Power grid fault detection method, computer equipment and storage medium

Abstract

The invention relates to the technical field of power grid intelligent monitoring, and provides a power grid fault detection method, computer equipment and a storage medium, and the method comprises the steps: processing power grid state parameters, and obtaining a series of continuous data frames; obtaining an instantaneous change rate of the power grid parameter based on the data frame; and identifying a sudden change point according to the power grid parameter instantaneous change rate, extracting target power grid state parameter data corresponding to the sudden change point, and performing fault detection according to the target power grid state parameter data to obtain a fault detection result. By calculating the instantaneous change rate of the state parameters of the power grid and identifying the abrupt change point, the abnormal event or fault in the power grid can be identified more accurately, the limitation of a fixed threshold value is avoided, and the change of the state of the power grid can be dynamically adapted. Fault detection is performed by extracting the target power grid state parameter data corresponding to the abrupt change point, so that the influence of interference factors such as noise on a detection result is reduced, and the false alarm rate is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent power grid monitoring, and in particular to a power grid fault detection method, computer equipment, and storage medium. Background Art

[0002] With the continuous development and acceleration of the intelligentization process of power systems, intelligent monitoring and dispatch guidance systems for power grids play a vital role in modern power management. However, existing power grid monitoring technologies still face many challenges in fault detection.

[0003] Traditionally, power grid fault detection systems have relied primarily on fixed warning thresholds to determine whether the grid is abnormal. The drawback of this approach is that it cannot fully adapt to the dynamic changes in the grid environment. Because grid operation is affected by a variety of factors, such as weather conditions, load fluctuations, and equipment aging, the characteristics of fault signals are often diverse and complex. Fixed threshold methods are unable to handle these complex and ever-changing fault signals, easily resulting in some abnormal signals being missed or a high false alarm rate. Missing abnormal signals can prevent potential faults from being discovered and addressed in a timely manner, increasing the risk of grid operation. False alarms, on the other hand, waste valuable operation and maintenance resources and reduce overall system efficiency. Summary of the Invention

[0004] Based on this, a power grid fault detection method, computer equipment and storage medium are proposed, aiming to solve the technical problem that the existing power grid fault detection relies on a fixed threshold, resulting in some abnormal signals being missed or a high false alarm rate.

[0005] A first aspect of the present application provides a power grid fault detection method, the method comprising:

[0006] Obtain grid status parameter data;

[0007] Processing the power grid state parameter data to obtain a data frame sequence;

[0008] Calculating the instantaneous rate of change of the power grid parameter according to the data frame sequence;

[0009] Identifying a sudden change point according to the instantaneous rate of change of the power grid parameter;

[0010] Extracting target data corresponding to the mutation point;

[0011] Fault detection is performed according to the target data to obtain a fault detection result.

[0012] Optionally, calculating the instantaneous rate of change of the power grid parameter according to the data frame sequence includes:

[0013] Segmenting the data frame sequence using a preset time window to obtain a sliding window sequence;

[0014] For each sliding window, obtaining the effective current value, the effective voltage value, and the frequency change value of each data frame in the sliding window;

[0015] Obtaining a current difference based on the effective current values ​​of two adjacent data frames, and obtaining an instantaneous rate of change of the current in the sliding window based on the current difference;

[0016] Obtaining a voltage difference based on voltage effective values ​​of two adjacent data frames, and obtaining an instantaneous rate of change of voltage in the sliding window based on the voltage difference;

[0017] A frequency difference is obtained based on the frequency change values ​​of two adjacent data frames, and an instantaneous frequency change rate of the sliding window is obtained based on the frequency difference.

[0018] Optionally, identifying a mutation point according to the instantaneous rate of change of the power grid parameter includes:

[0019] Compare the instantaneous rate of change of current corresponding to any sliding window with the current mutation threshold, the instantaneous rate of change of voltage with the voltage mutation threshold, and the instantaneous rate of change of frequency with the frequency mutation threshold;

[0020] If the instantaneous change rate of current corresponding to any sliding window exceeds the current mutation threshold, or the instantaneous change rate of voltage exceeds the voltage mutation threshold, or the instantaneous change rate of frequency exceeds the frequency mutation threshold, then the any sliding window is determined to be a mutation point.

[0021] Optionally, performing fault detection according to the target data to obtain a fault detection result includes:

[0022] Determine the current change trend based on the target current data;

[0023] Determine voltage change trend based on target voltage data;

[0024] Determine the frequency change trend based on the target frequency data;

[0025] Fault detection is performed according to the current variation trend, the voltage variation trend, and the frequency variation trend to obtain a fault detection result.

[0026] Optionally, the method further includes:

[0027] Filtering an executable historical fault scheduling plan from a plurality of historical fault scheduling plans based on the fault detection result;

[0028] Calculating a comprehensive efficiency index of a power supply adjustment path in the executable historical fault scheduling scheme;

[0029] Calculating the power supply stability impact value of the power supply adjustment path in the executable historical fault scheduling scheme;

[0030] Determining an optimal power supply adjustment path based on the comprehensive efficiency index and the power supply stability impact value;

[0031] Power supply scheduling is performed according to the optimal power supply adjustment path.

