Operation and maintenance scheduling method and device for power equipment cluster, equipment, medium and product

Abstract

The invention relates to an operation and maintenance scheduling method and device for a power equipment cluster, equipment, a medium and a product. The method comprises the following steps: acquiring a relation network diagram of a plurality of power devices and historical operation data of each power device; the relation network diagram takes the power devices as nodes, takes the electrical connection relations among the power devices as edges, and takes the association degrees among the power devices as edge weights; calculating centrality index data of each power device in the relation network diagram according to the relation network diagram; calculating power supply stability index data of each power device according to the historical operation data, and calculating operation and maintenance influence data of each power device according to the centrality index data and the power supply stability index data; and selecting a plurality of power devices according to the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster. By adopting the method, the operation and maintenance cluster configuration accuracy can be improved.

Description

Technical Field

[0001] This application relates to the field of power equipment operation and maintenance technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium and computer program product for the operation and maintenance scheduling of power equipment clusters. Background Technology

[0002] With the continuous growth of the proportion of new energy power generation, the types of power generation equipment in modern power systems are becoming increasingly diversified, including the coexistence of multiple power generation forms such as wind power, photovoltaic power, and thermal power. In this complex power environment, traditional power equipment operation and maintenance management mainly adopts an independent maintenance strategy based on the status of individual equipment, that is, monitoring the operating status, diagnosing faults, and formulating maintenance plans for each power device separately. However, this traditional method has significant technical shortcomings, mainly in that it cannot effectively identify and utilize the interrelationships and synergistic characteristics between power devices.

[0003] Specifically, the various generating devices in a power system are physically connected by electrical links to form a network structure, and their operation involves complex interrelationships such as power complementarity and load sharing. When traditional independent maintenance strategies are adopted, operation and maintenance decisions cannot comprehensively consider these interrelationships between devices, resulting in inaccurate scheduling of operation and maintenance resources. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for the operation and maintenance scheduling of power equipment clusters that can improve the accuracy of operation and maintenance cluster configuration, in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for the operation and maintenance scheduling of a power equipment cluster, including:

[0006] Obtain a relationship network diagram of multiple power devices and historical operating data of each power device; the relationship network diagram uses power devices as nodes, electrical connections between power devices as edges, and the degree of association between power devices as edge weights;

[0007] Based on the relationship network diagram, calculate the centrality index data of each of the power devices in the relationship network diagram;

[0008] Based on the historical operating data, calculate the power supply stability index data for each of the power devices, and calculate the operation and maintenance impact data for each of the power devices based on the centrality index data and the power supply stability index data.

[0009] Multiple power devices are selected based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster.

[0010] In one embodiment, the method further includes:

[0011] Obtain power generation demand data and matching degree data of each power device under multiple power generation modes within the target operation and maintenance cycle;

[0012] Based on the power generation demand data, determine the predicted frequency data for each of the power generation modes within the target operation and maintenance cycle;

[0013] For each of the power generation modes of each of the aforementioned power devices, power generation capacity data is calculated based on the matching degree data and the corresponding predicted frequency data;

[0014] Correspondingly, the step of selecting multiple power devices based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster includes:

[0015] Based on the power generation capacity data and the operation and maintenance influence data, multiple power devices are selected to obtain a collaborative operation and maintenance cluster.

[0016] In one embodiment, acquiring the power generation demand data within the target operation and maintenance cycle and the matching degree data of each of the power devices under multiple power generation modes includes:

[0017] In response to demand reception instructions, collect power generation demand data within the target operation and maintenance cycle;

[0018] Based on the historical operating data, extract the historical power generation datasets of each of the power devices under different power generation modes;

[0019] For each power generation mode, the power generation achievement rate data of each power device in the corresponding historical power generation dataset is calculated based on the expected power generation data and actual power generation data of each power device in the power generation mode.

[0020] Matching degree data is calculated based on the power generation achievement rate data of each of the power devices in each of the power generation modes.

[0021] In one embodiment, the step of selecting multiple power devices to obtain a collaborative operation and maintenance cluster based on the power generation capacity data and the operation and maintenance influence data includes:

[0022] Based on the power generation demand data, determine the maximum power demand within the target operation and maintenance cycle;

[0023] The rated power data of each of the power devices is traversed to generate candidate collaborative operation and maintenance clusters; wherein, the candidate collaborative operation and maintenance cluster is a combination of power devices whose sum of rated power data is greater than the maximum required power.

[0024] Calculate the average value of the operation and maintenance influence data of each power device in each candidate collaborative operation and maintenance cluster to obtain the cluster operation and maintenance influence data, and calculate the average value of the power generation capacity data of each power device in each candidate collaborative operation and maintenance cluster to obtain the cluster power generation capacity data.

[0025] Based on the cluster operation and maintenance influence data and the cluster power generation capacity data, a collaborative operation and maintenance cluster is selected from each of the candidate collaborative operation and maintenance clusters.

[0026] In one embodiment, the relationship network graph includes at least one pair of power devices, and the pair of power devices includes two power devices; obtaining the relationship network graph of multiple power devices includes:

[0027] Acquire time-series data of the historical power generation of each of the aforementioned power devices and power grid topology data;

[0028] For each of the power equipment pairs, a Pearson correlation coefficient is calculated based on the time series data, and the power generation correlation degree is calculated based on the Pearson correlation coefficient.

[0029] For each of the power equipment pairs, the grid connection density is calculated based on the grid topology data;

[0030] The correlation degree of power generation and the tightness of grid connection of each power equipment pair are weighted and fused to obtain the correlation degree between the power equipment, and the correlation degree is used as the edge weight of the corresponding edge in the relationship network graph.

