Support Vector Machine(SVM), of which the foundations have been developed by Vapnik (1995), is gaining popularity thanks to many attractive features and promising empirical performance. In this paper, we propose a new short-term load forecasting technique based on SVM. We discuss the input vector selection of SVM for load forecasting and analyze the prediction performance for various SVM parameters such as kernel function, cost coefficient C, and $varepsilon$ (the width of 8 $varepsilon-tube$). The computer simulation shows that the prediction performance of the proposed method is superior to that of the conventional neural networks.