[0032] Optionally, the selecting an executable historical fault scheduling solution from a plurality of historical fault scheduling solutions based on the fault detection result includes:

[0033] Screening out a plurality of candidate historical fault scheduling solutions from a plurality of historical fault scheduling solutions based on the fault type in the fault detection result;

[0034] Calculating the matching degree between the fault detection result and each candidate historical fault scheduling solution;

[0035] Filtering out a plurality of similar historical fault scheduling solutions from the plurality of candidate historical fault scheduling solutions according to the matching degree;

[0036] Obtain the power supply restoration time for each similar historical fault scheduling plan;

[0037] An executable historical fault scheduling plan is screened out from the multiple similar historical fault scheduling plans according to the power supply restoration time.

[0038] Optionally, the matching degree is calculated using the following formula:

[0039]

[0040] Among them, Z represents the matching degree, represents the active power of the i-th node in the historical fault scheduling scheme, represents the active power of the i-th node in the fault detection result, represents the reactive power of the jth node in the historical fault scheduling scheme, represents the reactive power of the jth node in the fault detection result, M represents the total number of nodes with active power in the fault detection result, and m represents the total number of nodes with reactive power in the fault detection result.

[0041] Optionally, the calculating the comprehensive efficiency index of the power supply adjustment path in the executable historical fault scheduling scheme includes:

[0042] Acquire power supply adjustment path data corresponding to the power supply adjustment path, the power supply adjustment path data including load carrying capacity, voltage, load current, line resistance, and power supply switching duration;

[0043] Calculating power loss based on the voltage, the load current, the line resistance, and the power switching duration;

[0044] A comprehensive efficiency index of the power supply adjustment path is obtained based on the power supply power loss, the power supply recovery time and the load carrying capacity.

[0045] A second aspect of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the power grid fault detection method when executing the computer program.

[0046] A third aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power grid fault detection method are implemented.

[0047] This application monitors various grid state parameters (such as voltage, current, and power) in real time to provide data support for subsequent processing and analysis. The grid state parameter data is then processed to obtain a series of continuous data frames, which helps better capture the dynamic changes in grid state parameters. By calculating the change in grid parameters between adjacent data frames, the instantaneous rate of change of the grid parameters is obtained, which can sensitively capture rapid changes in grid state and provide an important basis for identifying mutation points. Mutation points are identified based on the instantaneous rate of change of grid parameters. Mutation points often correspond to abnormal events or faults in the grid. After identifying the mutation points, the target grid state parameter data corresponding to the mutation points is extracted, and fault detection is performed based on the target grid state parameter data to obtain fault detection results. By calculating the instantaneous rate of change of grid state parameters and identifying mutation points, this application can more accurately identify abnormal events or faults in the grid, avoid the limitations of fixed thresholds, and dynamically adapt to changes in grid state. By extracting the target grid state parameter data corresponding to the mutation points for fault detection, the impact of interference factors such as noise on the detection results is reduced, thereby reducing the false alarm rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0049] Figure 1 It is a flow chart of the power grid fault detection method provided in an embodiment of the present application.

[0050] Figure 2 It is a flow chart of the smart grid dispatching method provided in the embodiment of the present application.

[0051] Figure 3 This is a functional module diagram of the power grid fault detection device provided in an embodiment of the present application.

[0052] Figure 4 It is a structural diagram of the computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0054] Figure 1 This is a flow chart of a power grid fault detection method provided in an embodiment of the present application. The power grid fault detection method includes the following steps.

[0055] S11, obtaining grid status parameter data.

[0056] In power system monitoring and management, grid status parameter data may include: current data, voltage data, and frequency data.

[0057] You can use current sensors to obtain grid current data, voltage sensors to obtain grid voltage data, and frequency sensors to obtain grid frequency data. To effectively obtain current, voltage, and frequency data, you can set the data collection interval (sampling period). For example, for applications with high real-time requirements, you can set a shorter interval (such as once per second); for applications with lower real-time requirements, you can set a longer interval (such as once per minute).

[0058] The current sensor acquires current data in amperes, the voltage sensor acquires voltage data in volts, and the frequency sensor acquires frequency data in hertz. For example, with a 10ms sampling period, the current sensor acquires current data of 2.1A, 2.3A, and 2.2A, respectively; the voltage sensor acquires voltage data of 220.5V, 221.1V, and 220.8V, respectively; and the frequency sensor acquires frequency data of 49.98Hz, 50.01Hz, and 49.99Hz, respectively.

[0059] S12: Process the power grid state parameter data to obtain a data frame sequence.

[0060] Processing the power grid state parameter data includes marking and encapsulating the power grid state parameter data.

[0061] The data collected by the current sensor, voltage sensor, and frequency sensor are marked according to the data collection timestamp. The data collection timestamp refers to the time information recorded during data collection, which is used to identify when the data was collected.

[0062] The data collected by the current sensor, voltage sensor, and frequency sensor at the same time is packaged into a data frame. Specifically, the current data, voltage data, and frequency data corresponding to the same data acquisition timestamp are packaged into a data frame. A data frame includes the current data, voltage data, and frequency data corresponding to the same timestamp. All data frames are arranged in chronological order to form a data frame sequence.

[0063] S13, calculating the instantaneous rate of change of the power grid parameters according to the data frame sequence.

[0064] The instantaneous rate of change of a grid parameter refers to the physical quantity that measures the speed at which a parameter (such as voltage, current, or power) in the grid changes over a short period of time. It can reflect the dynamic characteristics of the grid state. In this embodiment, the instantaneous rate of change of grid parameters includes the instantaneous rate of change of current, the instantaneous rate of change of voltage, and the instantaneous rate of change of frequency.