[0031] In one embodiment, calculating the grid connectivity density for each of the power equipment pairs based on the grid topology data includes:

[0032] From the power grid topology data, the electrical distance data between each pair of power equipment is extracted, and the maximum and minimum values ​​of the electrical distance data of all pairs of power equipment are selected to obtain the maximum and minimum electrical distance values.

[0033] For each pair of power equipment, the grid connection tightness is calculated based on the corresponding electrical distance data, the maximum electrical distance, and the minimum electrical distance.

[0034] Secondly, this application also provides an operation and maintenance dispatching device for a power equipment cluster, comprising:

[0035] The data acquisition module is used to acquire a relationship network diagram of multiple power devices and historical operating data of each power device; the relationship network diagram uses power devices as nodes, electrical connection relationships between power devices as edges, and correlation degree between power devices as edge weights;

[0036] The data calculation module is used to calculate the centrality index data of each of the power devices in the relationship network diagram based on the relationship network diagram;

[0037] The data processing module is used to calculate the power supply stability index data of each of the power devices based on the historical operating data, and to calculate the operation and maintenance impact data of each of the power devices based on the centrality index data and the power supply stability index data.

[0038] The cluster scheduling module is used to select multiple power devices based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster.

[0039] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the steps described in the first aspect.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps described in the first aspect.

[0041] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps described in the first aspect.

[0042] The aforementioned power equipment cluster operation and maintenance scheduling method, device, computer equipment, computer-readable storage medium, and computer program product acquire a relationship network diagram of multiple power equipment and historical operating data of each power equipment. The relationship network diagram uses power equipment as nodes, electrical connections between power equipment as edges, and the degree of correlation between power equipment as edge weights, solving the problem that traditional methods cannot identify the relationships between equipment. Based on the relationship network diagram, the centrality index of each power equipment in the relationship network diagram is calculated. Based on the historical operating data, the power supply stability index of each power equipment is calculated, and based on the centrality index and power supply stability index, the operation and maintenance influence data of each power equipment is calculated. By combining the centrality index, which reflects the importance of the equipment network, with the power supply stability index, which reflects the reliability of the equipment, the resulting operation and maintenance influence data can comprehensively reflect the importance of the equipment in the system, considering both the structural importance and operational reliability of the equipment, overcoming the limitations of single-index evaluation. Multiple power equipment are selected based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster. Using the operation and maintenance influence data to guide equipment selection, combinations of equipment with significant influence in the system and stable operation can be identified, forming a collaborative operation and maintenance cluster, thus improving the accuracy of operation and maintenance cluster configuration. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is an application environment diagram of the operation and maintenance scheduling method for a power equipment cluster in one embodiment;

[0045] Figure 2 This is a flowchart illustrating the operation and maintenance scheduling method for a power equipment cluster in one embodiment;

[0046] Figure 3 This is a flowchart illustrating the operation and maintenance scheduling method for a power equipment cluster in another embodiment;

[0047] Figure 4 This is a structural block diagram of the operation and maintenance scheduling device for a power equipment cluster in one embodiment;

[0048] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0051] The operation and maintenance scheduling method for power equipment clusters provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0052] In one exemplary embodiment, such as Figure 2 As shown, a method for operation and maintenance scheduling of power equipment clusters is provided, which can be applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps S202 to S208. Wherein:

[0053] Step S202: Obtain the relationship network diagram of multiple power devices and the historical operating data of each power device.

[0054] Power equipment refers to all types of equipment connected to the power system and participating in power production, transmission, or distribution. Specifically, it includes wind turbine generators, photovoltaic power generation equipment, thermal power generators, hydropower generation equipment, energy storage equipment, transformers, and switchgear. A relationship network graph is a graphical data structure used to represent the relationships between power equipment. Each power device acts as a node in the network, physical connections or functional associations between devices are represented as edges connecting the nodes, and edge weights are used to quantify the tightness of the association between devices.

[0055] The relationship network graph uses electrical equipment as nodes, electrical connections between electrical equipment as edges, and the degree of association between electrical equipment as edge weights. A relationship network graph can include at least one pair of electrical equipment, and each pair of electrical equipment consists of two electrical devices.

[0056] Historical operating data refers to various operating status information recorded by power equipment during its past operation, including power generation data, operating time data, fault record data, maintenance record data, and equipment status monitoring data. A power equipment pair refers to a combination of any two power devices in a relationship network diagram, used to analyze and calculate the relationships between devices.

[0057] For example, server 104 can acquire basic information and connection relationship data of power equipment from various monitoring points in the power system through the data acquisition module. Server 104 can access the power system's equipment management database, extract equipment list data containing basic attribute information such as equipment identifier, equipment type, rated power, and geographical location, and construct the node structure of the relationship network diagram based on this equipment information. Server 104 can obtain historical operating data of each power device from the power grid dispatching system, which covers detailed information such as the device's operating status, output power, operating efficiency, and fault conditions at different time periods. In the process of constructing the relationship network diagram, server 104 can abstract each power device as a node in the network diagram and assign a unique equipment identifier and corresponding attribute information to each node.

[0058] For example, server 104 can obtain time-series data of historical power generation of each power device and grid topology data; for each pair of power devices, calculate the Pearson correlation coefficient based on the time-series data, and calculate the power generation correlation degree based on the Pearson correlation coefficient; for each pair of power devices, calculate the grid connection tightness based on the grid topology data; and perform weighted fusion of the power generation correlation degree and grid connection tightness of each pair of power devices to obtain the correlation degree between power devices, and use the correlation degree as the edge weight of the corresponding edge in the relationship network graph.

