A method for analyzing and processing abnormal power distribution data based on communication network

Abstract

The present invention provides a method for analyzing and processing abnormal power distribution data based on a communication network, which belongs to the technical field of power systems, and specifically comprises: when determining that the local verification processing difficulty of a target device meets the requirements through a communication link between different power devices in a verification device group, determining the verification power device in the verification device group based on the abnormal probability of the power distribution data of different power devices in the verification device group and the communication link with other power devices in the verification device group, based on the power distribution data of different power devices in the verification device group obtained by the verification power device, and when using the verification power device to determine that the abnormal situation of the power distribution data of the target device within a preset time period does not meet the requirements, the power distribution data of the target device is subjected to abnormal identification and processing on a unified supervision platform, thereby achieving efficient identification and processing of the abnormal power distribution data.

Description

Technical Field

[0001] The present invention belongs to the technical field of power systems, and in particular relates to a method for analyzing and processing abnormal power distribution data based on a communication network. Background Art

[0002] The safe operation of the power system is inseparable from the support of monitoring data of different types of power equipment. Once there are abnormalities in the monitoring data of the power equipment, it will inevitably lead to misjudgment of the operating status of the power system by the operation management personnel.

[0003] In order to realize the identification and processing of abnormal power distribution data in the power system, the invention patent application CN202310952334.8 "A method, system, device and storage medium for identifying bad power grid data" inputs the extracted backbone communication network data flow characteristics into a pre-built and trained bad power grid data identification model for identification, thereby generating an evaluation report on bad power grid data. However, there are the following problems:

[0004] When identifying and processing abnormal power distribution data, the existing technical solutions often use a unified data supervision and analysis platform to identify and process abnormal power distribution data. However, for large-scale power distribution network systems, the amount of distribution data is very large. Therefore, the use of a unified data supervision and analysis platform will inevitably lead to the efficiency of abnormal identification and processing being unable to meet the requirements.

[0005] In response to the above technical problems, the present invention provides a method for analyzing and processing abnormal power distribution data based on a communication network. Summary of the invention

[0006] To achieve the purpose of the present invention, the present invention adopts the following technical solutions:

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions to achieve the purpose of the present invention:

[0008] According to one aspect of the present invention, a method for analyzing and processing abnormal power distribution data based on a communication network is provided.

[0009] A method for analyzing and processing abnormal power distribution data based on a communication network, specifically comprising:

[0010] S1 determines the abnormal probability of power distribution data of different power equipment and the target equipment for abnormal identification in the power equipment by using the historical analysis results;

[0011] S2 determines the associated power equipment associated with the power distribution data of the target equipment according to the node of the target equipment in the power distribution network, divides the target equipment and the associated power equipment into the same verification equipment group, and proceeds to the next step when it is determined that the local verification processing difficulty of the target equipment meets the requirements through the communication link between different power equipment in the verification equipment group;

[0012] S3 determines the verification power equipment in the verification equipment group based on the abnormal probability of power distribution data of different power equipment in the verification equipment group and the communication link with other power equipment in the verification equipment group;

[0013] S4 is based on the power distribution data of different power equipment in the verification equipment group obtained by the verification power equipment. When the verification power equipment is used to determine that the abnormal situation of the power distribution data of the target equipment within a preset time period does not meet the requirements, the power distribution data of the target equipment is subjected to abnormal identification processing on a unified supervision platform.

[0014] The beneficial effects of the present invention are:

[0015] 1. By verifying the communication links between different power equipment in the equipment group, it is determined whether the local verification processing difficulty of the target equipment meets the requirements, thereby avoiding the technical problem of high difficulty in local verification processing of the target equipment due to the overly complex communication links between the power equipment, and reducing the impact of local verification processing on the communication network. On the basis of ensuring the reliability of the communication network, it also lays the foundation for realizing local verification processing of the target equipment, further reducing the difficulty of abnormal identification of the unified supervision platform.

[0016] 2. Use the verification power equipment to determine whether the abnormal situation of the power distribution data of the target equipment within the preset time meets the requirements, thereby realizing the local verification processing of the target equipment, further reducing the difficulty of abnormal identification of the unified supervision platform, and at the same time, by judging whether the abnormal situation of the power distribution data of the target equipment within the preset time meets the requirements, the screening of target equipment with a higher degree of abnormality is realized, which improves the accuracy of abnormal data identification and processing while ensuring that the difficulty of abnormal identification of the unified supervision platform is controllable.

[0017] A further technical solution is that the historical analysis result includes the number of abnormalities of different abnormal types in the power distribution data of the power equipment.

