Tools
Tools
Chavan, Abhilash Anil (2019) Water, Gas & Electricity Consumption Behaviour Forecasting. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (650kB) | Preview |
Abstract
Water, gas and electricity are precious resources available to us, and fresh drinking water has limited availability. Daily millions of households and industries are supplied with these resources and forecasting the consumption need would help the managing authorities regularize the working timetables for these supplies. This study is based on the hypothesis that there are peaks and drops in the consumers consumption behaviour and knowing those needs would help management in providing the consumers with a tailored plan for usage, reducing the cost of supply and labour. For accurately forecasting the consumption need LSTM is implemented as LSTM was designed for forecasting time series data, and for evaluation of the model RMSE values were checked rather than the accuracy as RMSE gives clear idea how far the predicted values are from actual values. The data used in this study is a time series data available from the smart meters at an 30min time interval. The implemented model achieved 0.21litres RMSE value and outperformed every other model. With this low error rate, the forecasted values would help authorities detect anomalies in the consumption and develop a plan of action.
| 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: | Caoimhe Ní Mhaicín |
| Date Deposited: | 14 Oct 2019 09:19 |
| Last Modified: | 14 Oct 2019 09:19 |
| URI: | https://norma.ncirl.ie/id/eprint/3862 |
Actions (login required)
 |
View Item |