Predictive Modelling of Low Tariff Energy Consumption in UK

Patne, Sanket Sanjay (2023) Predictive Modelling of Low Tariff Energy Consumption in UK. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Deep learning applications are constantly evolving and it has seen more innovations in 2023 alone than ever in the past. In such an ever changing scenario its application in commercial sectors like load prediction can also not fall behind, but unlike traditional machine learning techniques these new techniques should be more widely applicable in scope for global adoption. This is a compact study towards determining which neural networks are best suited for load prediction as compared to the ones explored in previous studies that include LSTM, Bidirectional LSTM (Bi-LSTM), Multi-output Gaussian processes (MGP), etc. With the custom data formulated, best results were achieved by the CNN model with a MAPE values of 28.0559 percent and Variance Score of 0.0389. The best model was compared against models developed from the RNN and LSTM algorithms.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Mulwa, Catherine UNSPECIFIED
Uncontrolled Keywords:	Load prediction; Neural Networks; Hyper Parameter Tuning; Low tariff energy consumption
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:	20 May 2025 13:55
Last Modified:	20 May 2025 13:55
URI:	https://norma.ncirl.ie/id/eprint/7587

Actions (login required)

View Item