Scheduling event processing method and device, equipment, medium and product
By constructing preset association rules and using historical scheduling event data for clustering and association rule mining, scheduling events that may occur in the power grid system can be predicted and prevented, solving the problems of incomplete and inaccurate scheduling processing in the power grid system and achieving more efficient power grid control.
Patent Information
- Application Number
- CN202511052371.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-29
- Publication Date
- 2025-11-11
AI Technical Summary
Existing technologies cannot guarantee the comprehensiveness and accuracy of power grid system dispatching and processing, nor can they prevent dispatching events that may occur in the power grid system in advance.
By constructing preset association rules and using historical scheduling event data for clustering and association rule mining, the system can determine the subsequent events that may be triggered by the current scheduling event in the power grid system, and execute corresponding processing strategies within a preset time period to prevent them from occurring.
It improves the comprehensiveness and accuracy of power grid system control, reduces the risk of power grid failures, and enhances the safety and stability of operation.
Smart Images
Figure CN120933920A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of power system technology, and in particular to a method, apparatus, equipment, medium and product for handling dispatch events. Background Technology
[0002] By dispatching and controlling the power generation, transmission, and distribution processes in real time, the power supply and demand can be kept in dynamic balance at all times, thereby ensuring the safe, stable, and reliable operation of the entire power grid.
[0003] In traditional power grid dispatching event management practices, dispatchers and analysis systems primarily focus on immediate response to and analysis of individual, occurring dispatching events. For example, when a transformer trips due to a dispatching event, the focus is on quickly isolating the event, restoring power supply, and analyzing the root cause of the transformer's problem.
[0004] However, existing technologies cannot guarantee the comprehensiveness and accuracy of power grid system control during the scheduling process. Summary of the Invention
[0005] This application provides methods, apparatus, devices, media, and products for handling scheduling events, in order to improve the comprehensiveness and accuracy of power grid system control.
[0006] In a first aspect, embodiments of this application provide a scheduling event processing method, including:
[0007] Determine the first scheduling event in the power grid system;
[0008] According to a preset association rule, a second scheduling event corresponding to the first scheduling event is determined. The preset association rule is used to indicate that the second scheduling event will occur within a preset time period after the first scheduling event occurs.
[0009] The target processing strategy corresponding to the second scheduling event is executed within the preset time period to prevent the occurrence of the second scheduling event.
[0010] In one possible implementation, prior to determining the current first scheduling event in the power grid system, the method further includes:
[0011] Retrieve data from multiple historical scheduling events;
[0012] Cluster multiple historical scheduling event data to determine multiple clustered scheduling event clusters;
[0013] The preset association rules are generated based on the multiple clustered scheduling event clusters.
[0014] In one possible implementation, generating the preset association rule based on the plurality of clustered scheduling event clusters includes:
[0015] Based on the multiple clustered scheduling event clusters, determine the support and confidence between any two scheduling events;
[0016] Two scheduling events whose support is greater than a preset support and whose confidence is greater than a preset confidence are identified as a pair of related scheduling events.
[0017] Based on the associated scheduling event pairs, the preset association rules are established.
[0018] In one possible implementation, establishing the preset association rule based on the associated scheduling event pairs includes:
[0019] In a pair of related scheduling events, the scheduling event that occurs first is identified as the preceding scheduling event, and the scheduling event that occurs later is identified as the following scheduling event, thus establishing the preset association rule;
[0020] Accordingly, determining the second scheduling event corresponding to the first scheduling event according to preset association rules includes:
[0021] The first scheduling event is used as the preceding scheduling event and searched through the preset association rules. The subsequent scheduling event corresponding to the first scheduling event is determined as the second scheduling event.
[0022] In one possible implementation, determining two scheduling events with a support greater than a preset support and a confidence level greater than a preset confidence level as a pair of related scheduling events includes:
[0023] Two scheduling events whose support is greater than the preset support and whose confidence is greater than the preset confidence are identified as an initial scheduling event pair that are related.
[0024] For each initial scheduling event pair, the lift is determined as the ratio of the confidence of the initial scheduling event pair to the support of the subsequent scheduling events in the initial scheduling event pair.
[0025] If the lift is greater than the preset lift, then the associated initial scheduling event pair is determined as the associated scheduling event pair.
[0026] In one possible implementation, the method further includes:
[0027] The preset association rules are displayed visually.
