A Multi-Task Scheduling Optimization Method and System Based on Power Internet of Things

Abstract

This invention discloses a multi-task scheduling optimization method and system based on the power Internet of Things (IoT), relating to the field of power IoT technology. The method includes: acquiring the distribution mode of the power grid in a distribution area, analyzing frequent fault patterns, and identifying the types of high-frequency faulty components and their fault probability identifiers; obtaining redundant inventory data from a maintenance component library based on component type and deployment quantity, and performing inventory balancing analysis to derive an inventory balancing coefficient; when the inventory balancing coefficient is lower than a threshold, replenishing the inventory of high-frequency faulty component models. This solves the technical problem of insufficient inventory of high-frequency faulty components due to the lack of real-time analysis of inventory status in existing power operation and maintenance management, achieving the technical effect of real-time dynamic inventory optimization management.

Description

Technical Field

[0001] This application relates to the field of power Internet of Things (IoT) technology, and in particular to a multi-task scheduling optimization method and system based on power IoT. Background Technology

[0002] In modern power systems, with increasing power load and increasingly complex grid operating environments, traditional power operation and maintenance management faces numerous challenges, particularly in power distribution network management and emergency fault handling. Traditional methods relying on manual monitoring and experience-based judgment suffer from slow response times, low prediction accuracy, and inefficient resource scheduling. The status, failure rates, and inventory levels of numerous devices and components in a power system are typically dispersed, lacking unified real-time monitoring and intelligent optimization. This leads to uneven distribution of component and redundant inventory, impacting the efficiency and response speed of power operation and maintenance. Especially when grid equipment experiences frequent failures, the lack of accurate inventory status analysis and intelligent resource scheduling can result in spare parts shortages, hindering timely equipment repair and potentially causing power supply interruptions. Therefore, there is an urgent need for an optimization method that integrates power Internet of Things (IoT) technology for real-time monitoring, predictive analysis, and dynamic scheduling to improve power system operating efficiency, reduce fault response time, and effectively manage inventory resources.

[0003] At present, there is a technical problem in the relevant technologies that is the lack of real-time analysis of inventory status in power operation and maintenance management, which leads to insufficient inventory of high-frequency fault components. Summary of the Invention

[0004] This application provides a multi-task scheduling optimization method and system based on the power Internet of Things, which solves the technical problem of insufficient inventory of high-frequency fault components due to the lack of real-time analysis of inventory status in existing power operation and maintenance management.

[0005] This application provides a multi-task scheduling optimization method based on the power Internet of Things, including:

[0006] Obtain the distribution mode of the power grid in the distribution area; perform frequent fault pattern analysis based on the distribution mode of the power grid in the distribution area to obtain the high-frequency fault component type, wherein the high-frequency fault component type has a component fault probability identifier; obtain the component deployment quantity of the high-frequency fault component type in the distribution area; obtain the redundant inventory quantity of the high-frequency fault component model of the high-frequency fault component type based on the maintenance component library of the distribution area; perform a balance analysis on the redundant inventory quantity based on the component deployment quantity and the component fault probability identifier to obtain an inventory balance coefficient; when the inventory balance coefficient is less than or equal to the inventory balance coefficient threshold, replenish the inventory of the high-frequency fault component model.

[0007] This application also provides a multi-task scheduling optimization system based on the power Internet of Things, including:

[0008] The system comprises the following modules: a distribution mode acquisition module for obtaining the distribution mode of the power grid in the distribution area; a mode analysis module for performing frequent fault mode analysis of the power grid based on the distribution mode of the distribution area to obtain the high-frequency fault component type, wherein the high-frequency fault component type has a component fault probability identifier; a component deployment quantity acquisition module for obtaining the component deployment quantity of the high-frequency fault component type in the distribution area; a redundant inventory quantity acquisition module for obtaining the redundant inventory quantity of the high-frequency fault component type based on the maintenance component library of the distribution area; a balance analysis module for performing balance analysis on the redundant inventory quantity based on the component deployment quantity and the component fault probability identifier to obtain an inventory balance coefficient; and an inventory replenishment module for replenishing the inventory of the high-frequency fault component type when the inventory balance coefficient is less than or equal to an inventory balance coefficient threshold.

[0009] The proposed method and system for multi-task scheduling optimization based on the power Internet of Things first acquires the distribution mode of the power grid in the distribution area, analyzes the frequent fault patterns of the power grid, and identifies the types of high-frequency faulty components and their fault probability identifiers. Based on the component type and deployment quantity, redundant inventory data is obtained from the maintenance component library, and the inventory is balanced to obtain the inventory balance coefficient. When the inventory balance coefficient is lower than the threshold, the inventory of high-frequency faulty component models is replenished, thus achieving the technical effect of real-time dynamic inventory optimization management. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0011] Figure 1 A flowchart illustrating the multi-task scheduling optimization method based on the power Internet of Things provided in this application embodiment;

[0012] Figure 2 This is a schematic diagram of the structure of a multi-task scheduling optimization system based on the power Internet of Things provided in an embodiment of this application.

