Method for determining optimal regulation and control scheme of power grid and related device

Abstract

The embodiment of the invention relates to the field of data processing and power grid regulation and control, and provides a method and a related device for determining an optimal regulation and control scheme of a power grid, and the method comprises the steps: generating an alarm mode feature set according to the historical alarm data of the power grid; determining a causal relationship between an alarm signal and a fault event according to the alarm mode feature set to obtain an event causal relationship list; performing load prediction according to the historical load data and the current operation data of the power grid and the external factor information of the power grid to obtain a load prediction value; determining an emergency adjustment threshold value of a risk node according to the load prediction value and the event causal relationship list; generating an optimal response path of the fault event according to the emergency adjustment threshold value and the load prediction value; and generating the optimal regulation and control scheme of the power grid according to the optimal response path, so that the optimal regulation and control scheme of the power grid is generated based on the optimal response path, and the accuracy of determining the optimal regulation and control scheme of the power grid is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing and power grid control, and specifically to a method for determining an optimal power grid control scheme and related devices. Background Art

[0002] The field of power dispatching technology refers to the technology of coordinating, controlling and managing the power generation, transmission, distribution and consumption in the power system. Its main goal is to ensure the safe, stable and efficient operation of the power system. It includes real-time monitoring of the operating status of the power system, formulating and implementing the operation plan of the power system, coordinating the operation of various power equipment, and responding to emergencies and faults. Through effective dispatching strategies and technical means, the balance of power supply and demand can be achieved to ensure the continuous and reliable operation of the power system.

[0003] Among them, the power grid dispatch optimization system is a technical means in the field of power dispatch. Its main purpose is to optimize the operation mode of the power grid through algorithms and optimization models. During the operation of the power grid, the system can optimize the output of generator sets, power distribution of transmission lines, response to load demand, and other aspects to ensure that the power system achieves the optimal allocation of resources while meeting power supply needs.

[0004] In the process of power grid dispatch optimization, although the existing technology can optimize the dispatch of generator sets, transmission lines and load demands through algorithms and optimization models, it has the following problems when dealing with the complexity and dynamic changes in power grid operation. Specifically, it is difficult for the existing technology to respond to sudden abnormal conditions or rapidly changing load demands in the power system in a timely manner. The application of static models limits the dispatch system's accurate identification of alarm signals, resulting in inaccurate positioning of the source of the fault, which in turn affects the stability of the entire power grid. Summary of the invention

[0005] The embodiments of the present application provide a method and related devices for determining an optimal control scheme for a power grid, which can generate an optimal response path for a fault event by combining an alarm mode feature set generated by historical alarm data of the power grid and current operating data, and generate an optimal control scheme for the power grid based on the optimal response path, thereby improving the accuracy of determining the optimal control scheme for the power grid.

[0006] A first aspect of an embodiment of the present application provides a method for determining an optimal control scheme for a power grid, the method comprising:

[0007] Generate an alarm mode feature set based on historical alarm data of the power grid;

[0008] Determine the causal relationship between the alarm signal and the fault event according to the alarm mode feature set, and obtain an event causal relationship list;

[0009] Carry out load forecasting based on the historical load data of the power grid, the current operation data and the external factor information of the power grid to obtain the load forecast value;

[0010] Determine an emergency adjustment threshold of a risk node according to the load forecast value and the event causal relationship list;

[0011] generating an optimal response path for a fault event according to the emergency adjustment threshold and the load prediction value;

[0012] An optimal control scheme for the power grid is generated according to the optimal response path.

[0013] In this example, an alarm mode feature set is generated based on the historical alarm data of the power grid, the causal relationship between the alarm signal and the fault event is determined based on the alarm mode feature set to obtain an event causal relationship list, load forecasting is performed based on the historical load data of the power grid, the current operating data and the external factor information of the power grid to obtain a load forecast value, the emergency adjustment threshold of the risk node is determined based on the load forecast value and the event causal relationship list, the optimal response path of the fault event is generated based on the emergency adjustment threshold and the load forecast value, and the optimal control plan of the power grid is generated based on the optimal response path. Therefore, the optimal response path of the fault event can be generated in combination with the alarm mode feature set generated by the historical alarm data of the power grid and the current operating data, and the optimal control plan of the power grid is generated based on the optimal response path, thereby improving the accuracy of determining the optimal control plan of the power grid.

[0014] In a possible implementation, generating an alarm mode feature set according to historical alarm data of a power grid includes:

[0015] Determine the signal fluctuation information of each power grid device in the power grid according to the historical alarm data, and obtain a signal fluctuation feature set;

[0016] Performing clustering processing on the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set;

[0017] An alarm mode feature set is generated according to the cluster relationship set.

[0018] In a possible implementation, determining the signal fluctuation information of each power grid device in the power grid according to the historical alarm data to obtain the signal fluctuation feature set includes:

[0019] Determine the signal change frequency of each power grid device according to the historical alarm data;

[0020] Determine the total signal strength of each power grid device in each time period according to the historical alarm data;

[0021] A signal fluctuation feature set is generated according to the signal change frequency of each power grid device and the total signal strength of each power grid device in each time period.

