A smart grid multi-sensor fusion line loss analysis system and method

Abstract

The application provides a kind of smart grid multi-sensor fusion line loss analysis system and method, it is related to smart grid technical field, the system includes: line loss analysis matrix formulation module, line loss analysis matrix is formulated, line loss deviation is set;Dynamic analysis module determines line loss abnormal deviation, when exceeding the normal line loss preset threshold range corresponding to power transmission line, trigger dynamic analysis mechanism: based on line loss analysis matrix and line loss deviation carry out different data calibration;Dynamic allocation module, dynamically allocates the line loss control gain factor of each monitoring section;Line loss calibration module, through each edge calibration execution unit deployed in each monitoring section, carries out the line loss accuracy enhancement control of smart grid.The application solves the technical problems that line loss anomaly section and cause are difficult to accurately locate in the prior art, leading to inaccurate line loss analysis, accurately identifies the line loss problem of power grid through multi-sensor monitoring and data fusion.

Description

Technical Field

[0001] This application relates to the field of smart grid technology, specifically to a smart grid multi-sensor fusion line loss analysis system and method. Background Technology

[0002] In the field of smart grid line loss management, current analytical methods mainly rely on overall line loss calculation methods, which typically use extremely limited data dimensions, based solely on electricity consumption. This prevents them from penetrating the "black box" state of grid operation. The analysis results can only reflect the overall line loss rate of a line or distribution area, failing to pinpoint the specific section where anomalies occurred spatially, track the dynamic process of anomalies over time, or distinguish the specific causes of technical and managerial line losses. This leaves line loss analysis at a crude statistical level. The slow response to real-time dynamic changes in the grid makes it difficult to adjust grid operation strategies in a timely manner when anomalies occur, preventing the grid from operating within its optimal economic range for extended periods, thus impacting grid optimization scheduling and operational efficiency.

[0003] In summary, existing technologies suffer from the technical problem of inaccurate line loss analysis due to the difficulty in accurately locating abnormal line loss sections and their causes, which further affects the operating efficiency of the power grid. Summary of the Invention

[0004] The purpose of this application is to provide a smart grid multi-sensor fusion line loss analysis system and method to solve the technical problem in the prior art where the difficulty in accurately locating abnormal line loss sections and their causes leads to inaccurate line loss analysis, which in turn affects the operating efficiency of the power grid.

[0005] To achieve the above objectives, this application provides a smart grid multi-sensor fusion line loss analysis system and method.

[0006] Firstly, this application provides a smart grid multi-sensor fusion line loss analysis system, wherein the smart grid multi-sensor fusion line loss analysis system includes: a line loss analysis matrix formulation module, used to formulate a line loss analysis matrix based on the transmission lines of the smart grid through multi-sensor monitoring data and set a line loss deviation; a dynamic analysis module, used to determine the abnormal line loss offset through line parameter data, and when the abnormal line loss offset exceeds the preset threshold range of normal line loss corresponding to the transmission line, triggering a dynamic analysis mechanism: driving the line loss fusion decision unit of the power grid dispatch center to perform differentiated data calibration based on the line loss analysis matrix and the line loss deviation; a dynamic allocation module, used to dynamically allocate the line loss control gain factor of each monitoring segment according to the abnormal line loss offset; and a line loss calibration module, used to perform enhanced line loss accuracy control of the smart grid based on the line loss control gain factor of each monitoring segment through each edge calibration execution unit deployed in each monitoring segment.

[0007] Optionally, the association mapping unit is used to establish a three-dimensional topological coordinate system with the midpoint of the transmission line of the smart grid as the origin, perform association mapping on the multi-sensor monitoring data, and determine the current monitoring deviation and voltage monitoring deviation; the matrix construction unit is used to construct the line loss analysis matrix based on the current monitoring deviation and voltage monitoring deviation.

[0008] Optionally, the monitoring division unit is used to divide the transmission line of the smart grid into M uniformly distributed monitoring segments and obtain the weighted average value of line loss corresponding to the M uniformly distributed monitoring segments; the anomaly center coordinate identification unit is used to identify the anomaly center coordinate of the line loss by power balance, with the midpoint of the transmission line as the reference point and comparing the topological position of the M uniformly distributed monitoring segments; the difference comparison unit is used to compare the difference between the anomaly center coordinate of the line loss and the coordinate of the midpoint of the transmission line to determine the line loss anomaly offset vector value, wherein the line loss anomaly offset is the magnitude of the line loss anomaly offset vector value.

[0009] Optionally, a synchronization adjustment unit is used to drive the synchronous adjustment of each edge calibration execution unit using fuzzy PID control; and a calibration ratio determination unit is used to determine the target calibration ratio of each edge calibration execution unit based on the line loss analysis matrix and the line loss deviation using the line loss fusion decision unit.

[0010] Optionally, a level evaluation subunit is used to evaluate the local monitoring stability level based on the variance of the multi-sensor monitoring data in each edge calibration execution unit; a fuzzy control rule adjustment subunit is used to enable the fuzzy PID control, and the line loss fusion decision unit dynamically adjusts the fuzzy control rules based on the local monitoring stability level, wherein the integral term accumulation time is positively correlated with monitoring stability.

[0011] Optionally, the feedback adjustment unit is used to perform feedback adjustment using the line loss control gain factor to return to the normal line loss preset threshold range corresponding to the transmission line; the feedback calibration unit is used to collect the gain change rate of each monitoring segment during the feedback adjustment of the line loss control gain factor, and if the gain change rate exceeds the preset safety threshold, to pause one or more sets of data calibration actions corresponding to one or more edge calibration execution units.

[0012] Optionally, the dominant interference factor determination unit is used to perform feature analysis on environmental impact data to determine the dominant interference factor and activate the interference compensation unit; the compensation adjustment unit is used to dynamically adjust the compensation coefficient based on the dominant interference factor and through the matching relationship with the inherent compensation frequency of the interference compensation unit; and the line loss accuracy enhancement control unit is used to perform line loss accuracy enhancement control of the smart grid based on the line loss control gain factor of each monitoring segment and in combination with the compensation coefficient.

[0013] Optionally, an identification instruction triggering subunit is used to introduce changes in the line loss calculation accuracy of the smart grid. If the improvement speed within a preset time period after adjusting the compensation coefficient does not reach the expected improvement speed, a secondary interference identification instruction is triggered. A secondary interference factor determination subunit is used to determine the secondary interference factors of the environmental impact data based on the secondary interference identification instruction. A compensation strategy configuration subunit is used to configure a segmented compensation strategy according to the dominant interference factor and the secondary interference factor.

[0014] Optionally, an internal integration unit is provided for integrating an H-bridge compensation drive circuit within the edge calibration execution unit; the edge calibration unit is configured to: receive calibration instructions and compensation coefficients issued by the line loss fusion decision unit; generate a reverse interference current through the H-bridge compensation drive circuit based on the calibration instructions and compensation coefficients; and actively cancel interference through the reverse interference current.

