Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM)

Noman Shabbir; Roya Ahmadiahangar; Argo Rosin; Oleksandr Husev; Tanel Jalakas; João Martins

doi:10.1109/SEGE59172.2023.10274596

Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM)

Noman Shabbir, Roya Ahmadiahangar, Argo Rosin, Oleksandr Husev, Tanel Jalakas, João Martins

DEE - Departamento de Engenharia Electrotécnica e de Computadores

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Citations (Scopus)

Abstract

In modern power systems, load forecasting has become a crucial aspect. These advanced power systems demand flexibility, efficient operation, scalability, and better resource management. Future smart homes will incorporate both AC and DC distribution systems for energy efficiency. Therefore, accurate load forecasting is imperative. However, it can be a difficult task as it includes various factors such as the number of devices in a household, their diversity, time, location, season, and the behavior of the occupants. In this study, a short-term residential DC load forecasting model based on a deep learning algorithm called long-short-term memory networks (LSTM) has been developed. The model is trained using data from a household in Estonia and is evaluated by forecasting the next day's load. The simulation results provide quite an accurate forecasting with root mean square error (RMSE) is around 0.15 kW.

Original language	English
Title of host publication	SEGE 2023
Subtitle of host publication	2023 IEEE 11th International Conference on Smart Energy Grid Engineering
Place of Publication	Massachusetts
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	131-136
Number of pages	6
ISBN (Electronic)	979-8-3503-4071-6
ISBN (Print)	979-8-3503-4072-3
DOIs	https://doi.org/10.1109/SEGE59172.2023.10274596
Publication status	Published - 2023
Event	11th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2023 - Oshawa, Canada Duration: 13 Aug 2023 → 15 Aug 2023

Publication series

Name	IEEE International Conference on Smart Energy Grid Engineering (SEGE)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)	2575-2677
ISSN (Electronic)	2575-2693

Conference

Conference	11th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2023
Country/Territory	Canada
City	Oshawa
Period	13/08/23 → 15/08/23

Keywords

DC loads
deep learning
load forecasting
machine learning
residential load

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/SEGE59172.2023.10274596

Cite this

Shabbir, N., Ahmadiahangar, R., Rosin, A., Husev, O., Jalakas, T., & Martins, J. (2023). Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM). In SEGE 2023: 2023 IEEE 11th International Conference on Smart Energy Grid Engineering (pp. 131-136). (IEEE International Conference on Smart Energy Grid Engineering (SEGE)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/SEGE59172.2023.10274596

Shabbir, Noman ; Ahmadiahangar, Roya ; Rosin, Argo et al. / Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM). SEGE 2023: 2023 IEEE 11th International Conference on Smart Energy Grid Engineering. Massachusetts : Institute of Electrical and Electronics Engineers (IEEE), 2023. pp. 131-136 (IEEE International Conference on Smart Energy Grid Engineering (SEGE)).

@inproceedings{c181fc8d82614623825ebfd5fb73bfcd,

title = "Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM)",

abstract = "In modern power systems, load forecasting has become a crucial aspect. These advanced power systems demand flexibility, efficient operation, scalability, and better resource management. Future smart homes will incorporate both AC and DC distribution systems for energy efficiency. Therefore, accurate load forecasting is imperative. However, it can be a difficult task as it includes various factors such as the number of devices in a household, their diversity, time, location, season, and the behavior of the occupants. In this study, a short-term residential DC load forecasting model based on a deep learning algorithm called long-short-term memory networks (LSTM) has been developed. The model is trained using data from a household in Estonia and is evaluated by forecasting the next day's load. The simulation results provide quite an accurate forecasting with root mean square error (RMSE) is around 0.15 kW.",

keywords = "DC loads, deep learning, load forecasting, machine learning, residential load",

author = "Noman Shabbir and Roya Ahmadiahangar and Argo Rosin and Oleksandr Husev and Tanel Jalakas and Jo{\~a}o Martins",

note = "info:eu-repo/grantAgreement/EC/H2020/856602/EU# Funding Information: This work was supported by the Estonian Research Council grant PSG 739. Publisher Copyright: {\textcopyright} 2023 IEEE.; 11th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2023 ; Conference date: 13-08-2023 Through 15-08-2023",