[0022] In a possible implementation, clustering the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set includes:

[0023] Determine a signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain a signal difference measurement value set;

[0024] A clustering relationship set is determined according to the signal difference measurement value set.

[0025] In a possible implementation, determining the signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain a signal difference measurement value set includes:

[0026] The signal difference metric value in the signal difference metric value set is determined by the method shown in the following formula to obtain the signal difference metric value set:

[0027]

[0028] Among them, D new is the signal difference metric, p is the index of the time period, q is the total number of comparisons, and A p is the power grid equipment type coefficient, B p is the environmental impact coefficient, |S p1 -S p2 | is the absolute value of the signal strength difference, indicating that the signal strength of two different devices S in the pth time period p1 and S p2 The signal strength difference, C p is the operating frequency coefficient, and E is the grid state stability coefficient.

[0029] A second aspect of an embodiment of the present application provides a device for determining an optimal control scheme for a power grid, the device comprising:

[0030] A first generating unit, used to generate an alarm mode feature set according to historical alarm data of the power grid;

[0031] A first determining unit, configured to determine a causal relationship between an alarm signal and a fault event according to the alarm mode feature set, and obtain an event causal relationship list;

[0032] A prediction unit is used to perform load prediction based on the historical load data of the power grid, the current operation data and the external factor information of the power grid to obtain the load prediction value;

[0033] A second determining unit, configured to determine an emergency adjustment threshold of a risk node according to the load forecast value and the event causal relationship list;

[0034] A second generating unit, configured to generate an optimal response path for a fault event according to the emergency adjustment threshold and the load prediction value;

[0035] The third generating unit is used to generate an optimal control scheme for the power grid according to the optimal response path.

[0036] In a possible implementation, the first generating unit is specifically configured to:

[0037] Determine the signal fluctuation information of each power grid device in the power grid according to the historical alarm data, and obtain a signal fluctuation feature set;

[0038] Performing clustering processing on the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set;

[0039] An alarm mode feature set is generated according to the cluster relationship set.

[0040] In a possible implementation, in determining the signal fluctuation information of each power grid device in the power grid according to the historical alarm data to obtain the signal fluctuation feature set, the first generating unit is specifically configured to:

[0041] Determine the signal change frequency of each power grid device according to the historical alarm data;

[0042] Determine the total signal strength of each power grid device in each time period according to the historical alarm data;

[0043] A signal fluctuation feature set is generated according to the signal change frequency of each power grid device and the total signal strength of each power grid device in each time period.

[0044] In a possible implementation, in the aspect of performing clustering processing on the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain the cluster relationship set, the first generating unit is specifically configured to:

[0045] Determine a signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain a signal difference measurement value set;

[0046] A clustering relationship set is determined according to the signal difference measurement value set.

[0047] In a possible implementation, in determining the signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain the signal difference measurement value set, the first generating unit is specifically used to:

[0048] The signal difference metric value in the signal difference metric value set is determined by the method shown in the following formula to obtain the signal difference metric value set:

[0049]

[0050] Among them, D new is the signal difference metric, p is the index of the time period, q is the total number of comparisons, and A p is the power grid equipment type coefficient, B p is the environmental impact coefficient, |S p1 -S p2 | is the absolute value of the signal strength difference, indicating that the signal strength of two different devices S in the pth time period p1 and S p2 The signal strength difference, C p is the operating frequency coefficient, and E is the grid state stability coefficient.

[0051] A third aspect of an embodiment of the present application provides a terminal, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0052] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0053] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0055] Figure 1A flowchart of a method for determining an optimal power grid control scheme is provided for an embodiment of the present application;

[0056] Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0057] Figure 3 A structural schematic diagram of a device for determining an optimal power grid control scheme is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0059] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0060] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0061] In order to better understand the method for determining the optimal power grid control scheme provided by the embodiment of the present application, the following is a brief introduction to the method for determining the existing power grid control scheme. In the existing scheme, although the generator sets, transmission lines and load demands can be optimized and scheduled to a certain extent through algorithms and optimization models during the power grid dispatch optimization process, there are the following problems when dealing with the complexity and dynamic changes in power grid operation. Specifically, it is difficult for the existing technology to respond to sudden abnormal conditions or rapidly changing load demands in the power system in a timely manner. The application of static models limits the dispatch system's accurate identification of alarm signals, resulting in inaccurate positioning of the source of the fault, which in turn affects the stability of the entire power grid.

[0062] In order to solve the above-mentioned technical problems, an embodiment of the present application provides a method for determining an optimal control scheme for a power grid, which can generate an optimal response path for a fault event by combining an alarm mode feature set generated by historical alarm data of the power grid and current operating data, and generate an optimal control scheme for the power grid based on the optimal response path, thereby improving the accuracy of determining the optimal control scheme for the power grid.

[0063] See also Figure 1 , Figure 1 A flowchart of a method for determining an optimal power grid control scheme is provided for an embodiment of the present application. Figure 1 As shown, the method includes:

[0064] 101. Generate an alarm mode feature set based on historical alarm data of the power grid.

[0065] Among them, the alarm mode feature set includes abnormal fluctuation indicators of key node signals, frequency change patterns of signals, statistical characteristics of historical alarm events, etc.