[0059] To determine the edge weights in the network graph, server 104 can extract time-series data of power generation from the historical database of the power system, which records the power output changes of the devices within a specific time window. For each pair of power devices in the network graph, server 104 can extract the power generation sequence of the corresponding devices within the same time period using a data processing algorithm, and calculate the Pearson Correlation Coefficient (PRC) between these two sequences. Based on the numerical characteristics of the PRC, server 104 can apply a mathematical transformation function to convert the correlation coefficient into a power generation correlation value, which reflects the degree of synchronicity or complementarity of the two devices in terms of power generation changes. For example, based on the PRC, the power generation complementarity index between two power devices is calculated; the specific calculation formula is as follows:

[0060]

[0061] in, This is an index representing the complementarity of power generation between electrical power equipment i and electrical power equipment j. is the Pearson correlation coefficient between the power generation data of electrical power equipment i and electrical power equipment j.

[0062] Furthermore, server 104 can extract the electrical distance data between each pair of power devices from the power grid topology data, and select the maximum and minimum values ​​from the electrical distance data of all power device pairs to obtain the maximum and minimum electrical distance values. For each power device pair, the grid connection tightness is calculated based on the corresponding electrical distance data, the maximum electrical distance value, and the minimum electrical distance value. Server 104 can analyze the physical connection structure of the power grid and calculate the electrical distance data between each pair of power devices. Electrical distance refers to the length of the electrical path through which electricity is transmitted from one device to another in the power grid, and can be measured by impedance value or equivalent distance. Server 104 can traverse the electrical distance data of all power device pairs, identify the maximum and minimum distance values, and form a numerical range benchmark for electrical distance. Based on this numerical range, server 104 can normalize the electrical distance of each pair of devices and calculate the grid connection tightness value through mathematical transformation. This value reflects the degree of connection tightness between devices in the power grid topology. For example, the grid connection tightness index between two power devices is calculated based on electrical distance; the specific calculation formula is as follows:

[0063]

[0064] in, This is an indicator of the tightness of the power grid connection between electrical power equipment i and electrical power equipment j. The electrical distance between electrical equipment i and electrical equipment j. This represents the maximum electrical distance between all electrical equipment. This represents the minimum electrical distance between all electrical and power equipment.

[0065] After obtaining the correlation values ​​for power generation correlation and grid connection tightness, server 104 can use a weighted fusion algorithm to combine these two values ​​into a comprehensive inter-device correlation value. Server 104 can linearly weight and sum the power generation correlation and grid connection tightness according to preset weight coefficients to obtain the final correlation value. This correlation value considers both the correlation of devices in terms of operational characteristics and the tightness of their physical connections, thus more comprehensively reflecting the mutual influence between devices. Server 104 can use the calculated correlation value as the edge weight of the corresponding edge in the relationship network graph, completing the construction process of the relationship network graph.

[0066] Step S204: Calculate the centrality index data of each power device in the relationship network diagram based on the relationship network diagram.

[0067] Centrality is a numerical metric used to quantify the importance of nodes in a network. In a power equipment network diagram, centrality reflects the influence and importance of each power device within the overall network structure. A higher centrality value indicates that the device occupies a more central position in the network, has a wider impact on other devices, or is more significantly influenced by other important devices.

[0068] For example, server 104 can initialize all power device nodes in the relational network graph, setting the initial centrality value of each device to the reciprocal of the total number of nodes in the network. Subsequently, server 104 can construct an iterative update rule for centrality based on the network's connection structure and edge weight information. During each iteration, server 104 can collect the current centrality values ​​and corresponding edge weight values ​​of all directly connected neighboring devices for each power device in the network. Server 104 can analyze the connection relationships between devices to achieve the propagation and accumulation of centrality values. Specifically, server 104 can consider that the importance of a device depends not only on the number of devices connected to it, but more importantly on the importance of those connected devices themselves and the tightness of the connections. Therefore, when calculating the updated centrality of the target device, server 104 can multiply the centrality values ​​of all neighboring devices by their corresponding edge weights, divide the product by the sum of the degree weights of the neighboring devices, and finally sum the contributions of all neighboring devices. This calculation method reflects the transmission characteristic of importance in the network; that is, important devices will transmit importance to the devices connected to them, and the strength of this transmission depends on the tightness of the connections.

[0069] For example, server 104 can calculate the centrality index of each power device in the relational network graph based on the PageRank algorithm, specifically including: initializing the centrality index of all power devices to 1 / n, where n is the total number of power devices in the power grid; and constructing an iterative centrality calculation formula based on the PageRank algorithm.

[0070]

[0071] in, The centrality index of electrical power equipment i Let i be the set of electrical devices that are connected to electrical device i in the relational network graph. for The elements in The final association strength weight between electrical power equipment i and electrical power equipment j. Let j be the centrality index of electrical power equipment. Let j be the set of electrical devices that have connections with electrical device j in the relational network graph. for The elements in The final association strength weight between electrical power equipment k and electrical power equipment j is determined. The centrality index of the power equipment is calculated iteratively until it converges, and the converged value is used as the final determined centrality index of the power equipment. Based on the PageRank algorithm, the association weights between devices are considered, enabling the evaluation results to accurately identify high-impact devices that occupy pivotal positions in the network and whose outages could trigger cascading effects. By integrating stability and type importance indicators, the comprehensiveness and practicality of the evaluation results are further ensured. This respects the reliability of historical operational data and aligns with the strategic direction of the power grid's green transformation. It allows maintenance resources to be prioritized for devices that have the strongest constraints on the overall stability and efficient operation of the power grid, thereby achieving an optimization upgrade from "balanced maintenance" to "precise policy implementation," greatly improving the intelligence level of maintenance scheduling and the resilience of the power grid.

