A power equipment mutual exclusivity hierarchical determination method, system, device and medium based on a backtracking technique

Abstract

The application discloses a kind of based on backtracking technique's electric power equipment mutual exclusivity hierarchical determination method, system, equipment and medium, comprising: establishing power transmission section power flow control model, model is used to characterize the influence relationship of high-voltage maintenance equipment outage to associated low-voltage equipment power flow, and model is configured as single device control model or multi-loop control model according to maintenance scene;Predict the power flow data of high-voltage maintenance equipment and its associated low-voltage equipment in the maintenance period to be predicted using power flow backtracking technology, generate predicted power flow data sequence;The predicted power flow data sequence is substituted into power transmission section power flow control model, and the expected power flow value of associated low-voltage equipment is obtained when high-voltage maintenance equipment is shut down;According to the comparison result of expected power flow value and the thermal stability limit of associated low-voltage equipment, the mutual exclusivity between high-voltage maintenance equipment and associated low-voltage equipment is hierarchically determined. It can effectively optimize maintenance resource allocation and scheduling decision efficiency under the premise of guaranteeing power grid stable operation.

Description

Technical Field

[0001] This invention relates to the technical field of power system maintenance, and in particular to a method, system, equipment, and medium for determining the mutual exclusion of power equipment based on backtracking technology. Background Technology

[0002] With the growth of electricity demand, the power system has gradually evolved from a traditional unidirectional chain structure of generation, transmission, transformation, distribution, and consumption into a complex network that includes multiple entities such as new energy sources, energy storage, and microgrids. The number of devices has increased significantly, and the topological connections and functional couplings between devices are tighter. The maintenance of one device may affect the operating status of multiple related devices. If mutually exclusive devices are maintained at the same time, it can easily trigger systemic risks.

[0003] Existing rules for determining equipment mutual exclusion primarily rely on manual analysis of the spatial relationship between the out-of-power equipment and the substation, the voltage levels of different equipment, and the electrical connections between them, to construct mutual exclusion rules. These rules assess maintenance mutual exclusion based on three aspects: whether the outage creates electrical islanding, whether simultaneous maintenance of multiple devices generates additional outage loads, and whether the network reconfiguration caused by maintenance satisfies electrical constraints. While these studies are relatively comprehensive, they overlook the fact that the power system is a real-time operating system constantly affected by fluctuations from both the power supply and load sides. The load side experiences daily peak-to-valley differences and seasonal fluctuations; the power supply side is constrained by natural conditions, exhibiting randomness and intermittency in output. This dynamic fluctuation necessitates considering the power flow through the equipment when analyzing mutual exclusion for maintenance equipment. Therefore, a method for mutual exclusion analysis based on equipment power flow is urgently needed to accurately determine the mutual exclusion of equipment outages. Summary of the Invention

[0004] In view of the aforementioned existing problems, this invention is proposed. Therefore, this invention provides a method, system, device, and medium for determining the mutual exclusion of power equipment based on backtracking technology, solving the problem of inaccurate equipment mutual exclusion determination in existing power system maintenance plans.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide a method for determining the mutual exclusion of power equipment based on backtracking technology, including: establishing a power flow control model for a transmission section, wherein the model is used to characterize the influence relationship of the shutdown of high-voltage maintenance equipment on the power flow of associated low-voltage equipment, and the model is configured as a single equipment control model or a multi-circuit line control model according to the maintenance scenario. Power flow backtracking technology is used to predict the power flow data of the high-voltage equipment under maintenance and its associated low-voltage equipment during the maintenance period, and a predicted power flow data sequence is generated. Substituting the predicted power flow data sequence into the power flow control model of the transmission section, the expected power flow value of the associated low-voltage equipment is calculated when the high-voltage maintenance equipment is out of service. Based on the comparison between the expected power flow value and the thermal stability limit of the associated low-voltage equipment, the mutual exclusivity between the high-voltage maintenance equipment and the associated low-voltage equipment is classified and determined.

[0006] As a preferred embodiment of the power equipment mutual exclusion classification determination method based on backtracking technology described in this invention, the step of establishing a power flow control model for transmission sections includes: When the maintenance scenario involves a single device, a transmission section control model is established under the maintenance of a single device, represented as follows: ; in, The distribution coefficient, For high voltage level lines The initial power flow value, For low voltage level lines The initial power flow value, For low voltage level lines Thermal stability limits; When the maintenance scenario involves multiple circuits, a transmission section control model is established for power outage maintenance of multiple circuits, represented as follows: ; in, , These are the initial power flows of the double loop. To correlate the initial power flow of low-voltage lines, , The lines are respectively and lines For the line The distribution coefficient, For the line The thermal stability limit at the current temperature.

[0007] As a preferred embodiment of the power equipment mutual exclusion classification determination method based on backtracking technology described in this invention, the method includes: predicting the power flow data of the high-voltage maintenance equipment and its associated low-voltage equipment during the maintenance period using power flow backtracking technology, including: Collect historical power flow data, historical meteorological data, and future weather forecast data; Based on the similarity between the future weather forecast data and the historical weather data, target similar historical days are dynamically selected. The historical power flow data of the equipment corresponding to the similar historical days are trend-corrected, and weighted fusion is performed based on the similarity to generate a predicted power flow data sequence.

