Mapreduced short period load prediction method of multinucleated function learning SVM realizing multi-source heterogeneous data fusion

Abstract

A Mapreduced short period load prediction method of a multinucleated function learning SVM realizing multi-source heterogeneous data fusion is provided; the method uses multinucleated function to effectively process multi-source heterogeneous data affecting load prediction, and the data comprises history load data, meteorology factors, date types, holiday information, electricity price information and traffic information; the multi-source heterogeneous data can be effectively fused so as to improve nucleus machine performance, thus better using information from different data source; a multinucleated support vector machine is Mapreduced so as to have better speed-up ratio and scalability, thus applying to large scale data analysis.

Description

Technical field [0001] The invention relates to a short-term power load forecasting method based on multi-source heterogeneous big data. Background technique [0002] In the field of load forecasting, there are various factors that affect load forecasting, including historical load, weather, season, day type, traffic, real-time electricity price, economy, policy, etc. The time of construction of each autonomous system, R&D unit, and adoption of these data The technology and specific requirements of specific businesses have led to differences in data storage methods, data types, and update frequencies, which in turn presents many characteristics such as data heterogeneity, diverse sources, and massive data. These characteristics usually have their own different physical characteristics. Significance, dimensions, and statistical characteristics. In the existing load forecasting methods, the time series model cannot handle the influencing factors well; although the regression analy...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a multi-core function learning method that can effectively process various multi-source heterogeneous data that affect load forecasting, so as to solve the problem of the number and structure types of random factors that affect load changes collected due to the continuous development of smart grids More and more, the traditional load forecasting method cannot accurately deal with and apply these multi-source heterogeneous influencing factors and cannot meet the short-term load forecasting accuracy and speed requirements in the big data environment.

Images