Medium and Long-term Power Load Forecasting based on the Thought of Big Data

DOI

10.2991/emcs-16.2016.324How to use a DOI?

Keywords

Load forecasting; Big data; Correlation; Model; Refineload forecasting; Big data; Correlation; Model; Refine

Abstract

The traditional medium and long-term load forecasting methods are mainly carried out based upon model or algorithm, and forecasting results rely heavily on the accuracy of mathematical model, but model adaptability is very poor. Medium and long-term load forecasting lasts long and suffers from lots of uncertain influential factors in a broad spatial scope, so this paper proposes a big data technology-based medium and long-term load forecasting method. By analyzing the typical characteristics of the big data of load forecasting and the different levels of structure relations between the data, the paper sets up a big data system for load forecasting, a frame structure for load forecasting, and a big data-based medium and long-term refined load forecasting model, which falls into forecasting partition model and load forecasting model. The validity and practicability of this method is verified based on an analysis of the actual grid load in a certain region.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xianzheng Feng
AU  - Tingting Zhang
AU  - Hongjun Li
AU  - Bin Zhao
PY  - 2016/01
DA  - 2016/01
TI  - Medium and Long-term Power Load Forecasting based on the Thought of Big Data
BT  - Proceedings of the 2016 International Conference on Education, Management, Computer and Society
PB  - Atlantis Press
SP  - 1312
EP  - 1316
SN  - 2352-538X
UR  - https://doi.org/10.2991/emcs-16.2016.324
DO  - 10.2991/emcs-16.2016.324
ID  - Feng2016/01
ER  -