Forecasting the day-ahead Spinning Reserve requirement in competitive electricity market

Abstract

Ancillary services (AS) are essential for secure, stable and economical operation of the power system. Moreover, AS plays a vital role in free and fair trade of electricity in emerging competitive power market. Hence, the AS procurement is a major operational function for the independent system operator (ISO) in the electricity market. Spinning reserve (SR) is one of the most important AS required for maintaining power system reliability following a major contingency. An accurate short-term predication of day-ahead SR requirement helps the ISO to make effective and timely decisions in managing the compliance and reliability of the power system. Moreover, based on these forecasted information, market participants can derive the optimal bidding strategies for day-ahead SR market. An adaptive wavelet neural network (AWNN) is proposed in this paper for short-term prediction of day-ahead SR requirement in the California ISO (CAISO) controlled grid. The forecasted results are presented and compared with Artificial Neural Network (ANN) model and CAISO published forecast results. It is found that AWNN performs better than ANN and CAISO forecasted results.