[0015] Secondly, this application also provides a method for multi-sensor fusion line loss analysis in smart grids. This method includes: based on the transmission lines of the smart grid, a line loss analysis matrix is ​​formulated using multi-sensor monitoring data, and a line loss deviation is set; line loss anomaly offset is determined using line parameter data; when the line loss anomaly offset exceeds the preset threshold range of normal line loss corresponding to the transmission line, a dynamic analysis mechanism is triggered: driving the line loss fusion decision unit of the power grid dispatch center to perform differentiated data calibration based on the line loss analysis matrix and the line loss deviation; simultaneously, line loss control gain factors are dynamically allocated to each monitoring segment according to the line loss anomaly offset; based on the line loss control gain factors of each monitoring segment, line loss accuracy enhancement control of the smart grid is performed through edge calibration execution units deployed in each monitoring segment.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0017] The system employs a line loss analysis matrix formulation module for smart grid transmission lines, using multi-sensor monitoring data to formulate a line loss analysis matrix and set line loss deviation values. A dynamic analysis module determines abnormal line loss offsets based on line parameter data. When the abnormal offset exceeds the preset threshold range for normal line loss of the corresponding transmission line, a dynamic analysis mechanism is triggered, driving the line loss fusion decision unit of the power grid dispatch center to perform differentiated data calibration based on the line loss analysis matrix and line loss deviation. A dynamic allocation module dynamically allocates line loss control gain factors to each monitoring segment according to the abnormal line loss offset. A line loss calibration module enhances the accuracy of line loss control in the smart grid by using edge calibration execution units deployed in each monitoring segment, based on the line loss control gain factors of each monitoring segment. In other words, by deploying multiple sensors in different monitoring sections of the power grid, the status of each transmission line segment is monitored in real time. A line loss analysis matrix is ​​formulated, and a line loss deviation is set. When the line loss deviation of a certain monitoring segment exceeds the threshold, a dynamic analysis mechanism is triggered to perform differentiated data calibration based on the line loss analysis matrix and the line loss deviation. At the same time, line loss control gain factors are allocated to each monitoring segment according to the abnormal line loss offset. Through edge calibration execution units deployed in each monitoring segment, precise control of line loss is achieved, improving the accuracy of line loss analysis in the smart grid and thus improving the overall operating efficiency of the power grid.

[0018] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the structure of a smart grid multi-sensor fusion line loss analysis system according to this application.

[0021] Figure 2 This is a flowchart illustrating a multi-sensor fusion line loss analysis method for smart grids according to this application.

[0022] Figure labeling: Line loss analysis matrix formulation module 11, dynamic analysis module 12, dynamic allocation module 13, line loss calibration module 14. Detailed Implementation

[0023] This application provides a multi-sensor fusion line loss analysis system and method for smart grids, solving the technical problem in existing technologies where inaccurate line loss analysis is caused by the difficulty in accurately locating abnormal line loss sections and their causes, further affecting the operating efficiency of the power grid. By deploying multiple sensors in different monitoring sections of the power grid, the system monitors the status of each transmission line segment in real time, formulates a line loss analysis matrix, and sets line loss deviation values. When the line loss deviation of a monitoring segment exceeds a threshold, a dynamic analysis mechanism is triggered, performing differentiated data calibration based on the line loss analysis matrix and the line loss deviation value. Simultaneously, line loss control gain factors are allocated to each monitoring segment according to the abnormal line loss offset. Through edge calibration execution units deployed in each monitoring segment, precise control of line loss is achieved, improving the accuracy of smart grid line loss analysis and thus enhancing the overall operating efficiency of the power grid.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides a smart grid multi-sensor fusion line loss analysis system, wherein the smart grid multi-sensor fusion line loss analysis system is used to implement the steps of a smart grid multi-sensor fusion line loss analysis method, and the smart grid multi-sensor fusion line loss analysis system includes:

[0026] The line loss analysis matrix formulation module 11 is used for transmission lines based on smart grids to formulate a line loss analysis matrix and set the line loss deviation amount through multi-sensor monitoring data.

[0027] Furthermore, the line loss analysis matrix formulation module 11 in the smart grid multi-sensor fusion line loss analysis system is also used for: an association mapping unit, used to establish a three-dimensional topological coordinate system with the midpoint of the transmission line of the smart grid as the origin, and to perform association mapping on the multi-sensor monitoring data to determine the current monitoring deviation and voltage monitoring deviation; and a matrix construction unit, used to construct the line loss analysis matrix based on the current monitoring deviation and voltage monitoring deviation.

[0028] Specifically, various sensors are deployed at multiple key points along the transmission lines of the smart grid to simultaneously collect complete monitoring data of the transmission lines, resulting in multi-sensor monitoring data. This multi-sensor monitoring data comprises real-time measurements collected by various types of sensors deployed at each monitoring point along the transmission line, including current sensors measuring line current, voltage sensors measuring voltage to ground, temperature sensors measuring conductor temperature, and tilt / acceleration sensors monitoring conductor wind deflection and sag.

[0029] The midpoint of the transmission line is designated as the origin of the three-dimensional space, the direction along the line is the X-axis, the direction perpendicular to the ground is the Z-axis, and the horizontal direction perpendicular to the line is the Y-axis. In this way, every tower, sensor and actuator of the entire line is mapped to a precise three-dimensional coordinate system, thus obtaining a three-dimensional topological coordinate system.

[0030] Activate the established three-dimensional topological coordinate system and convert the physical location of each data point into a precise three-dimensional coordinate value. Compare the real-time current and voltage readings uploaded by each monitoring point with the theoretical expected values ​​corresponding to that point under the current system total load and operating mode to calculate the specific current monitoring deviation and voltage monitoring deviation. For example, consider a 10-kilometer-long 110 kV overhead transmission line. Establish a coordinate system with the midpoint of the line as the origin (0,0,0), and set up a comprehensive monitoring point every 500 meters along the line, for a total of 21 points. Data was collected at 2:05 PM on May 13th. The monitoring point located at coordinates (-2500,0,25), 2.5 kilometers west of the origin and 25 meters above the ground, uploaded data showing a measured current of 298A and a measured voltage of 112.5 kV. Based on the current power flow data from the dispatch center, the theoretical expected values ​​for this point at that moment are calculated to be a current of 305A and a voltage of 113.0 kV. Therefore, the current monitoring deviation at this point is 298 - 305 = -7A, indicating a missing current of 7A. The voltage monitoring deviation is 112.5 - 113.0 = -0.5kV, indicating a voltage deviation of 0.5kV.

[0031] The current timestamp, the coordinates of all monitoring points, and their corresponding current and voltage monitoring deviations are all written into a structured database table to construct the line loss analysis matrix. The line loss analysis matrix is ​​a structured, multi-dimensional dataset that links spatial location (three-dimensional coordinates), electrical quantity deviations (current and voltage deviations), and time. It can be understood as a large spreadsheet, where each row represents a time slice, each column represents a specific parameter of a monitoring point, and the table is filled with specific deviation values. The line loss analysis matrix is ​​continuously updated to ensure a high-precision panoramic view of line loss status that evolves over time.

[0032] Based on the calculation results in the line loss analysis matrix, a line loss deviation is set for each monitoring point. The line loss deviation reflects the degree of deviation between each monitoring point and the standard value, thus determining the optimization strategy for that location. The line loss deviation is obtained by comparing the differences between the current and voltage values ​​of a certain area in actual power grid operation and the ideal values. The magnitude of the deviation reflects the energy loss in that area. A larger deviation indicates higher line loss, meaning poor energy efficiency in that area, requiring further optimization. A smaller deviation indicates that the operation at that location is relatively normal and may not require special intervention.

