Research on power load forecasting of wavelet neural network based on the improved genetic algorithm

Abstract

This study aims at power load forecasting of the wavelet neural network based on improving genetic algorithm. The improved genetic algorithm is used to optimise the wavelet neural network, while the relevant mathematical models are constructed to reduce the deficiencies of the BP neural network algorithm. As a result, the study has improved the learning accuracy and the rate of convergence, reduced the errors and overcome the deficiencies of the BP algorithm. It is concluded that the power load forecasting model of the wavelet neural network, based on the improved genetic algorithm constructed in this study, can reduce errors and accord to the actual situation so that it has certain application values.

KEYWORDS:

• Power load forecasting mode
• optimisation
• back propagation
• improvement of genetic algorithm
• wavelet neural network

Disclosure statement

No potential conflict of interest was reported by the authors.