[0013] Figure labeling: 10 Distribution mode acquisition module, 20 Mode analysis module, 30 Component deployment quantity acquisition module, 40 Redundant inventory quantity acquisition module, 50 Balance analysis module, 60 Inventory replenishment module. Detailed Implementation

[0014] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0015] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same or different subsets of all possible embodiments and can be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0017] This application provides a multi-task scheduling optimization method based on the power Internet of Things, such as... Figure 1 As shown, the method includes:

[0018] Step S100: Obtain the distribution mode of the distribution network in the transformer substation. Specifically, multi-source data, including electrical parameters such as voltage, current, and power, geographical location, and equipment information, are collected and integrated through smart sensors, monitoring equipment, geographic information systems, and equipment ledgers in the transformer substation power grid. This data is then integrated to construct a data infrastructure platform. Based on this data, the operating status of the transformer substation power grid is analyzed to determine anomalies such as voltage fluctuations and current overloads, as well as power quality and power compensation. The topology and connection relationships are clarified. Subsequently, data analysis algorithms and modeling techniques are used, and a mathematical model is constructed based on the power grid topology, electrical parameters, and operating status using power system analysis software. This model details the characteristics and connection relationships of each component and their dynamic behavior. Simulation calculations are performed to simulate the operating response under different operating conditions, gaining a deeper understanding of the distribution mode characteristics. Finally, the distribution mode of the transformer substation power grid is generated, providing support for subsequent work to achieve refined management and optimized operation.

[0019] Step S200: Based on the distribution mode of the transformer substation power grid, perform frequent fault pattern analysis to obtain high-frequency fault component types, wherein the high-frequency fault component types have component fault probability identifiers. Specifically, analyze the distribution mode of the transformer substation power grid, extract the first transformer substation components and their models and electrical control parameters to construct an information database. Then, using the environmental monitoring data and distribution mode of the transformer substation deployment as constraints, collect a set of transformer substation power grid fault samples containing various environmental and operating condition information. Subsequently, perform frequent fault pattern analysis on the components based on the component models and electrical control parameters, calculate the number of samples that meet the conditions as the component trigger frequency, and calculate the proportion of the sample number as the fault probability identifier. When the component trigger frequency exceeds a threshold, the component and its information are associated and stored in the high-frequency fault component type and the fault probability identifier is stored for subsequent targeted management and maintenance, thereby improving the reliability and stability of the transformer substation power grid.

[0020] In one possible implementation, frequent fault pattern analysis of the power grid is performed based on the distribution mode of the distribution area to obtain high-frequency fault component types. These high-frequency fault component types have component fault probability identifiers. Step S200 further includes step S210, extracting a first distribution area component based on the distribution mode of the distribution area. This first distribution area component has a first distribution area component model and first distribution area component electrical control parameters. Specifically, the distribution mode of the distribution area is analyzed in depth and data is mined. The distribution mode of the distribution area includes information on the power grid topology, electrical parameter distribution, equipment connection relationships, and operating status. Through specific data extraction algorithms and model recognition techniques, the relevant information of the first distribution area component is accurately separated from this complex distribution mode. For example, when analyzing the power grid topology, the specific equipment connected to each node is identified; these devices are the first distribution area components. For each first distribution area component, its key attributes, namely the first distribution area component model and the first distribution area component electrical control parameters, are further extracted. Taking a transformer as an example, its model number may indicate its technical specifications such as capacity, winding structure, and cooling method, while the electrical control parameters cover operational control-related data such as oil temperature monitoring range, winding temperature alarm threshold, tap changer adjustment range, and control logic. This component model number and electrical control parameter information will serve as an important basis for subsequent fault analysis. They help to accurately locate and distinguish different types and characteristics of components among numerous power grid components, thus laying the foundation for targeted research on their fault modes.

[0021] Step S220 involves collecting a set of fault samples from the power grid in the distribution area, constrained by the environmental monitoring data of the distribution area and the power grid distribution mode of the distribution area. Specifically, after obtaining the first distribution area components and their related parameters, the set of fault samples from the power grid in the distribution area is constructed. This process uses the environmental monitoring data of the distribution area and the power grid distribution mode of the distribution area as constraints to ensure that the collected fault samples are representative and targeted. The environmental monitoring data of the distribution area includes information on various environmental factors such as ambient temperature, humidity, air pressure, electromagnetic interference intensity, and salt spray content (in coastal or specific industrial environments). These environmental factors are closely related to the occurrence of faults in power grid components. For example, high-temperature environments may accelerate the aging of insulation materials in electrical equipment, thereby increasing the risk of insulation breakdown faults; high-humidity environments may cause moisture on the surface of equipment, leading to leakage or short-circuit faults; strong electromagnetic interference may interfere with the control signals of equipment, resulting in malfunctions or faults. At the same time, the power grid distribution mode of the distribution area provides information on the operating conditions of the power grid when a fault occurs, such as load size, power factor, voltage stability, and power flow distribution. By comprehensively considering these environmental monitoring data and distribution mode information, fault samples that meet the criteria are selected from the historical fault record database of the power grid, the real-time fault monitoring system, and simulated fault experimental data (if available). For example, transformer fault samples occurring under high temperature and high load conditions, or relay protection device malfunction samples occurring in environments with strong electromagnetic interference, are selected. These selected fault samples are integrated to form a comprehensive and targeted set of power grid fault samples for the distribution area, providing sufficient data resources for subsequent frequent fault mode analysis.

