Time Series Forecasting Model with Error Correction by Structure Adaptive Support Vector Machine

Exactly power load forecasting especially the short-term load forecasting is of important significance in the case of energy shortage today. In power system, due to the complexity of the historical load data and the randomness of a lot of uncertain factors influence, the observed historical data showed linear and nonlinear characteristics. A hybrid methodology is proposed to take advantage of the unique strength of autoregressive integrated moving average (ARIMA) and SVM (support vector machine) networks in linear and nonlinear modeling, which is an error correction method to create synergies in the overall forecasting process. ARIMA model is used to generate a linear forecast in the first stage, and then SVM is developed as the nonlinear pattern recognition to correct the estimation error in ARIMA forecast. The effectiveness of the hybird-model has been tested by one example. The experimental results show that the hybrid model can more effectively improve the forecasting accuracy than ARIMA-BP.