Hossein Shayeghi - Technical Engineering Department University of Mohaghegh Ardabili Ardabil, Iran
Ali Ghasemi - Technical Engineering Department University of Mohaghegh Ardabili Ardabil, Iran

A deregulated electricity market is one of the keystones of up-and-coming smart grid deployments. In such a market, forecasting electricity prices (load) is vital to helping participants with the decision making process. Next-day price forecasting is an inherently difficult problem due to its special characteristics of dynamicity and non-stationary. In addition, price forecasting is performed from a point forecasting perspective, i.e., forecasting the exact values of future prices. Thus, in some applications, such as demand-side management, operation decisions are made based on certain price thresholds. We introduce a new hybrid multi-input multi-output (MIMO) forecasting methodology that exploits the unique strength of the Autoregressive Integrated Moving Average (ARIMA) and Least Squares Support Vector Machine (LSSVM) and Wavelet Transform (WT) models in forecasting electricity load/prices. Simulation results for Australia’s, Ontario’s, Iran’s and New England’s electricity market data are provided. Lastly, the application of the generated numerical results to a demand side management case study is demonstrated

Load/Price Forecasting, Smart Grid, Demand Side Manegment, LSSVM, ARIMA, WT