fluctuation range corresponding to the power grid operating parameter.

[0017] In this embodiment, the target centralized control area is taken as a medium-sized power supply area that includes multiple substations, transmission lines and power loads. In this medium-sized power supply area, there are various types of power grid operation equipment, such as transformers, circuit breakers, capacitor banks and so on.

[0018] For transformers, the power grid operating parameters that need to be collected include voltage, current, and oil temperature. The normal range for voltage may be set to 10kV-10.5kV, while the currently collected real-time voltage value is 10.3kV, and its fluctuation range may be between 10.2kV and 10.4kV. This is because during daily power transmission, the voltage will fluctuate within a certain range due to factors such as load changes and interference from adjacent lines.

[0019] Looking at the transmission lines, the collected parameters include line current and power factor. The normal range for line current is assumed to be 500A-600A, with the current real-time current value at 550A, fluctuating between 540A and 560A. The normal range for power factor is 0.9-0.95, with the real-time power factor at 0.93, fluctuating between 0.92 and 0.94. These fluctuations occur because of the different characteristics of the loads connected to the lines. For example, some industrial loads may be inductive, affecting the power factor, and the connection and disconnection of loads at different times can cause current fluctuations.

[0020] Regarding power load, the monitored parameter is load power, with a normal range set at 10MW-15MW. The currently collected real-time load power is 12MW, fluctuating between 11.5MW and 12.5MW. This is because different production activity periods, such as factory work hours, peak and off-peak hours in commercial areas, and peak (e.g., higher evening electricity consumption) and off-peak (e.g., lower daytime electricity consumption) for residents, all cause load power variations. By collecting various operating parameters of these power grid equipment and their corresponding fluctuation ranges, a comprehensive understanding of the power grid's operating status within the target centralized control area can be obtained.

[0021] Step S120: Based on the parameter fluctuation range, perform fuzzy membership processing on the real-time operating status data to generate a fuzzy rule set that matches the power grid operating parameters. The fuzzy rule set contains multiple fuzzy rules, and each fuzzy rule corresponds to a dynamic adjustment logic of a power grid operating parameter.

[0022] Taking the aforementioned medium-sized power supply area as an example, for the power grid operating parameter of transformer voltage, its key parameter type is voltage deviation. Assume that the fluctuation range of voltage deviation is divided into three fuzzy sub-intervals: a large negative deviation interval (below 10kV), a normal deviation interval (10kV-10.5kV), and a large positive deviation interval (above 10.5kV). Each fuzzy sub-interval corresponds to a membership function type; for example, the membership function type corresponding to the large negative deviation interval is a descending half-trapezoidal function.

[0023] When the acquired transformer voltage is 10.3kV, the membership weight of this voltage value within the normal deviation range is calculated to be 0.6 based on the membership function, indicating that there is a 60% probability that this voltage value is within the normal deviation range. Based on this membership weight and a preset rule template (e.g., if the load shows an increasing trend when the voltage is within the normal deviation range, the voltage should be kept stable; if the load shows a decreasing trend, the voltage can be appropriately reduced to reduce losses), a fuzzy rule subset regarding the key parameter type of transformer voltage is generated.

[0024] For the power factor parameter of transmission lines, its fluctuation range is divided into three fuzzy sub-intervals: low power factor interval (below 0.9), acceptable power factor interval (0.9-0.95), and high power factor interval (above 0.95). Assuming the current power factor is 0.93, the membership weight within the acceptable power factor interval is calculated to be 0.8. A corresponding fuzzy rule subset is generated based on a preset rule template (e.g., within the acceptable power factor interval, the need to adjust reactive power compensation equipment is determined by the line current magnitude).

[0025] Finally, the fuzzy rule subsets for various key parameter types, such as transformer voltage and transmission line power factor, are logically fused. For example, if the transformer voltage is in a range with a large positive deviation and the transmission line power factor is in a low power factor range, a comprehensive fuzzy rule is generated. The dynamic adjustment logic of this rule may be to first adjust the reactive power compensation device to improve the power factor, and then consider whether to adjust the transformer taps to reduce the voltage based on the adjusted situation, thereby generating the entire fuzzy rule set.

[0026] Step S130: Based on the fuzzy rule set, perform fuzzy logic optimization on the current control strategy of the target centralized control area to generate an optimized control strategy. The optimized control strategy includes multiple control instructions and the triggering conditions for each control instruction.

[0027] For example, in this medium-sized power supply area, the historical control strategy set of the target centralized control area includes multiple historical control commands and corresponding performance evaluation indicators for each historical control command. For instance, there was a historical control command that activated the cooling device when the transformer oil temperature exceeded 80°C, and its performance evaluation indicator was that the oil temperature dropped to below 75°C within 10 minutes, with a success rate of 90%.

[0028] The previously generated set of fuzzy rules is then matched with the set of historical control strategies. Assume that one fuzzy rule in the set relates to transformer oil temperature; when the oil temperature is in the higher range (75℃-85℃), the corresponding membership weight is 0.7. This fuzzy rule has a mapping relationship with the aforementioned historical control commands.

[0029] Candidate control commands that meet preset optimization conditions (execution performance evaluation indicators are higher than preset thresholds and triggering conditions match current power grid operating parameters) are selected from the historical control strategy set. If the preset threshold is set to an execution success rate of over 80%, then the above-mentioned control command regarding transformer oil temperature meets the conditions and becomes a candidate control command.

[0030] These candidate control commands are prioritized based on their execution performance evaluation metrics and the real-time matching degree of their triggering conditions. For example, consider a control command that adjusts the setting value of the line protection device when the transmission line current exceeds 600A, with an execution success rate of 85%. However, because the control command for the current transformer oil temperature has a higher real-time matching degree with the current grid operating parameters (transformer oil temperature close to 80℃), the transformer oil temperature control command has a higher priority, thus generating an initial optimized control strategy.

[0031] Considering the equipment response delay parameters in the target centralized control area, such as a possible 2-minute delay in starting the transformer cooling device, the execution timing of control commands in the initial optimized control strategy is modified. If the original strategy was to start the cooling device immediately when the oil temperature reaches 80℃, the modified strategy might send the start command when the oil temperature reaches 78℃ to compensate for the 2-minute delay, thus generating the final optimized control strategy. This optimized control strategy includes multiple control commands (such as transformer oil temperature control commands, transmission line current control commands, etc.) and the triggering conditions for each control command (such as transformer oil temperature 78℃, transmission line current 600A, etc.).

[0032] Step S140: Based on the triggering condition, the optimized control strategy is sent to the execution device within the target centralized control area, and the execution feedback data of the execution device on the control command is monitored.

[0033] In this embodiment, the triggering conditions in the optimized control strategy are analyzed within a medium-sized power supply area. For example, for the transformer oil temperature control command, the triggering condition is that the oil temperature reaches 78°C, and the corresponding power grid operating parameter threshold range is 78°C and above.

[0034] The system monitors the power grid operating parameters of the target centralized control area in real time. When the transformer oil temperature reaches 78°C, the corresponding control command is activated, which starts the transformer's cooling device. This activated control command is then encapsulated into an executable command format and sent to the target execution device (i.e., the transformer's cooling device) via the centralized control communication network.

[0035] The system receives the command response signal returned by the target execution device and records the timestamp and execution status identifier of the command response signal. Assuming the timestamp of the received response signal from the cooling device is 10:02:00 on August 1, 2023, and the execution status identifier is "successfully started," execution feedback data is generated based on this timestamp and execution status identifier. The command execution delay time is calculated; the time interval from when the oil temperature reaches 78℃ (assumed to be 10:00:00 on August 1, 2023) to receiving the response signal is 2 minutes, and the execution success rate is 100%. The above data constitutes the execution feedback data.

[0036] Similarly, for transmission line current control commands, when the transmission line current is detected to reach 600A, the control command to adjust the setting value of the line protection device is activated, and the command is sent, the response signal is received, and the execution feedback data is generated according to the above process.

[0037] Step S150: Based on the matching result of the execution feedback data and the preset feedback threshold, verify the effectiveness of the optimization control strategy, and dynamically adjust the optimization control strategy according to the verification result.

[0038] In this embodiment, it is assumed that the preset feedback thresholds include a 3-minute instruction execution delay time and a 90% execution success rate. The instruction execution delay time (e.g., 2 minutes for a transformer cooling device) and the execution success rate (e.g., 100%) are extracted from the execution feedback data to calculate the comprehensive execution efficiency index of the optimized control strategy.

