Effect of Demand-Side Management in Electricity Price/Load Forecasting in Smart Grids

Electricity price and load forecasting are two important problems for market participants and independent system operators (ISO) in smart grid environments. Most existing papers predict price and load separately, while, the aggregate reaction of consumers can potentially shift the demand curve in the market, resulting in prices that may differ from the initial forecasts. In this regards, demand-side management (DSM) constructs the customers responsible for improving the efficiency, reliability and sustainability of the power system. In this paper, we proposed a new multiinput multi-output (MIMO) system which can consider the interaction between load and price. Therefore, proposed Least Squares Support Vector Machine (LSSVM) to model the nonlinear pattern in price and load. Also, used discrete wavelet transform (DWT) to make valuable subsets. Moreover, proposed feature selection to select best input candidates. Finally, the MIMO-based LSSVM parameters are optimized by artificial bee colony (ABC) algorithm. Simulations carried out NEPOOL region (courtesy ISO New England) electricity market data, and showing that the proposed algorithm has good potential for simultaneous forecasting of electricity price and load in smart grids.