Forecasting Residential Energy Consumption: A Case Study for Greece

Dimitra Kouvara, Dimitrios Vogiatzis

2023

Abstract

Residential energy consumption forecasting has immense value in energy efficiency and sustainability. In the current work we tried to forecast energy consumption on residences in Athens, Greece. As a proof of concept, smart sensors were installed into two residences that recorded energy consumption, as well as indoors environmental variables (humidity and temperature). It should be noted that the data set was collected during the COVID-19 pandemic. Moreover, we integrated weather data from a public weather site. A dashboard was designed to facilitate monitoring of the sensors’ data. We addressed various issues related to data quality and then we tried different models to forecast daily energy consumption. In particular, LSTM neural networks, ARIMA, SARIMA, SARIMAX and Facebook (FB) Prophet were tested. Overall SARIMA and FB Prophet had the best performance.

Paper Citation

in Harvard Style

Kouvara D. and Vogiatzis D. (2023). Forecasting Residential Energy Consumption: A Case Study for Greece. In Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-648-4, SciTePress, pages 484-492. DOI: 10.5220/0011854500003467

in Bibtex Style

@conference{iceis23,
author={Dimitra Kouvara and Dimitrios Vogiatzis},
title={Forecasting Residential Energy Consumption: A Case Study for Greece},
booktitle={Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2023},
pages={484-492},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011854500003467},
isbn={978-989-758-648-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Forecasting Residential Energy Consumption: A Case Study for Greece
SN - 978-989-758-648-4
AU - Kouvara D.
AU - Vogiatzis D.
PY - 2023
SP - 484
EP - 492
DO - 10.5220/0011854500003467
PB - SciTePress