[0072] Through the above steps, server 104 achieves a quantitative assessment of the importance of power equipment based on network structure, overcoming the technical limitation of traditional methods that assess importance solely based on the equipment's own attributes while ignoring the influence of network structure. The centrality index data calculated in this step can identify the power equipment's location within the network. While these devices may perform poorly in individual attributes, their specific network positions significantly impact the entire system. The calculation of the centrality index fully utilizes the correlation and connection strength information between devices, and an iterative algorithm realizes the propagation and accumulation of importance within the network, ensuring that the final importance assessment considers both direct connections and indirect influence paths.

[0073] Step S206: Calculate the power supply stability index data for each power device based on historical operating data, and calculate the operation and maintenance impact data for each power device based on the centrality index data and the power supply stability index data.

[0074] Among them, power supply stability index data refers to quantitative values ​​reflecting the reliability of power equipment operation, calculated based on the historical operating performance of the equipment. These values ​​comprehensively consider historical performance across multiple dimensions, including equipment failure frequency, operational continuity, output power stability, and maintenance response capabilities. Operation and maintenance impact data refers to a comprehensive importance assessment value calculated by considering both network importance and operational reliability. This value quantifies the priority and impact of each power device in operation and maintenance decisions. Historical operating data can include various types of time-series data, such as equipment runtime records, fault event records, maintenance operation records, power output records, equipment status monitoring records, and performance evaluation records.

[0075] For example, server 104 can extract detailed historical operating data of each power device from the power system's operating database. Server 104 accesses the equipment management system, fault management system, and operation monitoring system through a data query interface to obtain historical data records containing complete information such as timestamps, device status, operating parameters, and fault information. Server 104 can preprocess and clean the obtained raw historical data, removing abnormal data points and missing data records. For each power device, server 104 can statistically analyze its operating data within a specified historical time period, calculating basic performance indicators such as device availability, failure rate, mean time between failures (MTBF), fault repair time, and power output stability.

[0076] In calculating power supply stability index data, server 104 can employ a multi-dimensional comprehensive evaluation method. First, server 104 calculates the equipment's time availability index, which equals the equipment's uptime divided by its total uptime, reflecting the equipment's reliability over time. Server 104 can further calculate the equipment's functional availability index, evaluating its stability over function by analyzing the distribution of the ratio of actual output power to rated output power. Server 104 can also calculate the equipment's fault recovery capability index, analyzing the average time required for the equipment to recover from a fault state to normal operation based on historical fault records, reflecting the equipment's maintenance response efficiency. Server 104 can then integrate these performance indicators from different dimensions using a weighted average method, with weighting coefficients set according to the importance of different indicators in the power supply stability assessment, to obtain comprehensive power supply stability index data for each device.

[0077] Furthermore, server 104 can calculate the operation and maintenance impact data for each power device using a weighted summation method. Server 104 can multiply the standardized centrality index data with the corresponding network importance weight coefficient, and the standardized power supply stability index data with the corresponding reliability weight coefficient, then add the two products to obtain the final operation and maintenance impact data. Server 104 sorts and analyzes the operation and maintenance impact data of all power devices, identifying high-impact devices that perform well in the comprehensive evaluation and low-impact devices that require special attention, providing a decision-making basis for subsequent operation and maintenance cluster selection.

[0078] Step S208: Select multiple power devices based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster.

[0079] For example, server 104 can rank and classify all power equipment based on the operation and maintenance influence data of each power device. Server 104 can set an importance level classification threshold according to the numerical distribution characteristics of the operation and maintenance influence data, dividing power equipment into three levels: high-importance equipment, medium-importance equipment, and general-importance equipment. Server 104 can prioritize selecting candidate equipment for the collaborative operation and maintenance cluster from high-importance equipment, ensuring that the selected equipment has strong network influence and operational reliability. Simultaneously, server 104 can obtain power demand data for future operation and maintenance cycles from the power system's demand forecasting module, including information such as maximum power demand, average power demand, and load change patterns.

[0080] Furthermore, server 104 can employ a multi-objective optimization method during the collaborative operation and maintenance cluster selection process. First, server 104 can set basic constraints for cluster selection based on the power supply requirements of the power system. Specifically, the total nominal output power of the selected equipment must be greater than or equal to the maximum power demand of the system during its future operation and maintenance cycle, ensuring that the selected cluster has the power supply capability to meet the system's basic operational needs. Under the premise of satisfying the power constraints, server 104 can further consider the objective of maximizing the cluster's operational and maintenance impact, using optimization algorithms to find the equipment cluster with the largest total operational and maintenance impact among all feasible equipment combinations. Server 104 can also consider the diversity and redundancy requirements of the cluster, avoiding excessive concentration of selected equipment in a particular type or region, ensuring that the cluster has good risk diversification characteristics and fault tolerance capabilities.

[0081] In some embodiments, server 104 can employ a heuristic search algorithm to intelligently explore the device combination space. First, server 104 sorts the devices in descending order based on their operational impact data, constructing a device importance ranking list. Then, it uses a greedy strategy to progressively build candidate clusters, starting with the most important devices. Server 104 can use dynamic programming to record and compare the performance of different device combinations, gradually converging to the optimal or near-optimal device combination scheme during the search process.