[0065] In an optional embodiment, calculating the instantaneous rate of change of the power grid parameter according to the data frame sequence includes:

[0066] Segmenting the data frame sequence using a preset time window to obtain a sliding window sequence;

[0067] For each sliding window, obtaining the effective current value, the effective voltage value, and the frequency change value of each data frame in the sliding window;

[0068] Obtaining a current difference based on the effective current values ​​of two adjacent data frames, and obtaining an instantaneous rate of change of the current in the sliding window based on the current difference;

[0069] Obtaining a voltage difference based on voltage effective values ​​of two adjacent data frames, and obtaining an instantaneous rate of change of voltage in the sliding window based on the voltage difference;

[0070] A frequency difference is obtained based on the frequency change values ​​of two adjacent data frames, and an instantaneous frequency change rate of the sliding window is obtained based on the frequency difference.

[0071] The time window can be a rolling time window or a sliding time window. A rolling time window continuously divides a data frame sequence into fixed-size windows, each of which is independent and non-overlapping. A sliding time window, on the other hand, allows overlap between windows and slides the window along the time axis by setting a sliding interval. By using a time window to slide across a data frame sequence with overlapping or non-overlapping time windows, multiple sliding windows can be obtained. These multiple sliding windows are sorted in chronological order to form a sliding window sequence. A sliding window includes multiple data frames, each of which corresponds to a current RMS value, a voltage RMS value, and a frequency change value.

[0072] The current RMS value can be the instantaneous current value, the voltage RMS value can be the instantaneous voltage value, and the frequency change value is calculated by the difference between the frequency data of two adjacent timestamps. For example, if the frequency data of the previous timestamp is 49.98 Hz and the frequency data of the next timestamp is 50.01 Hz, the frequency change value is 0.03 Hz.

[0073] The difference between the current RMS values ​​of two adjacent data frames is calculated to obtain the current difference, and the mean square error (MSE) calculation is performed based on all the current differences to obtain the instantaneous rate of change of current. The difference between the voltage RMS values ​​of two adjacent data frames is calculated to obtain the voltage difference, and the mean square error calculation is performed based on all the voltage differences to obtain the instantaneous rate of change of voltage. The difference between the frequency change values ​​of two adjacent data frames is calculated to obtain the frequency difference, and the mean square error calculation is performed based on all the frequency differences to obtain the instantaneous rate of change of frequency.

[0074] For example, assuming each data frame includes current data, voltage data, and frequency data at five timestamps, and the calculated current RMS values ​​are 2.1A, 2.3A, 2.2A, 2.4A, and 2.5A, respectively, then the corresponding current differences are 0.2A, -0.1A, 0.2A, and 0.1A, respectively. Similarly, the voltage and frequency differences are calculated.

[0075] S14, identifying a mutation point according to the instantaneous change rate of the power grid parameter.

[0076] A mutation point refers to a point where grid parameters change significantly in a short period of time. These changes may indicate an abnormality in the grid state or the occurrence of a fault.

[0077] Based on the fluctuation range of the power grid under normal operating conditions (i.e., the steady-state fluctuation range of the power grid), combined with the equipment operating conditions and safety control standards (i.e., the equipment rated value deviation standards), an instantaneous change rate threshold is set to distinguish between normal fluctuations and abnormal changes.

[0078] The instantaneous change rate thresholds include: current mutation threshold, voltage mutation threshold, and frequency mutation threshold. For example, the current mutation threshold is set based on the short-term allowable fluctuation of the equipment's rated current. For example, if the rated current of the power equipment is 10A and the short-term current fluctuation during normal operation is not allowed to exceed 5% of the rated current, then the current mutation threshold is set to 0.5A. The voltage mutation threshold is set based on the allowable voltage deviation range specified by the State Grid. For example, the voltage deviation of a 220V system is generally controlled within ±5%, so the voltage mutation threshold is set to 10V. The frequency mutation threshold is set based on the grid's stable operation standard. The grid's operating frequency is generally maintained within the range of 50Hz±0.05Hz, so the frequency mutation threshold is set to 0.05Hz.

[0079] The calculated instantaneous change rate of the power grid parameter is compared with the instantaneous change rate threshold, and the mutation point is identified based on the comparison result.

[0080] In an optional embodiment, identifying a mutation point according to the instantaneous rate of change of the grid parameter includes:

[0081] Compare the instantaneous rate of change of current corresponding to any sliding window with the current mutation threshold, the instantaneous rate of change of voltage with the voltage mutation threshold, and the instantaneous rate of change of frequency with the frequency mutation threshold;

[0082] If the instantaneous change rate of current corresponding to any sliding window exceeds the current mutation threshold, or the instantaneous change rate of voltage exceeds the voltage mutation threshold, or the instantaneous change rate of frequency exceeds the frequency mutation threshold, then the any sliding window is determined to be a mutation point.

[0083] The instantaneous rate of change is a physical quantity that describes how quickly data changes over a short period of time. By calculating the instantaneous rate of change, we can capture subtle changes in the data, providing a basis for subsequent threshold comparisons. By comparing the calculated instantaneous rate of change with the corresponding mutation threshold, we can determine whether the data has undergone significant mutations. If the instantaneous rate of change of a parameter exceeds the corresponding mutation threshold, it indicates that the parameter has undergone a mutation within the sliding window.