[0033] From the constructed line loss analysis matrix, features that significantly reflect line loss anomalies are extracted, such as current imbalance, voltage drop deviation, power factor drop, zero-sequence current anomaly, and temperature anomaly correlation. These features have different dimensions and cannot be directly added. Therefore, they need to be normalized to the same scale, such as 0 to 100 points. For example, for current imbalance: set 15% as the upper limit of normal, corresponding to a score of 0, and 35% as the lower limit of danger, corresponding to a score of 100. Then, when a 25% imbalance is detected, its normalized score = (25-15) / (35-15)*100 = 50 points. Different weights are assigned to each normalized feature value of all monitoring segments within each calculation cycle, and then a weighted average is performed to finally obtain the overall line loss deviation. The weights are not fixed, reflecting the importance of different features. Monitoring sections located at load centers and critical hubs receive higher data weights; persistent anomalies are weighted more than transient changes; and current and power anomalies are more decisive indicators of line loss than voltage anomalies, thus receiving higher weights. For example, suppose there are three critical monitoring sections A, B, and C on a transmission line. Section A has a weight of 1.2, a current imbalance score of 85, and a voltage drop deviation score of 30; section B has a weight of 1.0, a current imbalance score of 15, and a voltage drop deviation score of 70; and section C has a weight of 0.8, a current imbalance score of 10, and a voltage drop deviation score of 10. The weight for current imbalance is 0.6, and the weight for voltage drop deviation is 0.4. By weighted summation, the contribution value of monitoring segment A is (85*0.6+30*0.4)*1.2=75.6, monitoring segment B is 37.0, and monitoring segment C is 8.0. The total weighted sum is (0.6+0.4)*1.2+(0.6+0.4)*1.0+(0.6+0.4)*0.8=3.0. Therefore, the line loss deviation is calculated as (75.6+37.0+8.0) / 3.0=40.2.

[0034] By deploying multiple sensors to monitor key parameters such as current and voltage in real time, a comprehensive understanding of the power grid's operating status can be achieved. By calculating current and voltage deviations and constructing a line loss analysis matrix, the location of losses within the power grid can be precisely pinpointed, and the degree of line loss at each location can be quantified. By setting and dynamically adjusting line loss deviations, anomalies in the power grid can be detected in real time, and intervention can be implemented through optimized control strategies to improve the grid's operational efficiency and stability. Timely detection of line loss anomalies reduces energy waste, improves the overall operating efficiency of the power grid, thereby lowering operating costs and enhancing the reliability of the power system.

[0035] The dynamic analysis module 12 is used to determine the abnormal offset of line loss through line parameter data. When the abnormal offset of line loss exceeds the preset threshold range of normal line loss corresponding to the transmission line, the dynamic analysis mechanism is triggered: driving the line loss fusion decision unit of the power grid dispatch center to perform differential data calibration based on the line loss analysis matrix and the line loss deviation.

[0036] Furthermore, the dynamic analysis module 12 in the aforementioned smart grid multi-sensor fusion line loss analysis system is also used for: a monitoring division unit, used to divide the transmission line of the smart grid into M uniformly distributed monitoring segments and obtain the weighted average line loss of the M uniformly distributed monitoring segments; an anomaly center coordinate identification unit, used to identify the anomaly center coordinate of the line loss by power balance, with the midpoint of the transmission line as the reference point and comparing it with the topological position of the M uniformly distributed monitoring segments; and a difference comparison unit, used to compare the difference between the anomaly center coordinate of the line loss and the midpoint coordinate of the transmission line to determine the anomaly offset vector value of the line loss, wherein the anomaly offset is the magnitude of the anomaly offset vector value of the line loss.

[0037] Specifically, the entire transmission line is logically divided into M uniformly distributed monitoring sections of equal length. By comprehensively analyzing the historical and real-time data from all sensors within each section, a weighted average line loss is calculated for each section to represent its overall anomaly level. This weighted average line loss is a comprehensive line loss index calculated for each monitoring section; it is not a simple arithmetic average but rather takes into account the importance and reliability of data from different sensors within that section.

[0038] After obtaining the weighted average line loss of M uniformly distributed monitoring segments, a spatial positioning algorithm is activated, similar to calculating the centroid of a non-uniform pole: using the midpoint of the line as the origin, the topological center position of each monitoring segment is multiplied by the weighted average line loss of that segment. All these products are summed and then divided by the sum of all weights. The final calculated result is the centroid of the line loss anomaly in space, i.e., the coordinates of the line loss anomaly center. Power balance analysis is then used to determine which part of the line has line loss exceeding the normal range. The results of power balance analysis can reveal areas with significant line loss, thus identifying the location of the line loss anomaly center. The coordinates of the line loss anomaly center are calculated two-dimensional or three-dimensional spatial coordinates, representing the location of the most severe line loss anomaly along the entire line.

[0039] The coordinates of the abnormal line loss center, determined by power balance analysis, are compared with the coordinates of the midpoint of the transmission line to calculate the offset vector of the abnormal line loss. This vector represents the spatial displacement from the midpoint of the transmission line to the center of the abnormal line loss, thus clarifying the distance and direction of the abnormal center from the midpoint. The direction and magnitude of the offset vector help pinpoint the problem area and guide dispatchers to respond promptly. Calculating the magnitude of the offset vector yields the line loss abnormality offset, quantifying the distance of the abnormal center from the line's reference point, and directly reflecting the severity of the abnormality in space. For example, a transmission line is divided into 10 monitoring sections, each 2 kilometers long. The midpoint coordinates are (0,0). Calculating the weighted average line loss shows that the weighted average of the third section is abnormally high, reaching 85, while most other sections are between 10 and 25. Assuming the coordinate system unit is meters, with the origin in the east (positive), the topological coordinates of the center point of the third section are (-6000,0). The contributions from all monitoring segments are combined. Segment 3, with a weight of 85 significantly higher than other segments, will dominate the calculation. Through power balance weighted calculation, the final coordinates of the abnormal line loss center are determined to be (-5800, 50), very close to the center of segment 3. The difference between the abnormal line loss center coordinates and the midpoint coordinates of the transmission line is calculated, yielding an abnormal line loss offset vector value of (-5800, 50), indicating that the abnormal center is located 5800 meters west of the midpoint and slightly north by 50 meters. The abnormal line loss offset is approximately 5800.2 meters, indicating a severe abnormal line loss point approximately 5.8 kilometers west of the midpoint. Inspection or maintenance teams can directly travel to the area centered at (-5800, 50) with a radius of 500 meters for precise investigation, greatly saving time.

[0040] Transmission lines are divided into multiple evenly distributed monitoring sections to meticulously monitor the power grid's operational status and identify potential problems. Through power balance analysis, the center of abnormal line losses in the power grid can be accurately identified. By calculating the deviation of abnormal line losses, the specific location of the anomaly can be determined, enabling dispatchers to quickly locate the problem area and take appropriate control measures.