[0066] Specifically, a method for generating an alarm mode feature set based on historical alarm data of a power grid includes:

[0067] A1. Determine the signal fluctuation information of each power grid device in the power grid according to the historical alarm data, and obtain a signal fluctuation feature set.

[0068] A method for determining signal fluctuation information of each power grid device in a power grid according to historical alarm data to obtain a signal fluctuation feature set includes:

[0069] A11. Determine the signal change frequency of each power grid device according to the historical alarm data;

[0070] A12. Determine the total signal strength of each power grid device in each time period according to the historical alarm data;

[0071] A13. Generate a signal fluctuation feature set according to the signal change frequency of each power grid device and the total signal strength of each power grid device in each time period.

[0072] Among them, first calculate the signal change frequency F of the i-th power grid equipment i , and then sum the signal strength S of each time period to obtain the total signal strength S of the i-th power grid device i The power grid equipment may be, for example, a transformer, a transmission line, a switchgear, etc.

[0073] Specifically, the signal change frequency F of the i-th power grid device can be determined by the method shown in the following formula: i :

[0074]

[0075] Among them, x ij Represents the signal existence state (0 or 1) of the i-th power grid device in the j-th time period, and n represents the total number of time periods.

[0076] The total signal strength S of the i-th grid device is determined by the method shown in the following formula: i :

[0077]

[0078] s ik represents the signal strength of the i-th power grid device in the k-th time period, and m represents the number of measurement points of the signal strength.

[0079] Finally, the data of all recorded power grid devices are integrated (the signal change frequency of each power grid device and the total signal strength of each power grid device in each time period) to reflect the overall signal fluctuation of each component, thereby generating a signal fluctuation feature set.

[0080] A2. Clustering the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set.

[0081] Specifically, a method for obtaining a clustering relationship set includes:

[0082] A21. Determine a signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain a signal difference measurement value set;

[0083] The signal difference metric value in the signal difference metric value set is determined by the method shown in the following formula to obtain the signal difference metric value set:

[0084]

[0085] Among them, D new is the signal difference metric, p is the index of the time period, q is the total number of comparisons, and A p is the power grid equipment type coefficient, B p is the environmental impact coefficient, |S p1 -S p2 | is the absolute value of the signal strength difference, indicating that the signal strength of two different devices S in the pth time period p1 and S p2 The signal strength difference, C p is the operating frequency coefficient, and E is the grid state stability coefficient.

[0086] Specifically, D newIt is a signal difference measurement value, which is used to measure the comprehensive difference of signals between different devices in power grid monitoring. p is the index of the time period, which indicates the current time period. The value of p increases gradually with the passage of time. q is the total number of comparisons, which indicates the total number of time periods involved in the calculation. p is the device type coefficient, which indicates the impact of device type on signal differences in the pth time period, reflecting the functions and importance of different types of devices in the power grid system. This coefficient is set according to the role of the device in the power grid. For example, the core device has a higher weight, and B p is the environmental impact coefficient, which indicates the degree of influence of environmental factors (such as weather) in the pth time period, reflecting the impact of external environmental conditions on device signals. This coefficient is adjusted according to the weather report and environmental monitoring data of the day. p1 -S p2 | is the absolute value of the signal strength difference, indicating that the signal strength of two different devices S in the pth time period p1 and S p2 The signal strength difference between devices reflects the instantaneous signal difference between S p1 and S p2 are the signal strengths of two different devices in the pth time period, and are the actual values ​​of the power grid monitoring signals sent by the devices. p is the operation frequency coefficient, which indicates the operation activity frequency of the equipment in the pth time period, and reflects the weight of the high-frequency operation equipment in the signal clustering analysis. This coefficient is obtained through the equipment operation data in the power grid operation log. E is the power grid state stability coefficient, which reflects the overall operation stability of the power grid. The sensitivity of signal clustering is adjusted according to the comprehensive evaluation results of indicators such as power grid load change and failure rate. If the power grid is unstable, this coefficient will increase.

[0087] The specific calculation process is as follows:

[0088] Equipment type factor A p :Based on the role and importance of the equipment in the power grid. Assume that the equipment in the power grid can be divided into three categories: core equipment, secondary equipment, and auxiliary equipment, and the corresponding type coefficients are set to A core , A secondary and A auxiliary Through the historical data of the power grid management system and the function definition of the equipment, a fixed value is assigned to each type of equipment, for example, A core =1.5, A secondary =1.0, A auxiliary =0.5.

[0089] Environmental impact factor B p:Based on daily weather reports and environmental monitoring data, this coefficient is set to adjust the impact of external environmental changes on device signals. For example, if extreme weather is forecast, such as heavy rain or high temperatures, the probability of device failure may increase, thereby affecting signal strength. p The value of can be adjusted proportionally based on the severity of the environment, such as normal weather B normal =1.0, bad weather B harsh =1.5.

[0090] Operating frequency C p :This coefficient reflects the frequency of equipment use. Equipment operation data is obtained through the power grid operation log, and the average daily operation times of each equipment are calculated. For example, if the average daily operation times of a certain equipment exceeds 50% of the standard times, then C p Can be set to 1.5, otherwise 1.0. Helps increase the weight of frequently operated devices in signal clustering.

