Application of Grey LS-SVM in Mid and Long Term Power Load Forecasting

Abstract

Mid-long term load is affected by many factors, it is difficult to forecast by a single method. This paper analyzes the advantages and disadvantages of grey forecasting method and least squares support vector machine (LS-SVM) respectively, proposes a new forecasting model of grey least squares support vector machine which develops the advantages of accumulation generation in the grey forecasting method, weakens the effect of stochastic disturbing factors in original sequence, strengthens the regularity of data and avoids theoretical defects existing in the grey forecasting model. The simulation results show that this model performs well in generalization ability and forecasting precision. Keywords-mid-long term load forecasting; grey model; least squares support vector machine