[0039] For the control command for the transformer cooling device, the standard response delay time for this type of equipment (transformer) within the target centralized control area is assumed to be 2.5 minutes. Based on the difference between the command execution delay time and the standard response delay time (2 - 2.5 = -0.5 minutes), a delay deviation coefficient is calculated, assumed to be -0.2 using a specific formula. Based on the difference between the execution success rate and the preset success rate threshold (100% - 90% = 10%), a success rate compensation coefficient is calculated, assumed to be 0.1 using a formula. Based on the delay deviation coefficient and the success rate compensation coefficient, a local efficiency index for this control command is generated using a weighted summation formula, assumed to be 0.08. The local efficiency indices of all control commands (including transmission line current control commands, etc.) are normalized to obtain the comprehensive execution efficiency index, assumed to be 0.9.

[0040] Since the overall execution efficiency index of 0.9 is higher than the preset feedback threshold, the optimized control strategy is deemed to have met the effectiveness standard and no adjustment is required.

[0041] However, if the execution success rate is lower than a preset success rate threshold, for example, the execution success rate of a transmission line current control command is 80%, the fuzzy rule identifier corresponding to this control command is determined. Based on the fuzzy rule identifier, the target fuzzy rule and the associated power grid operation parameter type (such as transmission line current) are extracted from the fuzzy rule set. The current membership weight and fuzzy sub-interval partitioning parameters of the target fuzzy rule are obtained. Based on the difference between the execution success rate and the preset success rate threshold (80% - 90% = -10%), a membership weight adjustment amount is generated, assumed to be -0.1. Based on the membership weight adjustment amount, the membership weight of the target fuzzy rule is updated, or the boundary range of the fuzzy sub-interval is redefined.

[0042] Based on the adjusted fuzzy rules, candidate control instructions in the historical control strategy set are re-matched for conflict detection. If conflicting control instructions are detected, such as two control instructions targeting the same operation of the transmission line during the same time period but with contradictory logic, the highest priority control instruction is retained and the remaining conflicting instructions are removed based on the execution effect evaluation index. An updated set of candidate control instructions is generated based on the removal results, and the priorities and timing are re-sorted to generate an updated optimized control strategy, which replaces the original optimized control strategy.

[0043] The system continuously monitors the execution feedback data of the replaced optimized control strategy, collecting multiple batches of execution feedback data within a preset monitoring period (e.g., 1 hour). A sliding window average is calculated for the comprehensive execution efficiency index from these multiple batches of execution feedback data to obtain a dynamic efficiency evaluation value. If the dynamic efficiency evaluation value is higher than the preset feedback threshold for N consecutive monitoring periods (assuming N = 3), the updated optimized control strategy is deemed to have reached the stability standard. If not, the system triggers the fuzzy rule adjustment and optimized control strategy update process again based on the latest execution feedback data until the stability standard is reached. The current optimized control strategy is then marked as the final version, and a unique strategy identifier (including the target centralized control area code, generation timestamp, and version sequence number) is generated for it. The final version of the optimized control strategy is associated with the strategy identifier, encrypted, and transmitted to a designated storage partition in the centralized control strategy database. An index relationship is established between the strategy identifier and the historical control strategy set. The temporarily stored copy of the optimized control strategy in the centralized control communication network is deleted, and related computing resources are released. A strategy update completion notification (including the strategy identifier and effective time range) is sent to the monitoring terminal of the target centralized control area.

[0044] Based on the above steps, this embodiment of the application collects real-time operating status data of power grid equipment and performs fuzzy membership processing based on parameter fluctuation ranges to generate a fuzzy rule set. This effectively quantifies and analyzes the uncertainty of power grid operating parameters through fuzzy logic, generating dynamic adjustment logic that matches different operating parameters. In the control strategy optimization stage, the current control strategy is optimized using fuzzy logic based on the fuzzy rule set, generating an optimized control strategy containing multiple control commands and their triggering conditions. This achieves intelligent optimization of the control strategy for the centralized control area, comprehensively considering various operating parameters and their dynamic changes. This allows the optimized control strategy to better adapt to the complex operating conditions of the power grid, improving the accuracy and timeliness of the control strategy and effectively avoiding the lag and incompatibility problems that may occur with traditional control strategies. In terms of strategy execution and feedback verification, the optimized control strategy is sent to the execution equipment according to the triggering conditions, and the execution feedback data is monitored in real time. The optimized control strategy is dynamically adjusted based on the matching result of the execution feedback data and the preset feedback threshold, thus forming an adaptive optimization loop. This allows the entire centralized control automation system to continuously adjust and optimize itself according to the actual execution situation. Compared with traditional methods, instead of pre-setting fixed control strategies that cannot be flexibly changed according to actual performance, this method uses real-time feedback verification to ensure that the optimized control strategy remains effective under different power grid operation scenarios. This further enhances the ability of the centralized control automation system to cope with complex and ever-changing power grid operation environments and ensures the stable and efficient operation of the power grid.

[0045] In one possible implementation, step S120 includes:

[0046] Step S121: Extract the key parameter types from the power grid operation parameters. The key parameter types include voltage deviation, load fluctuation rate, and frequency offset.

[0047] Step S122: For each key parameter type, determine multiple fuzzy sub-intervals corresponding to the parameter fluctuation range, and each fuzzy sub-interval corresponds to a membership function type.

[0048] Step S123: According to the membership function type, assign a corresponding membership weight to each fuzzy sub-interval. The membership weight is used to quantify the distribution probability of the real-time running status data in the fuzzy sub-interval.

[0049] Step S124: Based on the membership weight and the preset rule template, generate a fuzzy rule subset corresponding to each key parameter type. The preset rule template contains the control logic mapping relationship under different power grid operation scenarios.

[0050] Step S125: Logically fuse the fuzzy rule subsets of each key parameter type to generate the fuzzy rule set.

[0051] In the previously mentioned medium-sized power supply area scenario, voltage deviation is a critical parameter. For example, if the normal operating voltage range of a transformer is set at 10kV - 10.5kV, but the actual voltage value collected is 10.3kV, this voltage deviation requires close monitoring. Load fluctuation is also a key parameter. Power load fluctuates significantly at different times, with a normal load power range of 10MW - 15MW. Actual load power fluctuation reflects load changes. Frequency offset is equally important; the standard frequency of the power grid is 50Hz, but a certain deviation may occur in actual operation.

[0052] Voltage deviation can be divided into four ranges: a large negative deviation range (below 10kV), a small negative deviation range (10kV-10.1kV), a normal range (10.1kV-10.4kV), a small positive deviation range (10.4kV-10.5kV), and a large positive deviation range (above 10.5kV). Each fuzzy sub-range corresponds to a membership function type. For example, the large negative deviation range corresponds to a descending half-trapezoidal function, the small negative deviation range to a left-triangular function, the normal range to a triangular function, the small positive deviation range to a right-triangular function, and the large positive deviation range to an ascending half-trapezoidal function. Based on these membership function types, a corresponding membership weight is assigned to each fuzzy sub-range. When the collected voltage is 10.3kV, the calculated membership weight of this voltage value in the normal range is 0.8, indicating that this voltage value has an 80% probability of being within the normal range. Based on this membership weight and the preset rule template (e.g., when the voltage is in the normal range and the load is stable, maintain the current voltage control strategy; if the load is rising and the voltage is close to the upper limit of the normal range, the reactive power compensation equipment can be adjusted appropriately to stabilize the voltage), a fuzzy rule subset corresponding to the key parameter type of voltage deviation is generated.

[0053] For load volatility, the fuzzy sub-intervals corresponding to its parameter fluctuation range are determined. These can be divided into low volatility intervals (fluctuation range within ±1MW), medium volatility intervals (fluctuation range between 1MW and 3MW), and high volatility intervals (fluctuation range greater than 3MW). The membership function types corresponding to each fuzzy sub-interval are left trapezoidal function, triangular function, and right trapezoidal function, respectively. Assuming the current load power fluctuation is 2MW, the calculated membership weight in the medium volatility interval is 0.6. Based on the membership weight and a preset rule template (e.g., when in the medium volatility interval and the frequency is stable, the backup power supply connection can be adjusted according to load forecast; if the frequency shifts and the load volatility is in the medium volatility interval, frequency adjustment is prioritized before considering load adjustment), a fuzzy rule subset corresponding to the load volatility is generated.

[0054] For frequency offset, it is assumed to be divided into four ranges: a large negative offset range (below 49.8Hz), a small negative offset range (49.8Hz - 49.9Hz), a normal range (49.9Hz - 50.1Hz), a small positive offset range (50.1Hz - 50.2Hz), and a large positive offset range (above 50.2Hz). Each range corresponds to a different membership function type. If the collected frequency is 50.05Hz, the membership weight in the normal range is calculated to be 0.9. Based on the membership weight and a preset rule template (e.g., no adjustment is needed if the voltage and load are stable in the normal range; if the load shows a changing trend in the small positive or small negative offset range, the generator's output power is adjusted), a fuzzy rule subset corresponding to the frequency offset is generated.

