NORMA eResearch @NCI Library

The Prediction and Optimisation of Smart Energy Usage through Machine Learning Recommendations

McGrane, Mark (2021) The Prediction and Optimisation of Smart Energy Usage through Machine Learning Recommendations. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (3MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (7MB) | Preview


Even though renewable energy does not have the same limited supply as fossil fuels, it is still a commodity that needs efficient management to maintain an uninterrupted supply. The development of the Colour Code My Energy (CCME) Recommder algorithm provides personalised recommendations to users on how their current usage compares to an optimum value. Armed with this knowledge, the premise occupants can make instant adjustments and recalibrations of their habits when needed. Applying a Deep Neural Network(DNN), outcome predictions of the algorithm were retrospectively applied to the Hourly Usage Energy (HUE) dataset and demonstrated how the algorithm builds a knowledge base of best behaviours over time, with improvements on the quality of recommendations as it learns. Over time, the algorithm substantially increased its knowledgeable recommendations. Beginning with the ability to recommend 20% of reads, this increased to 80% by the end of the 3rd year. The DNN attained a peak accuracy of 0.98. Also explored within the project was the prediction of daily energy usage for a premise through multiple regression algorithms with Root Mean Squared Error (RMSE) scores of under 0.05 achieved in two out of the three models. Results of this nature facilitate energy efficiency at the consumer and supply level.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 09 Dec 2021 11:15
Last Modified: 09 Dec 2021 11:15

Actions (login required)

View Item View Item