[0028] Secondly, embodiments of this application provide a scheduling event processing apparatus, comprising:
[0029] The first determining module is used to determine the current first scheduling event in the power grid system;
[0030] The second determining module is used to determine the second scheduling event corresponding to the first scheduling event according to a preset association rule, wherein the preset association rule is used to indicate that the second scheduling event will occur within a preset time period after the first scheduling event occurs.
[0031] The execution module is used to execute the target processing strategy corresponding to the second scheduling event within the preset time period to prevent the occurrence of the second scheduling event.
[0032] In one possible implementation, prior to determining the current first scheduling event in the power grid system, the scheduling event processing apparatus further includes a processing module for:
[0033] Retrieve data from multiple historical scheduling events;
[0034] Cluster multiple historical scheduling event data to determine multiple clustered scheduling event clusters;
[0035] The preset association rules are generated based on the multiple clustered scheduling event clusters.
[0036] In one possible implementation, the processing module is specifically used for:
[0037] Based on the multiple clustered scheduling event clusters, determine the support and confidence between any two scheduling events;
[0038] Two scheduling events whose support is greater than a preset support and whose confidence is greater than a preset confidence are identified as a pair of related scheduling events.
[0039] Based on the associated scheduling event pairs, the preset association rules are established.
[0040] In one possible implementation, the processing module is specifically used for:
[0041] In a pair of related scheduling events, the scheduling event that occurs first is identified as the preceding scheduling event, and the scheduling event that occurs later is identified as the following scheduling event, thus establishing the preset association rule;
[0042] Accordingly, the second determining module is specifically used for:
[0043] The first scheduling event is used as the preceding scheduling event and searched through the preset association rules. The subsequent scheduling event corresponding to the first scheduling event is determined as the second scheduling event.
[0044] In one possible implementation, the processing module is specifically used for:
[0045] Two scheduling events whose support is greater than the preset support and whose confidence is greater than the preset confidence are identified as an initial scheduling event pair that are related.
[0046] For each initial scheduling event pair, the lift is determined as the ratio of the confidence of the initial scheduling event pair to the support of the subsequent scheduling events in the initial scheduling event pair.
[0047] If the lift is greater than the preset lift, then the associated initial scheduling event pair is determined as the associated scheduling event pair.
[0048] In one possible implementation, the scheduling event processing device further includes a display module for:
[0049] The preset association rules are displayed visually.
[0050] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;
[0051] The memory stores computer-executed instructions;
[0052] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.
[0053] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.
[0054] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.
[0055] The scheduling event processing method, apparatus, device, medium, and product provided in this application first determine a first scheduling event currently existing in the power grid system. Then, based on preset association rules, they determine a second scheduling event corresponding to the first scheduling event. Finally, within a preset time period, they execute a target processing strategy corresponding to the second scheduling event to prevent the second scheduling event from occurring. The preset association rules specify that a second scheduling event will occur within a preset time period after the first scheduling event occurs. In this technical solution, by utilizing the association characteristics of scheduling events represented by the preset association rules, after determining the first scheduling event currently existing in the power grid system, it is possible to determine the second scheduling event that the first scheduling event will trigger. Before the second scheduling event occurs, a target processing strategy for handling the second scheduling event is executed to prevent its occurrence, thereby improving the comprehensiveness and accuracy of power grid system control. Attached Figure Description
[0056] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0057] Figure 1 Flowchart of the scheduling event handling method provided in this application Figure 1 ;
[0058] Figure 2 Flowchart of the scheduling event handling method provided in this application Figure 2 ;
[0059] Figure 3 Flowchart of the scheduling event handling method provided in this application Figure 3 ;
[0060] Figure 4 A schematic diagram illustrating the construction process of the preset association rules in the scheduling event handling method provided in this application;
[0061] Figure 5 A schematic diagram of the scheduling event processing device provided in this application;
[0062] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.
[0063] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation
[0064] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.
[0065] 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. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.
[0066] First, the technical terms used in this application will be explained:
[0067] Dispatch events: State changes or emergencies that occur during the operation of the power grid system and require dispatcher intervention. For example, equipment failures, load changes, and maintenance work are core and typical dispatch event types in power grid dispatching. Specifically, equipment failures can be transformer explosions or line trips, triggering dispatchers to perform emergency fault isolation and switch to backup lines; load changes can be sudden startups / shutdowns of large plants or surges in electricity demand due to extreme weather, triggering dispatchers to adjust generation output and switch reactive power compensation; maintenance work triggers dispatchers to execute pre-defined operation tickets (shutting down equipment, adjusting operating modes, restoring power supply), etc.