[0022] Step S230: Based on the power grid fault sample set of the distribution area, perform frequent fault pattern analysis on the first distribution area component according to the component model and electrical control parameters to obtain the triggering frequency and fault probability identifier of the first distribution area component. Specifically, based on the constructed power grid fault sample set of the distribution area, conduct in-depth frequent fault pattern analysis on the first distribution area component according to the component model and electrical control parameters. This analysis process is mainly achieved through data statistics and pattern recognition technology. First, for each component model and its corresponding electrical control parameter combination, a comprehensive search and statistics are performed in the power grid fault sample set. The number of samples that simultaneously satisfy the specific electrical control parameters and component model of the first distribution area component is calculated, and this number is determined as the triggering frequency of the first distribution area component. For example, for a specific type of circuit breaker, if 30 samples are found in the fault sample set whose electrical control parameters (such as abnormal opening and closing time, contact wear, etc.) match the standard parameters of that type of circuit breaker when the fault occurs, then the triggering frequency of that type of circuit breaker is 30. Furthermore, the percentage of samples that simultaneously meet both the electrical control parameters and the model number of the first transformer substation element is calculated, and this percentage is set as the fault probability identifier for the first transformer substation element. For example, if out of a total of 500 fault samples, 40 samples of a certain type of insulator have faults and all meet its specific electrical control parameters, then its fault probability identifier is 40 / 500 = 0.08. Through this analysis, the frequency and probability of fault occurrence for each type of first transformer substation element in grid operation can be quantitatively assessed, thereby identifying potential high-frequency fault element types.

[0023] Step S240: When the triggering frequency of the first transformer substation element is greater than or equal to the triggering frequency threshold, the first transformer substation element, its model number, and its electrical control parameters are associated and stored in the high-frequency fault element type. Simultaneously, the fault probability identifier of the first transformer substation element is stored in the element fault probability identifier. Specifically, when the triggering frequency of a certain first transformer substation element is greater than or equal to the triggering frequency threshold, it indicates that the element belongs to a high-incidence fault type in power grid operation. At this time, the first transformer substation element, its model number, and its electrical control parameters are associated and integrated, and stored in the high-frequency fault element type database. For example, if the triggering frequency of a certain type of fuse reaches or exceeds a set threshold, then the fuse, its model number, and electrical control parameters (such as rated current, fusing characteristic curve, etc.) are stored as a whole in the high-frequency fault element type. At the same time, the corresponding first transformer area component failure probability identifier is stored in a dedicated component failure probability identifier database. This enables the rapid and accurate acquisition of key information on these high-frequency faulty components during subsequent work such as inventory management, equipment maintenance planning, and fault prediction, providing strong data support and decision-making basis for improving the reliability and stability of the transformer area power grid.

[0024] In one possible implementation, based on the power grid fault sample set for the first distribution area, a frequent fault pattern analysis is performed on the first distribution area component based on its model and electrical control parameters to obtain the triggering frequency and fault probability identifier of the first distribution area component. Step S230 further includes step S231, which counts the number of samples that simultaneously satisfy the electrical control parameters and model of the first distribution area component, based on the power grid fault sample set for the first distribution area, to obtain the triggering frequency of the first distribution area component. Specifically, the power grid fault sample set for the first distribution area is organized and analyzed. The fault sample set contains detailed records of various fault events that have occurred in the power grid over a period of time, such as the time and location of the fault, the equipment involved, the fault phenomenon, and the power grid operating conditions at the time. For each fault sample, the component information involved is compared one by one with the electrical control parameters and model of the first distribution area component. For example, if the first transformer substation component is a circuit breaker of a certain model, its electrical control parameters include rated voltage, rated current, and opening / closing time range. When analyzing fault samples, it is checked whether the faulty circuit breaker is of that specific model and whether its electrical parameters at the time of the fault are within the set electrical control parameter range. By performing this traversal and comparison operation on the entire transformer substation power grid fault sample set, the number of samples that simultaneously meet the electrical control parameters and model of the first transformer substation component is counted. This counted number is the triggering frequency of the first transformer substation component, which directly reflects the frequency with which components of that model and with specific electrical control parameters occur in transformer substation power grid fault events. For example, if it is found that 50 samples of a certain model of insulator simultaneously meet its electrical control parameters and model requirements in the fault sample set, then the triggering frequency of that insulator is 50. This means that in past fault situations, this type of insulator has relatively frequently encountered problems and may be a potentially high-fault component type.

[0025] Step S232: Calculate the percentage of samples that simultaneously meet the electrical control parameters and model number of the first transformer substation element, and set this percentage as the fault probability identifier for the first transformer substation element. Specifically, after determining the triggering frequency of the first transformer substation element, the fault probability identifier is further calculated. The percentage of samples that simultaneously meet the electrical control parameters and model number of the first transformer substation element is used as the fault probability identifier for the first transformer substation element. For example, if the fault sample set of the transformer substation has a total of 1000 samples, and the number of fault samples that simultaneously meet the electrical control parameters and model number of a certain type of transformer is 80, then the fault probability identifier for that type of transformer is 80 / 1000 = 0.08. This fault probability identifier quantitatively represents, in percentage form, the probability of a component of that model with specific electrical control parameters failing in the transformer substation. By calculating the fault probability identifier, the risk level of different first-area components in the power grid operation can be more accurately assessed. In subsequent operation and maintenance management, these probability values ​​can be used to focus on high-frequency fault component types, reserve spare parts in advance, and formulate targeted maintenance strategies, thereby effectively improving the reliability and stability of the power grid in the distribution area and reducing the probability of fault occurrence and the losses caused by faults.