[0091] Grid state stability coefficient E: The overall operational stability of the grid is evaluated through a real-time monitoring system. Through a comprehensive evaluation of indicators such as load changes and failure rates of the grid, if the grid state is stable, E is set to 1.0; if it is unstable, E can be increased to 1.5 or higher to improve the sensitivity of signal clustering analysis.

[0092] In each time period p, each coefficient calculated above is multiplied by the absolute value of the signal difference in the corresponding time period. This method combines the influence of all relevant factors and provides more accurate data support for power grid dispatching.

[0093] Result D new A comprehensive adjusted signal difference metric is provided, which not only reflects the difference of the signal itself, but also takes into account the influence of external environment, equipment type, operating frequency and grid status. This makes grid monitoring more accurate, which plays an important role in preventing faults, optimizing dispatch and improving the operation efficiency of the grid.

[0094] A22. Determine a clustering relationship set according to the signal difference measurement value set.

[0095] The signal differences between different devices can be accumulated according to the signal difference measurement value set to determine the clustering result and finally form a clustering relationship set.

[0096] A3. Generate an alarm pattern feature set based on the cluster relationship set.

[0097] Based on the clustering relationship set, the influence of the signal on the equipment failure is evaluated, a weight is assigned to each signal type, and an alarm mode feature set is generated, specifically:

[0098] The signal weight W is calculated based on the frequency and strength of the signal. The weighted average method is used to determine the influence of each signal type. The calculation formula is:

[0099]

[0100] Among them, W is the weight value of the signal, F r and S r Respectively represent the frequency and average signal strength of the rth type of signal in the clustering results, and t represents the total number of signal types. The actual influence of each signal type in the fault is taken into account to ensure a more reasonable weight distribution.

[0101] 102. Determine the causal relationship between the alarm signal and the fault event according to the alarm mode feature set, and obtain an event causal relationship list.

[0102] The event causal relationship list includes the associated signal characteristics of load fluctuation and voltage abnormality events, the occurrence sequence and time interval of fault events, and the fault triggering factors of key equipment.

[0103] Specifically, the method of determining the causal relationship between the alarm signal and the fault event according to the alarm mode feature set and obtaining the event causal relationship list includes:

[0104] B1. Use the alarm mode feature set to filter the signals associated with power load fluctuation and voltage anomaly, record the signal features and occurrence time, and generate the associated signal set. The specific process is as follows;

[0105] The signal features include weights W inherited from the alarm pattern feature set, which are used to emphasize the importance of the signal in fault prediction. The generation of the feature set involves weighting each signal to ensure that signals that are highly relevant to the fault are prioritized. The calculation formula is: represents the weighted signal characteristics, is the signal weight inherited from the alert mode feature set, is the strength or frequency of the original signal. i1 represents different signal indexes, which are used to distinguish and track different signals in the power grid.

[0106] B2. Based on the associated signal set, compare the time of signal occurrence and the associated equipment failure event, sort the order of events, and generate causal time series sorting data. The specific process is:

[0107] The time of occurrence of events is located and compared by time marker T, and the time sequence is performed using the following formula: is the time point when the event occurs, n1 is the total number of events, is the weighted signal feature corresponding to each event. By sorting the time, we get the sorting result T sort , thereby revealing possible causal relationships.

[0108] B3. Sort the data by causal time series, build the relationship matrix between signals and events, calculate the correlation strength between signals and events, and generate a list of event causal relationships. The specific process is:

[0109] The method of constructing the relationship matrix relies on the integrated analysis of signal characteristics and time-sequencing data, and uses the following formula to calculate the association strength: represents the correlation strength between the i1th signal and the j1th event, is the weight of the i1th signal, is the ranking weight of the time point associated with the j1th event, m1 is the number of signals considered, and e is the base of the natural logarithm. By providing a smoothed correlation strength, it allows for a quantitative assessment of the complex relationship between events and signals.

[0110] 103. Load forecasting is performed based on the historical load data of the power grid, current operation data and external factor information of the power grid to obtain load forecast values.

[0111] The load forecast value includes the forecast load adjusted according to seasonal changes, analysis of key external factors affecting grid operation, and maximum power demand.

[0112] The details are as follows:

[0113] C1. Collect historical power grid load data and current operation data, record the fluctuation of power grid load in each period, collect load change data, and perform fluctuation trend analysis to generate real-time fluctuation data set. The specific process is as follows;

[0114] This process involves calculating the average load value for each time period And find the standard deviation of the load in each period To evaluate the volatility and reflect the real-time dynamic changes of load. The calculation formula is:

[0115] and

[0116] represents the load value of the i2th measuring point in the t1th time period, h is the total number of measuring points in this period, is the average load value, It represents the standard deviation of load fluctuation during this period, which is used to evaluate the load variation range and stability.