[0008] As a preferred embodiment of the power equipment mutual exclusion classification determination method based on backtracking technology described in this invention, the step of dynamically filtering target similar historical days based on the similarity between the future weather forecast data and the historical weather data includes: Set the weather forecast vector for the forecast day, and extract the historical weather measurement vector for the previous calendar year and the previous month of the same year from the historical database. The meteorological elements in the meteorological forecast vector and the meteorological observation vector are standardized to obtain a standardized meteorological feature vector. Based on the standardized vector, the Euclidean distance between the forecast day and each historical day is calculated, and the Euclidean distance is converted into a similarity index. Sort all candidate historical days according to similarity index, set a decreasing threshold, and examine them sequentially starting from the first historical day in the sorted sequence. If the similarity index of the kth historical day is not less than the product of the decreasing threshold and the highest similarity value, then include it in the set of similar days. The filtering process stops when the similarity value of the k-th historical day is less than the product of the decreasing threshold and the highest similarity value, or when the target historical day is examined. If the number of selected historical days is less than M, then the first M days are forcibly selected as the set of similar days; if there are more than N days, then only the first N days are selected to obtain the final target similar historical days.

[0009] As a preferred embodiment of the power equipment mutual exclusion classification determination method based on backtracking technology described in this invention, the method includes: performing trend correction on the historical power flow data of the equipment corresponding to the similar historical days, and weighted fusion based on the similarity to generate a predicted power flow data sequence, including: Obtain the device historical power flow data sequence for the corresponding time in the target similar historical day; Calculate the load growth rate coefficient, and use the load growth rate coefficient to perform amplitude correction on the historical power flow data sequence of the equipment to obtain trend-corrected power flow data; wherein, the load growth rate coefficient is the ratio of the maximum load of the entire network in the same region in the previous month to the maximum load of the entire network in the same period last year in the previous month; The normalized weights are calculated based on the similarity index corresponding to the target similar historical days; the trend-corrected tidal flow data of each target similar historical day are weighted and summed with the corresponding normalized weights to generate the predicted tidal flow data sequence.

[0010] As a preferred embodiment of the power equipment mutual exclusion classification determination method based on backtracking technology described in this invention, wherein: the predicted power flow data sequence is substituted into the power flow control model of the transmission section to calculate the expected power flow value of the associated low-voltage equipment when the high-voltage maintenance equipment is out of service, including: Obtain the predicted power flow data sequence of the high-voltage line to be inspected on the predicted date and its associated low-voltage line before the shutdown, as well as the predicted power flow data sequence of the equipment to be inspected before the shutdown. Substitute the predicted power flow data sequence of the maintenance equipment into the power flow control model of the transmission section to infer the expected power flow value of the associated equipment at the corresponding time when the maintenance equipment is out of service.

[0011] As a preferred embodiment of the power equipment mutual exclusion classification method based on backtracking technology described in this invention, the mutual exclusion between the high-voltage maintenance equipment and the associated low-voltage equipment is classified and determined according to the comparison result between the expected power flow value and the thermal stability limit value of the associated low-voltage equipment, including: The expected power flow time series of the associated equipment is compared with the thermal stability limit of the associated equipment; if the value at all times in the expected power flow time series is not greater than the thermal stability limit, then the mutual exclusion between the high-voltage maintenance equipment and the associated low-voltage equipment is determined to be at the safe level. If there is an over-limit moment that exceeds the thermal stability limit, then under the premise of satisfying the power grid operation constraints, it is determined whether there is a feasible control strategy that makes the power flow value of the associated equipment after control not greater than the thermal stability limit. If a feasible control strategy can be found for all out-of-limit moments, then the mutual exclusion is determined to be controllable; if there is at least one out-of-limit moment, and even if the feasible control strategy is adopted, it is still impossible to ensure that the power flow value of the associated equipment after control is not greater than the thermal stability limit, then the mutual exclusion is determined to be risky.

[0012] Secondly, the present invention provides a power equipment mutual exclusion classification judgment system based on backtracking technology, including: a model building module, used to establish a power flow control model of a transmission section, wherein the model is used to characterize the influence relationship of the power flow of associated low-voltage equipment after the high-voltage maintenance equipment is shut down, and the model is configured as a single equipment control model or a multi-circuit line control model according to the maintenance scenario. The power flow prediction module is used to predict the power flow data of the high-voltage maintenance equipment and its associated low-voltage equipment during the maintenance period using power flow backtracking technology, and generate a predicted power flow data sequence. The expected value calculation module is used to substitute the predicted power flow data sequence into the power flow control model of the transmission section to calculate the expected power flow value of the associated low-voltage equipment when the high-voltage maintenance equipment is out of service. The classification and determination module is used to classify and determine the mutual exclusion between the high-voltage maintenance equipment and the associated low-voltage equipment based on the comparison result between the expected power flow value and the thermal stability limit value of the associated low-voltage equipment.

