A neuro-fuzzy price forecasting approach in deregulated electricity markets

Bidding competition is a main transaction approach in a deregulated market. Locational marginal prices (LMPs) resulting from bidding competition signal electricity values at a node or in an area. The LMP reveals important information for market participants to develop their bidding strategies. Moreover, LMP is also a vital indicator for the Security Coordinator to perform market redispatch for congestion management. This paper presents a method using fuzzy reasoning and recurrent neural networks (RNNs) for forecasting LMPs. The fuzzy rules are used to perform the linguistic reasoning about the contingencies. The reasoning results serve as a part of inputs to the RNNs for forecasting the LMPs. The historical LMPs in the PJM market are used to test the proposed method. It is found that the proposed neuro-fuzzy method is capable of forecasting LMP values efficiently.