Abnormal monitoring method for scheduling operations based on business scenario analysis

Abstract

The present invention proposes a method for monitoring dispatching operation anomalies based on business scenario analysis, comprising: obtaining pre-dispatch grid operation data when issuing dispatching instructions to grid equipment, determining the business scenario corresponding to the dispatching instructions by performing feature analysis on the pre-dispatch grid operation data; obtaining historical status data and historical grid operation data of the grid equipment under the business scenario, and determining a core monitoring period based on changes in the historical status data and historical grid operation data; selecting historical status data for the core monitoring period and obtaining real-time status data of the grid equipment during the core monitoring period; analyzing the similarity between the real-time status data and the historical status data during the core monitoring period, and issuing a dispatching operation anomaly alarm if the similarity is less than a preset value. The present invention combines the response characteristics of different business scenarios to dispatching operations, shortens the sampling time of real-time status data related to dispatching, and improves the efficiency of anomaly monitoring.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid dispatching, and in particular relates to a method for monitoring abnormal dispatching operations based on business scenario analysis. Background Art

[0002] Grid dispatching management refers to the management of the grid's production operations, grid dispatching systems, and personnel duties by grid dispatching organizations in accordance with relevant regulations to ensure the safe, high-quality, and economical operation of the grid. Dispatching operations play a vital role in the safe and stable operation of the grid. Therefore, the operating status of the grid before and after dispatching is usually monitored in real time to ensure normal dispatching operations.

[0003] Since different dispatch instructions may be applied to different business scenarios, the response speed requirements for dispatch instructions in business scenarios such as load balancing, fault isolation, and relay protection often vary. However, as the scale of today's power grids continues to grow and the number of devices within them increases, existing dispatch operation monitoring methods, in order to adapt to various business scenarios, generally require large-scale, unified collection of massive dispatch-related data over a long period of time, starting from the issuance of the dispatch instruction. This ensures a complete understanding of the dispatch operation status and completes abnormal monitoring and analysis. This results in a large amount of dispatch-related data, increasing the analysis and computational pressure of abnormal monitoring, and leading to a large consumption of computing resources. Summary of the Invention

[0004] In order to address the shortcomings and deficiencies of the prior art in large-scale collection of massive scheduling-related data, which results in a large amount of scheduling-related data, increases the analysis and calculation pressure for abnormality monitoring, and leads to a large consumption of computing resources, the present invention proposes a scheduling operation abnormality monitoring method based on business scenario analysis, comprising:

[0005] Obtain pre-dispatch grid operation data when issuing dispatch instructions to grid equipment, and determine the business scenario corresponding to the dispatch instructions by performing feature analysis on the pre-dispatch grid operation data;

[0006] Obtain historical status data and historical grid operation data of the power grid equipment in the business scenario, and determine the core monitoring period based on changes in the historical status data and historical grid operation data;

[0007] Select the historical status data of the core monitoring period and obtain the real-time status data of the power grid equipment in the core monitoring period; analyze the similarity between the real-time status data and the historical status data in the core monitoring period, and issue a scheduling operation abnormality alarm if the similarity is less than a preset value.

[0008] Optionally, the determining the business scenario corresponding to the dispatch instruction by performing feature analysis on pre-dispatching power grid operation data includes:

[0009] Preprocessing the grid operation data before dispatching, including data cleaning and data normalization;

[0010] A feature matrix is generated based on the pre-processed pre-dispatch power grid operation data, the feature matrix is input into a pre-trained machine learning model, and the corresponding business scenario is determined according to the output result of the machine learning model.

[0011] Optionally, the machine learning model includes at least one of a decision tree, a support vector machine, and a logistic regression model.

[0012] Optionally, the business scenarios include load balancing services, fault isolation services, and relay protection services corresponding to different dispatching levels, and the dispatching levels include national dispatching, provincial dispatching, local dispatching, and county dispatching.