[0041] The abnormal offset of line loss is compared with the preset threshold range of normal line loss for the corresponding transmission line. The preset threshold of normal line loss is a standard value determined based on the design and historical operating data of the transmission line, representing the normal line loss range of the transmission line under normal conditions without faults or anomalies. When the abnormal offset of line loss exceeds the preset threshold range of normal line loss for the corresponding transmission line, a dynamic analysis mechanism is triggered. The dynamic analysis mechanism refers to the real-time monitoring and analysis of the power grid's operating data during power grid operation.

[0042] Once a line loss exceeding the normal range is detected, the dynamic analysis mechanism is activated, triggering further data calibration, adjustment, and decision support. The line loss fusion decision unit located in the power grid dispatch center is activated. This core component of the dispatch center is responsible for processing, analyzing, and making decisions based on line loss data collected from various monitoring points. In-depth analysis is performed based on the pre-constructed line loss analysis matrix and the calculated line loss deviation. The line loss analysis matrix clarifies the specific anomaly pattern, and the line loss deviation determines the overall severity of the anomaly. For example, retrieving the line loss analysis matrix reveals a current deviation of -7A in the anomaly center section, but the voltage deviation is not significant. However, the ambient temperature sensor in this section shows a connection point temperature as high as 75℃, prompting differential calibration. If it were pure electricity theft, there would typically be an increase in current rather than a decrease, while the voltage would drop significantly. The calibration conclusion is that the possibility of electricity theft is low, and the probability score of the relevant algorithm is lowered. The combination of current loss and high connection point temperature strongly suggests line aging or excessive contact resistance at the connection point. The high contact resistance caused a significant amount of electrical energy to be consumed at that point, resulting in a decrease in downstream current and causing localized high temperatures, which constitutes a serious technical line loss.

[0043] Data calibration is performed based on the previously constructed line loss analysis matrix and line loss deviation. The goal of data calibration is to differentiate line loss conditions across different driving segments, ensuring that the line loss data for each monitoring segment matches the actual operating conditions. The calibration process considers the specific circumstances of each monitoring segment, such as load size and environmental factors, and makes personalized adjustments by comparing actual line loss with standard line loss. Based on the line loss deviation of each monitoring segment, the calibration ratio for each segment is adjusted, and the final line loss data is adjusted using methods such as weighted averaging. For example, if the line loss deviation of a certain segment is large, the weight of that segment is increased to enhance the calibration intensity, thereby making the data for that segment more consistent with the data across the entire network.

[0044] By analyzing line parameter data and deviation calculations, abnormal line losses can be detected promptly, helping power grid operators accurately pinpoint problem areas. When line loss deviations exceed the normal range, a dynamic analysis mechanism can be quickly activated. Through differentiated data calibration by the line loss fusion decision unit, the data for each monitoring segment is optimized, making power grid dispatching more precise and effectively reducing energy consumption.

[0045] Furthermore, the dynamic analysis module 12 in the aforementioned smart grid multi-sensor fusion line loss analysis system is also used for: a synchronization adjustment unit, used to drive the synchronous adjustment of each edge calibration execution unit using fuzzy PID control; and a calibration ratio determination unit, used to determine the target calibration ratio of each edge calibration execution unit based on the line loss analysis matrix and the line loss deviation using the line loss fusion decision unit.

[0046] Furthermore, the dynamic analysis module 12 in the aforementioned smart grid multi-sensor fusion line loss analysis system is also used for: a level evaluation subunit, used to evaluate the local monitoring stability level based on the variance of the multi-sensor monitoring data in each edge calibration execution unit; and a fuzzy control rule adjustment subunit, used to enable the fuzzy PID control, wherein the line loss fusion decision unit dynamically adjusts the fuzzy control rules based on the local monitoring stability level, wherein the integral term accumulation time is positively correlated with monitoring stability.

[0047] Specifically, fuzzy PID control is used to drive each edge calibration execution unit. Fuzzy PID control combines the advantages of fuzzy control and classical PID control. Utilizing fuzzy logic, the parameters of the PID controller are adaptively adjusted based on the real-time operating state, i.e., the magnitude and trend of the error. Each execution unit, while running locally, has its built-in controller continuously monitoring the local control error and its rate of change, using fuzzy PID control to adjust the edge calibration execution unit. While PID controllers typically perform control tasks by adjusting proportional (P), integral (I), and derivative (D) parameters, fuzzy PID introduces fuzzy logic to dynamically adjust PID parameters to cope with different disturbances and complex environments. In fuzzy PID control, traditional PID parameters are dynamically adjusted through fuzzy inference based on the actual system state and environmental changes, thus better adapting to complex power grid environments. In simpler terms, if the error is still relatively large but is rapidly decreasing, the control force should be appropriately reduced to prevent overshoot.

[0048] Simultaneously, the line loss fusion decision unit performs comprehensive calculations based on the global line loss analysis matrix and line loss deviation to determine the target calibration ratio for each execution unit. For example, if the line loss analysis matrix reveals that the problem contribution of the anomaly center section accounts for 60%, its upstream and downstream sections account for 20% and 15% respectively, and the far end accounts for 5%, then according to this ratio, the overall control task is decomposed into specific target calibration ratios and distributed to the corresponding edge units. The target calibration ratio is a task quantification indicator calculated by the central decision unit and allocated to each edge unit, defining the responsibility share that each edge calibration execution unit should bear in the current global control task.

[0049] Each edge calibration execution unit receives the target calibration ratio from the central control and adjusts it through fuzzy PID control. In other words, by adjusting the edge calibration execution units of each monitoring segment, the grid parameters are synchronously adjusted according to the corresponding target calibration ratio. Each monitoring segment of the smart grid transmission line will adjust its current, voltage, and other parameters as needed, thereby achieving optimal control of the entire network's line loss. Synchronous adjustment means that all monitoring segments adjust according to unified instructions, ensuring that the states of each monitoring segment in the grid are coordinated and consistent, achieving overall network optimization. For example, based on the line loss analysis matrix, the distribution of abnormal current is found to be: monitoring segment A contributes 50A of abnormal current; monitoring segment B contributes 30A of abnormal current; and monitoring segment C contributes 20A of abnormal current. The target calibration ratio for each unit is calculated as follows: Unit A: 50 / (50+30+20)=50%, Unit B: 30%, and Unit C: 20%. An instruction is issued requiring Unit A to undertake a compensation task of 50A (100A*50%), Unit B to undertake 30A, and Unit C to undertake 20A. Upon receiving the command, Unit A begins driving its H-bridge circuit to output a 50A reverse interference current. At startup, its PID controller detects a sharp increase in output current. The fuzzy inference system immediately determines that the upward trend is too rapid and dynamically reduces the proportional gain in the PID algorithm, allowing the current to rise smoothly to 50A and avoiding overshoot. Simultaneously, Units B and C also begin operating synchronously. Due to the presence of line impedance, the strong injection behavior of Unit A may slightly affect the voltage at the monitoring points of Units B and C. At this time, Unit B's controller detects a slight fluctuation between the command and the actual output. Its fuzzy inference system determines that there is a small, persistent error and dynamically increases the integral coefficient to quickly eliminate this steady-state error, ensuring the output is accurately locked at 30A.

