Short Term Electricity Price Forecasting Using Biologically Inspired Support Vector Machine

Roslan, Mohamad Shafiq (2018) Short Term Electricity Price Forecasting Using Biologically Inspired Support Vector Machine. Project Report. Universiti Teknikal Malaysia Melaka, Melaka, Malaysia. (Submitted)

Text (24 Pages) Short Term Electricity Price Forecasting Using Biologically Inspired Support Vector Machine.pdf - Submitted Version Download (385kB)

Abstract

In deregulated electricity markets, consumers have the ability to choose their electricity supplier. Power producers and customers use short term price forecasts to manage and plan for bidding approaches, and hence increase the utility’s profit and energy efficiency. Thus, it allows for greater price flexibility and increased competition between electric providers. This project proposes a prediction model for short-term electricity price forecasting using Support Vector Machine (SVM) and Bacterial Foraging Optimization Algorithm (BFOA). Least Square Support Vector Machine (LSSVM) which is an algorithm that is improved from the SVM is used in this project. Bacterial Foraging Optimization Algorithm (BFOA) is used to optimize the parameters of the LSSVM model which is gamma (γ) and sigma (σ).Furthermore, BFOA optimizes number of features to be fed into LSSVM. The parameters of BFOA are varied to find the best LSSVM-BFOA configuration. The result showed that LSSVM-BFOA able to predict electricity price with good Mean Absolute Percentage Error (MAPE). The model is examined in the Ontario, electricity market in Canada

Actions (login required)

View Item