[0013] Thirdly, the present invention provides an electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the power equipment mutual exclusion classification determination method based on backtracking technology.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the power equipment mutual exclusion classification determination method based on backtracking technology.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: By introducing power flow backtracking technology, this invention incorporates meteorological characteristics affecting load fluctuations and renewable energy output, overcoming the limitations of traditional methods that rely solely on static topology to determine mutual exclusion. It accurately identifies dynamic mutual exclusion relationships that are only mutually exclusive at specific power flow levels, avoiding misjudgments or omissions caused by static assumptions. Furthermore, by classifying equipment mutual exclusion into levels, this invention provides dispatchers with more refined decision-making information than traditional binary judgments. For controllable equipment, maintenance can be scheduled after implementing corresponding control plans, improving the flexibility of maintenance planning.

[0016] By employing refined assessment and coordinated control plans, more equipment can be maintained simultaneously while ensuring the safe operation of the power grid. This shortens the total downtime of equipment, optimizes maintenance windows, and reduces generation opportunities or grid operation restrictions caused by equipment maintenance. The method of this invention does not rely on fixed manual rules but rather performs calculations and analyses based on real-time or predictive data. When the power grid topology changes or the installed capacity of new energy sources fluctuates, it can adapt to the new environment by re-collecting data and calculating distribution coefficients. Furthermore, it can be extended to scenarios involving the mutual exclusion analysis of multiple equipment maintenance combinations. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of a method for determining the mutual exclusion of power equipment based on backtracking technology according to an embodiment of the present invention; Figure 2This is a control operation area diagram of the distribution coefficient method control form of a power equipment mutual exclusion classification determination method based on backtracking technology, as described in one embodiment of the present invention. Figure 3 This is a flow control operation area diagram of a power equipment mutual exclusion classification determination method based on backtracking technology according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the power equipment mutual exclusion classification assessment process according to an embodiment of the present invention, which describes a power equipment mutual exclusion classification determination method based on backtracking technology. Figure 5 This is a network topology diagram of a local power system according to an embodiment of the present invention, which describes a method for determining the mutual exclusion of power equipment based on backtracking technology. Figure 6 This is an over-limit determination curve of a power equipment mutual exclusion classification determination method based on backtracking technology according to an embodiment of the present invention. Detailed Implementation

[0018] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0019] Example 1, referring to Figures 1-4 This is one embodiment of the present invention, which provides a method for determining the mutual exclusion hierarchy of power equipment based on backtracking technology, such as... Figure 1 As shown, it includes: S100: Establish a power flow control model for the transmission section. The model is used to characterize the impact of the shutdown of high-voltage maintenance equipment on the power flow of associated low-voltage equipment. The model is configured as a single equipment control model or a multi-circuit line control model according to the maintenance scenario. S200: Utilize power flow backtracking technology to predict power flow data of high-voltage maintenance equipment and its associated low-voltage equipment during the maintenance period, and generate a predicted power flow data sequence. S300: Substitute the predicted power flow data sequence into the power flow control model of the transmission section to calculate the expected power flow value of the associated low-voltage equipment when the high-voltage maintenance equipment is out of service. S400: Based on the comparison results between the expected power flow value and the thermal stability limit of the associated low-voltage equipment, the mutual exclusivity between the high-voltage maintenance equipment and the associated low-voltage equipment is classified and determined.

[0020] It should be noted that most existing studies only focus on hard conflicts at the physical connection level, such as multiple transformers connected to the same busbar, parallel lines in the same transmission corridor, and equipment sharing relay protection devices. Based on practical production experience, these devices are determined to be mutually exclusive due to topological breaks caused by simultaneous maintenance. Most models assume that load levels and renewable energy output are fixed during maintenance, but in reality, the mutual exclusivity of maintenance for the same equipment during peak and off-peak periods can be completely different. Identifying mutual exclusivity requires a large amount of real-time data, such as equipment status, load forecasting, and resource scheduling. However, existing studies largely rely on manually preset rules and do not fully utilize big data and artificial intelligence technologies to uncover implicit mutual exclusivity relationships. For example, training models to predict potential conflicts using historical maintenance data results in mutual exclusivity rule updates lagging behind system changes. This invention takes the line maintenance scenario of electromagnetic ring network as the research object, introduces the power flow distribution coefficient method to construct the power flow correlation between high voltage level network maintenance and shutdown equipment and low voltage level network equipment, and derives the power flow control formula for transmission section; uses power flow backtracking technology to learn the historical power flow data of equipment to achieve the prediction of future power flow; and combines the constructed power flow control formula for transmission section to carry out the analysis and judgment of equipment mutual exclusivity.

[0021] In this embodiment of the invention, step S100, which establishes a power flow control model for a transmission section, includes: When the maintenance scenario involves a single device, a transmission section control model is established under the maintenance of a single device, represented as follows: ; in, The distribution coefficient, For high voltage level lines The initial power flow value, For low voltage level lines The initial power flow value, For low voltage level lines Thermal stability limits; Furthermore, the control operating area diagram (shaded area) for the distribution coefficient method control form is as follows: Figure 2 As shown, the distribution coefficient The determination includes: Selecting the ground-state power flow at maximum load, and adjusting the unit output or load power to achieve high-voltage line performance... Disconnection causes low voltage level circuit Record the high-voltage line power level until it reaches its stable limit. Power before disconnection Low voltage level lines Power before disconnection Distribution coefficient Represented as: Furthermore, the power flow control operating area diagram is as follows: Figure 3 As shown, the shaded area represents the safe operation zone of the power grid. Taking a double-circuit line outage for maintenance as an example, the double-circuit lines on the same pole are paralleled. , The shutdown process was simultaneously broken down into line Service will be suspended first. Two more shutdown processes will be implemented. Under initial conditions, the high-voltage double-circuit line... , and low voltage level lines All are in normal operating condition, and the initial power flow has contributed to... , and ;line After the line was suspended , The power of the current , ,line After the trip, the line The power of the current .

