A research of Monte Carlo optimized neural network for electricity load forecast

Authors

Binbin Yong, Lanzhou UniversityFollow
Liang Huang, Lanzhou University
Fucun Li, University of WollongongFollow
Jun Shen, University of WollongongFollow
Xin Wang, Lanzhou University
Qingguo Zhou, Lanzhou UniversityFollow

RIS ID

115375

Publication Details

Yong, B., Huang, L., Li, F., Shen, J., Wang, X. & Zhou, Q. (2019). A research of Monte Carlo optimized neural network for electricity load forecast. The Journal of Supercomputing, Online First 1-14.

Abstract

In this paper, we apply the Monte Carlo neural network (MCNN), a type of neural network optimized by Monte Carlo algorithm, to electricity load forecast. Meanwhile, deep MCNNs with one, two and three hidden layers are designed. Results have demonstrated that three-layer MCNN improves 70.35% accuracy for 7-week electricity load forecast, compared with traditional neural network. And five-layer MCNN improves 17.24% accuracy for 7-week forecast. This proves that MCNN has great potential in electricity load forecast.