The mid-long term electric load forecasting provide essential data for the grid planning, it is helpful to optimize the planning of the power system. According to such features in mid-long term forecasting as small samples, poor information, uncertainty and nonlinearity, we can use the verhulst model in the grey system to do the forecasting. But in thinking of the differences of the sampling and the variations of the original sequence, the verhulst can’t do the forecasting exactly. So, through the method of doing equal-interval quantization and reforming the background value to the original sequence, we have established the improved verhulst model. The improved model is applied to the electric load prediction of one district and the accuracy of the min-long term load forecasting can be enhanced by our model.
A Hybrid Distribution Feeder Long-Term Load Forecasting Method Based on Sequence Prediction
