a new electricity price and load uncertainty prediction method based on optimal neural networks for deregulated electricity power markets

In recent years, short-term load and price forecast has always been a key issue for power system operation. in regulated power systems, short-term load forecast is an important tool for reliable and economic operation of power systems. many operating decisions are based on short-term load forecasting, such as dispatch scheduling of generating capacity, reliability analysis, security assessment and maintenance plan for the generators. on the other hand, electricity price variation are more important and effective factors for all power markets participants. bidding strategy, risk control, investment decisions, demand and supply balancing and power system reliability and other power markets applications are highly depended to load and price uncertainty. in this paper a new intelligent hybrid method has been proposed to price and load uncertainty prediction. the proposed method consists of an improved version of particle swarm optimization algorithm to fine tuning the main predictor system’s adjustable parameters. the price and load variation intervals have been predicted by predictor system based on multi-layer neural networks. the proposed method has been examined in some well-known power markets.