Electricity Market Price-spike Classification in the Smart Grid

Accurate electricity market price forecasting is essential for the market participants in the present competitive deregulated electric power industry. In this research, the smart meter data is concomitantly used with the market data to improve price spike forecast. Modern data mining tools like Naive- Bayesian classifier, Random Forest and Artificial Neural Network algorithms have been used for price-spike forecasting. The Australian Energy Market Operator (AEMO) data of Victorian region has been used to train and test the price-spike forecasting methodology. The results show that the usage of smart meter data can have a significant impact on the accuracy of the price-spike forecasts.