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 sy… stem planning. This study proposes a new short-term congestion forecasting algorithm based on the concept of system patterns—combinations of status flags for transmission lines and generating units. 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. Forecasting results based on a NYISO case study demonstrate the feasibility and accuracy of the proposed algorithm.