Study on the comprehensive model of mid-long term load forecasting

Mid-long term power load forecasting is the foundation and also an important premise of the power system planning. This paper analyzes and compares the characteristics of the present mid-long term load forecasting methods,and then classifies them simply. It improves the traditional electric consumption elasticity coefficient method,and combining with grey prediction model and secondary moving average method, establishes a new integrated model for load forecasting, and uses Genetic Algorithm(GA) to optimize the weight of each single forecasting model. Through simulation test with Artificial Neural Network(ANN) model, the results show that the proposed prediction model is of high precision and strong applicability.