[0022] High voltage level lines , Meanwhile, the shutdown due to maintenance resulted in low-voltage lines being affected. The derivation process of the flow control section is as follows. Define the coefficients. , , : make , in, For the line The distribution coefficient, For the line The distribution coefficient.

[0023] In this embodiment of the invention, when the maintenance scenario is a multi-circuit line, a transmission section control model is established for the multi-circuit line power outage maintenance. This model is used when two-circuit lines are mounted on the same pole. , The power flow control section that causes overcurrent on line c due to the tripping is represented as follows: ; in, , These are the initial power flows of the double loop. To correlate the initial power flow of low-voltage lines, , The lines are respectively and lines For the line The distribution coefficient, For the line The thermal stability limit at the current temperature.

[0024] In this embodiment of the invention, step S200, which uses power flow backtracking technology to predict the power flow data of the high-voltage maintenance equipment and its associated low-voltage equipment during the maintenance period, includes: Collect historical power flow data, historical meteorological data, and future weather forecast data; Based on the similarity between future weather forecast data and historical weather data, target similar historical days are dynamically selected. Trend correction is performed on the historical power flow data of equipment corresponding to similar historical days, and weighted fusion is performed based on similarity to generate a predicted power flow data sequence.

[0025] Specifically, the power flow data of the equipment mainly consists of active power, while the meteorological measured data includes temperature, humidity, light intensity, wind speed, precipitation, etc.

[0026] Furthermore, the data is cleaned to remove abnormal or bad data caused by power grid accidents or maintenance.

[0027] Furthermore, such as Figure 4 As shown, the key meteorological factors affecting load and new energy output are quantified, and a meteorological feature vector W=[temperature, humidity, light intensity, wind speed, precipitation] is constructed, i.e. W=[T,H,S,W,R].

[0028] In this embodiment of the invention, step S200, which dynamically filters out target similar historical days based on the similarity between future weather forecast data and historical weather data, includes: Set the weather forecast vector for the forecast day, and extract the historical weather measurement vector for the previous calendar year and the previous month of the same year from the historical database. Specifically, the meteorological information to be collected and the data sources are shown in Table 1: Table 1 Meteorological Information Collection Form

[0029] Furthermore, the meteorological elements in the weather forecast vector and the weather observation vector are standardized to obtain a standardized meteorological feature vector. Based on the standardized vector, the Euclidean distance between the forecast day and each historical day is calculated, and the Euclidean distance is converted into a similarity index. Specifically, due to the different dimensions of each feature, the original vectors are standardized to avoid the influence of numerical range on similarity calculation. First, Z-score standardization is performed to convert the data into data conforming to a standard normal distribution. The calculation formula is as follows: in, The original meteorological feature values ​​are represented by μ, which is the mean of the feature in historical samples from the same period. For example, if the forecast date is June 15th, then data from last June would be used. σ is the standard deviation. After standardization, each feature follows a distribution with a mean of 0 and a standard deviation of 1, resulting in a standardized meteorological feature vector. .

[0030] Furthermore, let the standardized meteorological forecast feature vector for the forecast date be... The standardized meteorological observation feature vector for day j in the historical timeline is: Calculate the Euclidean distance between the two. : Euclidean distance The smaller the value, the more similar the predicted date and the historical date j are in terms of meteorological characteristics. The calculated distance is used as the basis for subsequent similarity calculations.

[0031] Furthermore, all candidate historical days are sorted according to similarity index, a descent threshold is set, and the historical days are examined sequentially starting from the first historical day in the sorted sequence. If the similarity index of the kth historical day is not less than the product of the descent threshold and the highest similarity value, then it is included in the set of similar days. The filtering process stops when the similarity value of the k-th historical day is less than the product of the decreasing threshold and the highest similarity value, or when the target historical day is examined. If the number of selected historical days is less than M, then the first M days are forcibly selected as the set of similar days; if there are more than N days, then only the first N days are selected to obtain the final target similar historical days.

[0032] In this embodiment of the invention, the descent threshold can be set to 0.5, which means that the maximum similarity decay is allowed to be 50%.

[0033] Specifically, all candidate historical days are sorted according to Euclidean distance, and the top K historical days with the highest similarity are selected as the set of similar historical days. To avoid introducing redundant noise or losing effective information by fixing the value of K, the optimal number of similar days K is dynamically determined based on the meteorological similarity level between historical days and predicted days, with the value range limited to 5-10.

[0034] Furthermore, the calculated Euclidean distance is converted into a similarity index. , The value ranges from (0, 1], with larger values ​​indicating more similar weather patterns. All candidate historical dates are then sorted... Sort in descending order from largest to smallest to obtain the sequence. .

[0035] Specifically, the dynamic truncation rule is: Based on this, a descent threshold θ = 0.5 is set. Starting from the first historical day, the similarity is examined sequentially. If the similarity of the k-th historical day satisfies... If it appears for the first time, then include it in the set of similar days. If the number of historical days examined has reached the 10th, the screening process should be stopped. If the number obtained according to the above rules is less than 5, then the first 5 should be forcibly selected as similar days; if it is more than 10, then only the first 10 should be selected.

[0036] In this embodiment of the invention, step S200 involves trend correction of the historical power flow data of equipment corresponding to similar historical days, and weighted fusion based on similarity to generate a predicted power flow data sequence, including: Obtain the historical power flow data sequence of devices at corresponding moments within a similar historical day; Calculate the load growth rate coefficient and use the load growth rate coefficient to perform amplitude correction on the historical power flow data sequence of the equipment to obtain the trend-corrected power flow data; where the load growth rate coefficient is the ratio of the maximum load of the entire network in the same region in the previous month to the maximum load of the entire network in the same period last year in the previous month; Normalized weights are calculated based on the similarity index corresponding to the similar historical days of the target; the trend-corrected tidal flow data of each similar historical day of the target are weighted and summed with the corresponding normalized weights to generate a predicted tidal flow data sequence.

[0037] Specifically, the power flow data sequence of the target device at the corresponding time point is extracted from these K similar historical days in the historical database. Taking into account the natural growth of grid load and equipment capacity expansion, the historical power flow data is adjusted for amplitude, and the data is scaled using the load growth rate coefficient α of the same period last year and this year.

[0038] For the selected K similar days, their similarity to the predicted day is used as the basis for the calculation. As initial weights. To avoid differences in magnitude, normalized weights are used: Obviously And all weights are positive numbers.

[0039] The k-th similar Nikkei trend-corrected trend time series is: Then the predicted power flow value at time t is: .

[0040] Furthermore, based on the constructed power flow control model of the transmission section and the predicted power flow data obtained through power flow backtracking technology, a hierarchical evaluation method for the mutual exclusion of power equipment is proposed. This method classifies the mutual exclusion relationship between equipment into three levels: safe level (non-mutual exclusion), controllable level (weak mutual exclusion), and risk level (strong mutual exclusion), thereby providing grid dispatchers with a more refined basis for maintenance decision-making.

[0041] In this embodiment of the invention, step S300 involves substituting the predicted power flow data sequence into the power flow control model of the transmission section to calculate the expected power flow value of the associated low-voltage equipment when the high-voltage maintenance equipment is out of service, including: Obtain the predicted power flow data sequence of the high-voltage line to be inspected on the predicted date and its associated low-voltage line before the shutdown, as well as the predicted power flow data sequence of the equipment to be inspected before the shutdown. By substituting the predicted power flow data sequence of the maintenance equipment into the power flow control model of the transmission section, the expected power flow value of the associated equipment at the corresponding time when the maintenance equipment is out of service can be calculated.

[0042] Specifically, using power flow backtracking technology, the predicted power flow data sequence of the high-voltage line scheduled for maintenance (hereinafter referred to as "maintenance equipment") and its associated low-voltage lines (hereinafter referred to as "associated equipment") is obtained before the predicted shutdown date. This data sequence covers all time periods throughout the predicted day (e.g., at 15-minute or 1-hour intervals) and is denoted as the set. ,in This indicates the predicted time of day.

[0043] Simultaneously, obtain the predicted power flow data sequence of the equipment to be maintained on the same predicted date before its shutdown, denoted as set. .

[0044] Furthermore, the acquired power flow prediction data sequence of the maintenance equipment will be used. Substituting these values ​​into the power flow control model for the transmission section constructed in the first part, we can inversely deduce the expected power flow value of the associated equipment at the corresponding time if the maintenance equipment is out of service. Taking single-line maintenance as an example, we can obtain: in, To correlate the predicted power flow value of the low-voltage equipment at time t, The predicted power flow value of the high-voltage maintenance equipment before it is shut down at time t; The distribution coefficients have been obtained; therefore, the expected power flow time series of the associated equipment after the maintenance equipment is shut down can be constructed. The sequence is compared with the thermal stability limits of the associated equipment. By plotting the curves on the same coordinate system, the points at which the limits may be exceeded can be visually identified.

[0045] Furthermore, based on the aforementioned curves and in conjunction with the control measures that the power grid can take, the mutual exclusivity between the maintenance equipment and related equipment is classified and determined.

[0046] Judgment Condition 1: Static Limit Exceedance Analysis Expected trend time series Each and its thermal stability limit Compare them.

[0047] like All have This indicates that in all predicted scenarios, the associated devices will not exceed the limit, and are therefore classified as safe, meaning they are not mutually exclusive.

[0048] like , making If the limit is exceeded, then there is a risk of exceeding the limit, and the judgment condition 2 will be entered.

[0049] Judgment Condition 2: Consider the dynamic over-limit analysis of control measures For the set of times where there is a risk of exceeding the limit The analysis examines the available control measures for the power grid, such as adjusting the output of other generating units, switching reactive power compensation devices, adjusting transformer tap changes, and initiating demand-side response; whether these measures can eliminate all risks of exceeding limits. Control measures must also meet other constraints on power grid operation, such as upper and lower limits of generating unit output and allowable ranges of node voltages; the power flow values ​​of associated equipment after control should be assessed. .

[0050] like Under the premise of satisfying other power grid security constraints, feasible control strategies can be found to enable... If the condition is met, it is classified as an adjustable level, i.e., weakly mutually exclusive. Appropriate control plans are required when overhauling such equipment.

