Novel power system multi-source data mining method based on power big data

Abstract

The invention discloses a novel power system multi-source data mining method based on power big data, and relates to the technical field of data processing. According to the method, a clustering algorithm is adopted to analyze power consumption behaviors of industrial users, load power consumption characteristics are researched, a data mining technology is adopted, social characteristics of the users are obtained based on the data mining technology, social characteristic tags of typical users are established, and references are provided for power selling enterprises to provide personalized services for the users, user interaction and privacy protection research; by performing data analysis on the operation equipment and the power utilization user type in the power system, real-time accurate detection of the health state of the operation equipment is realized, a health examination report can be accurately given, a suggestion of maintenance time can be given according to data analysis of the power utilization user type and time, and intelligent management of power equipment maintenance is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing, and in particular relates to a novel power system multi-source data mining method based on power big data. Background Art

[0002] Cluster analysis refers to the process of grouping a collection of physical or abstract objects into multiple classes consisting of similar objects. It is an important human behavior. The goal of cluster analysis is to collect data and classify them based on similarity. Clustering comes from many fields, including mathematics, computer science, statistics, biology, and economics. In different application fields, many clustering techniques have been developed, which are used to describe data, measure the similarity between different data sources, and classify data sources into different clusters.

[0003] At present, in the management of power equipment, such as power grid substation equipment management, the existing technology often relies on the use of monitoring devices to detect each power equipment, and then a large number of manpower periodically patrols to detect the data of each monitoring device, or patrols the working conditions of the power equipment, and regularly provides paper reports to superiors. However, the method of manual detection of power equipment is difficult to conduct comprehensive detection of a large number of power equipment, and cannot integrate the monitoring data of each power equipment. In addition, no automated processing is achieved in the management process of power equipment, which makes it difficult to conduct comprehensive processing of the data of the power equipment. As a result, when the power equipment has data abnormalities, it is impossible to push relevant information to the relevant staff in a timely and accurate manner to provide fault warning. Even if the management personnel are notified in time after the failure occurs, it will take a long time to troubleshoot the failure, which not only consumes a lot of manpower and material resources, but also causes losses to production and life;

[0004] At the same time, there are many electricity users. How to reasonably supply electricity, or when to cut off power when maintenance is needed, when is the best time to cut off power? There is currently no data for analysis, and managers often rely on subjective decisions based on experience. Therefore, a new multi-source data mining method for power systems based on power big data is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide a new power system multi-source data mining method based on power big data to solve the existing problems.

[0006] In order to solve the above technical problems, the present invention is achieved through the following technical solutions:

[0007] The present invention is a novel power system multi-source data mining method based on power big data, comprising the following steps:

[0008] S1. Acquisition of data, including historical and real-time operation data of each power device in the power system; historical and real-time power consumption data of power users in the power consumption collection system;

[0009] S2, store the collected data in a unified manner on a server or cloud to establish typical user social characteristics;

[0010] S3. Perform cluster analysis on the data to obtain the system real-time operation database, fault repair database, and power demand database, and mine the user energy consumption characteristics based on load clustering technology;

[0011] S4. Process and analyze the classified data, give prompts on the health status and operating risks of the operating equipment, and provide guidance and suggestions on maintenance time.

[0012] Furthermore, the method of clustering and analyzing the data in step S3 is as follows: S31, extracting a typical load behavior pattern of a user, and extracting a typical load model by clustering the daily load curves of the user within a period of time;

[0013] S32. Establish a mathematical model based on multi-source data mining technology of power system, adopt k-means clustering algorithm to achieve fast and efficient classification of large data sets, calculate the sum of squared errors, obtain the error reduction coefficient, and combine the error reduction coefficient with the silhouette coefficient to construct a comprehensive benefit index;

[0014] S33. Use the k-means algorithm to cluster the samples, obtain the category label of each user, divide the users into groups according to their categories, and mine the energy consumption characteristics of users according to the groups.

[0015] Furthermore, the specific method for providing prompts for the health status and operating risk of the operating equipment in step S4 is:

[0016] S41, comparing the acquired real-time operation data of the equipment with the abnormal data in the maintenance database and the normal operation data provided by the manufacturer;

[0017] S42. Determine whether the comparison value exceeds the normal value. If so, determine that the device is abnormal. According to the device data source, obtain the device address information and generate a risk warning report.

[0018] Furthermore, the specific method for suggesting the maintenance time in step S4 is:

[0019] S43, according to the electricity demand database, the electricity users are divided into daytime electricity users, nighttime electricity users, and continuous electricity users according to the electricity consumption peak;

[0020] S44, then according to the time, the number of electricity users at the same time is statistically ranked, and finally the maintenance time is determined according to the electricity usage time type and time period electricity user data.

[0021] The present invention has the following beneficial effects:

[0022] The present invention adopts a clustering algorithm to analyze the electricity consumption behavior of industrial users, studies the load power consumption characteristics, adopts data mining technology, obtains the social characteristics of users based on data mining technology, and establishes typical user social characteristic labels, providing a reference for power sales companies to provide personalized services to users, user interaction and privacy protection research.

