Predicting China's Energy Consumption Using Artificial Neural Networks and Genetic Algorithms

In this work, artificial neural networks (ANN) based on genetic algorithm (GA) have been developed to predict energy consumption in China. The numbers of neurons in the hidden layer, the momentum rate and the learning rate are determined using the genetic algorithm. The inputs to the artificial neural networks model are four variables, namely, gross domestic product, industrial structure, total population and technology progress. It is verified that genetic algorithm could find the optimal architecture and parameters of the back-propagation algorithm. In addition, the artificial neural network model based genetic algorithm is tested and the results indicate that the energy consumption in China can be efficiently forecasted by this model. Compared with a network in which the ANN calibration is done using a trial-and-error approach, it can be found that this model can improve prediction accuracy.

I. Introduction

Today, China is the second largest consumer of energy products in the world behind the United States. China's role in the world energy market becomes increasingly influential.