A smart control system and method applied to smart grid equipment

Abstract

This invention discloses an intelligent control system and method for smart grid equipment, relating to the field of power grid equipment control technology. The invention collects environmental data from various monitoring stations in a target area, generating a priority sequence of affected power grid equipment and environmental change events. Based on the directionality of environmental changes and the location of power grid equipment, it analyzes the theoretical adjustment angle of the orientation of each power grid device, collects the operating status of the power grid equipment before and after adjustment, and analyzes the comprehensive command quality score. It analyzes data from several adjustments of the same power grid equipment to identify benefit inflection points, and updates the anomaly detection boundary line by combining the power grid equipment's operating time and the comprehensive command quality score. It collects data from power grid equipment before and after adjustment in real time, calculates the offset distance and direction from the anomaly detection boundary line, and analyzes the anomaly type by combining the synchronization of adjacent power grid equipment, outputting graded handling commands. This improves the accuracy of analysis and increases the anomaly detection rate.

Description

Technical Field

[0001] This invention relates to the field of power grid equipment control technology, specifically an intelligent control system and method applied to smart grid equipment. Background Technology

[0002] Traditional solutions, when evaluating the effects of adjustments, cannot effectively isolate the interference of natural environmental fluctuations on power generation. They often mistakenly attribute power increases or decreases caused by external environmental changes to equipment orientation adjustments, leading to erroneous benefit assessments. When multiple devices are simultaneously affected by environmental changes, the lack of a prioritization mechanism based on spatial distance and impact intensity forces all devices to be processed uniformly or in a random order, reducing overall response efficiency. Furthermore, existing anomaly detection methods generally use fixed thresholds or uniform models, failing to distinguish between environmental factors and individual equipment malfunctions, resulting in numerous false alarms or missed alarms, making it difficult for maintenance personnel to quickly locate the truly problematic equipment.

[0003] Therefore, this invention discloses an intelligent control system and method for smart grid equipment to solve the above problems. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent control system and method for smart grid equipment to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an intelligent control method for smart grid equipment, the method comprising the following steps: Step S100: Collect environmental data from each monitoring station in the target area and analyze environmental changes to generate a priority sequence of affected power grid equipment and environmental change events; Step S200: Based on the directionality of environmental changes and the location of power grid equipment, analyze the theoretical adjustment angle of the orientation of each power grid device, collect the operating status of the power grid equipment before and after the adjustment, and analyze the comprehensive command quality score; Step S300: Analyze the adjustment data of the same power grid equipment several times, identify the benefit inflection point, and update the anomaly identification boundary line by combining the power grid equipment operating time and comprehensive command quality score; Step S400: Collect data of power grid equipment before and after adjustment in real time, calculate the offset distance and offset direction of the anomaly identification boundary line, combine the synchronization analysis of adjacent power grid equipment to determine the anomaly type, and output graded handling instructions.

[0006] Step S100 includes the following: S101: Collect environmental data from each monitoring station within the target area; the environmental data includes, but is not limited to, wind speed, light intensity, temperature, and humidity; simultaneously collect the coordinates, equipment type, and rated power of each power grid device at each monitoring station; For each monitoring station, calculate the changes in wind speed, light intensity, and temperature and humidity. The wind speed change is equal to the wind speed at the current moment minus the wind speed at a certain time ago; the light intensity change is equal to the light intensity at the current moment minus the light intensity at a certain time ago; the temperature and humidity change index is equal to the temperature change multiplied by the humidity change index; the humidity change index is equal to - minus the humidity coefficient multiplied by the humidity at the current moment. The normalized wind speed change, light intensity change, and temperature and humidity change index are combined into a three-dimensional change vector, and the magnitude of the three-dimensional change vector is calculated as the environmental change intensity of the monitoring station. If the environmental change intensity of the monitoring station is greater than the first threshold, the corresponding monitoring station is marked as the change source station. S102: For each source site of change, calculate the radius of influence based on the intensity of environmental change, whereby the radius of influence is equal to the intensity of environmental change at the source site of change divided by the influence coefficient; for each power grid device, calculate the Euclidean distance between it and each source site of change; if the Euclidean distance is less than or equal to the radius of influence of the corresponding source site of change, then it is determined that the corresponding power grid device is affected by the source site of change. For all source sites identified as affecting the corresponding power grid equipment, a first contribution factor is calculated for each source site. The first contribution factor is equal to the intensity of environmental change at the source site divided by the sum of the Euclidean distance and distance coefficient between the power grid equipment and the source site. A second contribution factor is calculated, which is equal to a preset constant plus an environmental proportional characteristic value. The environmental proportional characteristic value is equal to the sensitivity adjustment coefficient multiplied by the change ratio. The change ratio is equal to the ratio of the absolute value of the change in illumination to the absolute value of the change in wind speed at the source site. The sum of the products of the first contribution factor and the second contribution factor for all source sites affected by the power grid equipment is recorded as the comprehensive impact weight of the power grid equipment. All power grid equipment is sorted in descending order of comprehensive impact weight to generate an impact priority sequence; S103: For any location within the target area, the predicted vector of environmental change at that location is equal to the sum of the vectors of all change source stations divided by the square of their distances to the location, and then divided by the sum of the reciprocals of the squares of the distances from all change source stations to the location. For each power grid device, calculate the environmental change prediction vector at the location of the power grid device based on its coordinates, and calculate the magnitude of the environmental change prediction vector; calculate the average magnitude of the environmental change prediction vectors at all locations of power grid devices as the intensity of environmental change across the entire field. If the intensity of the overall environmental change is less than the second threshold, no subsequent control action is triggered; if the intensity of the overall environmental change is greater than or equal to the second threshold, an environmental change event is generated; the environmental change event includes: trigger time, affected priority sequence, and dominant change direction of each power grid device; wherein, the dominant change direction of each power grid device is taken from the direction corresponding to the component with the largest absolute value in the environmental change prediction vector of the location of the power grid device; This invention calculates changes in three dimensions—wind speed, light intensity, and temperature and humidity—and uses this information to identify the true "source sites of change," avoiding frequent false triggers caused by noise or instantaneous fluctuations from single-point sensors and improving the rationality of control initiation. By calculating the average magnitude of the predicted environmental change vectors at all power grid equipment locations, the overall environmental change intensity is obtained. When this intensity is below a threshold, the control process is skipped directly, further avoiding meaningless adjustments to power grid equipment when the overall environment is stable, thus saving the lifespan of actuators and communication resources.