[0026] Step S300: Obtain the number of high-frequency faulty components deployed in the distribution area. Specifically, clarify the data source for obtaining the number of high-frequency faulty components deployed in the distribution area, integrate the distribution area power grid equipment management system database, asset ledger records, and real-time monitoring system equipment operation status data to construct a distribution area equipment information dataset. Then, based on the characteristics such as the model and electrical control parameters of the high-frequency faulty component type, use database query statements or data mining algorithms to filter matching component records in the dataset. Finally, count the number of filtered matching component records, exclude components that are scrapped, dismantled, or cannot operate in the short term due to maintenance, and verify the results by comparing with on-site operation and maintenance inspection records or confirming with remote monitoring equipment, providing reliable data basis for subsequent work.

[0027] In one possible implementation, obtaining the number of high-frequency faulty components deployed in the distribution area, step S300 further includes step S310, obtaining the number of components deployed in the distribution area that simultaneously meet the electrical control parameters and model of the components in the first distribution area. Specifically, equipment information data is obtained from the distribution area equipment management system and integrated with maintenance record data to form a distribution area equipment information database. Then, based on the model and electrical control parameters of the components in the first distribution area, database query technology is used to accurately filter out the component records that meet the requirements. During the process, the electrical control parameters are strictly matched to eliminate discrepancies. After that, the number of the filtered component records is counted. During the count, the component status is judged based on the maintenance records and the actual situation to determine whether to include it in the deployment quantity. Finally, the accuracy of the component deployment quantity is ensured by arranging maintenance personnel to conduct on-site inspections and verifying the statistical results, providing reliable data support for subsequent work.

[0028] Step S400: Obtain the redundant inventory quantity of high-frequency fault component models based on the transformer area maintenance component database. Specifically, log in to the transformer area maintenance component database through the database access interface and authentication. Then, use the database query function to filter component records in standby, idle, or available status using the high-frequency fault component model as the key search condition and the inventory status field. Next, directly read the value of the inventory quantity field in the filtered component records to determine the redundant inventory quantity. Finally, verify the completeness and accuracy of the data by comparing it with the inventory change history, providing a reliable basis for subsequent inventory management decisions.

[0029] Step S500: Based on the number of deployed components and the component failure probability identifier, a balance analysis is performed on the quantity of redundant inventory to obtain an inventory balance coefficient. Specifically, the number of components to be predicted for failure is obtained by multiplying the number of deployed components and the component failure probability identifier. This number is based on the current component distribution and past failure probabilities to estimate the number of possible future failure components. Then, the ratio of the quantity of redundant inventory to the quantity of predicted component failures is calculated as the inventory balance coefficient. This coefficient reflects the adequacy of redundant inventory relative to failure risk. A value close to 1 indicates that the inventory is reasonable, a value much less than 1 indicates a risk of operation and maintenance interruption, and a value much greater than 1 may indicate inventory backlog. It can intuitively present the balance relationship between inventory and failure risk, providing a scientific basis for inventory replenishment or adjustment to ensure the stable operation of the power system and optimize inventory management.

[0030] In one possible implementation, based on the number of components deployed and the component failure probability identifier, a balance analysis is performed on the redundant inventory quantity to obtain an inventory balance coefficient. Step S500 further includes step S510, multiplying the number of components deployed and the component failure probability identifier to obtain the predicted number of component failures. Specifically, the two key data points, the number of components deployed and the component failure probability identifier, are obtained. The number of components deployed reflects the actual distribution scale of a specific type of component in the power grid area; for example, 100 of a certain type of switch component are deployed in a certain area. The component failure probability identifier is obtained through in-depth analysis of the power grid failure sample set in the area. It quantifies the probability of failure of this type of component in past operation; for example, the failure probability identifier of this type of switch component is 0.1. Multiplying these two data points, i.e., 100 × 0.1 = 10, yields the predicted number of component failures, which is 10. This means that based on the current deployment and historical failure probabilities, it is expected that 10 of this type of switch component may fail in future operation. This calculation method takes into account both the existing quantity of components and their tendency to fail, providing a basic predictive data for assessing whether inventory can cope with potential failures.

[0031] Step S520: Calculate the ratio of the redundant inventory quantity to the predicted component failure quantity, and set it as the inventory balance coefficient. Specifically, after obtaining the predicted component failure quantity, the inventory balance coefficient is calculated. Obtain the redundant inventory quantity, which refers to the number of components of that model available for allocation to cope with failures in the maintenance component warehouse of the distribution area, excluding those currently in use and those already allocated. Assume the redundant inventory quantity of this model of switch component is 5. Calculate the ratio of the redundant inventory quantity to the predicted component failure quantity, i.e., 5 ÷ 10 = 0.5. This 0.5 is the inventory balance coefficient. The inventory balance coefficient is an important indicator for measuring the balance between inventory and possible component failures. If the inventory balance coefficient is equal to 1, it means that the amount of redundant inventory is just enough to meet the expected number of faulty components, and the inventory is in a relatively balanced state. If the inventory balance coefficient is less than 1, such as the current 0.5, it means that the amount of redundant inventory is insufficient to cope with possible failures, and it may be necessary to consider replenishing inventory to reduce the risk of power supply interruption or maintenance difficulties caused by component failure. If the inventory balance coefficient is greater than 1, it may mean that there is a certain amount of inventory backlog, and it is necessary to further assess whether there are problems with poor inventory management or excessive component reserves, so as to reasonably optimize the inventory structure, improve the utilization efficiency of inventory resources, and reduce costs.