[0082] For example, server 104 can employ a method combining multi-objective optimization and intelligent search to select the collaborative operation and maintenance cluster. Server 104 can obtain detailed power demand data for future operation and maintenance cycles from the power system's load forecasting system, which may include load forecast values ​​for each time period, peak load demand, minimum load demand, and load fluctuation characteristics. Server 104 can determine the minimum power supply capacity requirement that the collaborative operation and maintenance cluster must meet based on the load forecasting data, which can be set to 120% of the predicted maximum load demand to ensure that the cluster has sufficient power supply guarantee capability.

[0083] During the cluster candidate device selection phase, server 104 can sort all power devices based on operational influence data and select the top 50% of devices by operational influence as the candidate device pool for cluster selection. This ensures both the high quality of candidate devices and controls the complexity of the search space. Server 104 can use combinatorial optimization algorithms to generate all possible device combinations that satisfy power constraints. For a case containing n candidate devices, theoretically there are 2^n minus one non-empty device combination. Server 104 significantly reduces the number of combinations that need to be evaluated through pruning strategies and constraint filtering.

[0084] In the calculation of the cluster comprehensive evaluation index, server 104 can calculate the average operation and maintenance influence of the cluster, which is the arithmetic mean of the operation and maintenance influence data of all devices in the cluster. This index reflects the overall importance level of the cluster. Server 104 can further calculate the cluster type diversity index by statistically analyzing the number of different power generation types contained in the cluster and applying the diversity index formula to assess the cluster's degree of diversification in terms of technology types. Server 104 can also calculate the cluster's geographical distribution index by analyzing the spatial distribution characteristics of the cluster based on the geographical coordinate data of the devices, avoiding the geographical risks caused by the over-concentration of devices in specific areas. Server 104 can use an improved greedy algorithm combined with local search optimization to find the optimal collaborative operation and maintenance cluster. Candidate devices are arranged in descending order of operation and maintenance influence. The initial cluster is built starting from the device with the highest influence, and devices are added step by step until the power constraint condition is met. During each step of adding devices, after obtaining the initial cluster solution, a local search algorithm can be further used for optimization. Through operations such as device replacement, device addition, and device deletion, the neighborhood solution space is explored to find a cluster combination with better comprehensive evaluation index.

[0085] During the local search process, server 104 can employ simulated annealing to control the search strategy, allowing for the acceptance of temporarily poor solutions with a certain probability, thus preventing the algorithm from getting trapped in local optima. Server 104 can set search termination conditions, stopping the optimization process when a better solution is not found after multiple consecutive iterations or when the preset maximum search time is reached. Server 104 uses the optimal cluster obtained from the search as the final collaborative operation and maintenance cluster, and performs detailed performance analysis and verification on this cluster.

[0086] In the aforementioned power equipment cluster operation and maintenance scheduling method, a relationship network diagram of multiple power equipment and historical operating data of each power equipment are obtained. The relationship network diagram uses power equipment as nodes, electrical connections between power equipment as edges, and correlation between power equipment as edge weights, solving the problem that traditional methods cannot identify the correlation between equipment. Based on the relationship network diagram, the centrality index of each power equipment in the relationship network diagram is calculated. Based on the historical operating data, the power supply stability index of each power equipment is calculated, and based on the centrality index and power supply stability index, the operation and maintenance influence data of each power equipment is calculated. By combining the centrality index, which reflects the importance of the equipment network, with the power supply stability index, which reflects the reliability of the equipment, the obtained operation and maintenance influence data can comprehensively reflect the importance of the equipment in the system, taking into account both the structural importance of the equipment and the operational reliability, overcoming the limitations of single index evaluation. Multiple power equipment are selected based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster. By using the operation and maintenance influence data to guide equipment selection, it is possible to identify those equipment combinations that have a significant impact on the system and are operating stably, forming a collaborative operation and maintenance cluster, thus improving the accuracy of operation and maintenance cluster configuration.

[0087] In one exemplary embodiment, such as Figure 3 As shown, the above method may further include steps S302 to S306. Wherein:

[0088] Step S302: Obtain power generation demand data and matching degree data of each power equipment under multiple power generation modes within the target operation and maintenance cycle.

[0089] Among them, power generation demand data refers to the power demand forecast information of the power system at various time periods within the target operation and maintenance cycle, which can include time series data such as load demand curves, peak demand times, valley demand times, and demand change trends. Matching degree data refers to the quantitative value of the adaptability of each power equipment under different power generation modes.

[0090] For example, server 104 can respond to a demand receiving instruction and collect power generation demand data within the target operation and maintenance cycle; extract historical power generation datasets for each power device under different power generation modes based on historical operating data; for each power generation mode, calculate the power generation achievement rate data for each power device under the corresponding power generation mode based on the expected power generation data and actual power generation data of each power device in the corresponding historical power generation dataset; and calculate matching degree data based on the power generation achievement rate data of each power device under each power generation mode. Server 104 can connect to the load forecasting module of the power system through a data interface to obtain future power demand forecast results based on historical load data, weather forecast data, economic development data, and electricity consumption behavior analysis. Server 104 can extract detailed historical operating data of each device from the power device operation monitoring system and classify and divide the historical operating data according to different power generation modes using cluster analysis methods. For the historical power generation dataset under each power generation mode, server 104 can extract the expected power generation data and actual power generation data of each power device, calculate the power generation achievement rate data of each power device under each power generation mode, and calculate matching degree data based on the cleaned power generation achievement rate data.

