Electricity Price Forecasting in the Ireland Day Ahead Market: A Machine Learning Approach

Okonji, Chukwuwemeka Nwanze (2023) Electricity Price Forecasting in the Ireland Day Ahead Market: A Machine Learning Approach. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (923kB) | Preview

Abstract

Electricity markets, evolving from state-owned monopolies to liberalized structures, necessitate accurate price forecasting due to the non-storability of electricity and the demand-supply equilibrium requirement. Focused on the Irish Day-Ahead market, this research employs machine learning, including LSTM, Stacked LSTM, CNN-LSTM, and MLP, to predict the market clearing price. Despite limited prior work on this market, the study evaluates four models, identifying the hybrid CNNLSTM as the best performer with an RMSE of 0.025264, followed by 2-layer stacked LSTM and MLP. Although univariate in its approach, the research excels in capturing intricate market patterns. However, limitations include overlooking external factors like weather events, generation constraints, fossil and renewable fuels prices. Future work suggests expanding the model to consider fossil fuel and renewable energy prices, exploring the impact of trading volume, integrating weather data, evaluating across multiple markets, and optimizing model configurations for enhanced accuracy and robustness. This research contributes a benchmark for MCP forecasting in Ireland and offers insights for energy market stakeholders.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Uncontrolled Keywords:	Day-ahead Electricity Market; Market Clearing Price (MCP); Long short-term memory (LSTM); Multi-Layer Perceptron; ISEM
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electricity Supply Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	18 May 2025 15:04
Last Modified:	18 May 2025 15:04
URI:	https://norma.ncirl.ie/id/eprint/7580

Actions (login required)

View Item