[0007] Step S200 includes the following: S201: Determine the target orientation angle of the power grid equipment based on the type of the dominant change component; The theoretical adjustment angle is analyzed. The theoretical adjustment angle is equal to the difference between the target orientation angle and the current orientation angle. If the absolute value of the theoretical adjustment angle is less than the theoretical adjustment angle threshold, no adjustment command is generated. S202: Collect the average power of power grid equipment within the time window before adjustment, the average power within the time window after adjustment, and the rated power; Select several power grid devices of the same type as the current power grid devices, whose distance does not exceed the preset distance threshold, and whose orientation has not been adjusted, as a reference power grid device group; The apparent gain of the reference power grid equipment group and the apparent gain of the current power grid equipment are analyzed separately. The apparent gain of the reference power grid equipment group is equal to the ratio of the difference in average power of each power grid equipment in the reference power grid equipment group within the time window before and after adjustment to the average power after the rated power. The apparent gain of the current power grid equipment is equal to the difference in average power of the current power grid equipment within the time window before and after adjustment divided by the rated power of the current power grid equipment. The difference between the apparent gain of the current power grid equipment and the apparent gain of the reference power grid equipment group is recorded as the net benefit; S203: Obtain the actual adjustment angle and analyze the execution deviation score; analyze the benefit score based on the net benefit; The weighted sum of the execution deviation score and the benefit score is recorded as the comprehensive instruction quality score. This invention calculates net benefits by introducing the apparent gain of a reference power grid equipment group, eliminating the interference of natural environmental fluctuations on power changes. This ensures that the evaluation results truly reflect the "benefits brought by the adjustment command itself," improving the accuracy of command quality evaluation. The execution deviation score reflects the reliability of mechanical transmission and communication, while the benefit score reflects the effectiveness of the control strategy. The weighted sum of these two scores yields the command quality score, providing a reliable weighting basis for subsequent anomaly detection boundary adjustments. Different target orientation calculation methods are used based on the dominant change component, making the control logic physically interpretable and avoiding the problem of a uniform formula being inapplicable in all scenarios.

[0008] Step S300 includes the following: S301: Obtain the historical adjustment record table of the same power grid equipment. The historical adjustment record table contains the most recent adjustment events sorted by time. Each adjustment event records the actual adjustment angle and net benefit. Construct a scatter plot with the actual adjustment angle as the horizontal axis and the net benefit as the vertical axis. A sliding window segmented fitting method is adopted: starting from the minimum actual adjustment angle, a number of angles are added each time as a window. The least squares method is used to fit a straight line for the data points in each window. The form of the straight line is that the net benefit is equal to the slope multiplied by the actual adjustment angle plus the intercept. The sum of squared fitting residuals for each window is calculated. When the slope change of two consecutive windows exceeds the slope change threshold, the starting angle of the corresponding window is marked as the benefit inflection point. The fitted straight line of all data is used as the angle benefit response model of the power grid equipment; the angle benefit response model is in piecewise linear form or single linear form, and the inflection point identifier is output. S302: Analyze the mean and standard deviation of the historical net benefit residuals; the historical net benefit residuals are equal to the historical net benefit minus the net benefit predicted by the angle benefit response model; the net benefit predicted by the angle benefit response model is equal to the net benefit value corresponding to the actual adjustment angle in the angle benefit response model; The initial upper boundary offset is set to be equal to the mean of the historical net benefit residuals plus the standard deviation of the first net benefit residual; the standard deviation of the first net benefit residual is equal to the product of the first net benefit coefficient and the standard deviation of the historical net benefit residuals; the initial lower boundary offset is set to be equal to the mean of the historical net benefit residuals minus the standard deviation of the second net benefit residual; the standard deviation of the second net benefit residual is equal to the product of the second net benefit coefficient and the standard deviation of the historical net benefit residuals; wherein the first net benefit coefficient is less than the second net benefit coefficient; The lower boundary offset is adjusted according to the operating time of the power grid equipment: the operating time of the power grid equipment is in the form of a preset duration, and the adjusted lower boundary offset is equal to the initial lower boundary offset plus the first corrected lower boundary offset; the first corrected lower boundary offset is equal to the initial lower boundary offset multiplied by the operating time coefficient multiplied by the operating time of the power grid equipment divided by the total number of duration segments. The lower boundary offset is further adjusted based on the average of the most recent comprehensive instruction quality scores: the final lower boundary offset equals the adjusted lower boundary offset plus the second corrected lower boundary offset; the second corrected lower boundary offset equals the adjusted lower boundary offset multiplied by the instruction quality score coefficient multiplied by the difference in the average instruction quality scores; the difference in the average instruction quality scores equals one minus the average of the most recent comprehensive instruction quality scores. Generate anomaly detection boundary lines: For any adjusted angle, the lower limit of the anomaly detection boundary line is equal to the net benefit value predicted by the angle benefit response model plus the final lower boundary offset, and the upper limit of the anomaly detection boundary line is equal to the net benefit value predicted by the angle benefit response model plus the initial upper boundary offset.

[0009] This invention constructs a scatter plot based on historical adjustment data of the same power grid equipment and fits an angle benefit response model. This captures the unique mechanical characteristics, installation environment, and aging degree of each power grid device, avoiding systematic biases introduced by a unified theoretical model. The initial lower boundary is more lenient than the upper boundary, reflecting a higher sensitivity to "abnormal efficiency decline" than "abnormal efficiency increase." Simultaneously, the lower boundary is dynamically adjusted based on the power grid equipment's operating time and command quality score. This allows for a more lenient threshold when using older power grid equipment or command quality, reducing false alarms, while a stricter threshold is used when using younger power grid equipment or command quality, improving the detection rate. Both the response model and boundary parameters can be updated with new data, enabling the system to adaptively learn and track the slow degradation of power grid equipment performance.

[0010] Step S400 includes the following: S401: Obtain the actual adjustment angle, actual net benefit, angle benefit response model, and corresponding anomaly detection boundary line of the power grid equipment in this adjustment; Calculate the predicted net benefit based on the angle benefit response model, and calculate the real-time net benefit residual. Analyze the offset distance and offset direction; The analysis of offset distance specifically includes: if the real-time net benefit residual is greater than the upper limit of the anomaly detection boundary line, then the offset distance is equal to the real-time net benefit residual minus the upper limit of the anomaly detection boundary line; if the real-time net benefit residual is less than the lower limit of the anomaly detection boundary line, then the offset distance is equal to the lower limit of the anomaly detection boundary line minus the real-time net benefit residual; if the real-time net benefit residual is greater than or equal to the lower limit of the anomaly detection boundary line and less than or equal to the upper limit of the anomaly detection boundary line, then it is recorded as no offset. The analysis of the offset direction specifically includes: when the real-time net benefit residual is greater than the upper limit of the anomaly detection boundary line, it is a positive offset; when the real-time net benefit residual is less than the lower limit of the anomaly detection boundary line, it is a negative offset. S402: Obtain the abnormality identifier and offset direction of the power grid equipment, and at the same time select all power grid equipment of the same type that are less than the adjacent distance threshold from the power grid equipment, and analyze the abnormality of the adjacent power grid equipment. Analyze the proportion of anomalies occurring in adjacent power grid equipment, and the proportion of anomalies occurring in the same direction as the corresponding power grid equipment; Determine the type of anomaly based on the proportion of anomalies occurring in adjacent power grid equipment: If the proportion of abnormalities in adjacent power grid equipment is greater than the first proportion threshold and the offset direction is the same, it is determined to be an environmental abnormality. If the proportion of abnormalities among adjacent power grid equipment is less than the second proportion threshold, it is determined to be an individual abnormality of the power grid equipment. If the proportion of abnormalities among adjacent power grid equipment is greater than or equal to the second proportion threshold and less than or equal to the first proportion threshold, then the offset distance is further compared: if the offset distance of the power grid equipment is greater than several times the average offset distance of the adjacent power grid equipment, it is determined to be an individual abnormality of the power grid equipment; otherwise, it is determined to be an environmental abnormality. For cases determined to be individual power grid equipment anomalies, possible causes can be further subdivided according to the direction of the offset: negative offset corresponds to transmission mechanism jamming, sensor drift, or dust accumulation; positive offset corresponds to anomalies in the reference power grid equipment group. S403: Generate tiered handling instructions based on anomaly type, possible causes, and offset distance. If the anomaly type is environmental, no action will be taken on the power grid equipment, and an environmental anomaly alarm will be sent to the operation and maintenance center. If the anomaly type is an individual anomaly of the power grid equipment, it will be handled according to the following steps based on the offset distance: when the current offset distance is less than the first offset distance threshold, a self-test command will be sent; when the current offset distance is greater than or equal to the first offset distance threshold but less than the second offset distance threshold, a cleaning prompt will be sent and recorded in the predictive maintenance list; when the current offset distance is greater than or equal to the second offset distance threshold, a shutdown and maintenance command will be sent along with possible causes. The data from this anomaly determination will be written into the anomaly event log. The data includes the power grid equipment identifier, time, offset distance, determination result, actual adjustment angle, and net benefit.

[0011] This invention effectively distinguishes between "environmental anomalies" and "individual power grid equipment anomalies" by calculating the proportion of anomalies occurring in adjacent power grid equipment and the proportion of anomalies occurring in the same direction. This avoids unnecessary power grid equipment maintenance due to environmental events and prevents delays in handling power grid equipment failures by attributing them to the environment. By combining the results of offset direction and synchronicity analysis, possible causes can be identified, providing valuable diagnostic clues for on-site maintenance personnel.

[0012] An intelligent control system for smart grid equipment is provided, wherein the system is implemented using the aforementioned intelligent control method for smart grid equipment, and the system includes an environmental change analysis module, an instruction quality analysis module, an anomaly discrimination boundary analysis module, and a real-time anomaly analysis module. The environmental change analysis module is used to collect environmental data from each monitoring station in the target area and analyze environmental changes, generating a priority sequence of affected power grid equipment and environmental change events. The instruction quality analysis module is used to analyze the theoretical adjustment angle of the orientation of each power grid device based on the direction of environmental changes and the location of power grid equipment, collect the operating status of power grid equipment before and after adjustment, and analyze the comprehensive instruction quality score. The anomaly detection boundary analysis module is used to analyze the adjustment data of the same power grid equipment several times, identify the benefit inflection point, and update the anomaly detection boundary line by combining the power grid equipment running time and comprehensive instruction quality score. The real-time anomaly analysis module is used to collect data of power grid equipment before and after adjustment in real time, calculate the offset distance and offset direction of the anomaly identification boundary line, combine the synchronization analysis of adjacent power grid equipment to determine the anomaly type, and output graded handling instructions.

[0013] The environmental change analysis module includes a change source analysis unit, an impact analysis unit, and a change event analysis unit. The change source analysis unit is used to collect environmental data from each monitoring station within the target area; simultaneously, it collects the coordinates, equipment type, and rated power of each power grid device at each monitoring station; for each monitoring station, it calculates the wind speed change, light intensity change, and temperature and humidity change index; and determines the change source station based on the wind speed change, light intensity change, and temperature and humidity change index. The impact analysis unit is used to calculate the impact radius for each source site based on the intensity of environmental change, determine the impact of the source site on the power grid equipment based on the Euclidean distance between the power grid equipment and each source site, analyze the comprehensive impact weight of the power grid equipment, and sort all power grid equipment in descending order of comprehensive impact weight to generate an impact priority sequence. The change event analysis unit is used to calculate the environmental change prediction vector of the location of each power grid device based on its coordinates, and to calculate the magnitude of the environmental change prediction vector; to calculate the average value of the magnitude of the environmental change prediction vectors at all locations of power grid devices as the intensity of environmental change across the entire field; and to generate an environmental change event based on the intensity of environmental change across the entire field.

[0014] The instruction quality analysis module includes an adjustment analysis unit, a benefit analysis unit, and an adjustment evaluation unit; The adjustment analysis unit is used to determine the target orientation angle of the power grid equipment based on the type of the dominant change component; and to adjust the angle based on the target orientation angle analysis theory of the power grid equipment. The benefit analysis unit is used to collect the average power and rated power of the power grid equipment within the time window before and after the adjustment; analyze the apparent gain of the reference power grid equipment group and the apparent gain of the current power grid equipment; and analyze the net benefit. The adjustment evaluation unit is used to obtain the actual adjustment angle, analyze the execution deviation score of the power grid equipment, analyze the benefit score based on the net benefit, and analyze the comprehensive command quality score by combining the execution deviation score and the benefit score.

[0015] The anomaly detection boundary analysis module includes a model building unit and a boundary analysis unit; The model building unit is used to obtain the historical adjustment record table of the same power grid equipment; construct a scatter plot with the actual adjustment angle in the historical adjustment event as the horizontal axis and the net benefit as the vertical axis; and construct an angle benefit response model based on the scatter plot. The boundary analysis unit is used to analyze the mean and standard deviation of historical net benefit residuals; set initial upper boundary offset and lower boundary offset, and adjust the lower boundary offset according to the operating time of the power grid equipment and the mean of the recent comprehensive command quality scores; and generate anomaly discrimination boundary lines in combination with the angle benefit response model.

[0016] The real-time anomaly analysis module includes a real-time data analysis unit, an anomaly judgment unit, and a handling instruction analysis unit. The real-time data analysis unit is used to obtain the actual adjustment angle, actual net benefit, angle benefit response model and corresponding anomaly discrimination boundary line of the power grid equipment in this adjustment; calculate the predicted net benefit based on the angle benefit response model, calculate the real-time net benefit residual; and analyze the offset distance and offset direction. The anomaly judgment unit is used to obtain the anomaly identifier and offset direction of the power grid equipment, and at the same time select all power grid equipment of the same type that are less than the adjacent distance threshold from the power grid equipment to analyze the anomaly situation of the adjacent power grid equipment. Analyze the proportion of anomalies occurring in adjacent power grid equipment, and the proportion of anomalies occurring in the same direction as the corresponding power grid equipment; determine the anomaly type based on the proportion of anomalies occurring in adjacent power grid equipment; The disposal instruction analysis unit is used to generate graded disposal instructions based on the anomaly type, possible cause, and offset distance.

[0017] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention calculates the changes in three dimensions—wind speed, illumination, and temperature and humidity—and uses this to screen out the true "source sites of change," avoiding frequent false triggers caused by single-point sensor noise or instantaneous fluctuations, thus improving the rationality of control initiation. By calculating the average magnitude of the predicted environmental change vector at all grid equipment locations, the overall environmental change intensity is obtained. When this intensity is below a threshold, the control process is skipped directly, further avoiding meaningless grid equipment adjustments when the overall environment is stable, saving the actuator's lifespan and communication resources. This invention introduces the apparent gain of a reference grid equipment group to calculate the net benefit, eliminating the interference of natural environmental fluctuations on power changes, ensuring that the evaluation results truly reflect the "benefits brought by the adjustment command itself," and improving the accuracy of command quality evaluation. The execution deviation score reflects the reliability of mechanical transmission and communication, while the benefit score reflects the effectiveness of the control strategy. The weighted sum of these two scores yields the command quality score, providing a reliable weighting basis for subsequent anomaly detection boundary adjustments. Different target orientation calculation methods are used based on the dominant change component, making the control logic physically interpretable and avoiding the problem of a unified formula being inapplicable in all scenarios. This invention constructs a scatter plot based on historical adjustment data of the same power grid equipment and fits an angle benefit response model. This captures the unique mechanical characteristics, installation environment, and aging degree of each power grid device, avoiding systematic biases introduced by a unified theoretical model. The initial lower boundary is more lenient than the upper boundary, reflecting a higher sensitivity to "abnormal efficiency decline" than "abnormal efficiency increase." Simultaneously, the lower boundary is dynamically adjusted based on the power grid equipment's operating time and command quality score. This allows for a more lenient threshold when older power grid equipment or command quality is low, reducing false alarms, while a stricter threshold is used when younger power grid equipment or command quality is high, improving the detection rate. Both the response model and boundary parameters can be updated with new data, enabling the system to have adaptive learning capabilities and track the slow degradation of power grid equipment performance. By calculating the proportion of anomalies occurring in adjacent power grid equipment and the proportion of anomalies occurring in the same direction, this invention can effectively distinguish between "environmental anomalies" and "individual power grid equipment anomalies," avoiding unnecessary power grid equipment maintenance for environmental events and preventing delays in handling power grid equipment failures by attributing them to the environment. Combining the offset direction and synchronicity analysis results, possible causes can be identified, providing valuable diagnostic clues for on-site maintenance personnel. Attached Figure Description

[0018] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating an intelligent control method for smart grid equipment according to the present invention. Figure 2This is a schematic diagram of the structure of an intelligent control system applied to smart grid equipment according to the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 The present invention provides a technical solution: an intelligent control method for smart grid equipment, the method comprising the following steps: Step S100: Collect environmental data from each monitoring station in the target area and analyze environmental changes to generate a priority sequence of affected power grid equipment and environmental change events; Step S100 includes the following: S101: Collect environmental data from each monitoring station within the target area; environmental data includes, but is not limited to, wind speed, light intensity, temperature, and humidity; simultaneously collect the coordinates, type, and rated power of each power grid device at each monitoring station; For each monitoring station, calculate the changes in wind speed, light intensity, and temperature and humidity. The change in wind speed is equal to the wind speed at the current moment minus the wind speed at a certain time ago; the change in light intensity is equal to the light intensity at the current moment minus the light intensity at a certain time ago; the temperature and humidity change index is equal to the temperature change multiplied by the humidity change index; the humidity change index is equal to one minus the humidity coefficient multiplied by the humidity at the current moment. The normalized wind speed change, light intensity change, and temperature and humidity change index are combined into a three-dimensional change vector, and the magnitude of the three-dimensional change vector is calculated as the environmental change intensity of the monitoring station. If the environmental change intensity of the monitoring station is greater than the first threshold, the corresponding monitoring station is marked as the change source station. S102: For each source site of change, calculate the radius of influence based on the intensity of environmental change. The radius of influence is equal to the intensity of environmental change at the source site divided by the influence coefficient. For each power grid device, calculate the Euclidean distance between it and each source site of change. If the Euclidean distance is less than or equal to the radius of influence of the corresponding source site of change, then the corresponding power grid device is determined to be affected by the source site of change. For all source sites identified as affecting the corresponding power grid equipment, a first contribution factor is calculated for each source site. The first contribution factor is equal to the intensity of environmental change at the source site divided by the sum of the Euclidean distance between the power grid equipment and the source site plus a distance coefficient. A second contribution factor is calculated, which is equal to a preset constant plus an environmental proportional characteristic value. The environmental proportional characteristic value is equal to the sensitivity adjustment coefficient multiplied by the change ratio. The change ratio is equal to the ratio of the absolute value of the change in illumination to the absolute value of the change in wind speed at the source site. The sum of the products of the first contribution factor and the second contribution factor for all source sites affected by the power grid equipment is recorded as the comprehensive impact weight of the power grid equipment. All power grid equipment is sorted in descending order of comprehensive impact weight to generate an impact priority sequence; S103: For any location within the target area, the predicted vector of environmental change at that location is equal to the sum of the vectors of all change source stations divided by the square of their distances to the location, and the sum of the reciprocals of the squares of the distances from all change source stations to the location. For each power grid device, calculate the environmental change prediction vector at the location of the power grid device based on its coordinates, and calculate the magnitude of the environmental change prediction vector; calculate the average magnitude of the environmental change prediction vectors at all locations of power grid devices as the intensity of environmental change across the entire field. If the intensity of the overall environmental change is less than the second threshold, no subsequent control action will be triggered; if the intensity of the overall environmental change is greater than or equal to the second threshold, an environmental change event will be generated; the environmental change event includes: trigger time, affected priority sequence, and dominant change direction of each power grid device; wherein, the dominant change direction of each power grid device is taken from the direction corresponding to the component with the largest absolute value in the environmental change prediction vector at the location of the power grid device; Step S200: Based on the directionality of environmental changes and the location of power grid equipment, analyze the theoretical adjustment angle of the orientation of each power grid device, collect the operating status of the power grid equipment before and after the adjustment, and analyze the comprehensive command quality score; Step S200 includes the following: S201: Determine the target orientation angle of the power grid equipment based on the type of the dominant change component; Example 1: In this example, if the dominant change comes from the sunlight component, the target orientation of the grid equipment is directly facing the sunlight direction, and the sunlight direction angle is calculated from the wind vane of the monitoring station or from the position of the sun; if the dominant change comes from the wind speed component, for wind power grid equipment, the target orientation should be directly facing the wind direction to maximize wind energy capture; for photovoltaic grid equipment, when the wind speed increases, the tilt angle of the photovoltaic panels should be reduced to reduce wind resistance, and the target orientation angle = current orientation angle × (1 - wind speed change rate / 10), where the wind speed change rate is equal to the wind speed change divided by the wind speed some time ago, and if the wind speed was zero some time ago, it is taken as 1; if the dominant change comes from the temperature and humidity change component, the orientation of the grid equipment is not adjusted, but temperature and humidity anomalies are recorded. The theoretical adjustment angle is analyzed. The theoretical adjustment angle is equal to the difference between the target orientation angle and the current orientation angle. If the absolute value of the theoretical adjustment angle is less than the theoretical adjustment angle threshold, no adjustment command is generated. S202: Collect the average power of power grid equipment within the time window before adjustment, the average power within the time window after adjustment, and the rated power; Select several power grid devices of the same type as the current power grid devices, whose distance does not exceed the preset distance threshold, and whose orientation has not been adjusted, as a reference power grid device group; The apparent gain of the reference power grid equipment group and the apparent gain of the current power grid equipment are analyzed separately. The apparent gain of the reference power grid equipment group is equal to the ratio of the difference in average power of each power grid equipment in the reference power grid equipment group within the time window before and after adjustment to the average power after the rated power. The apparent gain of the current power grid equipment is equal to the difference in average power of the current power grid equipment within the time window before and after adjustment divided by the rated power of the current power grid equipment. The difference between the apparent gain of the current power grid equipment and the apparent gain of the reference power grid equipment group is recorded as the net benefit; S203: Obtain the actual adjustment angle and analyze the execution deviation score; analyze the benefit score based on the net benefit; Example 2: In this example, deviation scoring S is performed. exec The specific calculation method is as follows: ; Where, θ actual Indicates the actual adjustment angle, θ theory Indicates the theoretical adjustment angle; θ o This indicates the preset adjustment angle comparison value; Example 3: In this example, the benefit score S benefit The specific calculation method is as follows: ; Among them, G net Represents the net benefit value; α represents the preset benefit coefficient; The weighted sum of the execution deviation score and the benefit score is recorded as the comprehensive instruction quality score. Step S300: Analyze the adjustment data of the same power grid equipment several times, identify the benefit inflection point, and update the anomaly identification boundary line by combining the power grid equipment operating time and comprehensive command quality score; Step S300 includes the following: S301: Obtain the historical adjustment record table of the same power grid equipment. The historical adjustment record table contains the most recent adjustment events sorted by time. Each adjustment event records the actual adjustment angle and net benefit. Construct a scatter plot with the actual adjustment angle as the x-axis and the net benefit as the y-axis. A sliding window segmented fitting method is adopted: starting from the minimum actual adjustment angle, a number of angles are added each time as a window. The least squares method is used to fit a straight line for the data points in each window. The form of the straight line is that the net benefit is equal to the slope multiplied by the actual adjustment angle plus the intercept. The sum of squared fitting residuals for each window is calculated. When the slope change of two consecutive windows exceeds the slope change threshold, the starting angle of the corresponding window is marked as the benefit inflection point. The fitted straight line of all data is used as the angle benefit response model of the power grid equipment; the angle benefit response model can be in piecewise linear form or single linear form, and the inflection point identifier is output. S302: Analyze the mean and standard deviation of historical net benefit residuals; historical net benefit residuals equal historical net benefit minus the net benefit predicted by the angle benefit response model; the net benefit predicted by the angle benefit response model equals the net benefit value corresponding to the actual adjustment angle in the angle benefit response model; The initial upper boundary offset is set to be equal to the mean of the historical net benefit residuals plus the standard deviation of the first net benefit residual; the standard deviation of the first net benefit residual is equal to the product of the first net benefit coefficient and the standard deviation of the historical net benefit residuals; the initial lower boundary offset is set to be equal to the mean of the historical net benefit residuals minus the standard deviation of the second net benefit residual; the standard deviation of the second net benefit residual is equal to the product of the second net benefit coefficient and the standard deviation of the historical net benefit residuals; wherein the first net benefit coefficient is less than the second net benefit coefficient; The lower boundary offset is adjusted according to the operating time of the power grid equipment: the operating time of the power grid equipment is in the form of a preset duration, and the adjusted lower boundary offset is equal to the initial lower boundary offset plus the first corrected lower boundary offset; the first corrected lower boundary offset is equal to the initial lower boundary offset multiplied by the operating time coefficient multiplied by the operating time of the power grid equipment divided by the total number of duration segments. The lower boundary offset is further adjusted based on the average of the most recent comprehensive instruction quality scores: the final lower boundary offset equals the adjusted lower boundary offset plus the second corrected lower boundary offset; the second corrected lower boundary offset equals the adjusted lower boundary offset multiplied by the instruction quality score coefficient multiplied by the difference in the average instruction quality scores; the difference in the average instruction quality scores equals one minus the average of the most recent comprehensive instruction quality scores. Generate anomaly detection boundary lines: For any adjusted angle, the lower limit of the anomaly detection boundary line is equal to the net benefit value predicted by the angle benefit response model plus the final lower boundary offset, and the upper limit of the anomaly detection boundary line is equal to the net benefit value predicted by the angle benefit response model plus the initial upper boundary offset.