[0051] like Even with all feasible regulatory measures, it is still impossible to achieve this. If the conditions are met, the equipment is classified as high-risk, meaning strongly mutually exclusive. Such equipment must not be scheduled for maintenance simultaneously, or maintenance must be staggered during specific high-risk periods.

[0052] In this embodiment of the invention, step S400 involves classifying and determining the mutual exclusion between the high-voltage maintenance equipment and the associated low-voltage equipment based on the comparison result between the expected power flow value and the thermal stability limit value of the associated low-voltage equipment, including: The expected power flow time series of the associated equipment is compared with the thermal stability limit of the associated equipment; if the values ​​at all times in the expected power flow time series are not greater than the thermal stability limit, the mutual exclusion between the high-voltage maintenance equipment and the associated low-voltage equipment is determined to be at the safe level. If there is an over-limit moment that exceeds the thermal stability limit, then under the premise of satisfying the power grid operation constraints, determine whether there is a feasible control strategy that ensures that the power flow value of the associated equipment after control is not greater than the thermal stability limit. If a feasible control strategy can be found for all out-of-limit moments, then the mutual exclusion is determined to be controllable; if there is at least one out-of-limit moment, and even if a feasible control strategy is adopted, it is still impossible to ensure that the power flow value of the associated equipment after control is not greater than the thermal stability limit, then the mutual exclusion is determined to be risky.

[0053] Furthermore, based on the above judgment results, a list of mutually exclusive equipment within the maintenance cycle is generated, clearly indicating the mutual exclusion level and corresponding control plan suggestions for weakly mutually exclusive equipment, for reference by maintenance planners.

[0054] It should be noted that this invention overcomes the limitations of traditional methods that rely solely on static topology to determine mutual exclusion. By introducing power flow backtracking technology, it incorporates meteorological characteristics affecting load fluctuations and renewable energy output, enabling accurate identification of dynamic mutual exclusion relationships that are only mutually exclusive at specific power flow levels. This avoids misjudgments or omissions caused by static assumptions. For the first time, equipment mutual exclusion is classified into three levels: safe (non-mutually exclusive), controllable (weakly mutually exclusive), and risky (strongly mutually exclusive). This classification method provides dispatchers with more refined decision-making information than the traditional binary judgment (mutually exclusive / non-mutually exclusive). For controllable (weakly mutually exclusive) equipment, simultaneous maintenance is no longer strictly prohibited; instead, maintenance can be scheduled with corresponding control plans, greatly improving the flexibility of maintenance planning.

[0055] The above is an illustrative scheme of a power equipment mutual exclusion classification determination method based on backtracking technology according to this embodiment. It should be noted that the technical solution of this power equipment mutual exclusion classification determination system based on backtracking technology belongs to the same concept as the technical solution of the power equipment mutual exclusion classification determination method based on backtracking technology described above. Details not described in detail in the technical solution of the power equipment mutual exclusion classification determination system based on backtracking technology in this embodiment can be found in the description of the technical solution of the power equipment mutual exclusion classification determination method based on backtracking technology described above.

[0056] This embodiment provides a power equipment mutual exclusion classification determination system based on backtracking technology, comprising: The model building module is used to establish a power flow control model for transmission sections. The model is used to characterize the impact of high-voltage maintenance equipment shutdown on the power flow of associated low-voltage equipment. The model can be configured as a single equipment control model or a multi-circuit line control model according to the maintenance scenario. The power flow prediction module is used to predict the power flow data of high-voltage maintenance equipment and its associated low-voltage equipment during the maintenance period using power flow backtracking technology, and generate a predicted power flow data sequence. The expected value calculation module is used to substitute the predicted power flow data sequence into the power flow control model of the transmission section to calculate the expected power flow value of the associated low-voltage equipment when the high-voltage maintenance equipment is out of service. The classification and determination module is used to classify and determine the mutual exclusivity between high-voltage maintenance equipment and associated low-voltage equipment based on the comparison results between the expected power flow value and the thermal stability limit of the associated low-voltage equipment.

[0057] This embodiment also provides an electronic device applicable to the power equipment mutual exclusion classification determination method based on backtracking technology, including: The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes the computer-executable instructions to implement the power equipment mutual exclusion classification determination method based on backtracking technology as proposed in the above embodiments.

[0058] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the power equipment mutual exclusion classification determination method based on backtracking technology as proposed in the above embodiments.

[0059] The storage medium proposed in this embodiment and the method for determining the mutual exclusion of power equipment based on backtracking technology proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0060] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0061] Example 2, refer to Figures 5-6 This is one embodiment of the present invention. Unlike the first embodiment, this embodiment uses the maintenance of a local power system as an example to verify the beneficial effects of the present invention.

