A NEURAL NETWORK MODEL FOR PREDICTING SYSTEM MARGINAL PRICE IN THE UK POWER POOL

摘要

The prediction of System Marginal Price(SMP) in the UK Power Pool has become a crucial issue facing Independent Power Producers(IPPs) since electricity industry privatization in England and Wales in 1990. This paper presents a neural network model 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 coded in Visual C++ with a friendly windows interface and run on a PC.