Improving load forecast in energy markets during COVID-19

Ziyun Wang; Hao Wang

doi:10. 1145/3486611.3486648

Improving load forecast in energy markets during COVID-19

Ziyun Wang, Hao Wang

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

Abstract

The abrupt outbreak of the COVID-19 pandemic was the most significant event in 2020, which had profound and lasting impacts across the world. Studies on energy markets observed a decline in energy demand and changes in energy consumption behaviors during COVID-19. However, as an essential part of system operation, how the load forecasting performs amid COVID-19 is not well understood. This paper aims to bridge the research gap by systematically evaluating models and features that can be used to improve the load forecasting performance amid COVID-19. Using real-world data from the New York Independent System Operator, our analysis employs three deep learning models and adopts both novel COVID-related features as well as classical weather-related features. We also propose simulating the stay-at-home situation with pre-stay-at-home weekend data and demonstrate its effectiveness in improving load forecasting accuracy during COVID-19.

Original language	English
Title of host publication	Proceedings of the 2021 - ACM International Conference on Systems for Energy-Efficient Built Environments
Editors	Omprakash Gnawali, Zoltan Nagy
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Pages	168–171
Number of pages	4
ISBN (Electronic)	9781450391146
DOIs	https://doi.org/10. 1145/3486611.3486648
Publication status	Published - 2021
Event	ACM Conference on Embedded Systems for Energy-Efficient Buildings 2021 - Coimbra, Portugal Duration: 17 Nov 2021 → 18 Nov 2021 Conference number: 8th https://dl.acm.org/doi/proceedings/10.1145/3486611

Conference

Conference	ACM Conference on Embedded Systems for Energy-Efficient Buildings 2021
Abbreviated title	BuildSys’21
Country/Territory	Portugal
City	Coimbra
Period	17/11/21 → 18/11/21
Internet address	https://dl.acm.org/doi/proceedings/10.1145/3486611

UN SDGs

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

Access to Document

10. 1145/3486611.3486648

Cite this

@inproceedings{a94a583dbc594e8495497bb89f53031a,

title = "Improving load forecast in energy markets during COVID-19",

abstract = "The abrupt outbreak of the COVID-19 pandemic was the most significant event in 2020, which had profound and lasting impacts across the world. Studies on energy markets observed a decline in energy demand and changes in energy consumption behaviors during COVID-19. However, as an essential part of system operation, how the load forecasting performs amid COVID-19 is not well understood. This paper aims to bridge the research gap by systematically evaluating models and features that can be used to improve the load forecasting performance amid COVID-19. Using real-world data from the New York Independent System Operator, our analysis employs three deep learning models and adopts both novel COVID-related features as well as classical weather-related features. We also propose simulating the stay-at-home situation with pre-stay-at-home weekend data and demonstrate its effectiveness in improving load forecasting accuracy during COVID-19.",

author = "Ziyun Wang and Hao Wang",

year = "2021",

doi = "10. 1145/3486611.3486648",

language = "English",

pages = "168–171",

editor = "Omprakash Gnawali and Zoltan Nagy",

booktitle = "Proceedings of the 2021 - ACM International Conference on Systems for Energy-Efficient Built Environments",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

note = "ACM Conference on Embedded Systems for Energy-Efficient Buildings 2021, BuildSys{\textquoteright}21 ; Conference date: 17-11-2021 Through 18-11-2021",

url = "https://dl.acm.org/doi/proceedings/10.1145/3486611",

}

Wang, Z & Wang, H 2021, Improving load forecast in energy markets during COVID-19. in O Gnawali & Z Nagy (eds), Proceedings of the 2021 - ACM International Conference on Systems for Energy-Efficient Built Environments. Association for Computing Machinery (ACM), New York NY USA, pp. 168–171, ACM Conference on Embedded Systems for Energy-Efficient Buildings 2021, Coimbra, Portugal, 17/11/21. https://doi.org/10. 1145/3486611.3486648

Improving load forecast in energy markets during COVID-19. / Wang, Ziyun; Wang, Hao.

Proceedings of the 2021 - ACM International Conference on Systems for Energy-Efficient Built Environments. ed. / Omprakash Gnawali; Zoltan Nagy. New York NY USA : Association for Computing Machinery (ACM), 2021. p. 168–171.

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

TY - GEN

T1 - Improving load forecast in energy markets during COVID-19

AU - Wang, Ziyun

AU - Wang, Hao

N1 - Conference code: 8th

PY - 2021

Y1 - 2021

N2 - The abrupt outbreak of the COVID-19 pandemic was the most significant event in 2020, which had profound and lasting impacts across the world. Studies on energy markets observed a decline in energy demand and changes in energy consumption behaviors during COVID-19. However, as an essential part of system operation, how the load forecasting performs amid COVID-19 is not well understood. This paper aims to bridge the research gap by systematically evaluating models and features that can be used to improve the load forecasting performance amid COVID-19. Using real-world data from the New York Independent System Operator, our analysis employs three deep learning models and adopts both novel COVID-related features as well as classical weather-related features. We also propose simulating the stay-at-home situation with pre-stay-at-home weekend data and demonstrate its effectiveness in improving load forecasting accuracy during COVID-19.

AB - The abrupt outbreak of the COVID-19 pandemic was the most significant event in 2020, which had profound and lasting impacts across the world. Studies on energy markets observed a decline in energy demand and changes in energy consumption behaviors during COVID-19. However, as an essential part of system operation, how the load forecasting performs amid COVID-19 is not well understood. This paper aims to bridge the research gap by systematically evaluating models and features that can be used to improve the load forecasting performance amid COVID-19. Using real-world data from the New York Independent System Operator, our analysis employs three deep learning models and adopts both novel COVID-related features as well as classical weather-related features. We also propose simulating the stay-at-home situation with pre-stay-at-home weekend data and demonstrate its effectiveness in improving load forecasting accuracy during COVID-19.

U2 - 10. 1145/3486611.3486648

DO - 10. 1145/3486611.3486648

M3 - Conference Paper

SP - 168

EP - 171

BT - Proceedings of the 2021 - ACM International Conference on Systems for Energy-Efficient Built Environments

A2 - Gnawali, Omprakash

A2 - Nagy, Zoltan

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

T2 - ACM Conference on Embedded Systems for Energy-Efficient Buildings 2021

Y2 - 17 November 2021 through 18 November 2021

ER -