[0062] like Figure 5As shown, this embodiment takes the planned maintenance of high-voltage line 36-37 as an example. Low-voltage line 25-37 forms an electromagnetic loop with it. Maintenance of line 36-37 may cause line 25-37 to exceed its limits; therefore, component mutual exclusion analysis should be performed. 36-37 is a high-voltage line (500kV), and 25-37 is a low-voltage line (220kV). When the active power of line 36-37 is 303.92MW and the active power of line 25-37 is 322.03MW, if line 36-37 trips, line 25-37 will be fully loaded (power 454.00MW). Therefore, the calculated distribution coefficient is: Taking the meteorological forecast information for this region as an example, the meteorological information for that day (April 1, 2026) is shown in Table 2: Table 2 Weather forecast information for a certain region on a certain day

[0063] Historical sample data for the same period are shown in Table 3: Table 3 Historical meteorological statistics for a certain region

[0064] The historical daily climate data for the region over 15 days is shown in Table 4. It should be noted that the actual data should include the historical data from the past year plus the previous month of the same year, totaling 365+30 data points. This example only selects 15 data points for algorithm demonstration.

[0065] Table 4 Historical Daily Climate Information

[0066] The data was standardized, and the standardized daily weather information for the forecast is [0.0, 0.0, 0.375, 0.0, -0.2]. The standardized historical data is shown in Table 5. Table 5 Standardized historical data

[0067] Further, Euclidean distance is calculated, and then the formula is used. Similarity calculations were performed, and the results were sorted in descending order of similarity. The sorting results are shown in Table 6. Table 6 Sorting Results

[0068] Power flow correction and synthesis are performed, multiplied by the load growth factor, which is calculated by the ratio of the maximum power of the previous month this year to the maximum power of the previous month last year. According to the attenuation factor requirement, the previous 6 historical days are selected as the power flow reference, and normalized weights are calculated. The calculation results are shown in Table 7. Table 7 Calculation Results

[0069] The maximum power output of this region in the previous month of last year (March 2025) was 1782MW, and the maximum power output of this region in the previous month of this year (March 2026) was 1837MW. The calculation of the load growth factor is as follows. .

[0070] The original active power (in MW) of lines 36-37 at time t on similar days (t=51, with 15-minute intervals, 96 data points per day, t values ​​[1, 96]) is as follows. After correction using the load growth factor and weighted fusion according to normalized weights, it is shown in Table 8: Table 8. Results of normalized weighted fusion

[0071] The power flow values ​​(weighted fusion) for lines 36-37 at that time on the predicted date are obtained as follows: The same processing is applied to the data at all times to obtain the power flow data for lines 36-37 on the predicted day. Similarly, the same steps are used to calculate the power flow data for lines 25-37 on the predicted day. The processed data is then substituted into the formula. Therefore, the expected power flow time series of related equipment after maintenance shutdown is constructed. The sequence is compared with the thermal stability limits of the associated equipment. Plotted as a curve in the same coordinate system, such as Figure 6 As shown in the curve, it can be clearly observed that... All have This indicates that lines 36-37 and 25-37 will not be mutually exclusive on the predicted date, and the maintenance schedule for line 36-37 can be carried out normally.

[0072] This invention transforms complex electrical calculations into intuitive charts by inputting predicted power flow data into transmission section models and plotting them as limit-crossing judgment curves. This allows dispatchers to easily identify maintenance risk periods and levels, reducing decision-making difficulty. Through refined assessment and coordinated control plans, it allows for simultaneous maintenance of as much equipment as possible while ensuring the safe operation of the power grid. This shortens total equipment downtime, optimizes maintenance windows, and reduces generator opportunity losses or grid operation restrictions caused by equipment maintenance, resulting in significant economic and safety benefits.

[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for classifying and determining the mutual exclusion of power equipment based on backtracking technology, characterized in that, include: A power flow control model for transmission sections is established. The model is used to characterize the impact of high-voltage maintenance equipment shutdown on the power flow of associated low-voltage equipment. The model is configured as a single equipment control model or a multi-circuit line control model according to the maintenance scenario. Power flow backtracking technology is used to predict the power flow data of the high-voltage equipment under maintenance and its associated low-voltage equipment during the maintenance period, and a predicted power flow data sequence is generated. Substituting the predicted power flow data sequence into the power flow control model of the transmission section, the expected power flow value of the associated low-voltage equipment is calculated when the high-voltage maintenance equipment is out of service. Based on the comparison between the expected power flow value and the thermal stability limit of the associated low-voltage equipment, the mutual exclusivity between the high-voltage maintenance equipment and the associated low-voltage equipment is classified and determined.

2. The method for determining the mutual exclusion hierarchy of power equipment based on backtracking technology as described in claim 1, characterized in that, The establishment of the power flow control model for the transmission section includes: When the maintenance scenario involves a single device, a transmission section control model is established under the maintenance of a single device, represented as follows: ; in, The distribution coefficient, For high voltage level lines The initial power flow value, For low voltage level lines The initial power flow value, For low voltage level lines Thermal stability limits; When the maintenance scenario involves multiple circuits, a transmission section control model is established for power outage maintenance of multiple circuits, represented as follows: ; in, , These are the initial power flows of the double loop. To correlate the initial power flow of low-voltage lines, , The lines are respectively and lines For the line The distribution coefficient, For the line The thermal stability limit at the current temperature.

3. The method for determining the mutual exclusion of power equipment based on backtracking technology as described in claim 2, characterized in that, Power flow backtracking technology is used to predict power flow data for the high-voltage equipment under maintenance and its associated low-voltage equipment during the maintenance period, including: Collect historical power flow data, historical meteorological data, and future weather forecast data; Based on the similarity between the future weather forecast data and the historical weather data, target similar historical days are dynamically selected. The historical power flow data of the equipment corresponding to the similar historical days are trend-corrected, and weighted fusion is performed based on the similarity to generate a predicted power flow data sequence.