[0021] Step S400: Collect data of power grid equipment before and after adjustment in real time, calculate the offset distance and offset direction of the anomaly identification boundary line, combine the synchronization analysis of adjacent power grid equipment to determine the anomaly type, and output graded handling instructions.

[0022] Step S400 includes the following: S401: Obtain the actual adjustment angle, actual net benefit, angle benefit response model, and corresponding anomaly detection boundary line of the power grid equipment in this adjustment; Calculate the predicted net benefit based on the angle benefit response model, and calculate the real-time net benefit residual. Analyze the offset distance and offset direction; The analysis of offset distance specifically includes: if the real-time net benefit residual is greater than the upper limit of the anomaly detection boundary line, then the offset distance is equal to the real-time net benefit residual minus the upper limit of the anomaly detection boundary line; if the real-time net benefit residual is less than the lower limit of the anomaly detection boundary line, then the offset distance is equal to the lower limit of the anomaly detection boundary line minus the real-time net benefit residual; if the real-time net benefit residual is greater than or equal to the lower limit of the anomaly detection boundary line and less than or equal to the upper limit of the anomaly detection boundary line, then it is recorded as no offset. The analysis of the offset direction specifically includes: when the real-time net benefit residual is greater than the upper limit of the anomaly detection boundary line, it is a positive offset; when the real-time net benefit residual is less than the lower limit of the anomaly detection boundary line, it is a negative offset. S402: Obtain the anomaly identifier and offset direction of the power grid equipment, and at the same time select all power grid equipment of the same type that are less than the adjacent distance threshold from the power grid equipment, and analyze the anomaly of the adjacent power grid equipment. Analyze the proportion of anomalies occurring in adjacent power grid equipment, and the proportion of anomalies occurring in the same direction as the corresponding power grid equipment; Determine the type of anomaly based on the proportion of anomalies occurring in adjacent power grid equipment: If the proportion of abnormalities in adjacent power grid equipment is greater than the first proportion threshold and the offset direction is the same, it is determined to be an environmental abnormality. If the proportion of abnormalities among adjacent power grid equipment is less than the second proportion threshold, it is determined to be an individual abnormality of the power grid equipment. If the proportion of abnormalities among adjacent power grid equipment is greater than or equal to the second proportion threshold and less than or equal to the first proportion threshold, then the offset distance is further compared: if the offset distance of the power grid equipment is greater than several times the average offset distance of the adjacent power grid equipment, it is determined to be an individual abnormality of the power grid equipment; otherwise, it is determined to be an environmental abnormality. For cases determined to be individual power grid equipment anomalies, possible causes can be further subdivided according to the direction of the offset: negative offset corresponds to transmission mechanism jamming, sensor drift, or dust accumulation; positive offset corresponds to anomalies in the reference power grid equipment group. S403: Generate tiered handling instructions based on anomaly type, possible causes, and offset distance. If the anomaly type is environmental, no action will be taken on the power grid equipment, and an environmental anomaly alarm will be sent to the operation and maintenance center. If the anomaly type is an individual anomaly of the power grid equipment, it will be handled according to the following steps based on the offset distance: when the current offset distance is less than the first offset distance threshold, a self-test command will be sent; when the current offset distance is greater than or equal to the first offset distance threshold but less than the second offset distance threshold, a cleaning prompt will be sent and recorded in the predictive maintenance list; when the current offset distance is greater than or equal to the second offset distance threshold, a shutdown and maintenance command will be sent along with possible causes. The data from this anomaly determination will be written into the anomaly event log. The data includes the power grid equipment identifier, time, offset distance, determination result, actual adjustment angle, and net benefit.

