Forecasting electricity price volatility using artificial neural networks

Forecasting electricity price is a challenging task for on-line trading and e-commerce. Forecasting the hourly market clearing prices (MCP) in daily power markets is the most essential task and basis for any decision making in order to maximize the benefits. Volatility in electricity price in deregulated open power markets and its forecasting using neural networks is presented. Artificial neural networks are found to be most suitable tool as they can map the complex interdependencies between electricity price, historical load, temperature and other factors. The basic idea behind 'neural network approach' is to use history and other estimated factors in the future to 'fit' and 'extrapolate'the prices and quantities. The structure of the neural network is a three-layer back propagation (BP) network. The price forecasting results using the neural network model show that the price of electricity in the deregulated markets can be forecasted with reasonable accuracy.