[0091] Furthermore, server 104 can also remove outliers from the baseline achievement rate data based on the Grubbs criterion, and average the remaining baseline achievement rate data to obtain the average power generation achievement rate of power equipment under the power generation mode; the formula for the Grubbs criterion is:

[0092] ;

[0093] in, As the baseline achievement rate data, This is the average of all benchmark achievement rates. The standard deviation of all benchmark achievement rate data. The Grubbs number is obtained by looking up the Grubbs table; if it does not meet the Grubbs criterion formula, it is removed as an outlier. By using the Grubbs criterion to remove outliers, the robustness and reliability of historical data evaluation results are ensured, and misjudgments of the true capabilities of equipment due to accidental events are avoided.

[0094] For example, server 104 can process the requirements for formulating the operation and maintenance plan for a power grid system in the next quarter. It obtains hourly power demand forecast data for 2160 hours in the next quarter from the load forecasting system, with a maximum demand power of 8000MW and a minimum demand power of 3000MW. Server 104 can extract historical operating data of 150 power generation devices over the past two years from the equipment monitoring system and use the K-means clustering algorithm to identify six power generation modes: high load high renewable energy mode, high load low renewable energy mode, medium load balance mode, low load high renewable energy mode, low load low renewable energy mode, and emergency peak shaving mode. Taking a gas turbine unit as an example, server 104 calculates that the expected power generation of the equipment in the high load high renewable energy mode is 400MW on average, the actual power generation is 385MW on average, the average power generation achievement rate after outlier removal is 92.3%, the standard deviation is 3.1%, the stability coefficient is 0.966, and the final matching degree is 0.892.

[0095] Step S304: Determine the predicted frequency data for each power generation mode within the target operation and maintenance cycle based on the power generation demand data.

[0096] Among them, the predicted frequency data refers to the quantitative value of the frequency of each power generation mode expected to occur within the target operation and maintenance cycle, reflecting the probability or duration of different operation modes in the future.

[0097] For example, server 104 uses time series analysis to perform in-depth analysis and prediction of future system operating status based on power generation demand data within the target operation and maintenance cycle. Server 104 can divide the target operation and maintenance cycle into hours as the basic time unit. For each time unit, based on the predicted power generation demand level, expected renewable energy output, and the operating plan of traditional units, it determines the most likely power generation mode type for that time period. Considering the uncertainty of mode prediction, server 104 can assign the probability of occurrence to each power generation mode in each time period. Server 104 can calculate the cumulative frequency of each power generation mode throughout the entire target operation and maintenance cycle through statistical analysis, and divide the expected total occurrence time of each mode by the total duration of the target operation and maintenance cycle to obtain the duration proportion of each mode as the prediction frequency data.

[0098] For example, server 104 can perform hourly pattern discrimination analysis on the power generation demand forecast data for 2160 hours in the next quarter. The analysis results show that: the high-load, high-renewable-energy mode is expected to occur for 288 hours, with a prediction frequency of 0.133; the high-load, low-renewable-energy mode is expected to occur for 194 hours, with a prediction frequency of 0.090; the medium-load balanced mode is expected to occur for 864 hours, with a prediction frequency of 0.400; the low-load, high-renewable-energy mode is expected to occur for 432 hours, with a prediction frequency of 0.200; the low-load, low-renewable-energy mode is expected to occur for 324 hours, with a prediction frequency of 0.150; and the emergency peak-shaving mode is expected to occur for 68 hours, with a prediction frequency of 0.031. Server 104 can verify that the sum of the prediction frequencies of all modes is close to 1.000, ensuring the integrity and rationality of the probability distribution.

[0099] Step S306: For each power generation mode of each power device, calculate the power generation capacity data based on the matching degree data and the corresponding predicted frequency data.

[0100] Among them, power generation capacity data refers to the comprehensive power generation efficiency assessment value calculated by each power equipment after comprehensively considering the adaptability of different power generation modes and the distribution characteristics of future operating scenarios.

[0101] For example, server 104 can calculate the power generation capacity data of each power device using a weighted fusion method based on the matching degree data of each power device under multiple power generation modes and the predicted frequency data of each power generation mode within the target operation and maintenance cycle. Server 104 can calculate the power generation capacity data of each power device using a weighted average method, multiplying the matching degree data of the device under each power generation mode by the predicted frequency data of the corresponding mode, and then summing the weighted matching degree contribution values ​​of all power generation modes. Server 104 can further consider the impact of the device's physical attributes on power generation capacity, and use capacity correction coefficients, technical condition correction coefficients, and environmental adaptability correction coefficients to comprehensively correct the power generation capacity data.

[0102] Through the above steps, server 104 achieves a comprehensive assessment of the power generation capacity of power equipment for future operating scenarios, overcoming the technical limitations of traditional methods that rely solely on historical performance or static parameters to evaluate equipment capacity and cannot adapt to dynamic operating demands. The power generation capacity data calculated in this step fully considers the adaptability differences of equipment under different operating modes and the distribution characteristics of future operating scenarios, achieving a significant shift from static capacity assessment to dynamic demand matching through a scientific weighted fusion method.

[0103] Furthermore, server 104 can select multiple power devices based on power generation capacity data and operation and maintenance influence data to obtain a collaborative operation and maintenance cluster. For example, server 104 can determine the maximum demand power within the target operation and maintenance cycle based on power generation demand data; iterate through the rated power data of each power device to generate candidate collaborative operation and maintenance clusters; wherein, a candidate collaborative operation and maintenance cluster is a combination of power devices whose sum of rated power data is greater than the maximum demand power; calculate the average value of the operation and maintenance influence data of each power device in each candidate collaborative operation and maintenance cluster to obtain cluster operation and maintenance influence data, and calculate the average value of the power generation capacity data of each power device in each candidate collaborative operation and maintenance cluster to obtain cluster power generation capacity data; based on the cluster operation and maintenance influence data and the cluster power generation capacity data, select a collaborative operation and maintenance cluster from the candidate collaborative operation and maintenance clusters.