[0084] S15, extracting target data corresponding to the mutation point.

[0085] The sliding window corresponding to the mutation point and the two sliding windows preceding and following it are used as the target sliding window. The data frames within the target sliding window are extracted as target data. The target data includes the RMS current value, RMS voltage value, and frequency change value for each data frame within the target sliding window. The RMS current value for each data frame within the target sliding window is the target RMS current value, the RMS voltage value for each data frame within the target sliding window is the target RMS voltage value, and the frequency change value for each data frame within the target sliding window is the target frequency change value.

[0086] S16, performing fault detection according to the target data to obtain a fault detection result.

[0087] Fault detection is performed based on the current RMS value, voltage RMS value, and frequency change value of each data frame in the target sliding window to obtain fault detection results. The fault detection results may include: fault type, faulty power equipment ID, fault occurrence timestamp, abnormal parameter values, abnormal trend information, etc.

[0088] In an optional embodiment, performing fault detection according to the target data to obtain a fault detection result includes:

[0089] Determine the current change trend based on the target current data;

[0090] Determine voltage change trend based on target voltage data;

[0091] Determine the frequency change trend based on the target frequency data;

[0092] Fault detection is performed according to the current variation trend, the voltage variation trend, and the frequency variation trend to obtain a fault detection result.

[0093] The fault type is determined based on the current, voltage, and frequency trends. For example, if the current suddenly increases, the voltage suddenly decreases, and the frequency is stable, the fault type is a load surge fault; if the current suddenly decreases, the voltage drops sharply, and the frequency fluctuates violently, the fault type is a short circuit fault.

[0094] Figure 2 A flow chart of a method for intelligent dispatching of a power grid provided in an embodiment of the present application is provided, and the method for intelligent dispatching of a power grid includes the following steps.

[0095] S21 , selecting an executable historical fault scheduling solution from a plurality of historical fault scheduling solutions based on the fault detection result.

[0096] A historical fault dispatch plan is a fault response and solution developed based on past experience and strategies for handling similar faults. This plan includes diagnostic steps, remediation measures, required resources (such as spare parts and tools), and expected power restoration time for specific fault types.

[0097] In an optional implementation, the selecting an executable historical fault scheduling solution from a plurality of historical fault scheduling solutions based on the fault detection result includes:

[0098] Screening out a plurality of candidate historical fault scheduling solutions from a plurality of historical fault scheduling solutions based on the fault type in the fault detection result;

[0099] Calculating the matching degree between the fault detection result and each candidate historical fault scheduling solution;

[0100] Filtering out a plurality of similar historical fault scheduling solutions from the plurality of candidate historical fault scheduling solutions according to the matching degree;

[0101] Obtain the power supply restoration time for each similar historical fault scheduling plan;

[0102] An executable historical fault scheduling plan is screened out from the multiple similar historical fault scheduling plans according to the power supply restoration time.

[0103] Obtain parameters such as the fault type and fault occurrence timestamp from the fault detection result. Match the fault type in the fault detection result with the fault type in the historical fault scheduling plan, and query the historical fault scheduling plan with the same fault type as the fault type in the fault detection result as a candidate historical fault scheduling plan.

[0104] Calculate the matching degree between the fault detection result and each candidate historical fault scheduling plan.

[0105] In an optional embodiment, the matching degree is calculated using the following formula:

[0106]

[0107] Among them, Z represents the matching degree, represents the active power of the i-th node (power equipment, substation, etc.) in the historical fault dispatch plan, represents the active power of the i-th node in the fault detection result, represents the reactive power of the jth node in the historical fault scheduling scheme, represents the reactive power of the jth node in the fault detection result, M represents the total number of nodes with active power in the fault detection result, and m represents the total number of nodes with reactive power in the fault detection result.

[0108] Active power is calculated by the formula The reactive power is calculated by the formula Calculate and get, is the phase difference between current I and voltage U.

[0109] For example, assume that a candidate historical fault scheduling solution is:

[0110] Node 1:

[0111] Node 2:

[0112] Node 3:

[0113] The fault detection results are:

[0114] Node 1:

[0115] Node 2:

[0116] Node 3:

[0117] The matching degree between the fault detection result and the candidate historical fault scheduling plan is 0.767.

[0118] In an optional implementation, a matching threshold can be determined based on statistical analysis of dispatch execution and restoration success rates under different grid fault conditions. The statistical sample is selected from a past period of time, for example, fault events within five years. 1,000 valid samples are screened out, and the relationship between the matching degree of historical fault dispatch plans and the final power restoration success rate is calculated. When the matching degree is greater than 0.75, the restoration success rate stabilizes at above 85%. If the matching degree is less than 0.75, the restoration success rate drops below 60%. Therefore, the matching threshold is set at 0.75.

[0119] The matching degree is compared with a matching degree threshold (for example, 0.75). If the matching degree is greater than the matching degree threshold, it indicates that the corresponding candidate historical fault scheduling plan has a high similarity with the fault detection result, and the corresponding candidate historical fault scheduling plan is a similar historical fault scheduling plan.

[0120] Obtain the load transfer time, backup power supply startup time, and line switching time from similar historical fault scheduling plans. Calculate the power restoration time based on these times. For example, if the load transfer time is 20 minutes, the backup power supply startup time is 15 minutes, and the line switching time is 10 minutes, the power restoration time is 45 minutes.

