Heat demand prediction: a real-life data model vs simulated data model comparison

Naik, K. and Ianakiev, A. ORCID: 0000-0002-1413-8110, 2021. Heat demand prediction: a real-life data model vs simulated data model comparison. Energy Reports. ISSN 2352-4847 (Forthcoming)

[img] Text
1476772_Ianakiev.pdf - Post-print
Restricted to Repository staff only

Download (812kB)

Abstract

In the recent years machine learning algorithms have developed further and various applications are taking advantage of this advancement. Modern machine learning is now used in district heating for more precise and realistic heat demand prediction. Machine learning methods like Artificial Neural Network (ANN), Linear Regression (LR), and Decision Tree (DT) are commonly adopted in heat demand prediction to produce more accurate results. This research paper compares the performance of several machine learning methods on different datasets generated by the combination of simulations and real-life data collected from a local district heating site in Nottingham. The result shows that Linear Regression generates better prediction than Artificial Neural Network and Decision Tree, for dataset generated using simulator, whereas Decision Tree performs best for real-life data.

Item Type: Journal article
Publication Title: Energy Reports
Creators: Naik, K. and Ianakiev, A.
Publisher: Elsevier
Date: 5 October 2021
ISSN: 2352-4847
Identifiers:
NumberType
1476772Other
Divisions: Schools > School of Architecture, Design and the Built Environment
Record created by: Jeremy Silvester
Date Added: 08 Oct 2021 17:00
Last Modified: 08 Oct 2021 17:00
URI: http://irep.ntu.ac.uk/id/eprint/44377

Actions (login required)

Edit View Edit View

Views

Views per month over past year

Downloads

Downloads per month over past year