[0117] C2. Based on the real-time fluctuation data set, analyze the external factors of weather changes and seasonal power demand, evaluate the impact of external factors on the grid load, and generate external impact analysis results. The specific process is:

[0118] By analyzing the specific impact of external factors on the load, for each influencing factor Assign an influence coefficient β a The relevant calculation formula is:

[0119]

[0120] represents the external influence intensity in the t1th period, represents the value of the ath external factor in the t1th period, n2 is the total number of external factors, β a It is the influence coefficient of each external factor obtained through historical data regression analysis, reflecting the specific influence of different factors on the load, and β0 is the initial influence coefficient.

[0121] C3. Based on the external impact analysis results, combined with historical load data and real-time changes, load forecast calculation is performed using the sliding window method to generate load forecast values. The specific process is as follows;

[0122] In this step, the sliding window size W is set to the optimal value obtained from the periodic analysis of historical data, and the predicted load It is based on the weighted average load of the past W periods and the external influence adjustment.

[0123] The sliding window method follows the formula:

[0124]

[0125] Calculate the load forecast value for time period t1

[0126] in, It represents the load forecast value in time period t1, which is the target result obtained by the final calculation, reflecting the expected load situation of the power grid in this time period. W is the size of the sliding window, which represents the time window length of the historical data used to calculate the forecast value. Choosing a suitable W can smooth the fluctuation of historical data. j2 represents the index of each time period in the sliding window. represents the load value in time period j2, reflecting the actual load situation of the power grid in the past period. K′ is the network load stability coefficient, which represents the relative degree of load fluctuation in the past period. The calculated value is used to adjust the historical load data to make it closer to the actual fluctuating load level. S′ is the seasonal adjustment factor, which reflects the typical impact of seasons on load, especially under the influence of seasonal electrical equipment (such as air conditioning and heating). The calculated value is used to adjust the historical load data to make it more accurately reflect the load demand of the current season. It represents the external influence intensity in time period j2, reflecting the influence of external environmental factors (such as weather, festivals, etc.) on the grid load. R′ is the frequency regulation response rate, which represents the response efficiency of the grid system after a sudden load change. The calculated value is used to adjust the external influence data so that it can reflect the actual response capability of the grid in the frequency regulation operation. V′ is the load fluctuation index, which represents the volatility of the load in the historical data. The calculated value is used to adjust the external influence data so that it can reflect the actual performance of the load under different fluctuation conditions.

[0127] The calculation process is as follows:

[0128] The network load stability coefficient K′ is calculated by the average load value L per day in the past week. avg and standard deviation L std Calculated.

[0129] Calculate the average daily load value L avg :

[0130]

[0131] Where n is the number of days in a week, usually 7, L i is the load value on the i-th day.

[0132] Calculate the standard deviation L within the week std :

[0133]

[0134] The network load stability coefficient K′ is obtained by the following formula:

[0135]

[0136] This coefficient indicates the relative degree of load fluctuation. The larger the coefficient, the more severe the load fluctuation.

[0137] The frequency regulation response rate R′ is calculated by analyzing historical frequency regulation operation data to calculate the response efficiency of the power grid system after a sudden load change.

[0138] Extract the response time T of each frequency modulation operation from the historical frequency modulation records resp and load change rate Fchange :

[0139]

[0140] Where m is the total number of FM events, is the response time of the kth frequency modulation, is the corresponding load change rate.

[0141] R′ is calculated by weighted average, where the weight is determined by the frequency modulation response time and the load change rate. Frequency modulation events with shorter response time and greater change rate account for a higher proportion in the coefficient calculation.

[0142] The load fluctuation index V′ analyzes the load fluctuation within the time period based on the historical data of the power grid during the same period.

[0143] Extract the load change rate F from the historical data in the same time period hist :

[0144]

[0145] Among them, T is the length of the time period under investigation, L t and L t-1 are the load values ​​of the tth period and the previous period respectively. The calculated V′ is used to quantify the volatility of the load within the period. The greater the volatility, the higher the index.

[0146] The seasonal adjustment factor S′ is adjusted according to the typical impact of the season on the grid load, especially the impact on seasonal electrical equipment such as air conditioning and heating.

[0147] Analyze seasonal load changes in historical data, such as peak loads in summer and winter:

[0148]

[0149] in, is the peak load in the sth season, and n is the number of recorded seasons.

[0150] S′ reflects the impact of seasonal electricity consumption on the overall load. For example, the seasonal factor of the peak air conditioning usage in summer will be relatively high.

[0151] The final It is a more accurate load forecast value, which not only takes into account historical load patterns and external factors, but also introduces coefficients closely related to grid dispatching. It can more accurately reflect the actual operation status of the grid under different load fluctuations, frequency regulation responses, seasonal changes and other conditions, thereby providing more reliable data support for grid dispatching decisions.

[0152] 104. Determine an emergency adjustment threshold of the risk node according to the load forecast value and the event causal relationship list.

[0153] Emergency adjustment thresholds include emergency adjustment thresholds for risk nodes and threshold updates based on data analysis.