[0121] Compare the power restoration time with the restoration time threshold. If the power restoration time exceeds the restoration time threshold, delete the similar historical fault scheduling plan corresponding to the power restoration time. If the power restoration time is less than the restoration time threshold, retain the similar historical fault scheduling plan corresponding to the power restoration time. Determine the retained similar historical fault scheduling plan as the executable historical fault scheduling plan.

[0122] In an optional implementation, a restoration time threshold can be determined based on the relationship between power restoration time and the user impact range in historical restoration events. For example, when power restoration time exceeds 60 minutes, the number of affected users increases, the user complaint rate rises from 10% to over 40%, and the economic losses to the power grid increase significantly. Therefore, setting the restoration time threshold at 60 minutes ensures that the selection of historical fault scheduling plans balances restoration efficiency and economic costs.

[0123] S22: Calculate the comprehensive efficiency index of the power supply adjustment path in the executable historical fault scheduling solution.

[0124] Each historical fault scheduling plan corresponds to a power supply adjustment path, which includes the main power supply line, the backup power supply line, and possible multi-level grid switching paths. The power supply adjustment path data corresponding to the executable historical fault scheduling plan is obtained from the power supply network data system. The power supply adjustment path data includes the load carrying capacity, voltage, load current, line resistance, power supply switching time, etc. of each node in the power grid. The comprehensive efficiency index of the power supply adjustment path is calculated based on the power supply adjustment path data. The comprehensive efficiency index is an indicator used to evaluate the overall effectiveness of the fault scheduling plan. Its purpose is to quantitatively evaluate the overall effectiveness of different fault scheduling plans so that the optimal adjustment strategy can be quickly selected when facing power grid failures or changes in demand.

[0125] In an optional implementation, the calculating the comprehensive efficiency index of the power supply adjustment path in the executable historical fault scheduling scheme includes:

[0126] Acquire power supply adjustment path data corresponding to the power supply adjustment path, the power supply adjustment path data including load carrying capacity, voltage, load current, line resistance, and power supply switching duration;

[0127] Calculating power loss based on the voltage, the load current, the line resistance, and the power switching duration;

[0128] A comprehensive efficiency index of the power supply adjustment path is obtained based on the power supply power loss, the power supply recovery time and the load carrying capacity.

[0129] The following formula can be used to calculate the power loss in each path based on the voltage, the load current, the line resistance, and the power switching time:

[0130]

[0131] Among them, P loss,i Represents the power loss of the i-th path, V nom,j Represents the rated voltage of the jth node in the path, V act,j Represents the actual voltage of the jth node in the path, I load,j represents the load current of the jth node in the path, R j represents the line resistance of the jth node in the path, T switch,j represents the power supply switching time of the jth node in the path, T base,j represents the benchmark time of the jth node in the path, and W represents the total number of nodes in the path.

[0132] The rated voltage is the standard voltage value specified when the equipment or system is designed, such as 48V. The actual voltage is obtained by real-time measurement using a voltage monitoring device (such as a voltmeter or sensor), for example, 46.5V. The load current is measured using a current sensor or ammeter to measure the actual current value at the node, for example, 10A. The line resistance is calculated based on parameters such as the material, length, and cross-sectional area of ​​the wire. For example, a copper wire with a length of 100 meters and a cross-sectional area of ​​10 square millimeters has a resistivity of ρ of 0.0175Ω·mm. 2 / m, then line resistance = resistivity * length / cross-sectional area. The power supply switching duration is the time interval between power interruption and restoration, recorded by the power supply system's monitoring equipment, for example, 5 milliseconds. The base time is a reference value used to normalize the switching duration and can be determined based on system design requirements, for example, 10 milliseconds.

[0133] Assuming that the calculated power loss is 21.43, it means that the power loss of a single node due to factors such as voltage deviation, load current, and line resistance is approximately 21.43 watts.

[0134] For example, assuming that the power recovery time of path A is 10 minutes and the power recovery time of path B is 15 minutes, the recovery efficiency of path A is better; if the power loss of path A is 30kW and the power loss of path B is 50kW, path A with lower power loss is prioritized; if the load carrying capacity of path A is 400MW and the load carrying capacity of path B is 390MW, path A with stronger load carrying capacity is prioritized.

[0135] After obtaining the power loss, power restoration time, and load carrying capacity of each path, the power loss, power restoration time, and load carrying capacity of each path are first normalized to obtain normalized power loss, normalized power restoration time, and normalized load carrying capacity. Then, based on the normalized power loss, normalized power restoration time, normalized load carrying capacity, a preset power loss weight, a preset power restoration time weight, and a preset normalized load carrying capacity weight, a comprehensive efficiency index for each path is calculated. Comprehensive efficiency index = preset power loss weight × normalized power loss + preset power restoration time weight × normalized power restoration time + preset load carrying capacity weight × normalized load carrying capacity.

