Short-Term Electricity Price Forecasting Using Artificial Neural Network

Mohd Sidin, Siti Syakirah (2018) Short-Term Electricity Price Forecasting Using Artificial Neural Network. Project Report. UTeM, Melaka, Malaysia. (Submitted)

Text (24 Pages) Short-Term Electricity Price Forecasting Using Artificial Neural Network.pdf - Submitted Version Download (646kB)

Abstract

Electricity price forecasting has become a crucial job in energy market around the world. Hence, price forecasting also has become a major area of research in the electrical engineering field in recent years. However, predicting electricity price forecasting is a challenging task as the prices show complex volatility patterns. Price forecasting plays an important role in power system planning and operation as these are helpful for dispatch and short terms or spot trading. There are many methods in electricity price forecasting. One of the methods is artificial neural network. Artificial neural network is a computational system that inspired by the structure, ability to learn and method to learn by the human brain. Neural network is a good tool to forecast electricity price in deregulation energy market. Hence, neural network model for short term electricity price forecasting is developed in this project. The sensitivity analysis of neural network is performed to get better accuracy in price forecasting by varying learning rate, momentum rate and number of hidden neurons. Correlation analysis was performed to observe the strength of the relationship between input features and targeted output. The neural network model is examined on the Ontario energy market. The use of neural network to forecast electricity price is proven to produce better result compared to the other existing methods.

Actions (login required)

View Item