[0154] The details are as follows:

[0155] D1. Use load forecast values ​​and event causal relationship lists to analyze real-time alarm signals of key nodes, record the range and frequency of signal changes, organize signal characteristic data, and generate alarm signal characteristic sets. The specific process is as follows;

[0156] In this process, the real-time alarm signal of each key node is Comparison is performed to assess whether the signal exceeds the normal operating range, using the rate of change of the signal Δs v Calculate the degree of deviation from the predicted value. The formula is: s v It represents the actual load signal value of the vth node at time t1, which is used to reflect the instantaneous power consumption status of the node.

[0157] D2. Based on the alarm signal characteristic set, calculate the deviation between the signal change rate and the preset threshold, analyze the deviation trend and update the deviation record to generate the threshold deviation data set. The specific process is as follows;

[0158] Using event causality To adjust the deviation calculation to take into account the correlation between historical events and the current signal. The formula for calculating the deviation of the signal change rate is expanded to: δ v represents the deviation of the signal change rate of the vth node after adjusting for historical causality, z is the total number of events considered, and u is the index of the event, which is used to iterate each considered event to calculate the overall deviation.

[0159] D3. Update the threshold parameters to match the real-time operation requirements of the power grid through the threshold deviation data set, and generate adjusted threshold parameters. The specific process is as follows;

[0160] δ v Used to determine the new threshold for each node, ensuring that the threshold matches the real-time data and historical causal relationships. New threshold T v The calculation method is: T v =T base +b×δ v , T base is the basic threshold, which indicates the initial setting of the threshold, and b is the adjustment coefficient, which is set according to actual operation needs and is used to adjust the threshold according to the deviation trend. This adjustment mechanism ensures that the dynamic adjustment of the threshold is more accurate and reflects the operation status of the power grid in real time.

[0161] 105. Generate an optimal response path for a fault event according to the emergency adjustment threshold and the load forecast value.

[0162] The optimal response path includes response measures for priority nodes, resource allocation plans at critical time points, and estimated fault recovery time.

[0163] The details are as follows:

[0164] E1. Based on the adjusted threshold parameters and load forecast values, record and analyze the operating status of key components of transformers, transmission lines, and switchgear, measure the current and voltage data of each component, evaluate its load bearing capacity, identify the characteristics of potential fault points, and generate component status data sets. The specific process is as follows;

[0165] In this process, the current I of each key component c Continuously monitor the voltage Vc and calculate the load factor λ c To evaluate the load of the component, the formula is: I rated and V rated are the rated current and rated voltage of the component, T v is the adjusted threshold parameter, It is the load forecast value, which is used to determine the comparison between the actual operating state of the component and the predicted state.

[0166] E2. Use the component status data set to calculate the distance and time required from the potential fault point to the response device, analyze the resource consumption of each node in the path, and generate a response path resource table. The specific process is:

[0167] By determining the optimal combination of resources and time Use the expression: is the distance between the k2th nodes, is the speed limit of the path, n3 is the total number of nodes in the path, T v and The ratio is used to adjust the time estimate to ensure that it is consistent with current network conditions and predicted load.

[0168] E3. Select the path with the best resource consumption and response time through the response path resource table to generate the optimal response path. The specific process is as follows:

[0169] Using the cost function C path To evaluate the overall efficiency of each path, the cost function is: α and β1 are weight parameters used to adjust the time T fg and resource consumption Rfg The relative importance in path selection, d is the number of paths considered, T v and The ratio is used to refine the resource and time assessment to ensure that the response strategy matches the actual load situation.

[0170] 106. Generate an optimal power grid control plan according to the optimal response path.

[0171] The best control plan for the network can be the dispatch optimization result. The dispatch optimization result includes energy efficiency improvement in the dispatch area, synchronization of key operation time, and optimized equipment operation frequency information.

[0172] The details are as follows:

[0173] F1. Based on the optimal response path, measure and record the structural data of nodes and connections in the power grid, evaluate the impact of the data on the operation of the power grid, and generate topological complexity analysis results. The specific process is:

[0174] By identifying the configuration of key nodes and connections and how they affect the overall efficiency and stability of the power grid, the connection density and structural importance between nodes are calculated using the formula: C topo Represents topological complexity, which is used to measure the structural complexity of the network; L x is the number of lines connected to the xth node, which is used to measure the connectivity of the node; X is the total number of nodes in the network, which represents the network size. This metric helps identify key areas that may cause network bottlenecks or failures.

[0175] F2. Using the results of topological complexity analysis, calculate and adjust the operating parameters of transformers and transmission lines, perform time series analysis on frequency adjustment, and generate a dispatch strategy parameter table. The specific process is as follows;

[0176] By adjusting the network frequency to accommodate predicted load changes and actual demand, the formula used is: F adj =F base +r1·ΔF,F adj is the adjusted frequency, which is expressed as the adjusted frequency of the power grid operation; F base is the basic frequency, which refers to the basic frequency of standard operation of the power grid; ΔF is the change in frequency demand caused by topology changes or load changes, reflecting the impact of load changes on frequency; r1 is the adjustment coefficient, which is determined based on historical data and prediction models to accurately control the sensitivity of frequency adjustment.