[0055] Finally, the fuzzy rule subsets for various key parameter types, such as voltage deviation, load fluctuation rate, and frequency offset, are logically fused. For example, when the voltage is in the small positive deviation range, the load fluctuation rate is in the medium fluctuation range, and the frequency is in the normal range, the fused fuzzy rule might first observe for a period of time. If the load fluctuation rate shows an increasing trend, the reactive power compensation equipment is adjusted; if the frequency shows a small offset, the generator output power is fine-tuned. This generates the entire fuzzy rule set, which covers the comprehensive adjustment logic under various power grid operating parameter states, providing a basis for subsequent control strategy optimization.

[0056] In one possible implementation, step S130 includes:

[0057] Step S131: Obtain the historical control strategy set of the target centralized control area. The historical control strategy set includes multiple historical control instructions and the execution effect evaluation index corresponding to each historical control instruction.

[0058] In the aforementioned medium-sized power supply areas, the historical control strategy set includes numerous historical control commands and corresponding performance evaluation indicators for each command. For example, one historical control command addresses transformer oil overheating: when the transformer oil temperature exceeds 80°C, the cooling device is activated. The performance evaluation indicator for this command is a 90% probability that the oil temperature will drop below 75°C within 10 minutes, reflecting the effectiveness of this control command in historical execution. Another historical control command concerns transmission line overload protection: when the transmission line current exceeds 600A, the setting value of the line protection device is adjusted. Its performance evaluation indicator is an 85% probability that the overload risk will decrease to a safe range within 15 minutes after adjustment.

[0059] Step S132: Associate and match the fuzzy rule set with the historical control strategy set to determine the mapping relationship between each fuzzy rule in the fuzzy rule set and the historical control instruction.

[0060] Taking transformer oil temperature as an example, the fuzzy rule set contains fuzzy rules regarding transformer oil temperature in different ranges (such as 75℃-80℃, 80℃-85℃, etc.). These fuzzy rules are mapped to historical control commands for activating cooling devices when transformer oil temperature is too high. For transmission line current, the fuzzy rules regarding different fluctuation ranges of transmission line current (such as 550A-600A, 600A-650A, etc.) are mapped to historical control commands for transmission line overload protection. This mapping is established based on the correlation between power grid operating parameters and control commands.

[0061] Step S133: Based on the mapping relationship, candidate control instructions that meet preset optimization conditions are selected from the historical control strategy set. The preset optimization conditions include that the execution effect evaluation index is higher than a preset threshold and the triggering condition matches the current power grid operating parameters.

[0062] Assuming the preset threshold is set at 80% or higher for the performance evaluation index, the historical control command for activating the cooling device when the transformer oil temperature is too high has a performance evaluation index of 90%, which is higher than the preset threshold. Furthermore, if the current transformer oil temperature is close to 80°C, its triggering condition matches the current power grid operating parameters, therefore this command becomes a candidate control command. Similarly, the historical control command for transmission line overload protection has a performance evaluation index of 85%, which is higher than the preset threshold. If the current transmission line current is close to 600A, its triggering condition matches the current power grid operating parameters, also making it a candidate control command.

[0063] Step S134: Prioritize the candidate control instructions to generate an initial optimized control strategy. The priority ranking is based on the real-time matching degree of the execution effect evaluation index of the candidate control instructions and the triggering conditions.

[0064] For example, the evaluation index for the execution effect of the command to activate the cooling device when the transformer oil temperature is too high is 90%. If the current transformer oil temperature is 79℃, the real-time matching degree of its triggering condition is relatively high. The evaluation index for the execution effect of the command to activate the transmission line overload protection is 85%. If the current transmission line current is 590A, the real-time matching degree of its triggering condition is relatively low. Based on this, the command to activate the cooling device when the transformer oil temperature is too high has a higher priority than the command to activate the transmission line overload protection, thus generating an initial optimized control strategy.

[0065] Step S135: Based on the device response delay parameters of the target centralized control area, the execution timing of the control commands in the initial optimized control strategy is corrected to generate the optimized control strategy.

[0066] For example, if there is a 2-minute delay in the activation of the transformer's cooling system, the initial optimized control strategy might have set the system to activate immediately when the oil temperature reaches 80°C. Considering the 2-minute delay, the revised execution sequence would be to send the activation command when the oil temperature reaches 78°C. Similarly, for transmission line overload protection commands, if there is a 1-minute delay in adjusting the line protection device's setting value, the initial setting might have set it to adjust immediately when the current reaches 600A. The revised timing of these control commands results in an optimized control strategy that better adapts to the characteristics of the power grid's operating equipment, improving control accuracy and timeliness, and ensuring the stable operation of the power grid.

[0067] In one possible implementation, step S140 includes:

[0068] Step S141: Analyze the triggering conditions in the optimized control strategy and determine the threshold range of power grid operating parameters corresponding to each control command.

[0069] For example, in this medium-sized power supply area, for transformer oil temperature control commands, if the trigger condition in the optimized control strategy is set to activate the cooling device when the transformer oil temperature reaches 78℃, then the corresponding power grid operating parameter threshold range is 78℃ and above. For transmission line current control commands, if the setting is set to adjust the line protection device setting value when the transmission line current reaches 599A, then the power grid operating parameter threshold range is 599A and above.

[0070] Step S142: Monitor the power grid operation parameters of the target centralized control area in real time. When the power grid operation parameters are detected to fall within the threshold range of the power grid operation parameters, activate the corresponding control command.

[0071] For example, monitoring devices such as sensors installed on transformers and transmission lines continuously acquire power grid operating parameters. When the transformer oil temperature is detected to rise to 78°C, this value falls within the power grid operating parameter threshold range corresponding to the transformer oil temperature control command, thereby activating the corresponding control command, namely, the command to start the transformer cooling device. Similarly, when the transmission line current is detected to reach 599A, the command to adjust the setting value of the transmission line protection device is activated.

[0072] Step S143: The activated control command is encapsulated into a device executable command format and sent to the target execution device through the centralized control communication network.

[0073] For example, control commands for transformer cooling devices are encapsulated in a format recognizable by the device. For instance, oil temperature control commands are converted into specific digital signal codes and then sent to the transformer cooling device via a centralized control communication network. A similar process is performed on control commands for transmission line protection devices, converting current adjustment commands into a format recognizable by the protection device and sending them to it via a communication network.

[0074] Step S144: Receive the instruction response signal returned by the target execution device, and record the timestamp and execution status identifier of the instruction response signal.

[0075] For example, when a transformer cooling device receives a control command, it returns a command response signal. Assuming the timestamp of this received response signal is 10:02:00 on August 1, 2023, the execution status is marked as successful startup. For a transmission line protection device, upon receiving its returned command response signal, it records the corresponding timestamp, such as 10:10:00 on August 1, 2023, and the execution status is marked as successful adjustment.

[0076] Step S145: Based on the timestamp and the execution status identifier, generate the execution feedback data, which includes the instruction execution delay time and execution success rate.

[0077] For example, for control commands to transformer cooling devices, the execution delay time is calculated. The time interval from when the oil temperature reaches 78℃ (assuming it's 10:00:00 on August 1, 2023) to receiving the response signal is 2 minutes, with a 100% execution success rate. This data constitutes the execution feedback data. For control commands to transmission line protection devices, the calculated execution delay time is 1 minute (assuming the current reaches 599A at 10:09:00 on August 1, 2023), with a 100% execution success rate. This is also included in the execution feedback data.

[0078] In one possible implementation, step S150 includes:

[0079] Step S151: Extract the instruction execution delay time and execution success rate from the execution feedback data, and calculate the comprehensive execution efficiency index of the optimized control strategy.

[0080] Step S151 includes:

[0081] Step S1511: Obtain the standard response delay time of different equipment types within the target centralized control area. The equipment types include transformers, circuit breakers, and reactive power compensation devices.

[0082] Step S1512: For each control command, calculate the delay deviation coefficient based on the difference between the command execution delay time and the standard response delay time of the corresponding device type.

[0083] Step S1513: Calculate the success rate compensation coefficient based on the difference between the execution success rate and the preset success rate threshold.

[0084] Step S1514: Based on the delay deviation coefficient and the success rate compensation coefficient, generate the local efficiency index of the control command using a weighted summation formula.

[0085] Step S1515: Normalize the local efficiency indices of all control instructions to obtain the comprehensive execution efficiency index.

[0086] For example, the standard response delay time is assumed to be 2.5 minutes for transformers, 0.5 minutes for circuit breakers (although circuit breaker control commands are not involved in this scenario, they are listed for the sake of completeness of the calculation process), and 1 minute for reactive power compensation devices (again, not involved, but listed in full).