[0032] Step S600: When the inventory balance coefficient is less than or equal to the inventory balance coefficient threshold, inventory replenishment is performed for the high-frequency faulty component models. Specifically, firstly, the inventory balance coefficient is continuously monitored and compared with a preset threshold. This threshold is determined comprehensively based on multiple factors such as the reliability requirements of the power grid in the distribution area and the procurement cycle. When the inventory balance coefficient is less than or equal to the threshold, the inventory replenishment decision process is triggered. Then, for each high-frequency faulty component model, the difference between its predicted component failure quantity and the redundant inventory quantity is calculated to determine the replenishment demand. At the same time, the replenishment quantity is adjusted by taking into account recent component replacement plans, alternative components, and inventory cost budgets. After that, an inventory replenishment plan is formulated, which includes determining supplier selection criteria such as reputation, quality, price, and delivery cycle, considering transportation methods and logistics arrangements, and formulating transportation guarantee measures for special components. Finally, the plan is implemented, including signing contracts, tracking progress, inspection upon arrival, and warehousing registration, to improve the reliability and stability of the power grid operation and maintenance in the distribution area and ensure the continuous and stable power supply.

[0033] In one possible implementation, when the inventory balancing coefficient is less than or equal to the inventory balancing coefficient threshold, inventory replenishment is performed on the high-frequency faulty component model. Step S600 further includes step S610, which involves iterating through the predicted fault quantity of the first component model up to the predicted fault quantity of the Mth component model, and performing a balanced inventory quantity analysis based on the inventory balancing coefficient threshold to obtain the balanced inventory quantity of the first component model up to the balanced inventory quantity of the Mth component model. Specifically, the system iterates through the predicted fault quantity of the first component model up to the predicted fault quantity of the Mth component model in sequence. For each component model, its predicted fault quantity and the inventory balancing coefficient threshold are used as key data for balanced inventory quantity analysis. For example, assuming the inventory balancing coefficient threshold is set to 0.8, for a specific first component model, if its predicted fault quantity is 50, then its balanced inventory quantity is calculated according to the formula, assuming the calculated balanced inventory quantity for this model should be 40. This calculation process is based on a precise analysis of the predicted component failure risk and overall inventory balance requirements. By combining the predicted failure quantity for each component model with a threshold, and comprehensively considering various factors such as component importance, procurement cycle, and storage costs, a balanced inventory level that can achieve reasonable allocation of inventory resources while ensuring the stable operation of the power system is determined. After traversing all component models from the first to the Mth, a complete dataset of balanced inventory levels for the first component model up to the Mth component model is obtained. This dataset will serve as a crucial basis for subsequent inventory replenishment.

[0034] Step S620: Replenish the inventory of the high-frequency faulty component model based on the balanced inventory levels of the first component model up to the Mth component model. Specifically, after obtaining the balanced inventory levels of the first component model up to the Mth component model, inventory replenishment is carried out for the high-frequency faulty component models based on this data. For each high-frequency faulty component model, its current actual inventory quantity is compared with the corresponding balanced inventory quantity. If the actual inventory quantity of a certain high-frequency faulty component model is lower than its balanced inventory quantity, for example, a certain model of transformer has a balanced inventory of 10 units, but the actual inventory is only 6 units, then inventory replenishment is required. The replenishment quantity is determined based on the difference between the two, i.e., 4 units are replenished. During the replenishment process, factors such as the supplier's supply capacity, delivery cycle, and transportation links also need to be considered. For example, selecting suppliers with good reputations, who can supply on time and in the required quantity, and whose transportation is safe and reliable, ensures that the replenished components can arrive at the distribution area warehouse in a timely and accurate manner, thereby effectively improving the inventory level, enhancing the ability to cope with component failures, ensuring the stable operation of the distribution area power grid, and reducing the occurrence of power supply interruptions or maintenance difficulties caused by component shortages.

[0035] In one possible implementation, the inventory of the high-frequency faulty component model is replenished based on the balanced inventory of the first component model up to the balanced inventory of the Mth component model. Step S620 further includes step S621, obtaining the available inventory. Specifically, a comprehensive inventory check and data statistics are conducted on the transformer substation's inventory management system to determine the available inventory. This process involves a detailed inventory check of various components in the warehouse, including information such as component model, quantity, storage location, and inventory status. Using specific inventory management software or data recording systems, the quantities of components that have not been assigned to any use, are idle, and are available for replenishing inventory are identified and summarized to obtain the available inventory data. For example, in the transformer substation warehouse, a careful inventory check reveals that 30 insulators of a certain model and 20 fuses of a certain model are idle. These quantities will serve as one of the important basic data for optimizing the subsequent inventory replenishment plan, because the amount of available inventory directly affects the scale of resources that can be used to replenish the inventory of high-frequency faulty component models.