[0177] F3. Based on the dispatch strategy parameter table, adjust according to the current power load demand and generate the best power grid control plan. The specific process is:

[0178] The cost of using the optimal response path Cpath As input, to ensure that the optimal grid control scheme not only optimizes the efficiency of the grid but also meets the stability requirements of the grid. The final optimal grid control scheme formula is: C opt It is the total cost after optimization, which is used to evaluate the economy and efficiency of the overall scheduling; is the cost of the y-th path, indicating the resource consumption and operation cost under this path; Y is the number of paths, indicating the number of different strategies or path solutions considered; γ is the coefficient that weighs the influence of topological complexity, which is used to balance the path cost and the stability of the network structure, and is adjusted based on analysis and actual needs.

[0179] In this example, an alarm mode feature set is generated based on the historical alarm data of the power grid, the causal relationship between the alarm signal and the fault event is determined based on the alarm mode feature set to obtain an event causal relationship list, load forecasting is performed based on the historical load data of the power grid, the current operating data and the external factor information of the power grid to obtain a load forecast value, the emergency adjustment threshold of the risk node is determined based on the load forecast value and the event causal relationship list, the optimal response path of the fault event is generated based on the emergency adjustment threshold and the load forecast value, and the optimal control plan of the power grid is generated based on the optimal response path. Therefore, the optimal response path of the fault event can be generated in combination with the alarm mode feature set generated by the historical alarm data of the power grid and the current operating data, and the optimal control plan of the power grid is generated based on the optimal response path, thereby improving the accuracy of determining the optimal control plan of the power grid.

[0180] For the above embodiments, please refer to Figure 2 , Figure 2 A schematic diagram of the structure of a terminal provided in an embodiment of the present application, such as Figure 2 As shown, it includes a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0181] Generate an alarm mode feature set based on historical alarm data of the power grid;

[0182] Determine the causal relationship between the alarm signal and the fault event according to the alarm mode feature set, and obtain an event causal relationship list;

[0183] Carry out load forecasting based on the historical load data of the power grid, the current operation data and the external factor information of the power grid to obtain the load forecast value;

[0184] Determine an emergency adjustment threshold of a risk node according to the load forecast value and the event causal relationship list;

[0185] generating an optimal response path for a fault event according to the emergency adjustment threshold and the load prediction value;

[0186] An optimal control scheme for the power grid is generated according to the optimal response path.

[0187] In this example, an alarm mode feature set is generated based on the historical alarm data of the power grid, the causal relationship between the alarm signal and the fault event is determined based on the alarm mode feature set to obtain an event causal relationship list, load forecasting is performed based on the historical load data of the power grid, the current operating data and the external factor information of the power grid to obtain a load forecast value, the emergency adjustment threshold of the risk node is determined based on the load forecast value and the event causal relationship list, the optimal response path of the fault event is generated based on the emergency adjustment threshold and the load forecast value, and the optimal control plan of the power grid is generated based on the optimal response path. Therefore, the optimal response path of the fault event can be generated in combination with the alarm mode feature set generated by the historical alarm data of the power grid and the current operating data, and the optimal control plan of the power grid is generated based on the optimal response path, thereby improving the accuracy of determining the optimal control plan of the power grid.

[0188] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0189] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0190] In line with the above, see Figure 3 , Figure 3 The present invention provides a schematic diagram of a structure of a device for determining an optimal power grid control scheme. Figure 3 As shown, the device comprises:

[0191] The first generating unit 301 is used to generate an alarm mode feature set according to historical alarm data of the power grid;

[0192] A first determining unit 302 is used to determine the causal relationship between the alarm signal and the fault event according to the alarm mode feature set, and obtain an event causal relationship list;

[0193] The prediction unit 303 is used to perform load prediction based on the historical load data of the power grid, the current operation data and the external factor information of the power grid to obtain the load prediction value;

[0194] A second determining unit 304 is used to determine an emergency adjustment threshold of a risk node according to the load forecast value and the event causal relationship list;

[0195] A second generating unit 305, configured to generate an optimal response path for a fault event according to the emergency adjustment threshold and the load prediction value;

[0196] The third generating unit 306 is used to generate an optimal control scheme for the power grid according to the optimal response path.

[0197] In a possible implementation, the first generating unit 301 is specifically configured to:

[0198] Determine the signal fluctuation information of each power grid device in the power grid according to the historical alarm data, and obtain a signal fluctuation feature set;

[0199] Performing clustering processing on the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set;

[0200] An alarm mode feature set is generated according to the cluster relationship set.

[0201] In a possible implementation, in determining the signal fluctuation information of each power grid device in the power grid according to the historical alarm data to obtain the signal fluctuation feature set, the first generating unit 301 is specifically used to:

[0202] Determine the signal change frequency of each power grid device according to the historical alarm data;

[0203] Determine the total signal strength of each power grid device in each time period according to the historical alarm data;

[0204] A signal fluctuation feature set is generated according to the signal change frequency of each power grid device and the total signal strength of each power grid device in each time period.

[0205] In a possible implementation, in the aspect of clustering the alarm signals of the power grid devices according to the signal fluctuation feature set to obtain the cluster relationship set, the first generating unit 301 is specifically used to:

[0206] Determine a signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain a signal difference measurement value set;

[0207] A clustering relationship set is determined according to the signal difference measurement value set.

