| Medium and long term load forecasting is an important research content of power system planning and running, and is also the basis of power system planning and construction. The accuracy of load forecasting will directly affect power system investment and network layout, and is directly related to the security, economical efficiency and reliable operation of power grid.By analyzing the existing load forecasting methods from the aspects of calculation features and applicability, there are six methods of them that are selected to forecast medium and long term load in this paper. On the basis of traditional Grey Model, aiming at the shortage of the model background value and initial value, the paper introduces the particle swarm optimization, and the grey forecasting model based upon particle swarm optimization is presented. Because many direct and indirect factors will affect the accuracy of medium and long term load forecasting, secondly there is no efficient forecasting method that can make sure to achieve higher prediction accuracy in any conditions and obtain the powerful nonlinear mapping capability of neural network. Considering that, the combined forecasting model based on artificial neural network is presented in this paper. The examples show that these methods have higher precision in medium and long term load forecasting.Lastly, a set of medium and long term load forecasting software is developed with Lab VIEW graphical language, which has friendly man-machine interfaces and convenient operability. |