[0068] Next, the application scenarios involved in this application will be explained:
[0069] Electricity, as a special commodity that is generated and used immediately, is susceptible to supply-demand imbalances at any moment, which can trigger frequency fluctuations, voltage anomalies, or even large-scale power outages. Real-time command and control of power generation, transmission, and distribution through grid dispatch ensures a dynamic balance between power supply and demand, thereby guaranteeing the safe, stable, and reliable operation of the entire power grid. In other words, grid dispatch is extremely important.
[0070] In traditional power grid dispatching event management practices, dispatchers and analysis systems primarily focus on immediate response to and analysis of individual, occurring dispatching events. For example, when a transformer trips due to a dispatching event, the focus is on quickly isolating the event, restoring power supply, and analyzing the root cause of the transformer's problem.
[0071] However, with the continuous expansion of the power grid and the increasing complexity of the operating environment, the amount of dispatch event data generated has also increased dramatically. This means that there is a certain correlation between equipment in the power grid system. Various events such as equipment dispatch events, load changes, and planned maintenance may appear isolated, but in fact they may be driven by common factors or have the risk of chain reactions. This makes it impossible to deal with subsequent dispatch events that may occur in the power grid in advance, reducing the comprehensiveness and accuracy of power grid system control.
[0072] Based on this, the technical concept of this application is as follows: Considering that there are certain patterns and correlations among scheduling events, preset correlation rules can be constructed in advance based on the analysis of massive historical scheduling event data to identify hidden patterns and correlations. Thus, after a scheduling event occurs in the power grid system, other scheduling events that will subsequently occur are determined according to the preset correlation rules, and these other determined scheduling events are controlled in advance, thereby improving the comprehensiveness and accuracy of power grid system control.
[0073] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.
[0074] Figure 1 Flowchart of the scheduling event handling method provided in this application Figure 1 ,like Figure 1 As shown, this method can be implemented through the following steps:
[0075] S11. Determine the first scheduling event in the power grid system.
[0076] In practical applications, an Energy Management System (EMS) can collect real-time operational data of the power grid system across various dimensions, such as power generation output, load, line power flow, voltage, frequency, and switch status. Then, the operational data in each dimension is monitored in real time. If any deviation from normal operating conditions or violation of safety constraints is detected in any dimension's operational data, the corresponding first scheduling event is determined.
[0077] It should be understood that the number of the first scheduling events is greater than or equal to one, which can be determined according to the actual situation. This application embodiment does not impose specific restrictions on this.
[0078] It should be understood that when there are multiple scheduling events in the power grid system, the scheduling event with the highest priority among the multiple scheduling events can be determined as the first scheduling event. After all steps S11-S13 are executed for the first scheduling event, the scheduling event with the highest priority among the remaining scheduling events among the multiple scheduling events can be determined as the new first scheduling event.
[0079] S12. Determine the second scheduling event corresponding to the first scheduling event according to the preset association rules.
[0080] Among them, the preset association rule is used to indicate that a second scheduling event will occur within a preset time period after the first scheduling event occurs.
[0081] For example, the format of the preset association rule can be: scheduling event 1-scheduling event 2-preset duration. The first scheduling event can be brought into scheduling event 1 and traversed in the preset association rule to determine the second scheduling event corresponding to the first scheduling event and the preset duration.
[0082] It should be understood that preset association rules can be referenced. Figure 2 and Figure 3 The relevant descriptions in the corresponding embodiments will not be repeated here.
[0083] For example, the preset duration can be 1 minute, 2 minutes, 3 minutes, etc., which can be determined according to the actual situation. This application embodiment does not impose specific restrictions on this.
[0084] S13. Execute the target processing strategy corresponding to the second scheduling event within a preset time period to prevent the occurrence of the second scheduling event.
[0085] In practical applications, since the preset association rules indicate that a second scheduling event will occur within a preset time after the first scheduling event, the target processing strategy corresponding to the second scheduling event needs to be executed within the preset time to avoid the occurrence of the second scheduling event.
[0086] It should be understood that the target processing strategy corresponding to the second scheduling event is used to resolve the second scheduling event.