[0050] By employing fuzzy PID control, the operating parameters of each monitored segment of the power grid are adjusted in real time amidst complex environmental changes, enabling the grid to adaptively optimize line losses and reduce unnecessary losses. The combination of fuzzy PID control and a line loss analysis matrix adjusts grid parameters in real time based on the actual operating conditions of the grid, ensuring stable operation under varying loads and environmental conditions. Through precise target calibration ratios and synchronous adjustments, unified optimization is performed across the entire grid, reducing line losses caused by insufficient or excessive local adjustments, thereby improving the overall efficiency and stability of the power grid.

[0051] The dynamic allocation module 13 is used to dynamically allocate the line loss control gain factor of each monitoring segment according to the abnormal line loss offset.

[0052] Furthermore, the dynamic allocation module 13 in the smart grid multi-sensor fusion line loss analysis system is also used for: a feedback adjustment unit, used for feedback adjustment using the line loss control gain factor, and returning to the normal line loss preset threshold range corresponding to the transmission line; and a feedback calibration unit, used for collecting the gain change rate of each monitoring segment during the feedback adjustment of the line loss control gain factor, and pausing one or more sets of data calibration actions corresponding to one or more edge calibration execution units if the gain change rate exceeds a preset safety threshold.

[0053] Specifically, based on the calculated abnormal line loss offset, a unique line loss control gain factor is dynamically assigned to each monitoring segment. The closer a monitoring segment is to the anomaly center coordinates, the greater its contribution to the problem, and the higher the assigned gain factor, meaning a stronger correction is needed. Once a line loss control gain factor is assigned to each monitoring segment, a feedback adjustment process is initiated. The goal is to adjust the line loss control gain factor to bring the line loss value of each monitoring segment back to the normal preset threshold range. Changes in the line loss status are continuously monitored, and new abnormal line loss offsets are fed back to the decision unit. The decision unit compares the new offset with the normal threshold range. If it still hasn't returned to normal, the line loss control gain factor for each monitoring segment is dynamically adjusted. This process is repeated until the line loss status is brought back to the normal threshold range.

[0054] During the feedback adjustment of the line loss control gain factor, the gain factor changes over time. The gain factor at each moment is collected in real time to obtain the rate of gain change for each monitoring segment. The rate of gain change is how quickly the line loss control gain factor changes over time, i.e., the amount of change in the gain factor per unit time, reflecting the drastic nature of the adjustment process. The preset safety threshold is a safety upper limit set to prevent overly aggressive control actions that could lead to system oscillation or equipment damage.

[0055] When the rate of gain change exceeds a preset safety threshold, the adjustment process is considered too drastic and may trigger unnecessary risks or erroneous operations. An excessively rapid rate of gain change can lead to over-adjustment, affecting grid stability and potentially causing unnecessary power fluctuations. To prevent escalation, one or more sets of data calibration actions corresponding to one or more edge calibration execution units are suspended, maintaining them in their current state or safe mode, and the dispatcher is immediately notified for intervention.

[0056] For example, suppose that line loss control gain factors are assigned to three monitoring segments based on the abnormal line loss offset. The line loss control gain factor for the abnormal center segment is 1.0, the line loss control gain factor for the adjacent eastern segment is 0.6, the line loss control gain factor for the adjacent western segment is 0.5, and the line loss control gain factor for other distant segments is 0, and they do not participate in this control. The three edge units adjust their local reactive power compensation devices proportionally according to the line loss control gain factors. After 5 seconds, the abnormal line loss offset is detected to have decreased from 5800m to 4500m, but it is still outside the threshold. The decision unit dynamically updates the line loss control gain factor, increasing the line loss control gain factor of the core segment from 1.0 to 1.2 to increase the control strength. In the next control cycle of 2 seconds, an abnormally high rate of change of the gain factor of the core segment is detected, reaching 0.3 / s, which means that the gain factor is being increased at a rate of 0.3 per second, while the preset safety threshold is 0.2 / s. The adjustment in this section was determined to be too aggressive, potentially indicating an unknown fault. The protection mechanism was immediately triggered: the control actions of the core section edge unit were suspended and fixed at the current output level; an alarm was sent to the dispatcher that at kilometer 5.8 of the western section of the line, line loss control was abnormal, the gain change rate exceeded the limit, and automatic control had been suspended; please check the on-site equipment! Adjustments in other sections continued, but new disturbances were avoided.

[0057] By dynamically allocating the gain factor for line loss regulation, differentiated adjustments are made to different monitoring sections of the power grid, thereby finely controlling the line loss values ​​of each section. Through a feedback adjustment mechanism, the power grid's operating status is monitored in real time, ensuring that the line loss of each monitoring section remains stable within the normal threshold range, thus improving the operational stability of the power grid. By limiting the rate of gain change, over-adjustment is avoided, ensuring smooth power grid operation and preventing fluctuations or instability caused by excessively rapid adjustments.

[0058] The line loss calibration module 14 is used to enhance the accuracy of line loss control in the smart grid by adjusting the gain factor based on the line loss of each monitoring segment and through each edge calibration execution unit deployed in each monitoring segment.

[0059] Furthermore, the line loss calibration module 14 in the aforementioned smart grid multi-sensor fusion line loss analysis system is also used for: a dominant interference factor determination unit, used for performing feature analysis on environmental impact data to determine the dominant interference factor and activating the interference compensation unit; a compensation adjustment unit, used for dynamically adjusting the compensation coefficient based on the dominant interference factor and through the matching relationship with the inherent compensation frequency of the interference compensation unit; and a line loss accuracy enhancement control unit, used for enhancing the line loss accuracy of the smart grid based on the line loss control gain factor of each monitoring segment and in combination with the compensation coefficient.

[0060] Furthermore, the line loss calibration module 14 in the smart grid multi-sensor fusion line loss analysis system is also used for: an identification command triggering subunit, used to introduce changes in the line loss calculation accuracy of the smart grid, and if the improvement speed within a preset time period after adjusting the compensation coefficient does not reach the expected improvement speed, triggering a secondary interference identification command; a secondary interference factor determination subunit, used to determine the secondary interference factors of the environmental impact data based on the secondary interference identification command; and a compensation strategy configuration subunit, used to configure a segmented compensation strategy according to the dominant interference factor and the secondary interference factor.

[0061] Specifically, environmental monitoring sensors deployed along transmission lines continuously collect environmental impact data, including temperature, humidity, wind speed, and solar radiation intensity. This data is transmitted to a central processing unit, where feature extraction algorithms are used for in-depth analysis to identify the dominant interference factors that have the most significant impact on line losses during the current period. Dominant interference factors refer to those factors that have the primary impact on line losses in the smart grid under specific environmental conditions. For example, during the high-temperature period in summer, ambient temperature may be the dominant interference factor; in windy seasons, wind speed may be the dominant interference factor; and in areas with strong sunlight, solar radiation intensity may be the dominant interference factor. For instance, the operating conditions under high-temperature summer weather are: ambient temperature 38.5℃, wind speed 2.3 m / s, and solar radiation intensity 892 W / m². 2 The relative humidity was 45%. Through comparison with historical data and real-time analysis, it was found that temperature contributed 0.62 to line loss, solar radiation intensity contributed 0.25, and wind speed contributed 0.13. Therefore, ambient temperature was determined to be the dominant interference factor.