[0018] A further technical solution is that the abnormal types include data upload failure, data deviation and data missing.

[0019] A further technical solution is that the method for determining the abnormal probability of the power distribution data of the power equipment is:

[0020] Determine the number of abnormalities of different abnormal types in the power distribution data of the power equipment based on the historical analysis result;

[0021] Determine the data anomaly coefficient of different anomaly types by the ratio of the number of anomalies of different anomaly types to the threshold of the number of anomalies;

[0022] After normalizing the data anomaly coefficients under different anomaly types, corrected anomaly coefficients under different anomaly types are obtained, and the abnormal probability of the power distribution data of the power equipment is determined by the sum of the corrected anomaly coefficients under different anomaly types.

[0023] A further technical solution is to determine that the abnormal situation of the power distribution data of the target device within a preset time period does not meet the requirements, specifically including:

[0024] Based on the power distribution data of the power equipment, the verification power equipment is used to determine the number of times that the verification result of the power distribution data of the target equipment within a preset time period is abnormal, and use it as the number of verification abnormalities;

[0025] Whether the abnormal situation of the power distribution data of the target device within a preset time period meets the requirements is determined by checking the abnormal number of times.

[0026] A further technical solution is that when the abnormal situation of the power distribution data of the target device within a preset time period meets the requirements, the verification power equipment is continued to be used to perform verification processing on the power distribution data of the target device.

[0027] Other features and advantages will be described in the following description, and partly become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0028] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0030] Figure 1 It is a flow chart of a method for analyzing and processing abnormal power distribution data based on a communication network;

[0031] Figure 2 is a flow chart of a method for determining an abnormal probability of power distribution data of an electric power device;

[0032] Figure 3is a flow chart of a method for determining a local verification processing difficulty of a target device;

[0033] Figure 4 is a flow chart of a method for determining communication processing difficulty between different power devices;

[0034] Figure 5 The present invention is a flow chart of a method for determining a verification electrical device in a verification device group. DETAILED DESCRIPTION

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar structures, and thus their detailed description will be omitted.

[0036] The terms "a", "an", "the", and "said" are used to indicate the presence of one or more elements / components / etc.; the terms "comprising" and "having" are used to express an open-ended inclusive meaning and mean that additional elements / components / etc. may be present in addition to the listed elements / components / etc.

[0037] To solve the above problems, according to one aspect of the present invention, Figure 1 According to one aspect of the present invention, a method for analyzing and processing abnormal power distribution data based on a communication network is provided, which specifically includes:

[0038] S1 determines the abnormal probability of power distribution data of different power equipment and the target equipment for abnormal identification in the power equipment by using the historical analysis results;

[0039] Furthermore, the historical analysis result includes the number of abnormalities of different abnormal types in the power distribution data of the electric power equipment.

[0040] It should be noted that the abnormal types include data upload failure, data deviation and data missing.

[0041] Specifically, Figure 2 As shown, the method for determining the abnormal probability of the power distribution data of the power equipment is:

[0042] Determine the number of abnormalities of different abnormal types in the power distribution data of the power equipment based on the historical analysis result;

[0043] Determine the data anomaly coefficient of different anomaly types by the ratio of the number of anomalies of different anomaly types to the threshold of the number of anomalies;

[0044] After normalizing the data anomaly coefficients under different anomaly types, corrected anomaly coefficients under different anomaly types are obtained, and the abnormal probability of the power distribution data of the power equipment is determined by the sum of the corrected anomaly coefficients under different anomaly types.

[0045] Furthermore, when the abnormal probability of the power distribution data of the electric power equipment is within a preset abnormal interval, the electric power equipment is determined to be a target equipment for abnormal identification.

[0046] It should also be noted that when the power equipment does not belong to the target equipment for abnormal identification, it is determined whether the abnormal probability of the power distribution data of the power equipment is greater than the preset probability threshold. If so, the power distribution data of the power equipment is processed for abnormal identification on the unified supervision platform. If not, no abnormal identification processing is required.

[0047] In another embodiment, the method for determining the abnormal probability of the power distribution data of the power equipment is:

[0048] S11 determines whether the power distribution data of the power equipment has been abnormal based on the historical analysis result, if so, proceeds to the next step, if not, determines that no abnormality identification processing is required;

[0049] S12 determines the number of abnormalities of the power distribution data of the power equipment based on the historical analysis result, and judges whether the number of abnormalities of the power distribution data of the power equipment is less than the preset number of abnormalities. If so, proceed to step S15; if not, proceed to the next step;

[0050] S13 determines whether the number of abnormalities in the power distribution data of the power equipment is greater than a preset number threshold. If so, the power distribution data of the power equipment is processed for abnormality identification on a unified supervision platform. If not, proceed to the next step.