[0023] Please see Figure 2 The present invention provides a technical solution: an intelligent control system for smart grid equipment, the system comprising an environmental change analysis module, an instruction quality analysis module, an anomaly discrimination boundary analysis module, and a real-time anomaly analysis module; The environmental change analysis module is used to collect environmental data from various monitoring stations in the target area and analyze environmental changes, generating a priority sequence of affected power grid equipment and environmental change events; The instruction quality analysis module is used to analyze the theoretical adjustment angle of the orientation of each power grid device based on the direction of environmental changes and the location of power grid equipment, collect the operating status of power grid equipment before and after adjustment, and analyze the comprehensive instruction quality score. The anomaly detection boundary analysis module is used to analyze the adjustment data of the same power grid equipment several times, identify the benefit inflection point, and update the anomaly detection boundary line by combining the power grid equipment running time and comprehensive command quality score. The real-time anomaly analysis module is used to collect data on power grid equipment before and after adjustments in real time, calculate the offset distance and offset direction of the anomaly identification boundary line, analyze the anomaly type in conjunction with the synchronization of adjacent power grid equipment, and output graded handling instructions.

[0024] The environmental change analysis module includes a change source analysis unit, an impact analysis unit, and a change event analysis unit; The change source analysis unit is used to collect environmental data from each monitoring station within the target area; at the same time, it collects the coordinates, equipment type, and rated power of each power grid device at each monitoring station; for each monitoring station, it calculates the wind speed change, light intensity change, and temperature and humidity change index; and determines the change source station based on the wind speed change, light intensity change, and temperature and humidity change index. The impact analysis unit is used to calculate the impact radius for each source site based on the intensity of environmental change, determine the impact of the source site on the power grid equipment based on the Euclidean distance between the power grid equipment and each source site, analyze the comprehensive impact weight of the power grid equipment, and sort all power grid equipment in descending order of comprehensive impact weight to generate an impact priority sequence. The change event analysis unit is used to calculate the environmental change prediction vector at the location of each power grid device based on its coordinates, and to calculate the magnitude of the environmental change prediction vector; to calculate the average magnitude of the environmental change prediction vectors at all locations of power grid devices as the overall environmental change intensity; and to generate environmental change events based on the overall environmental change intensity.

[0025] The instruction quality analysis module includes an adjustment analysis unit, a benefit analysis unit, and an adjustment evaluation unit; The adjustment analysis unit is used to determine the target orientation angle of power grid equipment based on the type of dominant change component; the angle is adjusted based on the target orientation angle analysis theory of power grid equipment. The benefit analysis unit is used to collect the average power and rated power of power grid equipment within the time window before and after adjustment; analyze the apparent gain of the reference power grid equipment group and the apparent gain of the current power grid equipment; and analyze the net benefit. The adjustment evaluation unit is used to obtain the actual adjustment angle and analyze the execution deviation score of the power grid equipment; the benefit score is analyzed based on the net benefit; and the comprehensive command quality score is analyzed by combining the execution deviation score and the benefit score.

[0026] The anomaly detection boundary analysis module includes a model building unit and a boundary analysis unit; The model building unit is used to obtain the historical adjustment record table of the same power grid equipment; construct a scatter plot with the actual adjustment angle in the historical adjustment event as the horizontal axis and the net benefit as the vertical axis; and construct an angle benefit response model based on the scatter plot. The boundary analysis unit is used to analyze the mean and standard deviation of historical net benefit residuals; set initial upper and lower boundary offsets, and adjust the lower boundary offset based on the operating time of the power grid equipment and the mean of the quality scores of the most recent comprehensive commands; and generate anomaly discrimination boundary lines in combination with the angle benefit response model.

[0027] The real-time anomaly analysis module includes a real-time data analysis unit, an anomaly judgment unit, and a handling instruction analysis unit; The real-time data analysis unit is used to acquire the actual adjustment angle, actual net benefit, angle benefit response model and corresponding anomaly discrimination boundary line of the power grid equipment in this adjustment; calculate the predicted net benefit based on the angle benefit response model, calculate the real-time net benefit residual; and analyze the offset distance and offset direction. The anomaly detection unit is used to obtain the anomaly identifier and offset direction of the power grid equipment, and at the same time select all power grid equipment of the same type that are less than the adjacent distance threshold from the power grid equipment to analyze the anomaly of the adjacent power grid equipment. Analyze the proportion of anomalies occurring in adjacent power grid equipment, and the proportion of anomalies occurring in the same direction as the corresponding power grid equipment; determine the anomaly type based on the proportion of anomalies occurring in adjacent power grid equipment; The handling instruction analysis unit is used to generate graded handling instructions based on the anomaly type, possible cause, and offset distance.

[0028] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or electrical equipment that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or electrical equipment.

[0029] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A smart control method for smart grid equipment, characterized in that, The method includes the following steps: Step S100: Collect environmental data from each monitoring station in the target area and analyze environmental changes to generate a priority sequence of affected power grid equipment and environmental change events; Step S200: Based on the directionality of environmental changes and the location of power grid equipment, analyze the theoretical adjustment angle of the orientation of each power grid device, collect the operating status of the power grid equipment before and after the adjustment, and analyze the comprehensive command quality score; Step S300 includes the following: S301: Obtain the historical adjustment record table of the same power grid equipment; construct a scatter plot with the actual adjustment angle in the historical adjustment event as the horizontal axis and the net benefit as the vertical axis; construct an angle benefit response model based on the scatter plot; S302: Analyze the mean and standard deviation of historical net benefit residuals; set initial upper and lower boundary offsets, and adjust the lower boundary offset based on the operating time of power grid equipment and the mean of the quality scores of the most recent comprehensive commands; generate anomaly discrimination boundary lines by combining the angle benefit response model; Step S400: Collect data of power grid equipment before and after adjustment in real time, calculate the offset distance and offset direction of the anomaly identification boundary line, combine the synchronization analysis of adjacent power grid equipment to determine the anomaly type, and output graded handling instructions.