[0136] The comprehensive efficiency index of each path is a score between 0 and 1, which is used to comprehensively evaluate the effectiveness of the path. Among them, 0 represents a completely unavailable path and 1 represents the optimal path. The higher the score, the lower the power loss of the path, the shorter the power recovery time, and the stronger the load carrying capacity. Compare the comprehensive efficiency index with the preset comprehensive efficiency index benchmark value (for example, 0.8). The preset comprehensive efficiency index benchmark value is used to screen effective paths and reflects the expectations and requirements of the power grid dispatching center for path effectiveness. After calculating the comprehensive efficiency index of all paths, the paths that are lower than the preset comprehensive efficiency index benchmark value will be deleted because these paths have greater risks in power supply stability. The paths that are higher than the preset comprehensive efficiency index benchmark value will be retained because these paths will show higher stability and efficiency in actual applications, providing strong support for the power grid dispatching center.

[0137] In an optional embodiment, the process of normalizing the power loss of each path may include summing the power losses of all paths to obtain a total power loss, and calculating the ratio of the power loss of each path to the total power loss to obtain a normalized power loss. The process of normalizing the power recovery time and load carrying capacity of each path is similar to the process of normalizing the power loss of each path. This application will not elaborate further.

[0138] S23: Calculate the power supply stability impact value of the power supply adjustment path in the executable historical fault scheduling solution.

[0139] To calculate the power stability impact of a power adjustment path, we need to obtain grid alarm log data. This data includes key information such as the faulty power device ID, fault type, abnormal parameter values, timestamp, voltage deviation, current deviation, load imbalance rate, and power value. Key nodes such as the power device ID, line, and substation are obtained from the power adjustment path data corresponding to the power adjustment path. The power device ID in the grid alarm log data is matched with the power device ID corresponding to the power adjustment path to select the target alarm log data directly related to the power adjustment path.

[0140] The power supply stability impact value is calculated based on the voltage deviation, current deviation, load imbalance rate, and power values ​​in the target alarm log data. The power supply stability impact value indicates the impact of the alarm event on power supply stability. A higher power supply stability impact value indicates a greater impact on power supply stability. A lower power supply stability impact value indicates a smaller impact on power supply stability.

[0141] In an optional implementation, the following formula may be used to calculate the power supply stability impact value based on the voltage deviation, current deviation, load imbalance rate, and power value:

[0142]

[0143] Among them, S impact Represents the power supply stability impact value; ΔV i represents the voltage deviation of the i-th monitoring point, y represents the number of voltage monitoring points; ΔI j represents the current deviation of the jth monitoring point, x represents the number of current monitoring points; U k represents the load imbalance rate of the kth monitoring point, U avg represents the average load imbalance rate of all monitoring points, p represents the number of load monitoring points; p t represents the power value of the tth monitoring point, and q represents the number of power monitoring points.

[0144] Assume that the following data is collected during a monitoring session:

[0145] The number of voltage monitoring points is 3, and the corresponding voltage deviations are 2V, 3V, and 1.5V respectively;

[0146] The number of current monitoring points is 3, and the corresponding current deviations are 0.5A, 0.7A, and 0.6A respectively;

[0147] The number of load monitoring points is 3, and the corresponding load imbalance rates are 0.02, 0.025, and 0.018 respectively;

[0148] The number of power monitoring points is 3, and the corresponding power values ​​are 100KW, 150KW, and 120KW respectively;

[0149] The calculated power supply stability impact value is 115.4.

[0150] S24: Determine an optimal power supply adjustment path based on the comprehensive efficiency index and the power supply stability impact value.

[0151] A higher overall efficiency index indicates a more optimal power supply adjustment path, while a smaller power supply stability impact value indicates a more optimal power supply adjustment path. After obtaining each power supply adjustment path, select the power supply adjustment solution that meets power supply requirements, maintains power supply stability, and achieves the highest overall efficiency index.

[0152] S25: Perform power supply scheduling according to the optimal power supply adjustment path.

[0153] After obtaining the optimal power supply adjustment path, the historical fault scheduling scheme corresponding to the optimal power supply adjustment path is determined. Based on the determined historical fault scheduling scheme, a scheduling strategy is generated and converted into a structured instruction format. The structured instruction format includes the task ID, target device, load adjustment scheme, and execution steps. If the task ID is T001, the target device is transformer X1, and the load adjustment scheme is to transfer 20MW of load to the backup power source, the instruction format is as follows: {Task ID: T001, Target device: X1, Load adjustment: 20MW, Execution steps: [Start the backup power source, adjust the main grid load distribution, and monitor voltage stability]}.

[0154] By constructing a data frame sequence, taking sensor data such as current, voltage, and frequency as input, a sliding window is used to calculate the difference and mean square error, identify mutation points, and classify fault characteristics in combination with signal pattern matching, the dynamic adaptability of fault identification is improved. Load status data and equipment operation data are combined with the power supply recovery time to calculate, eliminate solutions with longer recovery times, and screen the optimal solution in real time based on the supply and demand status. During the power supply adjustment process, the switching loss is calculated and the efficiency is compared based on the switching path of the affected area to ensure more accurate energy distribution during the scheduling process. The analysis of the power grid alarm log data is combined with the device ID, alarm type, and abnormal parameter value to calculate the impact of the alarm event on the power supply stability, making the risk assessment results more targeted, enhancing the accuracy of scheduling execution, making power supply recovery faster, and reducing the impact of sudden anomalies on power grid operation. At the same time, resource allocation is optimized to reduce unnecessary power loss.