[0023] The present invention realizes real-time and accurate detection of the health status of operating equipment by performing data analysis on the operating equipment and electricity user types in the power system, and can accurately provide health examination reports. It can also provide suggestions on maintenance time based on the analysis of data on electricity user types and time, thereby realizing intelligent management of power equipment maintenance.

[0024] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0026] Figure 1 This is a flow chart of a new power system multi-source data mining method based on power big data. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 creative work are within the scope of protection of the present invention.

[0028] In the description of the present invention, it should be understood that the terms "upper", "middle", "outer", "inner" and the like indicating directions or positional relationships are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0029] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "provided with", "connected", etc. should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] See also Figure 1 As shown, the present invention is a new power system multi-source data mining method based on power big data, comprising the following steps:

[0031] S1. Acquisition of data, including historical and real-time operation data of each power device in the power system; historical and real-time power consumption data of power users in the power consumption collection system;

[0032] S2, store the collected data in a unified manner on a server or cloud to establish typical user social characteristics;

[0033] S3. Perform cluster analysis on the data to obtain the system real-time operation database, fault repair database, and power demand database, and mine the user energy consumption characteristics based on load clustering technology;

[0034] S4. Process and analyze the classified data, give prompts on the health status and operating risks of the operating equipment, and provide guidance and suggestions on maintenance time.

[0035] In one embodiment, the method for clustering and analyzing the data in step S3 is as follows: S31, extracting a typical load behavior pattern of a user, by clustering the daily load curves of the user within a period of time, and extracting a typical load model;

[0036] S32. Establish a mathematical model based on multi-source data mining technology of power system, adopt k-means clustering algorithm to achieve fast and efficient classification of large data sets, calculate the sum of squared errors, obtain the error reduction coefficient, and combine the error reduction coefficient with the silhouette coefficient to construct a comprehensive benefit index;

[0037] S33. Use the k-means algorithm to cluster the samples, obtain the category label of each user, divide the users into groups according to their categories, and mine the energy consumption characteristics of users according to the groups.

[0038] In one embodiment, the specific method for providing prompts for the health status and operating risk of the operating equipment in step S4 is:

[0039] S41, comparing the acquired real-time operation data of the equipment with the abnormal data in the maintenance database and the normal operation data provided by the manufacturer;

[0040] S42. Determine whether the comparison value exceeds the normal value. If so, determine that the device is abnormal. According to the device data source, obtain the device address information and generate a risk warning report.

[0041] In one embodiment, the specific method of the maintenance time suggestion in step S4 is:

[0042] S43, according to the electricity demand database, the electricity users are divided into daytime electricity users, nighttime electricity users, and continuous electricity users according to the electricity consumption peak;

[0043] S44, then according to the time, the number of electricity users at the same time is statistically ranked, and finally the maintenance time is determined according to the electricity usage time type and time period electricity user data.

[0044] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0045] The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A new multi-source data mining method for power system based on power big data, characterized by: The following steps are involved: S1. Acquisition of data, including historical and real-time operation data of each power device in the power system; historical and real-time power consumption data of power users in the power consumption collection system; S2, store the collected data in a unified manner on a server or cloud to establish typical user social characteristics; S3. Perform cluster analysis on the data to obtain the system real-time operation database, fault repair database, and power demand database, and mine the user energy consumption characteristics based on load clustering technology; S4. Process and analyze the classified data, give prompts on the health status and operating risks of the operating equipment, and provide guidance and suggestions on maintenance time.

2. According to a new type of power system multi-source data mining method based on power big data according to claim 1, it is characterized in that: The method for clustering and analyzing the data in step S3 is as follows: S31, extracting the typical load behavior pattern of the user, by clustering the daily load curve of the user within a period of time, and extracting the typical load model; S32. Establish a mathematical model based on multi-source data mining technology of power system, adopt k-means clustering algorithm to achieve fast and efficient classification of large data sets, calculate the sum of squared errors, obtain the error reduction coefficient, and combine the error reduction coefficient with the silhouette coefficient to construct a comprehensive benefit index; S33. Use the k-means algorithm to cluster the samples, obtain the category label of each user, divide the users into groups according to their categories, and mine the energy consumption characteristics of users according to the groups.

3. According to a new type of power system multi-source data mining method based on power big data according to claim 1, it is characterized in that: The specific method for providing prompts for the health status and operating risk of the operating equipment in step S4 is: S41, comparing the acquired real-time operation data of the equipment with the abnormal data in the maintenance database and the normal operation data provided by the manufacturer; S42. Determine whether the comparison value exceeds the normal value. If so, determine that the device is abnormal. According to the device data source, obtain the device address information and generate a risk warning report.

4. According to a new type of power system multi-source data mining method based on power big data according to claim 1, it is characterized in that: The specific method for suggesting the maintenance time in step S4 is: S43, according to the electricity demand database, the electricity users are divided into daytime electricity users, nighttime electricity users, and continuous electricity users according to the electricity consumption peak; S44, then according to the time, the number of electricity users at the same time is statistically ranked, and finally the maintenance time is determined according to the electricity usage time type and time period electricity user data.

Images