[0104] For example, server 104 can determine the maximum power demand within the target operation and maintenance cycle based on power generation demand data, and generate candidate collaborative operation and maintenance clusters by traversing the rated power data of each power device. Based on the TOPSIS formula, the comprehensive evaluation value of each candidate collaborative operation and maintenance cluster is calculated, and the candidate collaborative operation and maintenance cluster with the highest comprehensive evaluation value is selected as the optimal collaborative operation and maintenance cluster; the TOPSIS formula is as follows:

[0105]

[0106] in, The comprehensive evaluation value of the candidate collaborative operation and maintenance clusters. The cluster operation and maintenance influence of the candidate collaborative operation and maintenance cluster. For the cluster power generation capacity of the candidate collaborative operation and maintenance cluster, This represents the maximum impact of cluster operation and maintenance. Maximum power generation capacity of the cluster To minimize the impact on cluster operation and maintenance, To minimize the power generation capacity of the cluster, the power equipment in the collaborative operation and maintenance cluster will be used as the core power equipment to participate in the operation and maintenance scheduling during the future operation and maintenance cycle.

[0107] By performing this step, server 104 achieves intelligent selection of collaborative operation and maintenance clusters based on multi-objective optimization, solving the technical problem of low efficiency in operation and maintenance resource allocation caused by the lack of a systematic equipment selection strategy in traditional operation and maintenance methods. The collaborative operation and maintenance cluster selected in this step not only meets the system power supply requirements, but more importantly, achieves an optimal balance between operation and maintenance influence and power generation capacity.

[0108] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0109] Based on the same inventive concept, this application also provides an operation and maintenance scheduling device for a power equipment cluster to implement the operation and maintenance scheduling method for the power equipment cluster described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more operation and maintenance scheduling device embodiments for power equipment clusters provided below can be found in the limitations of the operation and maintenance scheduling method for power equipment clusters described above, and will not be repeated here.

[0110] In one exemplary embodiment, such as Figure 4 As shown, an operation and maintenance scheduling device for a power equipment cluster is provided, comprising: a data acquisition module 402, a data calculation module 404, a data processing module 406, and a cluster scheduling module 408, wherein:

[0111] The data acquisition module 402 is used to acquire a relationship network diagram of multiple power devices and historical operating data of each power device; the relationship network diagram uses power devices as nodes, electrical connection relationships between power devices as edges, and the degree of correlation between power devices as edge weights.

[0112] The data calculation module 404 is used to calculate the centrality index data of each power device in the relationship network diagram based on the relationship network diagram;

[0113] The data processing module 406 is used to calculate the power supply stability index data of each power device based on historical operating data, and to calculate the operation and maintenance impact data of each power device based on the centrality index data and the power supply stability index data.

[0114] The cluster scheduling module 408 is used to select multiple power devices based on operation and maintenance influence data to obtain a collaborative operation and maintenance cluster.

[0115] In one embodiment, the apparatus further includes: a prediction processing module, configured to acquire power generation demand data and matching degree data of each power device under multiple power generation modes within a target operation and maintenance cycle; determine the prediction frequency data of each power generation mode within the target operation and maintenance cycle based on the power generation demand data; calculate power generation capacity data for each power generation mode of each power device based on the matching degree data and the corresponding prediction frequency data; correspondingly, the cluster scheduling module 408 is configured to select multiple power devices based on the power generation capacity data and operation and maintenance influence data to obtain a collaborative operation and maintenance cluster.

[0116] In one embodiment, the prediction processing module is specifically used to respond to the demand receiving instruction, collect power generation demand data within the target operation and maintenance cycle; extract historical power generation datasets for each power device under different power generation modes based on historical operating data; calculate the power generation achievement rate data of each power device under each power generation mode based on the expected power generation data and actual power generation data of each power device in the corresponding historical power generation dataset; and calculate the matching degree data based on the power generation achievement rate data of each power device under each power generation mode.

[0117] In one embodiment, the cluster scheduling module 408 is specifically used to determine the maximum demand power within the target operation and maintenance cycle based on the power generation demand data; traverse the rated power data of each power device to generate candidate collaborative operation and maintenance clusters; wherein, the candidate collaborative operation and maintenance cluster is a combination of power devices whose sum of rated power data is greater than the maximum demand power; calculate the average value of the operation and maintenance influence data of each power device in each candidate collaborative operation and maintenance cluster to obtain the cluster operation and maintenance influence data, and calculate the average value of the power generation capacity data of each power device in each candidate collaborative operation and maintenance cluster to obtain the cluster power generation capacity data; and select a collaborative operation and maintenance cluster from each candidate collaborative operation and maintenance cluster based on the cluster operation and maintenance influence data and the cluster power generation capacity data.

[0118] In one embodiment, the relationship network graph includes at least one pair of power devices, and each pair of power devices includes two power devices. The data acquisition module 402 is specifically used to acquire time-series data of the historical power generation of each power device and grid topology data. For each pair of power devices, the Pearson correlation coefficient is calculated based on the time-series data, and the power generation correlation degree is calculated based on the Pearson correlation coefficient. For each pair of power devices, the grid connection tightness is calculated based on the grid topology data. The power generation correlation degree and grid connection tightness of each pair of power devices are weighted and fused to obtain the correlation degree between the power devices, and the correlation degree is used as the edge weight of the corresponding edge in the relationship network graph.