[0155] This application monitors various grid state parameters (such as voltage, current, and power) in real time to provide data support for subsequent processing and analysis. The grid state parameter data is then processed to obtain a series of continuous data frames, which helps better capture the dynamic changes in grid state parameters. By calculating the change in grid parameters between adjacent data frames, the instantaneous rate of change of the grid parameters is obtained, which can sensitively capture rapid changes in grid state and provide an important basis for identifying mutation points. Mutation points are identified based on the instantaneous rate of change of grid parameters. Mutation points often correspond to abnormal events or faults in the grid. After identifying the mutation points, the target grid state parameter data corresponding to the mutation points is extracted, and fault detection is performed based on the target grid state parameter data to obtain fault detection results. By calculating the instantaneous rate of change of grid state parameters and identifying mutation points, this application can more accurately identify abnormal events or faults in the grid, avoid the limitations of fixed thresholds, and dynamically adapt to changes in grid state. By extracting the target grid state parameter data corresponding to the mutation points for fault detection, the impact of interference factors such as noise on the detection results is reduced, thereby reducing the false alarm rate.

[0156] Figure 4 This is a functional module diagram of the power grid fault detection device provided in an embodiment of the present application.

[0157] In some embodiments, the power grid fault detection device 30 may include a plurality of functional modules composed of program code segments. The program code of each program segment in the power grid fault detection device 30 may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Function of power grid fault detection.

[0158] In this embodiment, the power grid fault detection device 30 can be divided into multiple functional modules based on their functions. These functional modules may include a data acquisition module 301, a data processing module 302, a transient calculation module 303, a mutation identification module 304, a data extraction module 305, and a fault detection module 306. A module, as referred to herein, refers to a series of computer-readable instruction segments that can be executed by at least one processor and perform a fixed function, and is stored in a memory. The functions of each module in this embodiment will be described in detail in subsequent embodiments.

[0159] The data acquisition module 301 is used to acquire power grid state parameter data.

[0160] The data processing module 302 is used to process the power grid state parameter data to obtain a data frame sequence;

[0161] The instantaneous calculation module 303 is used to calculate the instantaneous change rate of the power grid parameter according to the data frame sequence;

[0162] The mutation identification module 304 is used to identify the mutation point according to the instantaneous change rate of the power grid parameter;

[0163] The data extraction module 305 is used to extract target data corresponding to the mutation point;

[0164] The fault detection module 306 is configured to perform fault detection according to the target data to obtain a fault detection result.

[0165] In an optional embodiment, the power grid fault detection device 30 further includes the following modules:

[0166] A solution screening module 307 is configured to screen out executable historical fault scheduling solutions from a plurality of historical fault scheduling solutions based on the fault detection result;

[0167] An efficiency calculation module 308 is configured to calculate a comprehensive efficiency index of the power supply adjustment path in the executable historical fault scheduling scheme;

[0168] A stability calculation module 309 is used to calculate the power supply stability impact value of the power supply adjustment path in the executable historical fault scheduling solution;

[0169] A path determination module 310 is configured to determine an optimal power supply adjustment path based on the comprehensive efficiency index and the power supply stability impact value;

[0170] The power supply scheduling module 311 is configured to perform power supply scheduling according to the optimal power supply adjustment path.

[0171] It should be understood that the various variations and specific embodiments of the power grid fault detection method provided in the above embodiments are also applicable to the power grid fault detection device in this embodiment. Through the detailed description of the above power grid fault detection method, those skilled in the art can clearly understand the implementation process of the power grid fault detection device in this embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0172] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, all or part of the steps of the power grid fault detection method are implemented.

[0173] See Figure 4 FIG. 4 is a schematic diagram of the structure of a computer device 4 provided in an embodiment of the present application. In a preferred embodiment of the present application, the computer device 4 includes a memory 401 , at least one processor 402 , and at least one communication bus 403 .

[0174] Those skilled in the art should understand that Figure 4 The structure of the computer device 4 shown does not constitute a limitation of the embodiments of the present application. The computer device 4 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components.

[0175] In some embodiments, the computer device 4 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices. The computer device 4 may also include client devices, which include, but are not limited to, any electronic product capable of human-computer interaction with a client via a keyboard, mouse, remote control, touchpad, or voice-controlled device, such as a personal computer, tablet computer, smartphone, digital camera, etc.

[0176] It should be noted that the computer device 4 is only an example. Other existing or future electronic products that are suitable for this application should also be included in the scope of protection of this application and included here by reference.

[0177] In some embodiments, the memory 401 stores a computer program, and when the computer program is executed by the at least one processor 402, all or part of the steps in the power grid fault detection method are implemented. The memory 401 includes a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data. Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, at least one application required for a function, and the like.

[0178] In some embodiments, the at least one processor 402 is the control core (Control Unit) of the computer device 4, which uses various interfaces and lines to connect the various components of the entire computer device 4, and executes various functions and processes data of the computer device 4 by running or executing programs or modules stored in the memory 401, and calling data stored in the memory 401. For example, when the at least one processor 402 executes the computer program stored in the memory, it implements all or part of the steps of the power grid fault detection method described in the embodiment of the present application; or implements all or part of the functions of the power grid fault detection device. The at least one processor 402 can be composed of an integrated circuit, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips.