[0013] Optionally, determining the core monitoring period according to changes in historical status data and historical power grid operation data includes:

[0014] For the historical status data and historical grid operation data belonging to the same dispatching level, the correlation coefficients of the historical status data and historical grid operation data corresponding to the same sampling time are calculated respectively;

[0015] The sampling time corresponding to the highest correlation coefficient is marked as the core monitoring point;

[0016] An extended period corresponding to the scheduling level is determined, and a period between the time when the scheduling instruction is issued and the core monitoring point is spliced with the extended period to obtain a core monitoring period.

[0017] Optionally, the higher the scheduling level, the shorter the length of the corresponding extended period.

[0018] Optionally, the analyzing the similarity between the real-time status data and the historical status data during the core monitoring period includes: determining a plurality of judgment moments in the core monitoring period based on a preset frequency, and processing the real-time status data and the historical status data during the core monitoring period into a real-time status discrete sequence and a historical status discrete sequence respectively according to the judgment moments;

[0019] It is determined in turn whether the sequence values of the real-time state discrete sequence and the historical state discrete sequence at each judgment moment are the same, and the ratio of the number of judgment moments with the same sequence value to the number of all judgment moments is calculated as the similarity.

[0020] Optionally, after the scheduling operation abnormality alarm is issued, the scheduling operation abnormality monitoring method also includes a panoramic display of abnormal indicators of the scheduling operation abnormality, wherein the abnormal indicators include the scheduling instruction completion status, response delay status and scheduling instruction accumulation status.

[0021] The beneficial effects brought about by the technical solution provided by the present invention are:

[0022] The scheduling operation anomaly monitoring method proposed in the present invention combines the response characteristics of scheduling operations in different business scenarios, can determine the core monitoring period, shorten the sampling time of real-time status data related to scheduling, thereby reducing the amount of data that needs to be analyzed and improving the efficiency of anomaly monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A flowchart of a method for monitoring abnormal scheduling operations based on business scenario analysis, as proposed in an embodiment of the present invention;

[0025] Figure 2 This is a schematic diagram of splicing the core monitoring periods proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0027] The terms "first," "second," "third," "fourth," and so forth (if any) in the description and claims of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein.

[0028] It should be understood that in various embodiments of the present invention, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0029] It should be understood that in the present invention, "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus 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 units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0030] It should be understood that in the present invention, "multiple" refers to two or more. "And / or" is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "Contains A, B and C", "Contains A, B, C" means that A, B, and C are all included, "Contains A, B or C" means that one of A, B, and C is included, and "Contains A, B and / or C" means that any one, any two, or any three of A, B, and C are included.

[0031] It should be understood that, in the present invention, "B corresponding to A," "B corresponding to A," "A corresponds to B," or "B corresponds to A" means that B is associated with A and B can be determined based on A. Determining B based on A does not mean determining B based solely on A; B can also be determined based on A and / or other information. A and B match when the similarity between A and B is greater than or equal to a preset threshold.

[0032] Depending on the context, "if" as used herein may be interpreted as "when" or "when" or "in response to determining" or "in response to detecting."

[0033] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0034] Example

[0035] like Figure 1 As shown, this embodiment proposes a method for monitoring scheduling operation anomalies based on business scenario analysis, including:

[0036] S1: Obtain pre-dispatch grid operation data when issuing a dispatch instruction to the grid equipment, and determine the business scenario corresponding to the dispatch instruction by performing feature analysis on the pre-dispatch grid operation data;

[0037] S2: Obtain historical status data and historical grid operation data of the power grid equipment in the business scenario, and determine the core monitoring period according to changes in the historical status data and historical grid operation data;

[0038] S3: Select historical status data of the core monitoring period and obtain real-time status data of the power grid equipment in the core monitoring period; S4: Analyze the similarity between the real-time status data of the core monitoring period and the historical status data. If the similarity is less than a preset value, issue a scheduling operation abnormality alarm.