[0051] S14 determines the abnormal times of the power distribution data of the power equipment in different abnormal types based on the historical analysis results, and judges whether there is an abnormal type whose abnormal times do not meet the requirements. If so, the power distribution data of the power equipment is subjected to abnormal identification processing on the unified supervision platform. If not, proceed to the next step;

[0052] S15 determines the data anomaly coefficients of different anomaly types by the ratio of the number of anomalies of different anomaly types to the threshold of the number of anomalies, and judges whether the number of anomaly types whose data anomaly coefficients are greater than the preset coefficient threshold meets the requirement. If so, proceed to the next step; if not, perform anomaly identification processing on the power distribution data of the power equipment on the unified supervision platform;

[0053] S16 normalizes the data anomaly coefficients under different anomaly types to obtain corrected anomaly coefficients under different anomaly types, and determines the abnormal probability of the power distribution data of the power equipment by the sum of the corrected anomaly coefficients under different anomaly types.

[0054] S2 determines the associated power equipment associated with the power distribution data of the target equipment according to the node of the target equipment in the power distribution network, divides the target equipment and the associated power equipment into the same verification equipment group, and proceeds to the next step when it is determined that the local verification processing difficulty of the target equipment meets the requirements through the communication link between different power equipment in the verification equipment group;

[0055] Furthermore, the associated power equipment is a power equipment whose power distribution data is data associated with the power distribution data of the target equipment.

[0056] It should be noted that if Figure 3 As shown, the method for determining the difficulty of local verification processing of the target device is:

[0057] Obtaining the number of power devices in the verification device group, and determining the basic verification difficulty of the verification device group using the number of power devices;

[0058] Based on the communication links between different power devices in the verification device group, determining the length of the communication links between different power devices, and determining the difficulty of communication processing between different power devices in combination with the number of communication devices in the communication links between different power devices;

[0059] The communication processing difficulty between different power devices is normalized to obtain the communication difficulty coefficient between different power devices, and the local verification processing difficulty of the target device is determined based on the sum of the communication difficulty coefficients between different power devices and the product of the basic verification difficulty of the verification device group.

[0060] Specifically, Figure 4 As shown, the method for determining the difficulty of communication processing between different power devices is:

[0061] Based on the length of the communication link between different power devices, determining a preset communication processing difficulty corresponding to the length;

[0062] Determine the number interval of the number of communication devices in the communication link between different power devices based on the number of communication devices in the communication link, and determine the compensation amount of the communication processing difficulty between different power devices based on the preset compensation amount of the communication processing difficulty corresponding to the data interval;

[0063] The communication processing difficulty between different power devices is determined by the sum of the compensation amount of the communication processing difficulty and the preset communication processing difficulty.

[0064] Furthermore, when the local verification processing difficulty of the target device does not meet the requirement, the power distribution data of the target device is subjected to abnormal identification processing on a unified supervision platform.

[0065] It should also be noted that the method for determining the difficulty of the local verification processing of the target device is:

[0066] Obtain the number of power devices in the verification device group, determine whether the number of power devices in the verification device group meets the requirement, if so, proceed to the next step, if not, determine that the local verification processing difficulty of the target device does not meet the requirement;

[0067] Based on the communication links between different power devices in the verification device group, it is determined whether the number of power devices whose communication links are longer than a preset length meets the requirement, if so, proceeding to the next step, if not, determining that the local verification processing difficulty of the target device does not meet the requirement;

[0068] Determine whether the number of communication devices in the communication link is greater than the number of power devices of the preset number, and if so, proceed to the next step; if not, determine that the local verification processing difficulty of the target device does not meet the requirement;

[0069] Based on the communication links between different power devices in the verification device group, the lengths of the communication links between different power devices are determined, and the communication processing difficulty between different power devices is determined in combination with the number of communication devices in the communication links between different power devices, and it is judged whether the number of power devices whose communication processing difficulty does not meet the requirement meets the requirement, if so, proceeding to the next step, if not, determining that the local verification processing difficulty of the target device does not meet the requirement;

[0070] The basic verification difficulty of the verification equipment group is determined by utilizing the number of the power equipment, the communication processing difficulty between different power equipment is normalized to obtain the communication difficulty coefficient between different power equipment, and the local verification processing difficulty of the target equipment is determined based on the sum of the communication difficulty coefficients between different power equipment and the product of the basic verification difficulty of the verification equipment group.