[0119] In one embodiment, the data acquisition module 402 is specifically used to extract electrical distance data between each pair of power equipment from the power grid topology data, and select the maximum and minimum values ​​of the electrical distance data of all power equipment pairs to obtain the maximum and minimum electrical distance values; for each pair of power equipment, the grid connection tightness is calculated based on the corresponding electrical distance data, the maximum electrical distance value, and the minimum electrical distance value.

[0120] Each module in the aforementioned power equipment cluster's operation and maintenance dispatching device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can invoke and execute the corresponding operations of each module.

[0121] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media to run. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for the operation and maintenance scheduling of a power equipment cluster.

[0122] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0123] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0124] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0125] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0126] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0127] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0128] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0129] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for operation and maintenance scheduling of a power equipment cluster, characterized in that, The method includes: Obtain a relationship network diagram of multiple power devices and historical operating data of each power device; the relationship network diagram uses power devices as nodes, electrical connections between power devices as edges, and the degree of association between power devices as edge weights; Based on the relationship network diagram, calculate the centrality index data of each of the power devices in the relationship network diagram; Based on the historical operating data, calculate the power supply stability index data for each of the power devices, and calculate the operation and maintenance impact data for each of the power devices based on the centrality index data and the power supply stability index data. Multiple power devices are selected based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster.

2. The method according to claim 1, characterized in that, The method further includes: Obtain power generation demand data and matching degree data of each power device under multiple power generation modes within the target operation and maintenance cycle; Based on the power generation demand data, determine the predicted frequency data for each of the power generation modes within the target operation and maintenance cycle; For each of the power generation modes of each of the aforementioned power devices, power generation capacity data is calculated based on the matching degree data and the corresponding predicted frequency data; Correspondingly, the step of selecting multiple power devices based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster includes: Based on the power generation capacity data and the operation and maintenance influence data, multiple power devices are selected to obtain a collaborative operation and maintenance cluster.

3. The method according to claim 2, characterized in that, The acquisition of power generation demand data within the target operation and maintenance cycle and matching degree data of each power device under multiple power generation modes includes: In response to demand reception instructions, collect power generation demand data within the target operation and maintenance cycle; Based on the historical operating data, extract the historical power generation datasets of each of the power devices under different power generation modes; For each power generation mode, the power generation achievement rate data of each power device in the corresponding historical power generation dataset is calculated based on the expected power generation data and actual power generation data of each power device in the power generation mode. Matching degree data is calculated based on the power generation achievement rate data of each of the power devices in each of the power generation modes.

4. The method according to claim 2, characterized in that, The step of selecting multiple power devices based on the power generation capacity data and the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster includes: Based on the power generation demand data, determine the maximum power demand within the target operation and maintenance cycle; The rated power data of each of the power devices is traversed to generate candidate collaborative operation and maintenance clusters; wherein, the candidate collaborative operation and maintenance cluster is a combination of power devices whose sum of rated power data is greater than the maximum required power. Calculate the average value of the operation and maintenance influence data of each power device in each candidate collaborative operation and maintenance cluster to obtain the cluster operation and maintenance influence data, and calculate the average value of the power generation capacity data of each power device in each candidate collaborative operation and maintenance cluster to obtain the cluster power generation capacity data. Based on the cluster operation and maintenance influence data and the cluster power generation capacity data, a collaborative operation and maintenance cluster is selected from each of the candidate collaborative operation and maintenance clusters.

5. The method according to any one of claims 1 to 4, characterized in that, The relationship network diagram includes at least one pair of power devices, and the pair of power devices includes two power devices; obtaining the relationship network diagram of multiple power devices includes: Acquire time-series data of the historical power generation of each of the aforementioned power devices and power grid topology data; For each of the power equipment pairs, a Pearson correlation coefficient is calculated based on the time series data, and the power generation correlation degree is calculated based on the Pearson correlation coefficient. For each of the power equipment pairs, the grid connection density is calculated based on the grid topology data; The correlation degree between the power generation power and the grid connection tightness of each power equipment pair are weighted and fused to obtain the correlation degree between the power equipment, and the correlation degree is used as the edge weight of the corresponding edge in the relationship network graph.

6. The method according to claim 5, characterized in that, The calculation of grid connectivity density for each of the power equipment pairs based on the grid topology data includes: From the power grid topology data, the electrical distance data between each pair of power equipment is extracted, and the maximum and minimum values ​​of the electrical distance data of all pairs of power equipment are selected to obtain the maximum and minimum electrical distance values. For each pair of power equipment, the grid connection tightness is calculated based on the corresponding electrical distance data, the maximum electrical distance, and the minimum electrical distance.

7. A power equipment cluster operation and maintenance dispatching device, characterized in that, The device includes: The data acquisition module is used to acquire a relationship network diagram of multiple power devices and historical operating data of each power device; the relationship network diagram is based on power devices as nodes, electrical connections between power devices as edges, and the degree of correlation between power devices as edge weights. The data calculation module is used to calculate the centrality index data of each of the power devices in the relationship network diagram based on the relationship network diagram; The data processing module is used to calculate the power supply stability index data of each of the power devices based on the historical operating data, and to calculate the operation and maintenance impact data of each of the power devices based on the centrality index data and the power supply stability index data. The cluster scheduling module is used to select multiple power devices based on the operation and maintenance influence data to obtain a collaborative operation and maintenance cluster.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images