[0039] This embodiment first determines the business scenario corresponding to the scheduling instruction, and based on the characteristics of the business scenario in terms of scheduling response, determines the core monitoring period for analyzing whether the scheduling operation is abnormal. In the real-time monitoring process of the scheduling operation, it is only necessary to collect data during the core monitoring period to specifically judge whether the scheduling is normal, without having to continuously collect data for a long period of time after the scheduling instruction is issued to obtain abnormal monitoring results, thereby reducing the amount of data analysis and improving the efficiency of abnormal monitoring of scheduling operations.

[0040] In this embodiment, the feature analysis of the pre-dispatching grid operation data to determine the business scenario corresponding to the dispatch instruction includes:

[0041] Preprocessing the grid operation data before dispatching, including data cleaning and data normalization;

[0042] A feature matrix is generated based on the pre-processed pre-dispatch power grid operation data, the feature matrix is input into a pre-trained machine learning model, and the corresponding business scenario is determined according to the output result of the machine learning model.

[0043] This embodiment improves the data quality of the power grid operation data before scheduling through preprocessing, which is conducive to improving the accuracy of the output results of the machine learning model.

[0044] Furthermore, the machine learning model includes at least one of a decision tree, a support vector machine and a logistic regression model, and adopts an existing machine learning training method so that the machine learning model has the function of classifying the pre-dispatch power grid operation data to obtain corresponding business scenarios.

[0045] These service scenarios include load balancing, fault isolation, and relay protection services, corresponding to different dispatching levels: national, provincial, local, and county dispatching. In other words, these three levels all offer load balancing, fault isolation, and relay protection services.

[0046] In order to shorten the sampling time of real-time status data related to scheduling and thus reduce the amount of data that needs to be analyzed, this embodiment determines the core monitoring period based on changes in historical status data and historical power grid operation data. In one embodiment, the core monitoring period specifically includes:

[0047] For the historical status data and historical grid operation data belonging to the same dispatching level, the correlation coefficients of the historical status data and historical grid operation data corresponding to the same sampling time are calculated respectively;

[0048] The sampling time corresponding to the highest correlation coefficient is marked as the core monitoring point;

[0049] An extended period corresponding to the scheduling level is determined, and a period between the time when the scheduling instruction is issued and the core monitoring point is spliced with the extended period to obtain a core monitoring period.

[0050] like Figure 2 As shown in the figure, segment A1 represents the period between the time when the scheduling instruction is issued and the core monitoring point, and segment A2 represents the period between the core monitoring point and the sampling end point, that is, the extended period. Furthermore, the higher the scheduling level, the shorter the corresponding extended period.

[0051] It should be noted that the correlation coefficient in this embodiment is the Pearson coefficient. The corresponding same sampling moment refers to the historical status data and the historical power grid operation data at the same sampling moment. The sampling moment means the moment when the recording starts when the dispatch instruction is issued. When calculating the correlation coefficient, multiple sets of historical status data and historical power grid operation data corresponding to the same sampling moment are used to calculate the correlation coefficient. The higher the correlation coefficient, the more correlated the changes in the historical status data and the historical power grid operation data at the sampling moment are. In other words, at the sampling moment, the power grid equipment responds to the dispatch instruction, resulting in changes in the historical status data, which in turn causes changes in the historical power grid operation data. Therefore, the probability of judging that the sampling moment is the dispatch response moment is higher. In order to improve the fault tolerance of the determination of the dispatch response moment, a period of time is extended after the judgment of the dispatch corresponding moment, that is, the core monitoring point.

[0052] This embodiment analyzes whether the scheduling operation is abnormal based on the core monitoring period. Specifically, the analysis of the similarity between the real-time status data and the historical status data during the core monitoring period includes:

[0053] Determine multiple judgment moments in the core monitoring section based on a preset frequency, and process the real-time status data and historical status data in the core monitoring period into real-time status discrete sequences and historical status discrete sequences according to the judgment moments;

[0054] It is determined in turn whether the sequence values of the real-time state discrete sequence and the historical state discrete sequence at each judgment moment are the same, and the ratio of the number of judgment moments with the same sequence value to the number of all judgment moments is calculated as the similarity.