[0062] After identifying the dominant interference factor, the interference compensation unit is activated. The interference compensation unit is a module in the power grid used to correct measurement data when affected by environmental interference. Through a compensation algorithm, parameters in the power grid are dynamically adjusted to mitigate the impact of environmental interference. The interference compensation unit adjusts the power grid's operating state based on external interference factors to ensure accurate line loss calculations. For example, if analysis shows that ambient temperature is the dominant factor, the temperature compensation unit is activated; if wind speed has the greatest impact, the wind speed compensation unit is activated. For example, the temperature compensation unit is activated with a natural frequency of 0.001Hz; the solar radiation compensation unit is activated with a natural frequency of 0.01Hz; based on a real-time temperature change rate of 0.8℃ / h, the dynamically calculated compensation coefficient is 0.76.

[0063] A matching relationship is established between the changing characteristics of the dominant interference factor and the inherent frequency of the compensation unit, and the compensation coefficient is dynamically adjusted according to the dominant interference factor. The compensation coefficient is used to adjust the line loss data of each monitoring segment in the power grid to more accurately reflect the actual situation. The magnitude of the compensation coefficient depends on the intensity of the interference factor and the sensitivity of the power grid operation, and is usually between 0 and 1, representing the proportion of compensation intensity. For example, assuming that the basic line loss control gain factor of a certain monitoring segment is 0.85, combined with a compensation coefficient of 0.76, 0.85*(1+0.76)=1.496. Based on this gain factor, the edge calibration execution unit adjusts the output of the reactive power compensation device, raising the power factor from 0.89 to 0.94, so that the line loss rate of this segment decreases from the original 1.32% to 0.98%, returning to the normal threshold range.

[0064] The compensation coefficient, adjusted for environmental factors, is integrated with the original line loss control gain factors of each monitoring segment. A weighted algorithm, considering both technical and management line losses, is used to generate a final, precise control command, which is then sent to each edge calibration execution unit. This achieves enhanced accuracy control of smart grid line losses. Enhanced line loss accuracy control refers to the precise calibration and optimized control of grid line loss data through dynamic adjustment of the compensation coefficient and line loss control gain factors. This effectively eliminates line loss data deviations caused by environmental interference factors, improving the accuracy and efficiency of grid operation.

[0065] The system introduces the variation in line loss calculation accuracy in smart grids, which refers to the dynamic process by which the actual line loss calculation result approaches the ideal target value after compensation based on the dominant interference factor is applied. The system monitors the trend of line loss calculation accuracy changes, especially its rate of improvement, comparing the actual rate of improvement with the internal expected rate of improvement. If the rate of improvement within a preset time period does not reach the expected rate of improvement, the initial compensation strategy is deemed partially ineffective, triggering a secondary interference identification command. The expected rate of improvement is a set standard value, referring to the rate at which the line loss calculation accuracy is expected to improve over a period of time after adjusting the compensation coefficient. If the actual rate of improvement does not reach the expectation, the system will determine that there is a possible secondary interference and initiate the identification mechanism. The secondary interference identification command is used to further identify and analyze secondary interference factors that may lead to poor adjustment effects. Secondary interference factors refer to other environmental factors besides the dominant interference factors that may affect grid line losses. For example, these may include local electromagnetic interference, equipment failure, and sudden load increases. Although the impact of these factors is relatively small, they may still affect the accuracy of line losses, especially after the impact of the dominant interference factor is compensated, at which point the secondary interference factors may become more pronounced.

[0066] Once the dominant and secondary interference factors are identified, a segmented compensation strategy is configured based on their spatial distribution characteristics across the entire line. The compensation strategy for each monitoring segment will employ different methods depending on its location, environmental impact, and the specific interference factor. For monitoring segments significantly affected by the dominant interference factor, a stronger compensation is provided; while for segments only affected by secondary interference factors, the compensation strategy may be less stringent. For example, suppose the dominant interference factor is temperature and the secondary interference factor is wind speed. Wind speed is unevenly distributed across the line; the western section is located in a windy area with an average wind speed of 4.5 m / s, while the eastern section is located in a leeward area with an average wind speed of 1.5 m / s. For the western section, the temperature compensation coefficient is set to 0.65, but due to the wind-cooling effect, the actual temperature is lower than the measured air temperature, so the temperature compensation intensity is reduced; the wind speed compensation coefficient is set to 0.80. For the eastern section, the temperature compensation coefficient is set to 0.80 to maintain strong temperature compensation, and the wind speed compensation coefficient is set to 0.20 to activate weak wind-cooling compensation.

[0067] By analyzing the characteristics of environmental impact data, the dominant and secondary interference factors affecting the accuracy of power grid line loss calculations are accurately identified, allowing for targeted compensation measures. Based on these dominant and secondary interference factors, segmented compensation strategies are flexibly configured to achieve precise control of different monitoring segments of the power grid. Through differentiated compensation strategies, power grid line losses are precisely controlled, improving overall operational efficiency.

[0068] Furthermore, the line loss calibration module 14 in the aforementioned smart grid multi-sensor fusion line loss analysis system is also configured as follows: an internal integration unit for integrating an H-bridge compensation drive circuit within the edge calibration execution unit; and an edge calibration unit for configuring the edge calibration execution unit to: receive calibration instructions and compensation coefficients issued by the line loss fusion decision unit; generate a reverse interference current through the H-bridge compensation drive circuit based on the calibration instructions and compensation coefficients; and actively cancel interference through the reverse interference current.

[0069] Specifically, the edge calibration execution unit is an intelligent power electronic device deployed at various monitoring points along the transmission line. It is responsible for receiving instructions from the fusion decision unit and directly applying precise control to the electrical parameters of the line. The H-bridge compensation drive circuit is a classic and flexible power electronic switching circuit, typically consisting of four controllable switches forming an H-shaped topology. By controlling the on and off states of these switches, it can directly generate a compensation current or voltage whose magnitude and direction can be precisely controlled.

[0070] The configured edge calibration execution unit continuously monitors the communication network from the power grid dispatch center, ready to receive calibration instructions and compensation coefficients from the line loss fusion decision unit. The microprocessor inside the edge calibration execution unit parses the received calibration instructions and compensation coefficients. The microprocessor generates corresponding pulse width modulation signals to drive the power switches in the internally integrated H-bridge compensation drive circuit. By controlling the on / off timing and duty cycle of each power switch, the H-bridge circuit can invert a DC power supply into a reverse interference current that perfectly matches the target. The reverse interference current is a current generated by the H-bridge circuit that is opposite in phase and complementary in waveform to the detected interference or abnormal current. When this reverse current is injected into the line, it superimposes with the original abnormal current (vector addition), effectively canceling or weakening the abnormal current, achieving a "fight fire with fire" effect.

[0071] The reverse interference current is directly injected into the transmission line through a connecting reactor. It is equal in magnitude but opposite in direction to the abnormal current present in the transmission line, and the two cancel each other out upon encountering each other in the line. Through active cancellation, the current is precisely adjusted without altering the overall operation of the power grid, reducing line losses caused by interference and improving the accuracy and stability of the power grid operation. The adjustment of the reverse interference current is a dynamic process; the edge calibration execution unit adjusts it based on real-time monitoring data to ensure the current reaches the preset standard and avoids excessive energy loss.

