Prediction of system marginal price in the UK Power Pool using neural networks

There is an increasing interest in the prediction of system marginal price (SMP) in the Power Pool since electricity industry vesting in England and Wales in 1990. The prediction of SMP improves the financial performance of an independent power producer bidding in the day-ahead market. This paper presents a successful application of using neural networks to predict SMP at each settlement period on the next scheduling day in the UK Pool. The approach does not require any individual Pool participant commercially sensitive information; the historical public SMP and other data are used to train the neural network. The result reveals that the mean absolute percent error is reasonable. The program is run on a PC. The data processing program is coded in Visual C++ with a user friendly windows interface.