Electricity usage behavior analysis method based on FCM cluster algorithm

Abstract

The invention provides an electricity usage behavior analysis method based on an FCM clustering algorithm, comprising steps of (1) copying electricity usage data from a relation database into a distributed file system HDFS to determine the clustering number c and a stopping field Epsilon, (2) determining an initial clustering center according to the clustering result of the last time, and transmitting the data to data nodes participating distributed calculation, (3) performing pre-processing on the electricity usage data and producing a key value pair <user, profile>, (4) dividing all the key value pairs <user, profile> into a plurality of data subsets and transmitting the data subsets to a Map function for calculation, (5) transmitting the Map function calculation result to an Reduce node, wherein the Reduce task combines the middle key values produced by the Map according clustering numbers and then performs calculation to obtain a new clustering center, and (6) repeating the steps (2)-(5) until a membership grade matrix satisfies the conditions of the stopping field, finishing the algorithm and outputting the clustering result. The electricity usage behavior analysis method performs direction calculation based on the file massive history electricity usage data and obtains the electricity usage behavior characteristics.

Description

technical field [0001] The invention relates to the field of electric power big data, in particular to an electric power consumption behavior analysis method based on an FCM clustering algorithm. Background technique [0002] Based on smart meter data, statistics and mining of electricity consumption patterns of electric power customers are the basis for electric power companies to grasp the composition of customers and understand the characteristics of electricity consumption behavior. prerequisites. However, with the development of power communication technology, the power consumption data generated by the power consumption information collection system is high-frequency and massive every day. Electricity consumption data, from which to discover high-value information requirements. This is in line with the characteristics of typical big data applications, and it also means that traditional computing structures and data mining methods cannot meet the above requirements. ...

AI Technical Summary

Problems solved by technology

[0004] Traditional big data computing architectures, such as Hadoop, Fourinone, etc., are suitable for large-scale, high-concurrency numerical calculations, but the time required for a calculation may reach tens of minutes or even hours, and the resulting high delay problem limits The applicability of these computing architectures in high real-time big data applications

However, high-real-time streaming computing frameworks, such as Spark and Storm, are suitable for distributed real-time computing that processes high-speed and large-scale data streams, but their data structure design and object relationships are not suitable for large-scale parallel computing.

Images