[0036] Step S622, construct the inventory replenishment fitness function: Q3 = w1Q1 + w2Q2, where Q1 represents the first fitness function, Q2 represents the second fitness function, Q3 represents the inventory replenishment fitness function, and p i Characterizing the failure probability of the i-th component model, x i x represents the inventory quantity of the i-th component model configuration. i0Let w1 represent the balanced inventory level for the i-th component model, w2 represent the second weight, and w1 represent the first weight. Specifically, constructing the inventory replenishment fitness function is a key step in optimizing the inventory replenishment plan. The function consists of several parts, the first being the first fitness function. Where p i This represents the failure probability of the i-th component model. It's important to note that each component model may have multiple failure probability values; in this case, the maximum value is used. For example, a transformer model may have multiple failure probability values ​​under different operating conditions or historical fault records, such as 0.05, 0.08, etc. We take 0.08 as p. i The value of x. i x represents the inventory quantity of the i-th component model configuration. i0 This function represents the equilibrium inventory level for the i-th component model. By quantifying the relationship between the failure probability of different component models and the configured and equilibrium inventory levels, it reflects a correlation between component failure risk and inventory levels. The second fitness function... It primarily measures the impact of the deviation between the current inventory level and the equilibrium inventory level on the inventory replenishment plan, from the perspective of the difference between the current inventory level and the equilibrium inventory level. When x i With x i0 The greater the difference, The smaller the value, the less ideal the inventory status, and the more adjustments are needed. Finally, the inventory replenishment fitness function is Q3 = w1Q1 + w2Q2, where w1 represents the first weight and w2 represents the second weight. The determination of these two weights needs to comprehensively consider factors such as the grid's tolerance for fault risk and its requirements for inventory costs and resource utilization efficiency. For example, if the grid is more sensitive to fault risk, the value of w1 may be relatively large, focusing more on optimizing the inventory replenishment plan based on fault probability; conversely, if more emphasis is placed on inventory cost control, the value of w2 may be appropriately increased.

[0037] Step S623: Based on the available inventory and the inventory replenishment fitness function, optimize the inventory replenishment plan for the high-frequency faulty component model according to the balanced inventory levels of the first component model up to the Mth component model, and obtain the target inventory replenishment plan corresponding to the maximum value of the inventory replenishment fitness function for inventory replenishment. Specifically, based on the obtained available inventory and the constructed inventory replenishment fitness function, optimize the inventory replenishment plan for the high-frequency faulty component model with the balanced inventory levels of the first component model up to the Mth component model as the target reference. During the optimization process, different inventory replenishment strategies are substituted into the inventory replenishment fitness function for calculation and evaluation. For example, for a certain high-frequency faulty component model, consider different combinations of replenishment quantities and calculate the Q3 value under each combination. Through continuous trial and calculation, find the inventory replenishment plan that maximizes the inventory replenishment fitness function Q3; this plan is the target inventory replenishment plan. Once the target inventory replenishment plan is determined, perform the actual inventory replenishment operation according to the plan. This includes a series of processes such as placing orders with suppliers for the required components, arranging the transportation and receipt of the components, and updating the inventory management system in a timely manner after the components are put into storage, so as to ensure the smooth completion of inventory replenishment work and improve the reliability of power grid operation and maintenance and the scientific nature of inventory management.

[0038] This application embodiment adopts the method of acquiring the distribution mode of the power grid in the distribution area, analyzing the frequent fault patterns of the power grid, identifying the types of high-frequency faulty components and their fault probability identifiers; according to the component type and deployment quantity, redundant inventory data is obtained from the maintenance component library, and the inventory is balanced to obtain the inventory balance coefficient; when the inventory balance coefficient is lower than the threshold, the inventory of high-frequency faulty component models is replenished, thus achieving the technical effect of real-time dynamic inventory optimization management.

[0039] In the above text, refer to Figure 1 A multi-task scheduling optimization method based on the power Internet of Things according to embodiments of the present invention is described in detail. Next, reference will be made to... Figure 2 A multi-task scheduling optimization system based on the power Internet of Things is described according to an embodiment of the present invention.

[0040] The multi-task scheduling optimization system based on the power Internet of Things (IoT) according to embodiments of the present invention solves the technical problem of insufficient inventory of high-frequency fault components due to the lack of real-time analysis of inventory status in existing power operation and maintenance management, achieving the technical effect of real-time dynamic inventory optimization management. The multi-task scheduling optimization system based on the power IoT includes: a distribution mode acquisition module 10, a mode analysis module 20, a component deployment quantity acquisition module 30, a redundant inventory quantity acquisition module 40, a balance analysis module 50, and an inventory replenishment module 60.

[0041] The distribution mode acquisition module 10 is used to obtain the distribution mode of the power grid in the distribution area.

[0042] The pattern analysis module 20 is used to perform frequent fault pattern analysis of the power grid based on the distribution mode of the power grid in the distribution area, and to obtain the high-frequency fault component type, wherein the high-frequency fault component type has a component fault probability identifier.

[0043] The component deployment quantity acquisition module 30 is used to obtain the component deployment quantity of the high-frequency fault component type in the transformer area.

[0044] The redundant inventory quantity acquisition module 40 is used to obtain the redundant inventory quantity of high-frequency fault component models of high-frequency fault component types based on the maintenance component library of the transformer area.

[0045] The balance analysis module 50 is used to perform a balance analysis on the quantity of redundant inventory based on the number of components deployed and the component failure probability identifier, and obtain an inventory balance coefficient.

[0046] The inventory replenishment module 60 is used to replenish the inventory of the high-frequency faulty component model when the inventory balance coefficient is less than or equal to the inventory balance coefficient threshold.

