An Attention-Based Deep Learning Approach for Forecasting Electricity Prices in Real-Time Electricity Markets

do Carmo Junior, Jose Eustaquio

An Attention-Based Deep Learning Approach for Forecasting Electricity Prices in Real-Time Electricity Markets

dc.contributor.advisor	Zareipour, Hamidreza
dc.contributor.author	do Carmo Junior, Jose Eustaquio
dc.contributor.committeemember	de Souza, Roberto Medeiros
dc.contributor.committeemember	Papalexiou, Simon Michael
dc.date	2025-06-05
dc.date.accessioned	2025-01-16T21:30:11Z
dc.date.available	2025-01-16T21:30:11Z
dc.date.issued	2025-01-15
dc.description.abstract	Real-time electricity markets are characterized by irregular and sudden price swings, leading to high price volatility and significant uncertainties for market participants. Accurate and informative electricity price forecasts are essential to reduce these uncertainties and enable more effective decision-making in energy generation, consumption, strategy planning, and risk management. This thesis presents a new forecasting framework for electricity prices in real-time markets, leveraging the capabilities of deep learning and advanced feature engineering. The proposed methodology integrates the Temporal Fusion Transformer (TFT), a deep learning model applied to time series forecasting, with dynamic clustering techniques to enhance forecasting accuracy. This is done by combining Hierarchical Density-Based Spatial Clustering of Applications with Noise and Dynamic Time Warping to cluster generators based on attributes such as geographical location, fuel type, installed capacity, and generation patterns. These clusters provide new covariates for forecasting models, enabling the method to adapt to the unique characteristics of any electricity market. The effectiveness of the proposed framework is demonstrated through a case study of the Ontario electricity market, where the methodology outperforms the forecasts of the system operator in terms of average error, accuracy, precision, and recall across a six-hour forecast horizon. This study underlines the framework's versatility and offers valuable insights into electricity price behavior, aiding market participants in mitigating risks and optimizing energy strategies.
dc.identifier.citation	do Carmo, J. (2025). An attention-based deep learning approach for forecasting electricity prices in real-time electricity markets (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca.
dc.identifier.uri	https://hdl.handle.net/1880/120482
dc.language.iso	en
dc.publisher.faculty	Schulich School of Engineering
dc.publisher.institution	University of Calgary
dc.rights	University of Calgary graduate students retain copyright ownership and moral rights for their thesis. You may use this material in any way that is permitted by the Copyright Act or through licensing that has been assigned to the document. For uses that are not allowable under copyright legislation or licensing, you are required to seek permission.
dc.subject	Real-time electricity markets
dc.subject	Electricity price forecasting
dc.subject	Price volatility
dc.subject	Deep learning
dc.subject.classification	Engineering--Electronics and Electrical
dc.title	An Attention-Based Deep Learning Approach for Forecasting Electricity Prices in Real-Time Electricity Markets
dc.type	master thesis
thesis.degree.discipline	Engineering – Electrical & Computer
thesis.degree.grantor	University of Calgary
thesis.degree.name	Master of Science (MSc)
ucalgary.thesis.accesssetbystudent	I do not require a thesis withhold – my thesis will have open access and can be viewed and downloaded publicly as soon as possible.