4. The method for determining the mutual exclusion hierarchy of power equipment based on backtracking technology as described in claim 3, characterized in that, The dynamic selection of target similar historical days based on the similarity between the future weather forecast data and the historical weather data includes: Set the weather forecast vector for the forecast day, and extract the historical weather measurement vector for the previous calendar year and the previous month of the same year from the historical database. The meteorological elements in the meteorological forecast vector and the meteorological observation vector are standardized to obtain a standardized meteorological feature vector. Based on the standardized vector, the Euclidean distance between the forecast day and each historical day is calculated, and the Euclidean distance is converted into a similarity index. Sort all candidate historical days according to similarity index, set a decreasing threshold, and examine them sequentially starting from the first historical day in the sorted sequence. If the similarity index of the kth historical day is not less than the product of the decreasing threshold and the highest similarity value, then include it in the set of similar days. The filtering process stops when the similarity value of the k-th historical day is less than the product of the decreasing threshold and the highest similarity value, or when the target historical day is examined. If the number of selected historical days is less than M, then the first M days are forcibly selected as the set of similar days; if there are more than N days, then only the first N days are selected to obtain the final target similar historical days.

5. The method for determining the mutual exclusion hierarchy of power equipment based on backtracking technology as described in claim 4, characterized in that, The process involves trend correction of the historical power flow data corresponding to the similar historical days, followed by weighted fusion based on the similarity to generate a predicted power flow data sequence, including: Obtain the device historical power flow data sequence for the corresponding time in the target similar historical day; Calculate the load growth rate coefficient, and use the load growth rate coefficient to perform amplitude correction on the historical power flow data sequence of the equipment to obtain trend-corrected power flow data; wherein, the load growth rate coefficient is the ratio of the maximum load of the entire network in the same region in the previous month to the maximum load of the entire network in the same period last year in the previous month; The normalized weights are calculated based on the similarity index corresponding to the target similar historical days; the trend-corrected tidal flow data of each target similar historical day are weighted and summed with the corresponding normalized weights to generate the predicted tidal flow data sequence.

6. The method for determining the mutual exclusion hierarchy of power equipment based on backtracking technology as described in claim 5, characterized in that, Substituting the predicted power flow data sequence into the power flow control model of the transmission section, the expected power flow values ​​of the associated low-voltage equipment when the high-voltage maintenance equipment is out of service are calculated, including: Obtain the predicted power flow data sequence of the high-voltage line to be inspected on the predicted date and its associated low-voltage line before the shutdown, as well as the predicted power flow data sequence of the equipment to be inspected before the shutdown. Substitute the predicted power flow data sequence of the maintenance equipment into the power flow control model of the transmission section to infer the expected power flow value of the associated equipment at the corresponding time when the maintenance equipment is out of service.

7. The method for determining the mutual exclusion hierarchy of power equipment based on backtracking technology as described in claim 6, characterized in that, Based on the comparison between the expected power flow value and the thermal stability limit of the associated low-voltage equipment, the mutual exclusivity between the high-voltage maintenance equipment and the associated low-voltage equipment is classified and determined, including: The expected power flow time series of the associated equipment is compared with the thermal stability limit of the associated equipment; if the value at all times in the expected power flow time series is not greater than the thermal stability limit, then the mutual exclusion between the high-voltage maintenance equipment and the associated low-voltage equipment is determined to be at the safe level. If there is an over-limit moment that exceeds the thermal stability limit, then under the premise of satisfying the power grid operation constraints, it is determined whether there is a feasible control strategy that makes the power flow value of the associated equipment after control not greater than the thermal stability limit. If a feasible control strategy can be found for all out-of-limit moments, then the mutual exclusion is determined to be controllable; if there is at least one out-of-limit moment, and even if the feasible control strategy is adopted, it is still impossible to ensure that the power flow value of the associated equipment after control is not greater than the thermal stability limit, then the mutual exclusion is determined to be risky.

8. A power equipment mutual exclusion classification determination system based on backtracking technology, applied to the method described in any one of claims 1-7, characterized in that, include: The model building module is used to establish a power flow control model for transmission sections. The model is used to characterize the impact of high-voltage maintenance equipment shutdown on the power flow of associated low-voltage equipment. The model is configured as a single equipment control model or a multi-circuit line control model according to the maintenance scenario. The power flow prediction module is used to predict the power flow data of the high-voltage maintenance equipment and its associated low-voltage equipment during the maintenance period using power flow backtracking technology, and generate a predicted power flow data sequence. The expected value calculation module is used to substitute the predicted power flow data sequence into the power flow control model of the transmission section to calculate the expected power flow value of the associated low-voltage equipment when the high-voltage maintenance equipment is out of service. The classification and determination module is used to classify and determine the mutual exclusion between the high-voltage maintenance equipment and the associated low-voltage equipment based on the comparison result between the expected power flow value and the thermal stability limit value of the associated low-voltage equipment.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, they implement the steps of the power equipment mutual exclusion classification determination method based on backtracking technology as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the power equipment mutual exclusion classification determination method based on backtracking technology as described in any one of claims 1 to 7.

Images