[0047] The specific configuration of the pattern analysis module 20 will be described in detail below. As mentioned above, frequent fault pattern analysis of the power grid is performed based on the distribution mode of the distribution area to obtain the high-frequency fault component type, wherein the high-frequency fault component type has a component fault probability identifier. The pattern analysis module 20 further includes: a first distribution area component extraction unit, which is used to extract a first distribution area component based on the distribution mode of the distribution area power grid, wherein the first distribution area component has a first distribution area component model and a first distribution area component electrical control parameters; a sample set acquisition unit, which is used to collect a power grid fault sample set of the distribution area based on the environmental monitoring data of the distribution area deployment and the distribution mode of the distribution area power grid; and frequency identifier acquisition. The frequency identifier acquisition unit is used to perform frequent fault pattern analysis on the first transformer substation based on the transformer substation component model and the electrical control parameters of the first transformer substation component according to the transformer substation power grid fault sample set, and obtain the trigger frequency and fault probability identifier of the first transformer substation component; the probability identifier storage unit is used to associate and store the first transformer substation component, the first transformer substation component model and the electrical control parameters of the first transformer substation component into the high-frequency fault component type when the trigger frequency of the first transformer substation component is greater than or equal to the trigger frequency threshold, and at the same time store the fault probability identifier of the first transformer substation component into the component fault probability identifier.

[0048] Specifically, based on the power grid fault sample set of the distribution area, the first distribution area component is analyzed for frequent power grid fault patterns based on the component model and electrical control parameters of the first distribution area component to obtain the triggering frequency and fault probability identifier of the first distribution area component. The frequency identifier acquisition unit further includes: a first distribution area component triggering frequency acquisition subunit, which is used to count the number of samples that simultaneously meet the electrical control parameters and the component model of the first distribution area component based on the power grid fault sample set of the distribution area to obtain the triggering frequency of the first distribution area component; and a sample quantity ratio calculation subunit, which is used to calculate the sample quantity ratio that simultaneously meets the electrical control parameters and the component model of the first distribution area component, and set it as the fault probability identifier of the first distribution area component.

[0049] The specific configuration of the component deployment quantity acquisition module 30 will be described in detail below. As mentioned above, to obtain the component deployment quantity of the high-frequency fault component type in the transformer substation, the component deployment quantity acquisition module 30 further includes: a component deployment quantity acquisition unit, which is used to obtain the component deployment quantity in the transformer substation that simultaneously satisfies the electrical control parameters of the first transformer substation component and the component model of the first transformer substation component.

[0050] The specific configuration of the balance analysis module 50 will be described in detail below. As mentioned above, the redundant inventory quantity is balanced based on the component deployment quantity and the component failure probability identifier to obtain an inventory balance coefficient. The balance analysis module 50 further includes: a product calculation unit, which is used to perform a product calculation on the component deployment quantity and the component failure probability identifier to obtain the component failure prediction quantity; and an inventory balance coefficient setting unit, which is used to calculate the ratio of the redundant inventory quantity to the component failure prediction quantity and set it as the inventory balance coefficient.

[0051] The specific configuration of the inventory replenishment module 60 will be described in detail below. As mentioned above, when the inventory balancing coefficient is less than or equal to the inventory balancing coefficient threshold, inventory replenishment is performed on the high-frequency faulty component model. The inventory replenishment module 60 further includes: an inventory balancing analysis unit, which is used to traverse the predicted fault quantity of the first component model up to the predicted fault quantity of the Mth component model, and perform inventory balancing analysis in combination with the inventory balancing coefficient threshold to obtain the balanced inventory quantity of the first component model up to the balanced inventory quantity of the Mth component model; and an inventory replenishment unit, which is used to replenish the inventory of the high-frequency faulty component model according to the balanced inventory quantity of the first component model up to the balanced inventory quantity of the Mth component model.

[0052] Specifically, based on the balanced inventory levels of the first component model up to the balanced inventory levels of the Mth component model, inventory replenishment is performed for the high-frequency faulty component models. The inventory replenishment unit further includes: an idle inventory acquisition subunit, used to obtain idle inventory levels; and an inventory replenishment fitness function construction subunit, used to construct an inventory replenishment fitness function. Q3 = w1Q1 + w2Q2, where Q1 represents the first fitness function, Q2 represents the second fitness function, Q3 represents the inventory replenishment fitness function, and p i Characterizing the failure probability of the i-th component model, x i x represents the inventory quantity of the i-th component model configuration. i0 The equalization inventory level of the i-th component model is represented by w1, the first weight is represented by w2, and the second weight is represented by w2. The replenishment scheme optimization subunit is used to optimize the inventory replenishment scheme for the high-frequency faulty component model based on the idle inventory level, combined with the inventory replenishment fitness function, and based on the equalization inventory level of the first component model up to the equalization inventory level of the M-th component model, to obtain the target inventory replenishment scheme corresponding to the maximum value of the inventory replenishment fitness function and then replenish the inventory.

