Optimizing Energy Price Forecasting with Hybrid Deep Learning

Shetye, Shashank Rahul (2025) Optimizing Energy Price Forecasting with Hybrid Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (955kB) | Preview

Abstract

The precise forecasting of energy prices is pertinent to the smooth operation of energy markets, strategic considerations, and, hence, the integration of renewable sources in an increasingly volatile energy market. The research presents a new hybrid deep learning architecture for predicting the hourly market electricity price that synergistically combines Convolutional Neural Networks for spatial temporal feature extraction and Bidirectional Long Short-Term Memory networks for coding both forward and backward temporal dependencies into price volatility. The model considers multi-dimensional datasets containing historical electricity price data, energy consumption data, and comprehensive weather factors encompassing temperature, humidity, wind speed, and precipitation. Overall, the methodology discussed in this paper mainly focused on a hybrid approach: the study conduct numerous experimental evaluations where the CNN-BiLSTM model was compared to individual Gated Recurrent Unit (GRU) and LSTM models using the same datasets and metrics. Meanwhile, this work contributes to furthering the energy price forecasting techniques and can give able support to energy traders, market operators, and utility companies aiming at trying robust forecasting solutions to support their own strategic decisions in weather dependent electricity markets.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jameel Syed, Muslim UNSPECIFIED
Uncontrolled Keywords:	Electricity price forecasting; hybrid deep learning; CNN-BiLSTM; weather data integration; comparative analysis; GRU; LSTM; energy markets; bidirectional processing
Subjects:	T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electricity Supply H Social Sciences > HC Economic History and Conditions > Natural resources > Power resources > Energy consumption 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:	03 Jul 2026 10:59
Last Modified:	03 Jul 2026 10:59
URI:	https://norma.ncirl.ie/id/eprint/9462

Actions (login required)

View Item