[0208] In a possible implementation, in determining the signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain the signal difference measurement value set, the first generating unit 301 is specifically used to:

[0209] The signal difference metric value in the signal difference metric value set is determined by the method shown in the following formula to obtain the signal difference metric value set:

[0210]

[0211] Among them, D new is the signal difference metric, p is the index of the time period, q is the total number of comparisons, and A p is the power grid equipment type coefficient, B p is the environmental impact coefficient, |S p1 -S p2 | is the absolute value of the signal strength difference, indicating that the signal strength of two different devices S in the pth time period p1 and S p2 The signal strength difference, C p is the operating frequency coefficient, and E is the grid state stability coefficient.

[0212] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method for determining an optimal power grid control scheme as recorded in the above method embodiments.

[0213] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any method for determining an optimal power grid control scheme as recorded in the above method embodiments.

[0214] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0215] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0216] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0217] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0218] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0219] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0220] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0221] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for determining an optimal power grid control scheme, characterized in that: The method comprises: Generate an alarm mode feature set based on historical alarm data of the power grid; Determine the causal relationship between the alarm signal and the fault event according to the alarm mode feature set, and obtain an event causal relationship list; Carry out load forecasting based on the historical load data of the power grid, the current operation data and the external factor information of the power grid to obtain the load forecast value; Determine an emergency adjustment threshold of a risk node according to the load forecast value and the event causal relationship list; generating an optimal response path for a fault event according to the emergency adjustment threshold and the load prediction value; An optimal control scheme for the power grid is generated according to the optimal response path.

2. The method for determining the optimal control scheme of a power grid according to claim 1, characterized in that: The generating of the alarm mode feature set according to the historical alarm data of the power grid includes: Determine the signal fluctuation information of each power grid device in the power grid according to the historical alarm data, and obtain a signal fluctuation feature set; Performing clustering processing on the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set; An alarm mode feature set is generated according to the cluster relationship set.

3. The method for determining the optimal control scheme of the power grid according to claim 2, characterized in that: The method of determining the signal fluctuation information of each power grid device in the power grid according to the historical alarm data to obtain the signal fluctuation feature set includes: Determine the signal change frequency of each power grid device according to the historical alarm data; Determine the total signal strength of each power grid device in each time period according to the historical alarm data; A signal fluctuation feature set is generated according to the signal change frequency of each power grid device and the total signal strength of each power grid device in each time period.

4. The method for determining the optimal control scheme of the power grid according to claim 3, characterized in that: The clustering process is performed on the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set, including: Determine a signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain a signal difference measurement value set; A clustering relationship set is determined according to the signal difference measurement value set.

5. The method for determining the optimal control scheme of a power grid according to claim 4, characterized in that: The step of determining the signal difference measurement value between each power grid device and other power grid devices according to the signal fluctuation feature set to obtain a signal difference measurement value set includes: The signal difference metric value in the signal difference metric value set is determined by the method shown in the following formula to obtain the signal difference metric value set: Among them, D new is the signal difference metric, p is the index of the time period, q is the total number of comparisons, and A p is the power grid equipment type coefficient, B p is the environmental impact coefficient, |S p1 -S p2 | is the absolute value of the signal strength difference, indicating that the signal strength of two different devices S in the pth time period p1 and S p2 The signal strength difference, C p is the operating frequency coefficient, and E is the grid state stability coefficient.

6. A device for determining an optimal control scheme for a power grid, characterized in that: The device comprises: A first generating unit, used to generate an alarm mode feature set according to historical alarm data of the power grid; A first determining unit, configured to determine a causal relationship between an alarm signal and a fault event according to the alarm mode feature set, and obtain an event causal relationship list; A prediction unit is used to perform load prediction based on the historical load data of the power grid, the current operation data and the external factor information of the power grid to obtain the load prediction value; A second determining unit, configured to determine an emergency adjustment threshold of a risk node according to the load forecast value and the event causal relationship list; A second generating unit, configured to generate an optimal response path for a fault event according to the emergency adjustment threshold and the load prediction value; The third generating unit is used to generate an optimal control scheme for the power grid according to the optimal response path.

7. The device for determining the optimal control scheme of a power grid according to claim 6, characterized in that: The first generating unit is specifically used for: Determine the signal fluctuation information of each power grid device in the power grid according to the historical alarm data, and obtain a signal fluctuation feature set; Performing clustering processing on the alarm signals of the power grid equipment according to the signal fluctuation feature set to obtain a cluster relationship set; An alarm mode feature set is generated according to the cluster relationship set.

8. The device for determining the optimal control scheme of a power grid according to claim 7, characterized in that: In the aspect of determining the signal fluctuation information of each power grid device in the power grid according to the historical alarm data to obtain the signal fluctuation feature set, the first generating unit is specifically used for: Determine the signal change frequency of each power grid device according to the historical alarm data; Determine the total signal strength of each power grid device in each time period according to the historical alarm data; A signal fluctuation feature set is generated according to the signal change frequency of each power grid device and the total signal strength of each power grid device in each time period.

9. A terminal, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method for determining the optimal control scheme of a power grid as described in any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method for determining the optimal control scheme of a power grid as described in any one of claims 1 to 5.

Images