[0087] Assuming the instruction execution delay is 2 minutes, the difference from the standard response delay of 2.5 minutes is -0.5 minutes. Using a specific formula (assuming the formula is: Delay Deviation Coefficient = (Instruction Execution Delay - Standard Response Delay) / Standard Response Delay), the delay deviation coefficient is calculated to be -0.2. Based on the difference between the execution success rate and the preset success rate threshold, a success rate compensation coefficient is calculated. Assuming the preset success rate threshold is 90% and the execution success rate is 100%, the difference is 10%. Using another formula (assuming the formula is: Success Rate Compensation Coefficient = (Execution Success Rate - Preset Success Rate Threshold) / 100), the success rate compensation coefficient is calculated to be 0.1. Based on the delay deviation coefficient and the success rate compensation coefficient, a weighted summation formula (assuming the formula is: Local Efficiency Index = 0.6 × Success Rate Compensation Coefficient + 0.4 × Delay Deviation Coefficient) is used to generate the local efficiency index of this control instruction, which is calculated to be 0.08.

[0088] For control commands of transmission line protection devices, the same steps are followed for calculation. The command execution delay time is 1 minute, the standard response delay time is assumed to be 1 minute (if a more accurate standard exists), the difference is 0 minutes, and the delay deviation coefficient is 0. The execution success rate is 100%, the preset success rate threshold is 90%, and the success rate compensation coefficient is 0.1. The local efficiency index is calculated to be 0.06 using a weighted summation formula (assuming the weighting coefficients are the same).

[0089] Assuming there are only these two control commands, the sum of the total local efficiency indices is 0.08 + 0.06 = 0.14. The normalized local efficiency index of the transformer cooling device control command is 0.08 / 0.14≈0.57, and the normalized local efficiency index of the transmission line protection device control command is 0.06 / 0.14≈0.43. The comprehensive execution efficiency index is 0.57×100% +0.43×100% = 100% (this is a simplified example; actual calculations may be more complex).

[0090] Step S152: Compare the comprehensive execution efficiency index with the preset feedback threshold. If the comprehensive execution efficiency index is lower than the preset feedback threshold, it is determined that the optimization control strategy has not reached the effectiveness standard.

[0091] Assuming the preset feedback threshold is 90%, since the calculated comprehensive execution efficiency index is 100%, which is higher than the preset feedback threshold, the optimization control strategy is deemed to have reached the effectiveness standard and no adjustment is required.

[0092] Step S153: According to the control instruction that the execution success rate is lower than the preset success rate threshold, backtrack to the corresponding fuzzy rule and adjust the membership weight or fuzzy sub-interval division method in the fuzzy rule.

[0093] If the execution success rate falls below a preset success rate threshold, for example, in another scenario where the execution success rate of the transmission line protection device is 80%, the process begins by backtracking to the corresponding fuzzy rule based on the control command whose execution success rate is below the preset success rate threshold. The fuzzy rule identifier corresponding to the transmission line protection device control command is determined, and the target fuzzy rule and the associated power grid operating parameter type (i.e., transmission line current) are extracted from the fuzzy rule set. The current membership weight and fuzzy sub-interval partitioning parameters of the target fuzzy rule are obtained. Based on the difference between the execution success rate and the preset success rate threshold (80% - 90% = -10%), a membership weight adjustment is generated, assuming it is -0.1 obtained through a specific algorithm.

[0094] Based on the membership weight adjustment, update the membership weight of the target fuzzy rule, or redivide the boundary range of the fuzzy subintervals. For example, if the original membership weight is 0.8, it will be updated to 0.7; or if the original fuzzy subinterval division is 550A - 600A, 600A - 650A, etc., it will be redivided into 540A - 590A, 590A - 640A, etc.

[0095] Step S154: Based on the adjusted fuzzy rules, regenerate the updated optimized control strategy and replace the original optimized control strategy with the updated optimized control strategy.

[0096] For example, candidate control instructions in the historical control strategy set are re-matched, and conflict detection is performed. If conflicting control instructions exist, such as two control instructions both targeting the operation of the transmission line at the same time but with contradictory logic, the highest priority control instruction is retained and the remaining conflicting instructions are removed based on the execution effect evaluation index. An updated set of candidate control instructions is generated based on the removal results, and the priorities are re-sorted and the timing is corrected. The corrected set of candidate control instructions is encapsulated into an updated optimized control strategy, and the storage location of the original optimized control strategy is overwritten through the centralized control communication network.

[0097] Step S155: Continuously monitor the execution feedback data of the replaced optimized control strategy until the comprehensive execution efficiency index reaches the preset feedback threshold.

[0098] For example, within a preset monitoring period (e.g., 1 hour), multiple batches of execution feedback data are collected. The overall execution efficiency index from these multiple batches of feedback data is averaged using a sliding window to obtain a dynamic efficiency evaluation value. If the dynamic efficiency evaluation value is higher than the preset feedback threshold for N consecutive monitoring periods (assuming N = 3), the updated optimized control strategy is deemed to have reached the stability standard. If it does not, the fuzzy rule adjustment and optimized control strategy update process is triggered again based on the latest execution feedback data until the stability standard is reached. For example, in subsequent monitoring, if the dynamic efficiency evaluation value is 85% in the first monitoring period, failing to reach the preset feedback threshold of 90%, the fuzzy rules and optimized control strategy are adjusted until the dynamic efficiency evaluation value is higher than 90% for three consecutive monitoring periods. The current optimized control strategy is then marked as the final version, and a unique strategy identifier (including the target centralized control area code, generation timestamp, and version serial number) is generated for it. The final version of the optimized control policy is associated with the policy identifier, encrypted, and transmitted to the designated storage partition of the centralized control policy database. An index relationship is established between the policy identifier and the historical control policy set. The copy of the optimized control policy temporarily stored in the centralized control communication network is deleted, and the relevant computing resources are released. A policy update completion notification (including the policy identifier and effective time range) is sent to the monitoring terminal of the target centralized control area.

[0099] In one possible implementation, step S153 includes:

[0100] Step S1531: Determine the fuzzy rule identifier corresponding to the control instruction whose execution success rate is lower than the preset success rate threshold.

[0101] Suppose that during the power grid control process in a medium-sized power supply area, the success rate of executing control commands for adjusting transmission line protection devices is found to be lower than a preset success rate threshold. In the entire power grid control strategy system, each control command is associated with a specific fuzzy rule and has a unique identifier to distinguish different fuzzy rules. For control commands for adjusting transmission line protection devices, the corresponding fuzzy rule identifier is found by querying the mapping table between control commands and fuzzy rules.

[0102] Step S1532: Based on the fuzzy rule identifier, extract the target fuzzy rule and the power grid operation parameter type associated with the target fuzzy rule from the fuzzy rule set.

[0103] For example, from a large set of fuzzy rules, the target fuzzy rule can be accurately located based on its identifier. This target fuzzy rule is associated with the power grid operating parameter type of transmission line current, and it describes the adjustment logic corresponding to the transmission line current in different ranges. For example, it may include logic such as adopting a certain adjustment method for protection devices when the transmission line current is in the 550A-600A range, and adopting a different adjustment method when the current is in the 600A-650A range.

[0104] Step S1533: Obtain the current membership weight and fuzzy sub-interval division parameters of the target fuzzy rule, and generate the membership weight adjustment amount based on the difference between the execution success rate and the preset success rate threshold.

[0105] Assume the preset success rate threshold for adjusting the transmission line protection device is 90%, while the actual success rate is 80%, with a difference of -10%. In the target fuzzy rule, the membership weight corresponding to the transmission line current range of 550A-600A is currently 0.8, and the fuzzy sub-interval division parameter is the boundary value of this interval, 550A and 600A. Through a specific algorithm (this algorithm is preset based on historical power grid operation data, equipment characteristics, and control strategy requirements), the membership weight adjustment amount is generated based on the -10% difference, assumed to be -0.1.

[0106] Step S1534: Update the membership weight of the target fuzzy rule according to the membership weight adjustment amount, or redefine the boundary range of the fuzzy sub-interval.

[0107] In this example, based on the calculation results, the membership weight of the 550A - 600A interval is updated from 0.8 to 0.7. Alternatively, if the boundary range of the fuzzy sub-interval is redefined, the original 550A - 600A interval may be adjusted to 540A - 590A to adapt to the new control requirements. The above adjustments are based on the fact that the actual control effect of the transmission line current is not ideal, and the purpose is to make the fuzzy rules more consistent with the actual operation of the power grid.

[0108] Step S1535: Add the updated target fuzzy rule back to the fuzzy rule set and delete the original target fuzzy rule.

[0109] For example, the adjusted target fuzzy rules are reintegrated into the fuzzy rule set to ensure the completeness and accuracy of the set. Simultaneously, the original target fuzzy rules are deleted to avoid confusion during subsequent optimization control strategy generation. In this way, the fuzzy rule set is updated, providing a more reasonable basis for regenerating the optimization control strategy.