[0087] The scheduling event handling method provided in this application first determines a first scheduling event currently existing in the power grid system, then determines a second scheduling event corresponding to the first scheduling event based on preset association rules, and finally executes a target processing strategy corresponding to the second scheduling event within a preset time period to prevent the occurrence of the second scheduling event. The preset association rules specify that a second scheduling event will occur within a preset time period after the occurrence of the first scheduling event. In this technical solution, by utilizing the association characteristics of scheduling events represented by the preset association rules, after determining the first scheduling event currently existing in the power grid system, it is possible to determine the second scheduling event that the first scheduling event will trigger, and execute a target processing strategy to handle the second scheduling event before its occurrence, thereby preventing the second scheduling event from happening and improving the comprehensiveness and accuracy of power grid system control.
[0088] Next, the principles and steps for constructing preset association rules will be explained.
[0089] Figure 2 Flowchart of the scheduling event handling method provided in this application Figure 2 ,like Figure 2 As shown, the method may further include the following steps:
[0090] S21. Obtain data from multiple historical scheduling events.
[0091] Historical scheduling event data can include equipment fault records, load change data, and scheduling operation logs.
[0092] In one possible implementation, scheduling event data of the power grid system during historical periods can be collected and directly identified as historical scheduling event data.
[0093] In another possible implementation, dispatch event data of the power grid system within historical time periods can be collected and identified as initial historical dispatch event data. Then, duplicate, erroneous, and missing data are removed from the initial historical dispatch event data, and different types of numerical data are normalized to bring them within a uniform numerical range, thus obtaining the historical dispatch event data.
[0094] In this process, data cleaning and normalization are performed on the initial historical scheduling event data to eliminate noise and inconsistencies, improve the quality of historical scheduling event data, and ensure the accuracy of subsequent pre-defined association rules.
[0095] It should be understood that the historical period can be the past month, the past three months, or the past six months, etc., which can be determined according to the actual situation, and will not be elaborated here.
[0096] S22. Cluster multiple historical scheduling event data to determine multiple clustered scheduling event clusters.
[0097] In one possible implementation, a day can be divided into multiple time periods, and historical scheduling event data can be further divided according to these time periods to obtain sub-historical scheduling event data for each time period. Then, feature extraction is performed on the sub-historical scheduling event data for each time period to determine event characteristics such as the type and frequency of events occurring within each time period. Next, clustering algorithms (such as K-means clustering or hierarchical clustering) are used to calculate and analyze these features, grouping similar event patterns together to obtain multiple clustered scheduling event clusters.
[0098] For example, the above time period can be 1 hour, 2 hours or 3 hours, etc., which can be determined according to the actual situation, and will not be elaborated here.
[0099] Furthermore, it is also possible to determine the time periods during which each cluster of scheduling events frequently occurs.
[0100] For example, cluster scheduling event cluster 1 includes equipment overload and voltage fluctuation, corresponding to peak electricity consumption periods; cluster scheduling event cluster 2 includes equipment maintenance and fault events, corresponding to off-peak periods at night.
[0101] S23. Generate preset association rules based on multiple clustered scheduling event clusters.
[0102] In one possible implementation, association rule mining algorithms (such as the Apriori algorithm, FP-Growth algorithm, etc.) can be used to calculate the support and confidence between multiple clustered scheduling event clusters. Then, based on the support and confidence, frequently occurring simultaneous or sequentially occurring within a short period of time scheduling event pairs can be determined, and preset association rules can be constructed based on these scheduling event pairs.
[0103] It should be understood that this implementation method can be referenced. Figure 3 The relevant content in the illustrated embodiments will not be repeated here.
[0104] In the above embodiments, by clustering multiple historical scheduling event data, similar historical scheduling events are grouped into one category, forming clustered scheduling event clusters. Then, association rule mining algorithms are used to uncover deep relationships between scheduling events, thereby establishing preset association rules that can explain the relationships between scheduling events. This technical solution, through a combination of clustering and association analysis, achieves comprehensive and in-depth analysis of power grid scheduling events, improves the accuracy of preset association rule creation, provides a strong basis for subsequent power grid scheduling decisions, and thus predicts and prevents potential power grid problems, improving the safety and stability of power grid operation.