year = "2023",

doi = "10.1109/SEGE59172.2023.10274596",

language = "English",

isbn = "979-8-3503-4072-3",

series = "IEEE International Conference on Smart Energy Grid Engineering (SEGE)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "131--136",

booktitle = "SEGE 2023",

address = "United States",

}

Shabbir, N, Ahmadiahangar, R, Rosin, A, Husev, O, Jalakas, T & Martins, J 2023, Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM). in SEGE 2023: 2023 IEEE 11th International Conference on Smart Energy Grid Engineering. IEEE International Conference on Smart Energy Grid Engineering (SEGE), Institute of Electrical and Electronics Engineers (IEEE), Massachusetts, pp. 131-136, 11th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2023, Oshawa, Canada, 13/08/23. https://doi.org/10.1109/SEGE59172.2023.10274596

Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM). / Shabbir, Noman; Ahmadiahangar, Roya; Rosin, Argo et al.
SEGE 2023: 2023 IEEE 11th International Conference on Smart Energy Grid Engineering. Massachusetts: Institute of Electrical and Electronics Engineers (IEEE), 2023. p. 131-136 (IEEE International Conference on Smart Energy Grid Engineering (SEGE)).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM)

AU - Shabbir, Noman

AU - Ahmadiahangar, Roya

AU - Rosin, Argo

AU - Husev, Oleksandr

AU - Jalakas, Tanel

AU - Martins, João

PY - 2023

Y1 - 2023

N2 - In modern power systems, load forecasting has become a crucial aspect. These advanced power systems demand flexibility, efficient operation, scalability, and better resource management. Future smart homes will incorporate both AC and DC distribution systems for energy efficiency. Therefore, accurate load forecasting is imperative. However, it can be a difficult task as it includes various factors such as the number of devices in a household, their diversity, time, location, season, and the behavior of the occupants. In this study, a short-term residential DC load forecasting model based on a deep learning algorithm called long-short-term memory networks (LSTM) has been developed. The model is trained using data from a household in Estonia and is evaluated by forecasting the next day's load. The simulation results provide quite an accurate forecasting with root mean square error (RMSE) is around 0.15 kW.

AB - In modern power systems, load forecasting has become a crucial aspect. These advanced power systems demand flexibility, efficient operation, scalability, and better resource management. Future smart homes will incorporate both AC and DC distribution systems for energy efficiency. Therefore, accurate load forecasting is imperative. However, it can be a difficult task as it includes various factors such as the number of devices in a household, their diversity, time, location, season, and the behavior of the occupants. In this study, a short-term residential DC load forecasting model based on a deep learning algorithm called long-short-term memory networks (LSTM) has been developed. The model is trained using data from a household in Estonia and is evaluated by forecasting the next day's load. The simulation results provide quite an accurate forecasting with root mean square error (RMSE) is around 0.15 kW.

KW - DC loads

KW - deep learning

KW - load forecasting

KW - machine learning

KW - residential load

UR - http://www.scopus.com/inward/record.url?scp=85175254142&partnerID=8YFLogxK

U2 - 10.1109/SEGE59172.2023.10274596

DO - 10.1109/SEGE59172.2023.10274596

M3 - Conference contribution

AN - SCOPUS:85175254142

SN - 979-8-3503-4072-3

T3 - IEEE International Conference on Smart Energy Grid Engineering (SEGE)

SP - 131

EP - 136

BT - SEGE 2023

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Massachusetts

T2 - 11th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2023

Y2 - 13 August 2023 through 15 August 2023

ER -

Shabbir N, Ahmadiahangar R, Rosin A, Husev O, Jalakas T, Martins J. Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM). In SEGE 2023: 2023 IEEE 11th International Conference on Smart Energy Grid Engineering. Massachusetts: Institute of Electrical and Electronics Engineers (IEEE). 2023. p. 131-136. (IEEE International Conference on Smart Energy Grid Engineering (SEGE)). doi: 10.1109/SEGE59172.2023.10274596

Residential DC Load Forecasting Using Long Short-term Memory Network (LSTM)

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this