[0110] In one possible implementation, step S154 includes:

[0111] Step S1541: Based on the adjusted fuzzy rule set, re-match the candidate control instructions in the historical control strategy set.

[0112] In power grid control within medium-sized power supply areas, the historical control strategy set contains numerous control commands for different power grid operating conditions, each with corresponding performance evaluation indicators. The adjusted fuzzy rule set alters the judgment logic and weight allocation for power grid operating parameters, necessitating a re-matching of candidate control commands within the historical control strategy set. For example, for transformer oil temperature control commands and transmission line protection device adjustment commands, their matching degree with power grid operating parameters is reassessed based on the new fuzzy rules to determine which commands meet the new optimization conditions and become candidate control commands.

[0113] Step S1542: Conflict detection is performed on the re-matched candidate control commands. The conflict detection includes detecting logical contradictions among multiple control commands received by the same device at the same time period.

[0114] In power grid operation, the same equipment (such as a transmission line) may be affected by multiple control commands at the same time. For example, one candidate control command might be to increase reactive power compensation to stabilize voltage under a specific transmission line current, while another candidate control command might be to adjust the setting value of the line protection device under the same current condition. However, the execution of these two commands may interfere with each other, resulting in logical contradictions. By analyzing the target, operating conditions, and operating results of each candidate control command in detail, such logical contradictions can be detected.

[0115] Step S1543: If a conflict control command is detected, then based on the execution effect evaluation index of the conflict control command, retain the control command with the highest priority and eliminate the remaining conflict commands.

[0116] Suppose that for a transmission line within a certain current range, there are two conflicting control commands. One is to adjust the setting value of the line protection device, with an effectiveness evaluation index of 85% for reducing the line overload risk to a safe range within 30 minutes. The other is to change the input level of the reactive power compensation equipment, with an effectiveness evaluation index of 80% for controlling the line voltage fluctuation within ±5% within 30 minutes. Since the effectiveness evaluation index for adjusting the setting value of the line protection device is higher, this command is retained, while the command to change the input level of the reactive power compensation equipment is discarded.

[0117] Step S1544: Generate an updated set of candidate control instructions based on the elimination results, and re-sort the priority and correct the timing.

[0118] After conflict detection and instruction elimination, an updated set of candidate control instructions is obtained. These candidate control instructions are then re-prioritized, based on the performance evaluation index and the real-time matching degree of the triggering conditions. For example, for a transformer oil temperature control instruction, if its performance evaluation index is a 90% probability of reducing the oil temperature to a safe range within 10 minutes, and the current transformer oil temperature is close to the triggering condition value, then its priority is relatively high. Simultaneously, considering equipment response delay parameters, the execution timing of control instructions is corrected. For instance, if there is a 2-minute delay in starting the transformer cooling device, the original setting was to start at 80℃; after correction, the start instruction might be sent when the oil temperature reaches 78℃.

[0119] Step S1545: The modified candidate control instruction set is encapsulated into the updated optimized control strategy, and the storage location of the original optimized control strategy is overwritten through the centralized control communication network.

[0120] For example, the candidate control command set processed through the above steps is encapsulated in a specific format to form an updated optimized control strategy that can be recognized and executed by the power grid execution equipment. Then, this new optimized control strategy is sent to the corresponding storage location through the centralized control communication network, overwriting the original optimized control strategy, so that the new optimized strategy can be adopted in subsequent power grid operation control to improve the efficiency and stability of power grid operation.

[0121] In one possible implementation, step S155 includes:

[0122] Step S1551: Within a preset monitoring period, collect multiple batches of execution feedback data of the replaced optimized control strategy.

[0123] For example, in the power grid control of a medium-sized power supply area, the preset monitoring cycle is set to 1 hour. Within this 1 hour, execution feedback data of the optimized control strategy after replacement is collected every 10 minutes. For example, for transformer oil temperature control commands, the command execution delay time and execution success rate are recorded each time data is collected. If, within a certain 10-minute period, the transformer oil temperature reaches the trigger condition (e.g., 78°C), the cooling device starts after a 2-minute delay, and the execution success rate is 100%, this constitutes a set of execution feedback data. Similarly, for transmission line protection device adjustment commands, when the transmission line current reaches the trigger condition (e.g., 599A), the execution delay time (assumed to be 1 minute) and execution success rate (assumed to be 100%) of the protection device setting value adjustment command are recorded. By collecting these data multiple times within the preset 1-hour monitoring cycle, multiple batches of execution feedback data are obtained.

[0124] Step S1552: Calculate the sliding window average value of the comprehensive execution efficiency index in multiple batches of execution feedback data to obtain a dynamic efficiency evaluation value. If the dynamic efficiency evaluation value is higher than the preset feedback threshold in N consecutive monitoring periods, it is determined that the updated optimization control strategy has reached the stability standard.

[0125] Assuming a sliding window size of 3 batches of data is used, for every 3 consecutive batches of execution feedback data, the local efficiency index of each control command (such as transformer oil temperature control command and transmission line protection device adjustment command) is calculated. Then, following the previous calculation method (e.g., calculating the delay deviation coefficient based on the difference between the command execution delay time and the standard response delay time of the corresponding equipment type, calculating the success rate compensation coefficient based on the difference between the execution success rate and the preset success rate threshold, generating the local efficiency index of the control command through a weighted summation formula, and finally normalizing the local efficiency indices of all control commands to obtain the comprehensive execution efficiency index), the comprehensive execution efficiency index of these 3 batches of data is calculated. The average of these comprehensive execution efficiency indices is taken as the dynamic efficiency evaluation value. If the dynamic efficiency evaluation value is higher than the preset feedback threshold for N consecutive monitoring periods (assuming N = 3), the updated optimized control strategy is deemed to have reached the stability standard. For example, if the preset feedback threshold is set to 90%, and the calculated dynamic efficiency evaluation values ​​are 92%, 93%, and 95% respectively within three consecutive 1-hour monitoring cycles, all of which are higher than 90%, then the updated optimized control strategy is determined to have reached the stability standard.

[0126] Step S1553: If the dynamic efficiency evaluation value does not reach the preset feedback threshold, the fuzzy rule adjustment and optimization control strategy update process is triggered again based on the latest execution feedback data. When the stability standard is reached, the current optimization control strategy is marked as the final version, and a unique strategy identifier is generated for the final version of the optimization control strategy. The unique strategy identifier includes the target centralized control area code, the generation timestamp, and the version serial number.

[0127] Suppose that within a certain monitoring period, the dynamic efficiency assessment value is 85%, which is lower than the preset feedback threshold of 90%. In this case, analysis is performed based on the latest collected execution feedback data. For example, if it is found that the execution success rate of the transmission line protection device adjustment command has decreased in recent batches of data, then the fuzzy rule corresponding to this control command is adjusted. Following the previously described method, the fuzzy rule identifier corresponding to the control command with an execution success rate lower than the preset success rate threshold is determined. The target fuzzy rule and the associated power grid operating parameter type (transmission line current) are extracted from the fuzzy rule set. The current membership weight and fuzzy sub-interval partitioning parameters of the target fuzzy rule are obtained. Based on the difference between the execution success rate and the preset success rate threshold, a membership weight adjustment amount is generated. Then, the membership weight is updated or the boundary range of the fuzzy sub-interval is redefined based on the adjustment amount. Subsequently, an updated optimized control strategy is regenerated based on the adjusted fuzzy rules. This includes rematching candidate control instructions in the historical control strategy set, performing conflict detection (such as detecting the logical contradictions of multiple control instructions received by the same device at the same time; if there is a conflict, the highest priority control instruction is retained and the remaining conflicting instructions are removed based on the performance evaluation index), generating an updated set of candidate control instructions based on the removal results, re-prioritizing and timing the instructions, and finally encapsulating the corrected set of candidate control instructions into a new optimized control strategy, which is then overridden by the centralized control communication network.

[0128] When the stability standard is reached after multiple adjustments, the current optimized control strategy is marked as the final version, and a unique strategy identifier is generated for the final version of the optimized control strategy. This unique strategy identifier includes the target centralized control area code (for example, the specific code for a medium-sized power supply area is "MG-001"), the generation timestamp (such as 12:00:00 on August 1, 2023, indicating the time when the optimized control strategy was finally determined), and the version serial number (assumed to be "V3.0", indicating that this is the third version after multiple adjustments).

[0129] Step S1554: Associate the final version of the optimized control strategy with the strategy identifier, encrypt it, and transmit it to a designated storage partition of the centralized control strategy database. Establish an index relationship between the strategy identifier and the historical control strategy set in the centralized control strategy database so that version comparison can be performed during subsequent strategy retrieval.