[0055] When the similarity is less than the preset value, it means that the response of the power grid equipment to the dispatch instruction at this time is significantly different from the historical response, so the probability of abnormal dispatch operation is high.

[0056] After the abnormal dispatching operation alarm is issued, the abnormal dispatching operation monitoring method also includes a panoramic display of abnormal indicators of the abnormal dispatching operation, wherein the abnormal indicators include the completion status of the dispatching instructions, the response delay status and the accumulation status of the dispatching instructions, so that the staff can quickly and timely understand the specific abnormal performance of the dispatching operation, and then quickly make response decisions.

[0057] The serial numbers in the above embodiments are for description only and do not represent the order of assembly or use of the components.

[0058] The above descriptions are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for monitoring abnormal scheduling operations based on business scenario analysis, characterized in that: The method for monitoring abnormal scheduling operations includes: Obtain pre-dispatch grid operation data when issuing dispatch instructions to grid equipment, and determine the business scenario corresponding to the dispatch instructions by performing feature analysis on the pre-dispatch grid operation data; Obtain historical status data and historical grid operation data of the power grid equipment in the business scenario, and determine the core monitoring period based on changes in the historical status data and historical grid operation data; Select historical status data of a core monitoring period and obtain real-time status data of power grid equipment during the core monitoring period; Analyze the similarity between the real-time status data and the historical status data during the core monitoring period. If the similarity is less than the preset value, an abnormal scheduling operation alarm will be issued. The business scenarios include load balancing services, fault isolation services, and relay protection services corresponding to different dispatching levels, including national dispatching, provincial dispatching, local dispatching, and county dispatching; Determining the core monitoring period based on changes in historical status data and historical power grid operation data includes: For the historical status data and historical grid operation data belonging to the same dispatching level, the correlation coefficients of the historical status data and historical grid operation data corresponding to the same sampling time are calculated respectively; The sampling time corresponding to the highest correlation coefficient is marked as the core monitoring point; An extended period corresponding to the scheduling level is determined, and a period between the time when the scheduling instruction is issued and the core monitoring point is spliced with the extended period to obtain a core monitoring period.

2. The method for monitoring abnormal scheduling operations based on business scenario analysis according to claim 1 is characterized in that: The feature analysis of the pre-dispatch grid operation data is performed to determine the business scenario corresponding to the dispatch instruction, including: Preprocessing the grid operation data before dispatching, including data cleaning and data normalization; A feature matrix is generated based on the pre-processed pre-dispatch power grid operation data, the feature matrix is input into a pre-trained machine learning model, and the corresponding business scenario is determined according to the output result of the machine learning model.

3. The method for monitoring abnormal scheduling operations based on business scenario analysis according to claim 2, characterized in that: The machine learning model includes at least one of a decision tree, a support vector machine, and a logistic regression model.

4. The method for monitoring abnormal scheduling operations based on business scenario analysis according to claim 1, characterized in that: The higher the scheduling level, the shorter the corresponding extended period.

5. The method for monitoring abnormal scheduling operations based on business scenario analysis according to claim 1, characterized in that: The analysis of the similarity between the real-time status data and the historical status data during the core monitoring period includes: Determine multiple judgment moments in the core monitoring section based on a preset frequency, and process the real-time status data and historical status data in the core monitoring period into real-time status discrete sequences and historical status discrete sequences according to the judgment moments; It is determined in turn whether the sequence values of the real-time state discrete sequence and the historical state discrete sequence at each judgment moment are the same, and the ratio of the number of judgment moments with the same sequence value to the number of all judgment moments is calculated as the similarity.

6. The method for monitoring abnormal scheduling operations based on business scenario analysis according to claim 1, characterized in that: After the dispatching operation abnormality alarm is issued, the dispatching operation abnormality monitoring method further includes a panoramic display of abnormal indicators of the dispatching operation abnormality, wherein the abnormal indicators include the dispatching instruction completion status, response delay status and dispatching instruction accumulation status.

Images