[0179] In some embodiments, the at least one communication bus 403 is configured to implement connection and communication between the memory 401 and the at least one processor 402, etc. Although not shown, the computer device 4 may also include a power supply (such as a battery) to power each component. Preferably, the power supply can be logically connected to the at least one processor 402 through a power management device, so that functions such as charging, discharging, and power consumption management can be implemented through the power management device. The power supply may also include one or more DC or AC power supplies, a recharging power supply fault detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components. The computer device 4 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0180] The above-mentioned integrated unit implemented in the form of a software functional module can be stored in a computer-readable storage medium. The above-mentioned software functional module is stored in a storage medium and includes a number of instructions for causing a computer device 4 (which can be a personal computer, computer device 4, or network device, etc.) or a processor to execute part of the method described in each embodiment of the present application.

[0181] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is only a logical function division, and other division methods may be used in actual implementation.

[0182] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, and may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of this embodiment based on actual needs.

Claims

1. A power grid fault detection method, characterized in that: The method comprises: Obtain grid status parameter data; Processing the power grid state parameter data to obtain a data frame sequence; Calculating the instantaneous rate of change of the power grid parameter according to the data frame sequence; Identifying a sudden change point according to the instantaneous rate of change of the power grid parameter; Extracting target data corresponding to the mutation point; Fault detection is performed according to the target data to obtain a fault detection result.

2. The power grid fault detection method according to claim 1, characterized in that: The calculating of the instantaneous rate of change of the power grid parameter according to the data frame sequence includes: Segmenting the data frame sequence using a preset time window to obtain a sliding window sequence; For each sliding window, obtaining the effective current value, the effective voltage value, and the frequency change value of each data frame in the sliding window; Obtaining a current difference based on the effective current values ​​of two adjacent data frames, and obtaining an instantaneous rate of change of the current in the sliding window based on the current difference; Obtaining a voltage difference based on voltage effective values ​​of two adjacent data frames, and obtaining an instantaneous rate of change of voltage in the sliding window based on the voltage difference; A frequency difference is obtained based on the frequency change values ​​of two adjacent data frames, and an instantaneous frequency change rate of the sliding window is obtained based on the frequency difference.

3. The power grid fault detection method according to claim 2, characterized in that: The identifying of a mutation point according to the instantaneous rate of change of the power grid parameter comprises: Compare the instantaneous rate of change of current corresponding to any sliding window with the current mutation threshold, the instantaneous rate of change of voltage with the voltage mutation threshold, and the instantaneous rate of change of frequency with the frequency mutation threshold; If the instantaneous change rate of current corresponding to any sliding window exceeds the current mutation threshold, or the instantaneous change rate of voltage exceeds the voltage mutation threshold, or the instantaneous change rate of frequency exceeds the frequency mutation threshold, then the any sliding window is determined to be a mutation point.

4. The power grid fault detection method according to claim 3, characterized in that: The performing fault detection according to the target data to obtain a fault detection result includes: Determine the current change trend based on the target current data; Determine voltage change trend based on target voltage data; Determine the frequency change trend based on the target frequency data; Fault detection is performed according to the current variation trend, the voltage variation trend, and the frequency variation trend to obtain a fault detection result.

5. The power grid fault detection method according to claim 1, characterized in that: The method further comprises: Filtering an executable historical fault scheduling plan from a plurality of historical fault scheduling plans based on the fault detection result; Calculating a comprehensive efficiency index of a power supply adjustment path in the executable historical fault scheduling scheme; Calculating the power supply stability impact value of the power supply adjustment path in the executable historical fault scheduling scheme; Determining an optimal power supply adjustment path based on the comprehensive efficiency index and the power supply stability impact value; Power supply scheduling is performed according to the optimal power supply adjustment path.

6. The power grid fault detection method according to claim 5, characterized in that: The step of selecting an executable historical fault scheduling solution from a plurality of historical fault scheduling solutions based on the fault detection result includes: Screening out a plurality of candidate historical fault scheduling solutions from a plurality of historical fault scheduling solutions based on the fault type in the fault detection result; Calculating the matching degree between the fault detection result and each candidate historical fault scheduling solution; Filtering out a plurality of similar historical fault scheduling solutions from the plurality of candidate historical fault scheduling solutions according to the matching degree; Obtain the power supply restoration time for each similar historical fault scheduling plan; An executable historical fault scheduling plan is screened out from the multiple similar historical fault scheduling plans according to the power supply restoration time.

7. The power grid fault detection method according to claim 6, characterized in that: The matching degree is calculated using the following formula: Among them, Z represents the matching degree, represents the active power of the i-th node in the historical fault scheduling scheme, represents the active power of the i-th node in the fault detection result, represents the reactive power of the jth node in the historical fault scheduling scheme, represents the reactive power of the jth node in the fault detection result, M represents the total number of nodes with active power in the fault detection result, and m represents the total number of nodes with reactive power in the fault detection result.

8. The power grid fault detection method according to claim 5, characterized in that: Calculating the comprehensive efficiency index of the power supply adjustment path in the executable historical fault scheduling solution includes: Acquire power supply adjustment path data corresponding to the power supply adjustment path, the power supply adjustment path data including load carrying capacity, voltage, load current, line resistance, and power supply switching duration; Calculating power loss based on the voltage, the load current, the line resistance, and the power switching duration; A comprehensive efficiency index of the power supply adjustment path is obtained based on the power supply power loss, the power supply recovery time and the load carrying capacity.

9. A computer device, characterized in that: The computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the power grid fault detection method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the power grid fault detection method according to any one of claims 1 to 8 are implemented.

Images