Research on Short-term Photovoltaic Power Prediction Algorithm Based on Spark and Optimized RBFNN

DOI

10.2991/iceeecs-16.2016.157How to use a DOI?

Keywords

photovoltaic power forecasting; RBFNN; Spark; cluster of similar days

Abstract

To overcome the problem of poor accuracy of short-term photovoltaic power prediction, This paper proposes a short-term PV power prediction algorithm based on radial basis function neural network(RBFNN) after similar day clustering on solar irradiance and air temperature as the input variables; At the same time, it introduces the particle swarm optimization(PSO) algorithm to optimize the kernel function parameters of the neural network. In view of the time-consume problem of the large amount of historical data in the photovoltaic power station, Spark cloud platform which based on memory is used to realize parallel the processing algorithm. Through an example experiment, it is verified that the proposed model improves the prediction accuracy, and the parallel algorithm greatly reduces the computation time.

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  - Baoyi Wang
AU  - Zhen Hao
AU  - Shaomin Zhang
PY  - 2016/12
DA  - 2016/12
TI  - Research on Short-term Photovoltaic Power Prediction Algorithm Based on Spark and Optimized RBFNN
BT  - Proceedings of the 2016 4th International Conference on Electrical & Electronics Engineering and Computer Science (ICEEECS 2016)
PB  - Atlantis Press
SP  - 800
EP  - 805
SN  - 2352-538X
UR  - https://doi.org/10.2991/iceeecs-16.2016.157
DO  - 10.2991/iceeecs-16.2016.157
ID  - Wang2016/12
ER  -