[0071] S3 determines the verification power equipment in the verification equipment group based on the abnormal probability of power distribution data of different power equipment in the verification equipment group and the communication link with other power equipment in the verification equipment group;

[0072] Specifically, Figure 5As shown, the method for determining the verification power equipment in the verification equipment group is:

[0073] Based on the communication link between the power device in the verification device group and other power devices in other verification device groups, determine the length of the communication link between the power device and other power devices, and determine the difficulty of communication processing between the power device and other power devices in combination with the number of communication devices in the communication link between the power device and other power devices;

[0074] Determining a comprehensive communication processing difficulty of the electric power device based on a weight of the communication processing difficulty with other electric power devices;

[0075] The verification processing priority coefficient of the power equipment is determined by the comprehensive communication processing difficulty of the power equipment and the abnormal probability of the power distribution data, and the verification power equipment in the verification equipment group is determined by using the verification processing priority coefficient.

[0076] Furthermore, the verification power device is a power device with the largest verification processing priority coefficient in the verification device group.

[0077] It should also be noted that the method for determining the verification power equipment in the verification equipment group is:

[0078] S31 determines the length of the communication link between the power device in the verification device group and other power devices in other verification device groups based on the communication link between the power device in the verification device group and other power devices, and judges whether the average value of the length of the communication link between the power device and other power devices meets the requirements, if yes, proceeds to the next step, if not, determines that the power device does not belong to the verification power device;

[0079] S32 determines whether the average value of the number of communication devices in the communication link between the power device and other power devices meets the requirement, if yes, proceeds to the next step, if no, determines that the power device does not belong to the verification power device;

[0080] S33 determines the communication processing difficulty between the power device and other power devices based on the length of the communication link between the power device and other power devices and the number of communication devices in the communication link between the power device and other power devices, and determines whether there are other power devices whose communication processing difficulty does not meet the requirements. If yes, proceed to the next step; if not, proceed to step S35;

[0081] S34 determines whether the number of other power devices whose communication processing difficulty does not meet the requirement meets the requirement, if so, proceeds to the next step, if not, determines that the power device does not belong to the verification power device;

[0082] S35: judging whether the comprehensive communication processing difficulty of the power equipment meets the requirements based on the weight of the communication processing difficulty between other power equipment and the comprehensive communication processing difficulty of the power equipment; if so, proceeding to the next step; if not, determining that the power equipment does not belong to the verification power equipment;

[0083] S36 determines the verification processing priority coefficient of the power equipment according to the comprehensive communication processing difficulty of the power equipment and the abnormal probability of the power distribution data, and uses the verification processing priority coefficient to determine the verification power equipment in the verification equipment group.

[0084] S4 is based on the power distribution data of different power equipment in the verification equipment group obtained by the verification power equipment. When the verification power equipment is used to determine that the abnormal situation of the power distribution data of the target equipment within a preset time period does not meet the requirements, the power distribution data of the target equipment is subjected to abnormal identification processing on a unified supervision platform.

[0085] Specifically, determining that the abnormal situation of the power distribution data of the target device within a preset time period does not meet the requirements specifically includes:

[0086] Based on the power distribution data of the power equipment, the verification power equipment is used to determine the number of times that the verification result of the power distribution data of the target equipment within a preset time period is abnormal, and use it as the number of verification abnormalities;

[0087] Whether the abnormal situation of the power distribution data of the target device within a preset time period meets the requirements is determined by checking the abnormal number of times.

[0088] Furthermore, when the abnormal situation of the power distribution data of the target device within the preset time period meets the requirements, the verification power equipment is continued to be used to perform verification processing on the power distribution data of the target device.

[0089] It should be noted that the power distribution data of the target device is processed for abnormal identification on the unified supervision platform, specifically including:

[0090] The power distribution data of the target device is sent to a unified supervision platform, and the unified supervision platform uses a preset abnormality recognition model to perform abnormality recognition processing on the power distribution data of the target device.

[0091] It can be understood that the preset abnormality recognition model is constructed based on an artificial intelligence model trained based on the historical power distribution data of the target device.