[0105] Figure 3 Flowchart of the scheduling event handling method provided in this application Figure 3 ,like Figure 3 As shown, S23 can be achieved through the following steps:
[0106] S31. Based on multiple clustered scheduling event clusters, determine the support and confidence between any two scheduling events.
[0107] Support refers to the frequency with which two scheduling events occur simultaneously or sequentially within a short period of time.
[0108] The support (A->B) between scheduled event A and scheduled event B can be calculated using the following formula:
[0109] Support(A->B) = (Number of time periods containing both scheduled events A and B) / (Total number of time periods)
[0110] For example, suppose there are 1000 time periods in total, and scheduled event A and scheduled event B occur 50 times within the same time period. That is, there are 50 time periods in which scheduled event A and scheduled event B coexist. In this case, the support between scheduled event A and scheduled event B is 50 / 1000 = 0.05.
[0111] It should be understood that the support between scheduled event A and scheduled event B ranges from [0,1]. The larger the support value, the more frequently scheduled events A and B occur simultaneously.
[0112] Confidence level refers to the conditional probability that scheduling event B will also occur when scheduling event A occurs.
[0113] The confidence (A->B) between scheduled event A and scheduled event B can be calculated using the following formula:
[0114] Confidence(A->B) = (Number of time periods containing both scheduled events A and B) / (Number of time periods containing scheduled event A) = Support(A->B) / Support(A)
[0115] For example, suppose there are 1000 time periods in total, and scheduling event A occurs in 100 time periods. Within these 100 time periods, scheduling event B occurs either immediately after or simultaneously with scheduling event A in 50 time periods. Therefore, the confidence level between scheduling event A and scheduling event B is 50 / 100 = 0.5.
[0116] It should be understood that the confidence level between scheduling event A and scheduling event B ranges from [0,1]. The higher the confidence level, the higher the probability that scheduling event B will also occur when scheduling event A occurs.
[0117] S32. Two scheduling events with a support greater than the preset support and a confidence greater than the preset confidence are identified as a pair of related scheduling events.
[0118] As indicated in section S31, higher support and confidence levels indicate a stronger correlation between two scheduling events. Therefore, based on experimental data and / or expert experience, the minimum support and minimum confidence levels between two correlated scheduling events can be predetermined. The minimum support level can be set as the preset support level, and the minimum confidence level can be set as the preset confidence level.
[0119] Therefore, in practical applications, when the support between two scheduling events is greater than the preset support and the confidence is greater than the preset confidence, it can be determined that there is a correlation between the two scheduling events, and thus the two scheduling events can be identified as a pair of related scheduling events.
[0120] S33. Establish preset association rules based on the related scheduling event pairs.
[0121] For example, if it is found that after an overload event occurs in the main transformer of a substation, the probability of a fault in a transmission line near the substation increases significantly within a certain time range, and the preset support and confidence thresholds are met, then the association rules between the two events can be extracted, indicating that the overload of the main transformer will cause a fault in the adjacent line, thus providing a basis for dispatchers to take preventive measures in advance.
[0122] In one possible implementation, the scheduling event that occurs first in a pair of related scheduling events can be identified as the preceding scheduling event, and the scheduling event that occurs later can be identified as the following scheduling event, thus establishing a preset association rule.
[0123] Furthermore, the preset association rule can also include a preset duration, which can be the length of the time period during which the associated scheduling event pair frequently occurs.
[0124] Based on this implementation, S12 can be implemented as follows: the first scheduling event is used as the previous scheduling event and traversed and searched in the preset association rules, and the subsequent scheduling event corresponding to the first scheduling event is determined as the second scheduling event.
[0125] In another possible implementation, two scheduling events with support greater than a preset support and confidence greater than a preset confidence are first identified as related initial scheduling event pairs. Then, for each initial scheduling event pair, the lift is determined as the ratio of the confidence of the initial scheduling event pair to the support of the subsequent scheduling event in the initial scheduling event pair. If the lift is greater than a preset lift, then the related initial scheduling event pair is confirmed as a related scheduling event pair.
[0126] The lift (Lift(A->B)) between scheduled event A and scheduled event B can be calculated using the following formula:
[0127] Lift(A->B)=Confidence(A->B) / Support(B)
[0128] For example, suppose there are 1000 time periods in total. Scheduling event A occurs in 100 time periods. In these 100 time periods, scheduling event B occurs immediately after or simultaneously with scheduling event A in 50 time periods. Scheduling event B occurs alone 80 times in the entire 1000 time periods. Then the support of scheduling event B is 80 / 1000 = 0.08, and the lift between scheduling event A and scheduling event B is 0.5 / 0.08 = 6.25.