2. The intelligent control method for smart grid equipment according to claim 1, characterized in that: Step S100 includes the following: S101: Collect environmental data from each monitoring station within the target area; simultaneously collect the coordinates, equipment type, and rated power of each power grid device at each monitoring station; for each monitoring station, calculate the wind speed change, light intensity change, and temperature and humidity change index. The source sites of change are determined based on changes in wind speed, changes in sunlight, and temperature and humidity indices. S102: For each source site of change, calculate the radius of influence based on the intensity of environmental change, and determine the impact of the source site on the power grid equipment based on the Euclidean distance between the power grid equipment and each source site of change; analyze the comprehensive impact weight of the power grid equipment; sort all power grid equipment in descending order of comprehensive impact weight to generate an affected priority sequence; S103: For each power grid device, calculate the environmental change prediction vector at the location of the power grid device based on the coordinates, and calculate the magnitude of the environmental change prediction vector; calculate the average of the magnitudes of the environmental change prediction vectors at all locations of the power grid devices as the intensity of environmental change across the entire field; generate environmental change events based on the intensity of environmental change across the entire field.

3. The intelligent control method for smart grid equipment according to claim 2, characterized in that: The determination of the source site of change specifically includes: combining the normalized wind speed change, light intensity change, and temperature and humidity change index into a three-dimensional change vector, and calculating the magnitude of the three-dimensional change vector as the environmental change intensity of the monitoring site; if the environmental change intensity of the monitoring site is greater than a first threshold, the corresponding monitoring site is marked as the source site of change.

4. The intelligent control method for smart grid equipment according to claim 2, characterized in that: Step S200 includes the following: S201: Determine the target orientation angle of the power grid equipment based on the type of the dominant change component; adjust the angle based on the target orientation angle analysis theory of the power grid equipment; S202: Collect the average power and rated power of power grid equipment within the time window before and after adjustment; Analyze the apparent gain of the reference power grid equipment group and the apparent gain of the current power grid equipment respectively; and analyze the net benefit. S203: Obtain the actual adjustment angle and analyze the execution deviation score of the power grid equipment; analyze the benefit score based on the net benefit; combine the execution deviation score and the benefit score to analyze the comprehensive command quality score; Step S300: Analyze the adjustment data of the same power grid equipment several times, identify the benefit inflection point, and update the anomaly detection boundary line by combining the power grid equipment operating time and comprehensive instruction quality score.

5. The intelligent control method for smart grid equipment according to claim 4, characterized in that: The apparent gain of the reference power grid equipment group is equal to the ratio of the difference in average power of each power grid equipment in the reference power grid equipment group within the time window before and after adjustment to the average value after rated power. The apparent gain of the current power grid equipment is equal to the difference in the average power of the current power grid equipment within the time window before and after the adjustment, divided by the rated power of the current power grid equipment.

6. The intelligent control method for smart grid equipment according to claim 4, characterized in that: The adjustment of the lower boundary offset based on the power grid equipment operating time is as follows: the power grid equipment operating time is in the form of a preset duration, and the adjusted lower boundary offset is equal to the initial lower boundary offset plus the first corrected lower boundary offset; the first corrected lower boundary offset is equal to the initial lower boundary offset multiplied by the operating time coefficient multiplied by the power grid equipment operating time divided by the total number of duration segments.

7. The intelligent control method for smart grid equipment according to claim 4, characterized in that: Step S400 includes the following: S401: Obtain the actual adjustment angle, actual net benefit, angle benefit response model, and corresponding anomaly detection boundary line of the power grid equipment in this adjustment; Calculate the predicted net benefit based on the angle benefit response model, calculate the real-time net benefit residual, and analyze the offset distance and offset direction. S402: Obtain the anomaly identifier and offset direction of the power grid equipment; simultaneously select all power grid equipment of the same type that are less than the adjacent distance threshold from the power grid equipment; analyze the anomaly situation of the adjacent power grid equipment; analyze the proportion of anomalies among the adjacent power grid equipment, and the proportion of anomalies with the same offset direction as the corresponding power grid equipment; determine the anomaly type based on the proportion of anomalies among the adjacent power grid equipment. S403: Generate graded handling instructions based on the anomaly type, possible cause, and offset distance.

8. The intelligent control method for smart grid equipment according to claim 7, characterized in that: The analysis of offset distance specifically includes: if the real-time net benefit residual is greater than the upper limit of the anomaly detection boundary line, then the offset distance is equal to the real-time net benefit residual minus the upper limit of the anomaly detection boundary line; if the real-time net benefit residual is less than the lower limit of the anomaly detection boundary line, then the offset distance is equal to the lower limit of the anomaly detection boundary line minus the real-time net benefit residual; if the real-time net benefit residual is greater than or equal to the lower limit of the anomaly detection boundary line and less than or equal to the upper limit of the anomaly detection boundary line, then it is recorded as no offset; the analysis of offset direction specifically includes: when the real-time net benefit residual is greater than the upper limit of the anomaly detection boundary line, it is a positive offset; when the real-time net benefit residual is less than the lower limit of the anomaly detection boundary line, it is a negative offset.

9. An intelligent control system for smart grid equipment, wherein the system is implemented using the intelligent control method for smart grid equipment as described in any one of claims 1-8, characterized in that, The system includes an environmental change analysis module, an instruction quality analysis module, an anomaly detection boundary analysis module, and a real-time anomaly analysis module; The environmental change analysis module is used to collect environmental data from each monitoring station in the target area and analyze environmental changes, generating a priority sequence of affected power grid equipment and environmental change events. The instruction quality analysis module is used to analyze the theoretical adjustment angle of the orientation of each power grid device based on the direction of environmental changes and the location of power grid equipment, collect the operating status of power grid equipment before and after adjustment, and analyze the comprehensive instruction quality score. The anomaly detection boundary analysis module is used to analyze the adjustment data of the same power grid equipment several times, identify the benefit inflection point, and update the anomaly detection boundary line by combining the power grid equipment running time and comprehensive instruction quality score. The real-time anomaly analysis module is used to collect data of power grid equipment before and after adjustment in real time, calculate the offset distance and offset direction of the anomaly identification boundary line, combine the synchronization analysis of adjacent power grid equipment to determine the anomaly type, and output graded handling instructions.

Images