[0130] For example, the optimized control strategy and strategy identifier are encrypted using a specific encryption algorithm (such as AES) to ensure data security. The encrypted data is then transmitted to a dedicated storage partition in the centralized control strategy database for optimized control strategies in medium-sized power supply areas. An index relationship is established in the centralized control strategy database between strategy identifiers and historical control strategy sets to facilitate version comparison during subsequent strategy retrieval. This way, when it is necessary to query historical control strategies or compare different versions of optimized control strategies, relevant information can be quickly and accurately retrieved based on the index relationship.

[0131] Step S1555: Delete the copy of the optimized control strategy temporarily stored in the centralized control communication network and release the relevant computing resources.

[0132] During previous optimization control strategy updates, copies of the optimization control strategy may be stored in a temporary storage area of ​​the centralized control communication network to facilitate data transmission and processing. Once the final version of the optimization control strategy has been successfully stored in the centralized control strategy database and the index relationship has been established, these temporarily stored copies can be deleted, releasing the computing resources they occupy (such as network bandwidth and storage space), thereby improving the resource utilization rate of the entire power grid control system.

[0133] Step S1556: Send a policy update completion notification to the monitoring terminal of the target centralized control area. The policy update completion notification includes the policy identifier and the effective time range.

[0134] For example, a notification can be sent to the monitoring terminal in a medium-sized power supply area, stating that "the optimized control strategy update is complete, the strategy identifier is MG-001-20230801120000-V3.0, and the effective time is from 12:00:00 on August 1, 2023." After receiving the notification, relevant personnel at the monitoring terminal can understand the update status of the optimized control strategy and can query the detailed strategy content in the centralized control strategy database based on the strategy identifier, so as to monitor and manage the power grid operation.

[0135] In one possible implementation, after step S150, the method further includes:

[0136] Step S160: Based on the final version of the optimized control strategy and the execution feedback data, perform AI model training operations. Specific steps include:

[0137] Step S161: Generate a training dataset corresponding to the final version of the optimized control strategy. The training dataset includes the historical sequence of power grid operating parameters of the target centralized control area, the control command execution sequence of the optimized control strategy, and the comprehensive execution efficiency index sequence of the execution feedback data, wherein the historical sequence of power grid operating parameters and the control command execution sequence are aligned by timestamps.

[0138] In this embodiment, within a medium-sized power supply area, the historical sequence of power grid operating parameters for the target centralized control area includes the changes in relevant parameters of various devices over time. For example, for transformers, the historical sequence records voltage, oil temperature, and current values ​​at different points in time; for transmission lines, it records parameters such as current and power factor. The time span of the aforementioned historical sequence of power grid operating parameters may be several weeks or months, providing a sufficiently long period to reflect the power grid operating status under different conditions.

[0139] The optimized control strategy's control command execution sequence records the execution status of each control command at the corresponding time point. For example, the control command to activate the cooling device when the transformer oil temperature reaches a specific value is recorded at its execution time; similarly, the control command to adjust the protection device's setting value when the transmission line current reaches a set value is also recorded at its execution time. Furthermore, the historical sequence of power grid operating parameters and the control command execution sequence are aligned with timestamps, meaning that the sampling time of each power grid operating parameter can accurately correspond to the execution time of the corresponding control command.

[0140] The overall execution efficiency index sequence of the execution feedback data is a time sequence of the efficiency evaluation indexes calculated beforehand for each control command. For example, at a certain moment, the overall execution efficiency index after executing the transformer oil temperature control command is 90%, and the overall execution efficiency index after executing the transmission line protection device adjustment command is 85%. These indices are arranged in chronological order to form the overall execution efficiency index sequence. By combining these three parts, a training dataset corresponding to the final version of the optimized control strategy is generated.

[0141] Step S162: Based on the training dataset, extract the key parameter fluctuation patterns in the historical sequence of the power grid operation parameters, and perform spatiotemporal correlation matching between the key parameter fluctuation patterns and the command triggering conditions in the control command execution sequence to generate a parameter-command mapping feature vector. The parameter-command mapping feature vector includes the triggering time of each control command, the fluctuation amplitude and duration of the associated power grid operation parameters.

[0142] For example, for transformers, a key parameter fluctuation pattern might be an upward trend in oil temperature over a period of time or a fluctuation in voltage amplitude during a specific period. Taking oil temperature as an example, if the oil temperature gradually rises from 70℃ to 80℃ over a certain period, this is a key parameter fluctuation pattern. When the oil temperature reaches 78℃, a control command to start the cooling device is triggered. This fluctuation pattern is then correlated and matched with the command triggering conditions. Specifically, the parameter-command mapping feature vector includes the triggering time of each control command (e.g., starting the transformer cooling device at 10:00:00 on August 1, 2023), the fluctuation amplitude of the associated grid operating parameters (the fluctuation amplitude of 8℃ as the oil temperature rises from 70℃ to 78℃), and the duration (2 hours from the start of the rise to the triggering of the control command). The same operation is performed for the current parameters of transmission lines and their corresponding protection device adjustment commands, thereby constructing a complete parameter-command mapping feature vector.

[0143] Step S163: The parameter-instruction mapping feature vector is labeled and bound to the comprehensive execution efficiency index sequence to generate a supervised model training sample set, wherein the parameter-instruction mapping feature vector is used as the input feature and the comprehensive execution efficiency index is used as the prediction label.

[0144] In this process, the parameter-command mapping feature vector is used as the input feature, and the comprehensive execution efficiency index is used as the prediction label. For example, an input feature is the parameter-command mapping feature vector related to the transformer oil temperature triggering the cooling device under a specific fluctuation mode, and its corresponding prediction label is the comprehensive execution efficiency index of 90% at that time. In this way, each set of input features and its corresponding prediction label constitutes a sample in the supervised model training sample set, and many such samples are combined to form a complete supervised model training sample set.

[0145] Step S164: Train the prediction model based on the supervised model training sample set to obtain the prediction model.

[0146] In one possible implementation, step S164 includes:

[0147] Step S1641: Configure the initial training parameters of the prediction model. The prediction model includes a combination structure of a multi-layer temporal attention network and a fully connected decision layer. The temporal attention network is used to capture the temporal dependencies in the parameter-instruction mapping feature vector. The fully connected decision layer is used to output the correlation matrix between the triggering conditions of the prediction control instruction and the estimated execution efficiency.

[0148] For example, temporal attention networks are used to capture temporal dependencies in parameter-command mapping feature vectors. For instance, when dealing with multiple fluctuations in transformer oil temperature and the corresponding control command execution, temporal attention networks can focus on the sequence of oil temperature fluctuations and the time interval between them and control command execution. The fully connected decision layer outputs a correlation matrix between the predicted triggering conditions of control commands and the estimated execution efficiency. For example, it can predict the probability of a control command being triggered under specific grid operating parameters and the estimated execution efficiency that might be achieved after execution.

[0149] Step S1642: Divide the supervised model training sample set into a training subset and a validation subset according to a preset ratio, and perform multiple rounds of iterative training on the prediction model through the training subset. In each iteration, the backpropagation algorithm is used to update the weight parameters of the temporal attention network and the bias coefficient of the fully connected decision layer.

[0150] For example, the samples can be divided into an 80%:20% subset, with 80% serving as the training subset and 20% as the validation subset. The prediction model is then trained iteratively using the training subset. In each iteration, the backpropagation algorithm is used to update the weight parameters of the temporal attention network and the bias coefficients of the fully connected decision layer. In each iteration, the model adjusts its parameters based on the samples in the training subset to make the prediction results closer to the actual overall performance efficiency.

[0151] Step S1643: After each round of iterative training, the current loss function value and prediction accuracy index of the prediction model are calculated using the validation subset. If the current loss function value does not converge or the prediction accuracy index is lower than the preset model threshold, the number of layers of the temporal attention network or the activation function type of the fully connected decision layer is adjusted, and iterative training is restarted.

[0152] The loss function value reflects the degree of difference between the prediction model's prediction and the true label, while the prediction accuracy metric represents the proportion of correctly predicted samples. If the current loss function value has not converged (i.e., the loss function value has not stabilized at a small value with increasing iterations) or the prediction accuracy metric is lower than the preset model threshold (e.g., the preset model threshold is set to 85%, while the actual calculated prediction accuracy metric is 80%), then the number of layers in the temporal attention network or the activation function type of the fully connected decision layer is adjusted, and iterative training is restarted. For example, if the current temporal attention network has 3 layers, it may be increased to 4 layers; if the activation function type of the fully connected decision layer is the Sigmoid function, it may be adjusted to the ReLU function, and then the iterative training process is restarted.

[0153] Step S1644: When the prediction model reaches the convergence state and the prediction accuracy index is higher than the preset model threshold, the network parameters of the prediction model are frozen, and the prediction model is deployed to the real-time inference interface of the centralized control strategy optimization engine. The real-time inference interface is used to receive the current power grid operating parameter sequence and output a set of predictive control commands.