[0053] The multi-task scheduling optimization system based on the power Internet of Things provided in the embodiments of the present invention can execute the multi-task scheduling optimization method based on the power Internet of Things provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0054] Although this application makes various references to certain modules in the system according to the embodiments of this application, any number of different modules can be used and run on user terminals and / or servers. The various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0055] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application. In some cases, the actions or steps described in this application can be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A multi-task scheduling optimization method based on the power Internet of Things, characterized in that, include: Obtain the distribution mode of the power grid in the transformer substation; Based on the distribution mode of the power grid in the transformer area, a frequent fault pattern analysis of the power grid is performed to obtain the high-frequency fault component type, wherein the high-frequency fault component type has a component fault probability identifier. Obtain the number of components deployed in the transformer substation for the aforementioned high-frequency fault component type; Based on the maintenance component database of the transformer substation, obtain the redundant inventory quantity of high-frequency fault component models of high-frequency fault component types; Based on the number of components deployed and the component failure probability identifier, a balance analysis is performed on the redundant inventory quantity to obtain the inventory balance coefficient. When the inventory balance coefficient is less than or equal to the inventory balance coefficient threshold, the inventory of the high-frequency faulty component model is replenished. The step of performing a balance analysis on the redundant inventory quantity based on the deployment quantity of the components and the failure probability identifier of the components to obtain an inventory balance coefficient includes: The predicted number of component failures is obtained by multiplying the number of deployed components and the component failure probability identifier. Calculate the ratio of the redundant inventory quantity to the predicted component failure quantity, and set it as the inventory balance coefficient; When the inventory balancing coefficient is less than or equal to the inventory balancing coefficient threshold, the inventory of the high-frequency faulty component model is replenished, including: Iterate through the predicted failure quantity of the first component model up to the predicted failure quantity of the Mth component model, and combine the inventory balance coefficient threshold to perform balanced inventory quantity analysis to obtain the balanced inventory quantity of the first component model up to the balanced inventory quantity of the Mth component model. Based on the balanced inventory level of the first component model up to the balanced inventory level of the Mth component model, replenish the inventory of the high-frequency faulty component model. The step of replenishing the inventory of the high-frequency faulty component model based on the balanced inventory level of the first component model up to the balanced inventory level of the Mth component model includes: Obtain available inventory; Construct the inventory replenishment fitness function: , , , in, Characterizing the first fitness function, Characterizing the second fitness function, The fitness function characterizing inventory replenishment Characterizes the failure probability of the i-th component model. Characterizes the inventory quantity of the i-th component model configuration. Characterizes the balanced inventory level of the i-th component model. Characterizes the first weight, Characterizes the second weight; Based on the available inventory, combined with the inventory replenishment fitness function, the inventory replenishment scheme for the high-frequency faulty component model is optimized according to the balanced inventory of the first component model up to the balanced inventory of the Mth component model, and the target inventory replenishment scheme corresponding to the maximum value of the inventory replenishment fitness function is obtained for inventory replenishment. The process involves performing frequent fault pattern analysis on the distribution mode of the power grid in the transformer substation to obtain high-frequency fault component types. These high-frequency fault component types are characterized by component fault probability identifiers, including: Based on the power distribution mode of the distribution area, the first distribution area component is extracted, wherein the first distribution area component has a first distribution area component model and first distribution area component electrical control parameters; Using the environmental monitoring data deployed in the transformer area and the power distribution mode of the transformer area as constraints, a set of fault samples of the transformer area power grid is collected; Based on the power grid fault sample set of the transformer area, the power grid fault frequent mode analysis of the first transformer area component is performed on the first transformer area component based on the first transformer area component model and the first transformer area component electrical control parameters to obtain the first transformer area component trigger frequency and the first transformer area component fault probability identifier. When the trigger frequency of the first transformer area component is greater than or equal to the trigger frequency threshold, the first transformer area component, the first transformer area component model and the electrical control parameters of the first transformer area component are associated and stored in the high-frequency fault component type. At the same time, the fault probability identifier of the first transformer area component is stored in the component fault probability identifier.

2. The method as described in claim 1, characterized in that, Based on the power grid fault sample set of the first distribution area, and based on the component model and electrical control parameters of the first distribution area, a frequent fault mode analysis of the first distribution area component is performed to obtain the triggering frequency and fault probability identifier of the first distribution area component, including: Based on the power grid fault sample set of the transformer area, the number of samples that simultaneously meet the electrical control parameters of the first transformer area component and the model of the first transformer area component is counted to obtain the triggering frequency of the first transformer area component. The percentage of samples that simultaneously meet the electrical control parameters of the first transformer area component and the model number of the first transformer area component is calculated and set as the fault probability identifier of the first transformer area component.

3. The method as described in claim 1, characterized in that, Obtaining the number of components deployed in the transformer substation for the aforementioned high-frequency fault component type includes: Obtain the number of components deployed in the first distribution area that simultaneously meet the electrical control parameters of the first distribution area component and the model number of the first distribution area component.

4. A multi-task scheduling and optimization system based on the power Internet of Things, characterized in that, The system is used to implement the multi-task scheduling optimization method based on the power Internet of Things as described in any one of claims 1-3, and the system includes: A power distribution mode acquisition module is used to obtain the power distribution mode of the distribution network in the transformer substation. The pattern analysis module is used to perform frequent fault pattern analysis of the power grid based on the distribution mode of the distribution network in the transformer area, and obtain the high-frequency fault component type, wherein the high-frequency fault component type has a component fault probability identifier. A component deployment quantity acquisition module is used to obtain the component deployment quantity of the high-frequency fault component type in the transformer area. A redundant inventory quantity acquisition module is used to obtain the redundant inventory quantity of high-frequency fault component models of high-frequency fault component types based on the maintenance component library of the transformer area. The balance analysis module is used to perform balance analysis on the quantity of redundant inventory based on the number of components deployed and the component failure probability identifier, and obtain the inventory balance coefficient. An inventory replenishment module is used to replenish the inventory of the high-frequency faulty component model when the inventory balance coefficient is less than or equal to the inventory balance coefficient threshold.

Images