NORMA eResearch @NCI Library

Short-Term Electrical Load Forecasting for Irish Supermarkets with Weather Forecast Data

Orr, Martin (2021) Short-Term Electrical Load Forecasting for Irish Supermarkets with Weather Forecast Data. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
Preview
PDF (Configuration manual)
Download (2MB) | Preview

Abstract

With the roll out of smart meters there is great potential to better understand how and when our buildings use energy. This presents an opportunity to rethink how we purchase our energy and also to have a better grasp on our electricity grids. Much of the research in short term electrical load forecasting has been carried out using historic weather data. This works quite well but is not able to account for sudden changes in the weather. This study describes the differences in model results that are found from using both weather forecast and historic data and gives a sense of the value of acquiring weather data. As there can also be sudden level changes in energy load profiles for various reasons it is important that energy prediction tools are able to identify these changes and predict accordingly. This study takes a look at convolutional neural networks as a method of doing this as they have proven effective in identifying shapes in image data. The key findings in this report are that weather forecast data is marginally better than historic data for electricity demand forecasting and that convolutional neural networks are very effective in predicting 30 minute values 24 hours ahead but their predictions for a full day are around the same strength as a linear regression model. There is scope for further research with convolutional neural networks.

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
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Electricity Supply
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Clara Chan
Date Deposited: 11 Dec 2021 11:35
Last Modified: 11 Dec 2021 11:35
URI: https://norma.ncirl.ie/id/eprint/5205

Actions (login required)

View Item View Item