[0129] In this context, a lift greater than 1 indicates a positive correlation between scheduling events A and B, meaning that the occurrence of scheduling event A increases the probability of scheduling event B occurring. A lift equal to 1 indicates that scheduling events A and B are independent, and a lift less than 1 indicates a negative correlation. Since the lift factor takes into account the frequency of subsequent scheduling events, it can filter out initial scheduling event pairs that, despite having high confidence levels, already have frequent subsequent scheduling events.
[0130] Therefore, based on experimental data and / or expert experience, the minimum lift between two related scheduling events can be predetermined and set as the preset lift. This preset lift should be greater than 1.
[0131] It should be understood that the implementation of determining two scheduling events with support greater than the preset support and confidence greater than the preset confidence as an initial scheduling event pair with a correlation is the same as in S32, and will not be explained in detail here.
[0132] Furthermore, based on any of the above embodiments, the preset association rules can also be visualized.
[0133] In practical applications, visualization tools can be used to display the pre-defined association rules in chart form, such as drawing distribution maps of clustered scheduling event clusters and network diagrams of pre-defined association rules. Dispatchers can use these visualizations to intuitively understand the occurrence patterns and relationships of events during power grid operation, thereby optimizing power grid dispatching strategies and developing proactive countermeasures, such as rationally arranging equipment maintenance plans and adjusting load allocation strategies, to reduce the risk of power grid failures and improve power grid operating efficiency and reliability.
[0134] Next, a specific example will be used to explain the construction process of the above-mentioned preset association rules.
[0135] Figure 4 This is a schematic diagram illustrating the construction process of the preset association rules in the scheduling event handling method provided in this application, as shown below. Figure 4 As shown, the process of constructing this preset association rule can be achieved through the following steps:
[0136] S41. Data collection and preprocessing.
[0137] This process can acquire multiple initial historical scheduling event data and preprocess them to generate multiple historical scheduling event data.
[0138] The preprocessing includes removing duplicate, erroneous, and missing data from the initial historical scheduling event data, and normalizing different types of numerical data to bring them into a uniform numerical range.
[0139] S42, Temporal Cluster Analysis.
[0140] In this process, cluster analysis was performed on multiple historical scheduling event data to identify multiple clustered scheduling event clusters.
[0141] S43. Association analysis and mining.
[0142] Among them, preset association rules are generated based on multiple clustered scheduling event clusters.
[0143] S44. Results Display and Application.
[0144] This includes displaying preset association rules and optimizing power grid dispatching strategies.
[0145] It should be understood that any of the above embodiments can be applied to scenarios such as power grid dispatching, equipment fault diagnosis, and line loss analysis.
[0146] Figure 5 A schematic diagram of the scheduling event processing device provided in this application is shown below. Figure 5 As shown, the scheduling event processing device 50 provided in this embodiment includes:
[0147] The first determining module 501 is used to determine the current first scheduling event in the power grid system.
[0148] The second determining module 502 is used to determine the second scheduling event corresponding to the first scheduling event according to a preset association rule. The preset association rule is used to indicate that the second scheduling event will occur within a preset time period after the first scheduling event occurs.
[0149] The execution module 503 is used to execute the target processing strategy corresponding to the second scheduling event within a preset time period to prevent the occurrence of the second scheduling event.
[0150] In one possible implementation, before determining the current first scheduling event in the power grid system, the scheduling event processing device 50 further includes a processing module for:
[0151] Retrieve data from multiple historical scheduling events.
[0152] Clustering of multiple historical scheduling event data to identify multiple clustered scheduling event clusters.
[0153] Based on multiple clustered scheduling event clusters, preset association rules are generated.
[0154] In one possible implementation, the processing module is specifically used for:
[0155] Based on multiple clustered scheduling event clusters, determine the support and confidence between any two scheduling events.
[0156] Two scheduling events with support greater than the preset support and confidence greater than the preset confidence are identified as a pair of related scheduling events.
[0157] Establish preset association rules based on the related scheduling event pairs.
