The Suitability of Sarimax Time Series and LSTM Neural Networks for Predicting Electricity Consumption in Ireland

Connolly, Edmond (2021) The Suitability of Sarimax Time Series and LSTM Neural Networks for Predicting Electricity Consumption in Ireland. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The recent decade has focused attention more than ever before on the increasing carbon emissions and detrimental effect energy consumption has on the world we live in. Smart Grids have brought a new level of control and a new capacity to understanding this activity. A vital component of addressing energy consumption is the ability to accurately forecast it. Through this mitigating waste and anticipating the effect of future government policies may be achieved. This research will develop two predictive models and examine the capability of using meteorological data to forecast the daily electricity consumption in the Republic of Ireland for a two month period in 2020. Input features are historical energy consumption and meteorological data from the period 2014 to the end of 2020. It comprises 2558 rows of 64 columns of data. A Sarimax time series and a Long Short Term Memory (LSTM) Neural Network were employed to forecast electricity demand in the short term (60 days). The Long Short Term Memory Network achieved a higher degree of accuracy in forecasting the electricity consumption of the test period than the Sarimax model achieved.

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:	15 Nov 2021 17:06
Last Modified:	15 Nov 2021 17:06
URI:	https://norma.ncirl.ie/id/eprint/5143

Actions (login required)

View Item