[0072] For example, suppose a 5-amp capacitive reactive current generated by an illegal electricity theft device is detected at a monitoring point, causing abnormal line loss at that point. The line loss fusion decision unit sends a command to the edge execution unit at that point. The calibration command is to inject a +5A inductive reactive current, opposite in phase to the capacitive reactive current, i.e., a reverse interference current; the compensation coefficient is 0.98, and according to real-time calculation, compensation with 98% intensity is required. The edge execution unit receives the command. Its internal controller calculates the target current amplitude to be generated as 5A*0.95=4.9A based on the compensation coefficient of 0.98. The controller generates a pulse width modulation signal to drive the four insulated gate bipolar transistors (IGBTs) of the H-bridge compensation drive circuit, causing them to output a 50Hz inductive reactive current with a precise phase of 4.9A. The 4.9A inductive reactive current is injected into the line and vector-superimposed with the 5A capacitive reactive current generated by the electricity theft device. The total reactive current at the monitoring point drops sharply from the abnormal 5A to a near-normal 0.1A. The corresponding reactive power line loss also decreased by more than 95%. The power factor measured by the upstream gate meter was significantly improved, and the line loss of the entire system returned to normal.

[0073] The H-bridge compensation drive circuit generates a reverse interference current to offset line loss fluctuations caused by environmental interference, load changes, or equipment failures, thereby improving the stability of the power grid. The combination of calibration commands and compensation coefficients makes the current adjustment process more precise, dynamically adjusting the compensation level based on real-time monitoring data to ensure the current in the power grid is always maintained at its optimal state. In the event of power grid anomalies, it responds quickly and actively cancels interference, thereby improving the power grid's adaptability to environmental changes and its anti-interference capability, ensuring the long-term efficient operation of the power grid.

[0074] In summary, the smart grid multi-sensor fusion line loss analysis system provided in this application has the following technical advantages:

[0075] The line loss analysis matrix formulation module 11 is used to formulate a line loss analysis matrix based on multi-sensor monitoring data for transmission lines in a smart grid, and to set the line loss deviation. The dynamic analysis module 12 is used to determine the abnormal line loss offset based on line parameter data. When the abnormal line loss offset exceeds the preset threshold range of normal line loss for the corresponding transmission line, a dynamic analysis mechanism is triggered: driving the line loss fusion decision unit of the power grid dispatch center to perform differentiated data calibration based on the line loss analysis matrix and the line loss deviation. The dynamic allocation module 13 is used to dynamically allocate the line loss control gain factor of each monitoring segment according to the abnormal line loss offset. The line loss calibration module 14 is used to enhance the line loss accuracy control of the smart grid based on the line loss control gain factor of each monitoring segment, through each edge calibration execution unit deployed in each monitoring segment. In other words, by deploying multiple sensors in different monitoring sections of the power grid, the status of each transmission line segment is monitored in real time. A line loss analysis matrix is ​​formulated, and a line loss deviation is set. When the line loss deviation of a certain monitoring segment exceeds the threshold, a dynamic analysis mechanism is triggered to perform differentiated data calibration based on the line loss analysis matrix and the line loss deviation. At the same time, line loss control gain factors are allocated to each monitoring segment according to the abnormal line loss offset. Through edge calibration execution units deployed in each monitoring segment, precise control of line loss is achieved, improving the accuracy of line loss analysis in the smart grid and thus improving the overall operating efficiency of the power grid.

[0076] Example 2: Based on the same inventive concept as the smart grid multi-sensor fusion line loss analysis system in Example 1, this application also provides a smart grid multi-sensor fusion line loss analysis method. Please refer to the appendix. Figure 2 The aforementioned smart grid multi-sensor fusion line loss analysis method includes:

[0077] For transmission lines based on smart grids, a line loss analysis matrix is ​​formulated using multi-sensor monitoring data, and line loss deviation is set. Line loss anomaly offset is determined using line parameter data. When the line loss anomaly offset exceeds the preset threshold range for normal line loss of the corresponding transmission line, a dynamic analysis mechanism is triggered: This drives the line loss fusion decision unit of the power grid dispatch center to perform differentiated data calibration based on the line loss analysis matrix and line loss deviation. Simultaneously, line loss control gain factors are dynamically allocated to each monitoring segment according to the line loss anomaly offset. Based on the line loss control gain factors of each monitoring segment, the accuracy of line loss control in the smart grid is enhanced through edge calibration execution units deployed in each monitoring segment.

[0078] Furthermore, the transmission line based on the smart grid, through multi-sensor monitoring data, formulates a line loss analysis matrix, including: establishing a three-dimensional topological coordinate system with the midpoint of the transmission line of the smart grid as the origin, performing correlation mapping on the multi-sensor monitoring data, determining the current monitoring deviation and voltage monitoring deviation; and constructing the line loss analysis matrix based on the current monitoring deviation and voltage monitoring deviation.

[0079] Furthermore, determining the abnormal offset of line loss through line parameter data includes: dividing the transmission line of the smart grid into M uniformly distributed monitoring segments, and obtaining the weighted average of line loss corresponding to the M uniformly distributed monitoring segments; using the midpoint of the transmission line as a reference point, and comparing the topological positions of the M uniformly distributed monitoring segments, identifying the coordinates of the abnormal line loss center through power balance; comparing the difference between the coordinates of the abnormal line loss center and the coordinates of the midpoint of the transmission line to determine the abnormal line loss offset vector value, wherein the abnormal line loss offset is the magnitude of the abnormal line loss offset vector value.

[0080] Furthermore, the differential data calibration based on the line loss analysis matrix and the line loss deviation includes: using fuzzy PID control to drive the synchronous adjustment of each edge calibration execution unit; and simultaneously, using the line loss fusion decision unit to determine the target calibration ratio of each edge calibration execution unit based on the line loss analysis matrix and the line loss deviation.

[0081] Furthermore, the method of using fuzzy PID control to drive the synchronous adjustment of each edge calibration execution unit includes: in each edge calibration execution unit, evaluating the local monitoring stability level based on the variance of the multi-sensor monitoring data; enabling the fuzzy PID control, and the line loss fusion decision unit dynamically adjusting the fuzzy control rules based on the local monitoring stability level, wherein the integral term accumulation time is positively correlated with the monitoring stability.

[0082] Furthermore, the step of dynamically allocating the line loss control gain factor for each monitoring segment based on the abnormal line loss offset includes: using the line loss control gain factor for feedback adjustment to bring it back to the normal line loss preset threshold range corresponding to the transmission line; during the feedback adjustment of the line loss control gain factor, collecting the gain change rate of each monitoring segment; if the gain change rate exceeds the preset safety threshold, pausing one or more sets of data calibration actions corresponding to one or more edge calibration execution units.

[0083] Furthermore, the method of enhancing the accuracy of line loss control in the smart grid based on the line loss control gain factor of each monitoring segment includes: performing feature analysis on environmental impact data to determine the dominant interference factors and activating the interference compensation unit; dynamically adjusting the compensation coefficient based on the dominant interference factors and the inherent compensation frequency of the interference compensation unit; and enhancing the accuracy of line loss control in the smart grid based on the line loss control gain factor of each monitoring segment and the compensation coefficient.