[0092] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0093] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A method for analyzing and processing abnormal power distribution data based on a communication network, characterized in that: Specifically include: Determine the abnormal probability of power distribution data of different power equipment and the target equipment for abnormal identification in the power equipment by using the historical analysis results; Determine the associated power equipment associated with the power distribution data of the target equipment according to the node of the target equipment in the power distribution network, divide the target equipment and the associated power equipment into the same verification equipment group, and proceed to the next step when it is determined through the communication link between different power equipment in the verification equipment group that the local verification processing difficulty of the target equipment meets the requirement; Determining the verification power equipment in the verification equipment group based on the abnormal probability of power distribution data of different power equipment in the verification equipment group and the communication link with other power equipment in the verification equipment group; Based on the power distribution data of different power devices in the verification device group obtained by the verification power device, when the verification power device determines that the abnormal situation of the power distribution data of the target device within a preset time period does not meet the requirements, the power distribution data of the target device is subjected to abnormal identification processing on the unified supervision platform; The method for determining the difficulty of local verification processing of the target device is: Obtaining the number of power devices in the verification device group, and determining the basic verification difficulty of the verification device group using the number of power devices; Based on the communication links between different power devices in the verification device group, determining the length of the communication links between different power devices, and determining the difficulty of communication processing between different power devices in combination with the number of communication devices in the communication links between different power devices; Normalizing the communication processing difficulties between different power devices to obtain communication difficulty coefficients between different power devices, and determining the local verification processing difficulty of the target device according to the product of the sum of the communication difficulty coefficients between different power devices and the basic verification difficulty of the verification device group; When the local verification processing difficulty of the target device does not meet the requirement, the power distribution data of the target device is subjected to abnormal identification processing on the unified supervision platform; The method for determining the verification power equipment in the verification equipment group is: Based on the communication link between the power device in the verification device group and other power devices in other verification device groups, determine the length of the communication link between the power device and other power devices, and determine the difficulty of communication processing between the power device and other power devices in combination with the number of communication devices in the communication link between the power device and other power devices; Determining a comprehensive communication processing difficulty of the electric power device based on a weight of the communication processing difficulty with other electric power devices; The verification processing priority coefficient of the power equipment is determined by the comprehensive communication processing difficulty of the power equipment and the abnormal probability of the power distribution data, and the verification power equipment in the verification equipment group is determined by using the verification processing priority coefficient.

2. The abnormal power distribution data analysis and processing method based on the communication network according to claim 1, characterized in that: The historical analysis result includes the abnormal times of different abnormal types of the power distribution data of the electric power equipment.

3. The abnormal power distribution data analysis and processing method based on the communication network according to claim 2, characterized in that: The abnormal types include data upload failure, data deviation and data missing.

4. The abnormal power distribution data analysis and processing method based on a communication network according to claim 1, characterized in that: The method for determining the abnormal probability of the power distribution data of the power equipment is: Determine the number of abnormalities of different abnormal types in the power distribution data of the power equipment based on the historical analysis result; Determine the data anomaly coefficient of different anomaly types by the ratio of the number of anomalies of different anomaly types to the threshold of the number of anomalies; After normalizing the data anomaly coefficients under different anomaly types, corrected anomaly coefficients under different anomaly types are obtained, and the abnormal probability of the power distribution data of the power equipment is determined by the sum of the corrected anomaly coefficients under different anomaly types.

5. The abnormal power distribution data analysis and processing method based on the communication network according to claim 1, characterized in that: When the power equipment does not belong to the target equipment for abnormal identification, it is determined whether the abnormal probability of the power distribution data of the power equipment is greater than the preset probability threshold. If so, the power distribution data of the power equipment is processed for abnormal identification on the unified supervision platform. If not, no abnormal identification processing is required.

6. The abnormal power distribution data analysis and processing method based on a communication network according to claim 1, characterized in that: The associated power equipment is a power equipment whose power distribution data is data-associated with the power distribution data of the target equipment.

7. The abnormal power distribution data analysis and processing method based on a communication network according to claim 1, characterized in that: Determining that the abnormality of the power distribution data of the target device within a preset time period does not meet the requirements specifically includes: Based on the power distribution data of the power equipment, the verification power equipment is used to determine the number of times that the verification result of the power distribution data of the target equipment within a preset time period is abnormal, and use it as the number of verification abnormalities; Whether the abnormal situation of the power distribution data of the target device within a preset time period meets the requirements is determined by checking the abnormal number of times.

8. The abnormal power distribution data analysis and processing method based on a communication network according to claim 7, characterized in that: When the abnormal situation of the power distribution data of the target device within the preset time period meets the requirement, the verification power equipment is continued to be used to perform verification processing on the power distribution data of the target device.

9. The abnormal power distribution data analysis and processing method based on a communication network according to claim 1, characterized in that: The power distribution data of the target device is processed for abnormal identification on a unified supervision platform, specifically including: The power distribution data of the target device is sent to a unified supervision platform, and the unified supervision platform uses a preset abnormality recognition model to perform abnormality recognition processing on the power distribution data of the target device.

Images