[0154] When the prediction model reaches convergence (the loss function value stabilizes at a small value) and the prediction accuracy exceeds a preset model threshold (e.g., 90%), the network parameters of the prediction model are frozen, and the prediction model is deployed to the real-time inference interface of the centralized control strategy optimization engine. This real-time inference interface is used to receive the current power grid operating parameter sequence and output a set of predictive control commands. For example, when the current power grid operating parameter sequence such as the transformer's oil temperature, voltage, and current is received in real time, the prediction model can output a set of predictive control commands, such as whether the cooling device needs to be started or whether the voltage needs to be adjusted, based on previously learned patterns.

[0155] Step S1645: Based on the predictive control instruction set, pre-screen the fuzzy sub-interval partitioning method and membership weight in the fuzzy rule set, remove fuzzy rules associated with inefficient instructions in the predictive control instruction set, and generate a simplified fuzzy rule candidate pool.

[0156] Fuzzy rules in the fuzzy rule set that are associated with inefficient instructions (such as instructions with low execution efficiency or those rarely triggered) in the predictive control instruction set are removed, resulting in a simplified fuzzy rule candidate pool. For example, if a fuzzy rule is always associated with transformer oil temperature control instructions with low execution efficiency, then this fuzzy rule will be removed.

[0157] Step S1646: Perform cross-cycle correlation analysis between the simplified fuzzy rule candidate pool and the historical control strategy set to identify target fuzzy rules that are strongly correlated with efficient control instructions in multiple historical cycles, and add dynamic priority coefficients to the target fuzzy rules.

[0158] Identify target fuzzy rules that are strongly correlated with efficient control commands across multiple historical periods (such as different time periods over the past few months). For example, if a fuzzy rule is closely related to the efficient execution of transmission line protection device adjustment commands in multiple historical periods, then this fuzzy rule is a target fuzzy rule. Add dynamic priority coefficients to these target fuzzy rules, for example, increasing their priority coefficient from 1 to 1.5.

[0159] Step S1647: Based on the dynamic priority coefficient, the rule triggering order in the fuzzy rule set is reordered, and the reordered fuzzy rule set is integrated with the prediction model into the generation process of the next round of optimized control strategy, so that the set of predicted control instructions output by the prediction model participates in the matching and screening of candidate control instructions first.

[0160] For example, when generating the next round of optimized control strategies, the set of predictive control commands output by the predictive model is given priority in the matching and selection of candidate control commands. In this way, through AI model training operations, the generation process of the fuzzy rule set and the optimized control strategy is continuously optimized, thereby improving the accuracy and efficiency of power grid control.

[0161] Figure 2 The illustration shows exemplary hardware and software components of a fuzzy logic-based centralized control automation strategy optimization system 100 that can implement the ideas of this application, according to some embodiments of this application. For example, a processor 120 can be used in the fuzzy logic-based centralized control automation strategy optimization system 100 and to perform the functions in this application.

[0162] The fuzzy logic-based centralized control automation strategy optimization system 100 can be a general-purpose server or a special-purpose server; both can be used to implement the fuzzy logic-based centralized control automation strategy optimization method of this application. Although only one server is shown in this application, for convenience, the functions described in this application can be implemented in a distributed manner on multiple similar platforms to balance the load.

[0163] For example, the fuzzy logic-based centralized control automation strategy optimization system 100 may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and various forms of storage media 140, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the fuzzy logic-based centralized control automation strategy optimization system 100 may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The methods of this application can be implemented according to these program instructions. The fuzzy logic-based centralized control automation strategy optimization system 100 also includes an input / output (I / O) interface 150 between the computer and other input / output devices.

[0164] For ease of explanation, only one processor is described in the fuzzy logic-based centralized control automation strategy optimization system 100. However, it should be noted that the fuzzy logic-based centralized control automation strategy optimization system 100 of this application may also include multiple processors. Therefore, the steps executed by one processor as described in this application may also be executed jointly by multiple processors or individually. For example, if the processor of the fuzzy logic-based centralized control automation strategy optimization system 100 executes steps A and B, it should be understood that steps A and B may also be executed jointly by two different processors or individually by one processor. For example, the first processor executes step A, the second processor executes step B, or the first processor and the second processor jointly execute steps A and B.

[0165] Furthermore, this embodiment of the invention also provides a readable storage medium, wherein computer-executable instructions are preset in the readable storage medium, and when the processor executes the computer-executable instructions, the above-mentioned centralized control automation strategy optimization method based on fuzzy logic is implemented.

[0166] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for optimizing centralized control automation strategies based on fuzzy logic, characterized in that, The method includes: Collect real-time operating status data of power grid operating equipment within the target centralized control area. The real-time operating status data includes at least one power grid operating parameter and the parameter fluctuation range corresponding to the power grid operating parameter. Based on the fluctuation range of the parameters, the real-time operating status data is processed by fuzzy membership to generate a set of fuzzy rules that match the power grid operating parameters. The set of fuzzy rules contains multiple fuzzy rules, and each fuzzy rule corresponds to a dynamic adjustment logic of the power grid operating parameters. Based on the set of fuzzy rules, the current control strategy of the target centralized control area is optimized by fuzzy logic to generate an optimized control strategy. The optimized control strategy includes multiple control instructions and the triggering conditions of each control instruction. Based on the triggering conditions, the optimized control strategy is sent to the execution devices within the target centralized control area, and the execution feedback data of the execution devices in response to the control commands is monitored. Based on the matching results of the execution feedback data and the preset feedback threshold, the effectiveness of the optimized control strategy is verified, and the optimized control strategy is dynamically adjusted according to the verification results. After the step of sending a policy update completion notification to the monitoring terminal in the target centralized control area, the method further includes: Based on the final version of the optimized control strategy and the execution feedback data, the AI ​​model training operation is performed. The specific steps include: Generate a training dataset corresponding to the final version of the optimized control strategy. The training dataset includes a historical sequence of power grid operating parameters of the target centralized control area, a sequence of control command execution of the optimized control strategy, and a sequence of comprehensive execution efficiency indicators of the execution feedback data. The historical sequence of power grid operating parameters and the sequence of control command execution are aligned by timestamps. Based on the training dataset, key parameter fluctuation patterns are extracted from the historical sequence of power grid operating parameters, and the key parameter fluctuation patterns are spatiotemporally correlated and matched with the command triggering conditions in the control command execution sequence to generate a parameter-command mapping feature vector. The parameter-command mapping feature vector includes the triggering time of each control command, the fluctuation amplitude and duration of the associated power grid operating parameters. The parameter-instruction mapping feature vector is labeled and bound to the comprehensive execution efficiency index sequence to generate a supervised model training sample set, wherein the parameter-instruction mapping feature vector is used as the input feature and the comprehensive execution efficiency index is used as the prediction label; The prediction model is trained based on the supervised model training sample set. The step of training the prediction model based on the supervised model training sample set includes: Configure the initial training parameters of the prediction model. The prediction model includes a combination structure of a multi-layer temporal attention network and a fully connected decision layer. The multi-layer temporal attention network is used to capture the temporal dependencies in the parameter-instruction mapping feature vector. The fully connected decision layer is used to output the correlation matrix between the triggering conditions of the prediction control instruction and the estimated execution efficiency. The supervised model training sample set is divided into a training subset and a validation subset according to a preset ratio, and the prediction model is trained through multiple rounds of iteration using the training subset. In each iteration, the backpropagation algorithm is used to update the weight parameters of the multi-layer temporal attention network and the bias coefficient of the fully connected decision layer. After each round of iterative training, the current loss function value and prediction accuracy index of the prediction model are calculated using the validation subset. If the current loss function value does not converge or the prediction accuracy index is lower than the preset model threshold, the number of layers of the multilayer temporal attention network or the activation function type of the fully connected decision layer is adjusted, and iterative training is restarted. When the prediction model reaches convergence and the prediction accuracy index is higher than the preset model threshold, the network parameters of the prediction model are frozen, and the prediction model is deployed to the real-time inference interface of the centralized control strategy optimization engine. The real-time inference interface is used to receive the current power grid operating parameter sequence and output a set of predictive control commands. Based on the predictive control instruction set, the fuzzy sub-interval division method and membership weight in the fuzzy rule set are pre-screened to remove fuzzy rules associated with inefficient instructions in the predictive control instruction set, and a simplified fuzzy rule candidate pool is generated. The simplified fuzzy rule candidate pool is subjected to cross-cycle correlation analysis with the historical control strategy set to identify target fuzzy rules that are strongly correlated with efficient control instructions in multiple historical cycles, and a dynamic priority coefficient is added to the target fuzzy rules. Based on the dynamic priority coefficient, the triggering order of the rules in the fuzzy rule set is reordered, and the reordered fuzzy rule set is integrated with the prediction model into the generation process of the next round of optimized control strategy, so that the set of predicted control instructions output by the prediction model participates in the matching and screening of candidate control instructions first.