[0084] Furthermore, the dynamic adjustment of the compensation coefficient through the matching relationship with the inherent compensation frequency of the interference compensation unit includes: introducing the change in the line loss calculation accuracy of the smart grid; if the improvement speed within a preset time period after adjusting the compensation coefficient does not reach the expected improvement speed, triggering a secondary interference identification command; determining the secondary interference factors of the environmental impact data based on the secondary interference identification command; and configuring a segmented compensation strategy according to the dominant interference factors and the secondary interference factors.

[0085] Furthermore, the deployment of each edge calibration execution unit includes: the edge calibration execution unit integrates an H-bridge compensation drive circuit; the edge calibration execution unit is configured to: receive calibration instructions and compensation coefficients issued by the line loss fusion decision unit; generate a reverse interference current through the H-bridge compensation drive circuit based on the calibration instructions and compensation coefficients; and actively cancel interference through the reverse interference current.

[0086] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The smart grid multi-sensor fusion line loss analysis system and specific examples in the aforementioned embodiment one are also applicable to the smart grid multi-sensor fusion line loss analysis method in this embodiment. Through the foregoing detailed description of the smart grid multi-sensor fusion line loss analysis system, those skilled in the art can clearly understand the smart grid multi-sensor fusion line loss analysis method in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0087] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0088] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A smart grid multi-sensor fusion line loss analysis system, characterized in that, The method comprises the following steps: A line loss analysis matrix module is used to formulate a line loss analysis matrix based on the power transmission line of the smart grid through multi-sensor monitoring data, and set a line loss deviation amount; A dynamic analysis module is used to determine a line loss abnormal deviation amount through line parameter data, and when the line loss abnormal deviation amount exceeds a normal line loss preset threshold range corresponding to the power transmission line, a dynamic analysis mechanism is triggered: driving a line loss fusion decision unit of a power grid dispatching center to perform differential data calibration based on the line loss analysis matrix and the line loss deviation amount; A dynamic allocation module is used to dynamically allocate line loss control gain factors of each monitoring segment according to the line loss abnormal deviation amount; A line loss calibration module is used to perform smart grid line loss precision enhancement control through each edge calibration execution unit deployed in each monitoring segment based on the line loss control gain factors of each monitoring segment; The line loss calibration module comprises: A dominant interference factor determination unit is used to determine a dominant interference factor by performing feature analysis on environmental influence data, and activate an interference compensation unit; A compensation adjustment unit is used to dynamically adjust a compensation coefficient based on the dominant interference factor through a matching relationship with an inherent compensation frequency of the interference compensation unit; A line loss precision enhancement control unit is used to perform smart grid line loss precision enhancement control based on the line loss control gain factors of each monitoring segment in combination with the compensation coefficient; The compensation adjustment unit comprises: An identification instruction triggering subunit is used to introduce a line loss calculation precision change of the smart grid, and if the improvement speed within a preset time period after adjusting the compensation coefficient does not reach an expected improvement speed, a secondary interference identification instruction is triggered; A secondary interference factor determination subunit is used to determine a secondary interference factor of the environmental influence data based on the secondary interference identification instruction; A compensation strategy configuration subunit is used to configure a segmented compensation strategy according to the dominant interference factor and the secondary interference factor.

2. The smart grid multi-sensor fusion line loss analysis system of claim 1, wherein, The dynamic analysis module further comprises: A monitoring division unit is used to divide the power transmission line of the smart grid into M evenly distributed monitoring segments, and obtain line loss weighted average values corresponding to the M evenly distributed monitoring segments; An abnormal center coordinate identification unit is used to take the midpoint of the power transmission line as a reference point, and compare the topological positions of the M evenly distributed monitoring segments to identify a line loss abnormal center coordinate through power balance; A difference comparison unit is used to compare the line loss abnormal center coordinate with the midpoint coordinate of the power transmission line to determine a line loss abnormal deviation vector value, and the line loss abnormal deviation amount is the modulus value of the line loss abnormal deviation vector value.

3. The smart grid multi-sensor fusion line loss analysis system of claim 2, wherein, The dynamic allocation module further comprises: A feedback adjustment unit is used to perform feedback adjustment using the line loss control gain factor, and return to the normal line loss preset threshold range corresponding to the power transmission line; A feedback calibration unit is used to collect gain change rates of each monitoring segment during feedback adjustment of the line loss control gain factor, and if the gain change rate exceeds a preset safety threshold, suspend one or more groups of data calibration actions of the corresponding one or more edge calibration execution units.

4. The smart grid multi-sensor fusion line loss analysis system of claim 1, wherein, The line loss calibration module further comprises: An internal integrated unit is configured to internally integrate an H-bridge type compensation driving circuit in the edge calibration execution unit; An edge calibration unit is configured to configure the edge calibration execution unit to receive a calibration instruction and a compensation coefficient issued by the line loss fusion decision unit, generate a reverse interference current through the H-bridge type compensation driving circuit based on the calibration instruction and the compensation coefficient, and perform active interference cancellation through the reverse interference current.

5. The smart grid multi-sensor fusion line loss analysis system of claim 1, wherein, The line loss analysis matrix formulation module comprises: An association mapping unit is configured to establish a three-dimensional topological coordinate system with a midpoint of a power transmission line in a smart grid as an origin, to perform association mapping on the multi-sensor monitoring data, and to determine current monitoring deviation and voltage monitoring deviation; A matrix construction unit is configured to construct the line loss analysis matrix based on the current monitoring deviation and the voltage monitoring deviation.

6. The smart grid multi-sensor fusion line loss analysis system of claim 5, wherein, The dynamic analysis module further comprises: A synchronous adjustment unit is configured to drive each edge calibration execution unit to be synchronously adjusted by using fuzzy PID control; A calibration proportion determination unit is configured to determine a target calibration proportion of each edge calibration execution unit based on the line loss analysis matrix and a line loss deviation amount, and using the line loss fusion decision unit.

7. The smart grid multi-sensor fusion line loss analysis system of claim 6, wherein, The synchronous adjustment unit comprises: A level evaluation subunit is configured to evaluate local monitoring stability level based on variance of the multi-sensor monitoring data in each edge calibration execution unit; A fuzzy control rule adjustment subunit is configured to enable the fuzzy PID control, and the line loss fusion decision unit dynamically adjusts fuzzy control rules based on the local monitoring stability level, wherein the integral term accumulation time is positively correlated with the monitoring stability.

8. A smart grid multi-sensor fusion line loss analysis method, characterized in that, The smart grid multi-sensor fusion line loss analysis method is executed by the smart grid multi-sensor fusion line loss analysis system of any one of claims 1 to 7, and comprises: Based on the power transmission line of the smart grid, a line loss analysis matrix is formulated based on multi-sensor monitoring data, and a line loss deviation amount is set; Through line parameter data, a line loss abnormal offset amount is determined, and when the line loss abnormal offset amount exceeds a normal line loss preset threshold range corresponding to the power transmission line, a dynamic analysis mechanism is triggered: a line loss fusion decision unit of a power grid dispatching center performs differential data calibration based on the line loss analysis matrix and the line loss deviation amount; At the same time, the line loss control gain factor of each monitoring section is dynamically allocated according to the line loss abnormal offset amount; Based on the line loss control gain factor of each monitoring section, the line loss precision enhancement control of the smart grid is performed through each edge calibration execution unit deployed in each monitoring section.

Images