[0158] In one possible implementation, the processing module is specifically used for:
[0159] In a pair of related scheduling events, the scheduling event that occurs first is identified as the preceding scheduling event, and the scheduling event that occurs later is identified as the following scheduling event, thus establishing a preset association rule.
[0160] Accordingly, the second determining module 502 is specifically used for:
[0161] The first scheduling event is used as the preceding scheduling event and is traversed and searched in the preset association rules. The subsequent scheduling event corresponding to the first scheduling event is determined as the second scheduling event.
[0162] In one possible implementation, the processing module is specifically used for:
[0163] Two scheduling events with support greater than the preset support and confidence greater than the preset confidence are identified as an initial scheduling event pair that are related.
[0164] For each initial scheduling event pair, the lift is determined by the ratio of the confidence of the initial scheduling event pair to the support of the subsequent scheduling events in the initial scheduling event pair.
[0165] If the lift is greater than the preset lift, then the initial scheduling event pairs that are related will be identified as related scheduling event pairs.
[0166] In one possible implementation, the scheduling event processing device 50 further includes a display module for:
[0167] The preset association rules are displayed visually.
[0168] The scheduling event processing device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.
[0169] Figure 6 A schematic diagram of the structure of the electronic device provided in this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes at least one processor 601 and a memory 602. Optionally, the electronic device 60 further includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.
[0170] In a specific implementation, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to perform the above-described method.
[0171] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.
[0172] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.
[0173] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.
[0174] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.
[0175] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0176] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.
[0177] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.
[0178] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.
[0179] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0180] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0181] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0182] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.
[0183] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.
[0184] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.
Claims
1. A method for handling scheduling events, characterized in that, include: Determine the first scheduling event in the power grid system; According to a preset association rule, a second scheduling event corresponding to the first scheduling event is determined. The preset association rule is used to indicate that the second scheduling event will occur within a preset time period after the first scheduling event occurs. The target processing strategy corresponding to the second scheduling event is executed within the preset time period to prevent the occurrence of the second scheduling event.
2. The method according to claim 1, characterized in that, Before determining the current first scheduling event in the power grid system, the method further includes: Retrieve data from multiple historical scheduling events; Cluster multiple historical scheduling event data to determine multiple clustered scheduling event clusters; The preset association rules are generated based on the multiple clustered scheduling event clusters.
3. The method according to claim 2, characterized in that, The step of generating the preset association rule based on the multiple clustered scheduling event clusters includes: Based on the multiple clustered scheduling event clusters, determine the support and confidence between any two scheduling events; Two scheduling events whose support is greater than a preset support and whose confidence is greater than a preset confidence are identified as a pair of related scheduling events. Based on the associated scheduling event pairs, the preset association rules are established.
4. The method according to claim 3, characterized in that, The step of establishing the preset association rule based on the associated scheduling event pairs includes: In a pair of related scheduling events, the scheduling event that occurs first is identified as the preceding scheduling event, and the scheduling event that occurs later is identified as the following scheduling event, thus establishing the preset association rule; Accordingly, determining the second scheduling event corresponding to the first scheduling event according to preset association rules includes: The first scheduling event is used as the preceding scheduling event and searched through the preset association rules. The subsequent scheduling event corresponding to the first scheduling event is determined as the second scheduling event.
5. The method according to claim 4, characterized in that, The step of determining two scheduling events with a support greater than a preset support and a confidence level greater than a preset confidence level as a pair of related scheduling events includes: Two scheduling events whose support is greater than the preset support and whose confidence is greater than the preset confidence are identified as an initial scheduling event pair that are related. For each initial scheduling event pair, the lift is determined as the ratio of the confidence of the initial scheduling event pair to the support of the subsequent scheduling events in the initial scheduling event pair. If the lift is greater than the preset lift, then the associated initial scheduling event pair is determined as the associated scheduling event pair.
6. The method according to any one of claims 1-5, characterized in that, The method further includes: The preset association rules are displayed visually.
7. A scheduling event processing device, characterized in that, include: The first determining module is used to determine the current first scheduling event in the power grid system; The second determining module is used to determine the second scheduling event corresponding to the first scheduling event according to a preset association rule, wherein the preset association rule is used to indicate that the second scheduling event will occur within a preset time period after the first scheduling event occurs. The execution module is used to execute the target processing strategy corresponding to the second scheduling event within the preset time period to prevent the occurrence of the second scheduling event.
8. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-6.
10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-6.