Integration Of Convolutional Neural Network and Support Vector Regression For Electricity Price Forecasting

Accurate electricity price forecasting (EPF) plays a crucial role in bid strategies and risk reduction for market participants in the competitive electricity market. However, forecasting of electricity prices accurately is a highly demanding task due to the intricate nonlinearity present in the price dynamics. This paper introduces a combination of deep learning (DL) technique with machine learning (ML) model to forecast electricity prices in the Australian energy market operator (AEMO) for hourly price prediction utilizing load and renewable energy supply data from five major economical states New South Wales (NSW), Queensland (QLD), South Australia (SA), Tasmania (TAS) and Victoria (VIC). The proposed work integrates the convolutional neural network (CNN) and support vector regression (SVR) to identify short-term local dependency patterns among variables and uncover long-term correlations for time series patterns and forecast the hourly ahead price. The suggested model (CNN-SVR) is contrasted to various models such as CNN-LSTM, BiLSTM, SVR, and their performance is evaluated using various metrics, including mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE).