The Modeling And Empirical Analysis Of Power Demand In China

Power is the main component of energy resources contributing greatly to China's rapid economic development and the improvement of people's living standards. Taking the unstationary in the economic time series into consideration, the author models power demand in China by using methodology of cointegration and error correction model. From the non-linearity in the economic time series, artificial neural network is introduced. To advoid entering into local minimum point for improper selection of initial parameters value of back-propagation neural network, immune particle swarm algorithm is introduced. We forecast the power demand in China using the two models, thus proved the validity of these two models. Finally, we put forward some proposals about the development of power industry in China.