Multi-source heterogeneous power load data fusion method and device, equipment and storage medium

Abstract

The invention relates to a multi-source heterogeneous power load data fusion method and device, equipment and a storage medium. The method comprises the steps of obtaining a multi-source heterogeneous text of power load data, and performing format normalization processing on the heterogeneous text; extracting key characters from the heterogeneous text to construct a knowledge dictionary, and obtaining an object database of the heterogeneous text through multi-source object name classification; matching the knowledge dictionary with the object name by adopting a MapReduce programming model parallel processing technology, and then matching the object name with the object data; and carrying out longitudinal parameter fusion and transverse parameter fusion on the multi-source matching result after Reduce processing. Through multi-level processing of multi-source heterogeneous power grid load big data, a whole set of electric power big data fusion strategy and evaluation from fusion to evaluation are provided, and data fusion is high in practicability and efficiency.

Description

technical field [0001] The present application relates to the field of big data, and in particular, to a method, apparatus, device and storage medium for data fusion of multi-source heterogeneous power loads. Background technique [0002] Power load data has the characteristics of large scale, wide variety and fast changing speed, and is a typical big data. At present, according to different professional needs, each department usually establishes its own model parameter library and maintains it independently. Due to the lack of a collaborative management mechanism, it is difficult to ensure its consistency, which is embodied in the fact that the parameters of different majors are of different types and codes. It is stored in the form of files with naming rules, and it is difficult to identify and share parameter information with each other. [0003] The patent document with publication number CN107402976A discloses a method and system for power grid multi-source data fusion...

AI Technical Summary

Problems solved by technology

At present, according to different professional needs, each department usually establishes its own model parameter library and maintains it independently. Due to the lack of a collaborative management mechanism, it is difficult to ensure its consistency. Specifically, the parameters of different specialties are coded in different types. It is difficult to identify each other and share parameter information because it is stored in the form of a file with naming rules

[0003] The patent document with the publication number CN107402976A discloses a multi-source data fusion method and system based on a multivariate heterogeneous model. It establishes a unified model including the data of each source system, and calculates the matching degree between models through model traversal and comparison, achieving 90% % of the data is automatically integrated and fused, but the method and system do not propose a method for big data of electric load, which is weakly targeted; the patent document with the publication number CN103617557A proposes a multi-source heterogeneous power grid operating parameter for the power grid operating parameters Analysis system, but the relevant big data processing technology has not been introduced for the processing of massive parameters, and the data processing efficiency needs to be improved

Images