2. The method for optimizing centralized control automation strategies based on fuzzy logic according to claim 1, characterized in that, The step of performing fuzzy membership processing on the real-time operating status data based on the parameter fluctuation range to generate a set of fuzzy rules matching the power grid operating parameters includes: Extract the key parameter types from the power grid operating parameters. The key parameter types include voltage deviation, load fluctuation rate, and frequency offset. For each key parameter type, multiple fuzzy sub-intervals corresponding to the parameter fluctuation range are determined, and each fuzzy sub-interval corresponds to a membership function type; According to the membership function type, a corresponding membership weight is assigned to each fuzzy sub-interval, and the membership weight is used to quantify the distribution probability of the real-time running status data in the fuzzy sub-interval; Based on the membership weight and the preset rule template, a fuzzy rule subset corresponding to each key parameter type is generated. The preset rule template contains the control logic mapping relationship under different power grid operation scenarios. The fuzzy rule set is generated by logically fusing the fuzzy rule subsets of each key parameter type.

3. The centralized control automation strategy optimization method based on fuzzy logic according to claim 1, characterized in that, The step of performing fuzzy logic optimization on the current control strategy of the target centralized control area based on the fuzzy rule set to generate an optimized control strategy includes: Obtain the set of historical control strategies for the target centralized control area. The set of historical control strategies includes multiple historical control instructions and the execution effect evaluation index corresponding to each historical control instruction. The fuzzy rule set is associated and matched with the historical control strategy set to determine the mapping relationship between each fuzzy rule in the fuzzy rule set and the historical control command. Based on the mapping relationship, candidate control instructions that meet preset optimization conditions are selected from the set of historical control strategies. The preset optimization conditions include that the performance evaluation index is higher than a preset threshold and the triggering condition matches the current power grid operating parameters. The candidate control instructions are prioritized to generate an initial optimized control strategy. The priority ranking is based on the performance evaluation index of the candidate control instructions and the real-time matching degree of the triggering conditions. Based on the device response delay parameters of the target centralized control area, the execution timing of control commands in the initial optimized control strategy is corrected to generate the optimized control strategy.

4. The method for optimizing centralized control automation strategies based on fuzzy logic according to claim 3, characterized in that, The step of sending the optimized control strategy to the execution devices within the target centralized control area according to the triggering condition, and monitoring the execution feedback data of the execution devices in response to the control commands, includes: Analyze the triggering conditions in the optimized control strategy to determine the threshold range of power grid operating parameters corresponding to each control command; The power grid operation parameters of the target centralized control area are monitored in real time. When the power grid operation parameters fall into the threshold range of the power grid operation parameters, the corresponding control command is activated. The activated control commands are encapsulated into a device-executable command format and sent to the target execution device via the centralized control communication network. Receive the instruction response signal returned by the target execution device, and record the timestamp and execution status identifier of the instruction response signal; Based on the timestamp and the execution status identifier, the execution feedback data is generated, which includes the instruction execution delay time and the execution success rate.

5. The method for optimizing centralized control automation strategies based on fuzzy logic according to claim 4, characterized in that, The process of verifying the effectiveness of the optimized control strategy based on the matching results of the execution feedback data and the preset feedback threshold, and dynamically adjusting the optimized control strategy according to the verification results, includes: Extract the instruction execution delay time and execution success rate from the execution feedback data, and calculate the comprehensive execution efficiency index of the optimized control strategy; The overall execution efficiency index is compared with the preset feedback threshold. If the overall execution efficiency index is lower than the preset feedback threshold, the optimization control strategy is determined to have failed to meet the effectiveness standard. According to the control instruction that the execution success rate is lower than the preset success rate threshold, backtrack to the corresponding fuzzy rule and adjust the membership weight or fuzzy sub-interval division method in the fuzzy rule; Based on the adjusted fuzzy rules, a new optimized control strategy is generated and the new optimized control strategy replaces the original optimized control strategy. Continuously monitor the execution feedback data of the optimized control strategy after replacement until the comprehensive execution efficiency index reaches the preset feedback threshold; The step of extracting the instruction execution latency and execution success rate from the execution feedback data and calculating the comprehensive execution efficiency index of the optimized control strategy includes: Obtain the standard response delay time of different equipment types within the target centralized control area, where the equipment types include transformers, circuit breakers, and reactive power compensation devices; For each control command, a delay deviation coefficient is calculated based on the difference between the command execution delay time and the standard response delay time of the corresponding device type; A success rate compensation coefficient is calculated based on the difference between the execution success rate and the preset success rate threshold. Based on the delay deviation coefficient and the success rate compensation coefficient, the local efficiency index of the control command is generated by a weighted summation formula. The local efficiency indices of all control commands are normalized to obtain the comprehensive execution efficiency index.

6. The method for optimizing centralized control automation strategies based on fuzzy logic according to claim 5, characterized in that, The step of backtracking to the corresponding fuzzy rule based on the control instruction that the execution success rate is lower than a preset success rate threshold, and adjusting the membership weight or fuzzy sub-interval division method in the fuzzy rule, includes: Determine the fuzzy rule identifier corresponding to the control instruction whose execution success rate is lower than a preset success rate threshold; Based on the fuzzy rule identifier, extract the target fuzzy rule and the power grid operation parameter type associated with the target fuzzy rule from the fuzzy rule set; Obtain the current membership weight and fuzzy sub-interval division parameters of the target fuzzy rule, and generate a membership weight adjustment amount based on the difference between the execution success rate and the preset success rate threshold; Based on the membership weight adjustment amount, update the membership weight of the target fuzzy rule, or redefine the boundary range of the fuzzy sub-interval; The updated target fuzzy rule is added back to the fuzzy rule set, and the original target fuzzy rule is deleted.

7. The method for optimizing centralized control automation strategies based on fuzzy logic according to claim 5, characterized in that, The step of regenerating an updated optimized control strategy based on the adjusted fuzzy rules and replacing the original optimized control strategy with the updated optimized control strategy includes: Based on the adjusted fuzzy rule set, candidate control instructions in the historical control strategy set are re-matched; Conflict detection is performed on the rematched candidate control commands, and the conflict detection includes detecting logical contradictions among multiple control commands received by the same device at the same time period; If a conflict control instruction is detected, the highest priority control instruction is retained and the remaining conflict instructions are removed based on the performance evaluation index of the conflict control instruction. An updated set of candidate control instructions is generated based on the elimination results, and the priority is reordered and the timing is corrected. The revised set of candidate control instructions is encapsulated into the updated optimized control strategy, and the storage location of the original optimized control strategy is overwritten through the centralized control communication network.

8. The method for optimizing centralized control automation strategies based on fuzzy logic according to claim 7, characterized in that, The continuous monitoring of the execution feedback data of the optimized control strategy after replacement until the comprehensive execution efficiency index reaches the preset feedback threshold includes: Within a preset monitoring period, collect multiple batches of execution feedback data for the replaced optimized control strategy; The dynamic efficiency evaluation value is obtained by calculating the average value of the comprehensive execution efficiency index in multiple batches of execution feedback data through a sliding window. If the dynamic efficiency evaluation value is higher than the preset feedback threshold in N consecutive monitoring periods, it is determined that the updated optimization control strategy has reached the stability standard. If the dynamic efficiency evaluation value does not reach the preset feedback threshold, the fuzzy rule adjustment and optimization control strategy update process is triggered again based on the latest execution feedback data. When the stability standard is reached, the current optimization control strategy is marked as the final version, and a unique strategy identifier is generated for the final version of the optimization control strategy. The unique strategy identifier includes the target centralized control area code, the generation timestamp, and the version serial number. The final version of the optimized control strategy is associated with the strategy identifier, encrypted, and transmitted to a designated storage partition of the centralized control strategy database. An index relationship between the strategy identifier and the historical control strategy set is established in the centralized control strategy database so that version comparison can be performed during subsequent strategy retrieval. Delete the copy of the optimized control strategy temporarily stored in the centralized control communication network and release the related computing resources; A policy update completion notification is sent to the monitoring terminal of the target centralized control area. The policy update completion notification includes the policy identifier and the effective time range.

9. A centralized control automation strategy optimization system based on fuzzy logic, characterized in that, The fuzzy logic-based centralized control automation strategy optimization system includes a processor and a memory, the memory and the processor being connected. The memory is used to store programs, instructions or code, and the processor is used to execute the programs, instructions or code in the memory to implement the fuzzy logic-based centralized control automation strategy optimization method according to any one of claims 1-8.

Images