Short-Term Congestion Forecasting in Wholesale Power Markets

Abstract

Short-term congestion forecasting is highly important for market participants in wholesale power markets that use locational marginal prices (LMPs) to manage congestion. Accurate congestion forecasting facilitates market traders in bidding and trading activities and assists market operators in system planning. This study proposes a new short-term forecasting algorithm for congestion, LMPs, and other power system variables based on the concept of system patterns - combinations of status flags for generating units and transmission lines. The advantage of this algorithm relative to standard statistical forecasting methods is that structural aspects underlying power market operations are exploited to reduce forecast error. The advantage relative to previously proposed structural forecasting methods is that data requirements are substantially reduced. Forecasting results based on a NYISO case study demonstrate the feasibility and accuracy of the proposed algorithm.