Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana

Francis Kwabena Oduro-Gyimah; Maxwell Akwasi Boateng; Usman Abdallah; Kwame Osei Boateng; Daniel M. O. Adjin; Julius Quarshie Azasoo

doi:10.1109/icsiot55070.2021.00016

Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana

Francis Kwabena Oduro-Gyimah, Maxwell Akwasi Boateng, Usman Abdallah, Kwame Osei Boateng, Daniel M. O. Adjin, Julius Quarshie Azasoo

Research output: Contribution to Book/Report › Conference Contribution › peer-review

Abstract

The study considered providing the best model among competing models for forecasting electricity load demand. Data from Helios Towers was used for this purpose. The study applied the Autoregressive Integrated Moving Average (ARIMA) model and residuals from the model tested for heteroscedasticity. The residuals were found to be heteroscedastic, thus, the Autoregressive Conditional Heteroscedastic (ARCH) and the Generalized Autoregressive Conditional Heteroscedastic (GARCH) models were applied to the data set. Competing models namely, ARCH (1), ARCH (2), ARCH (3) and GARCH (1, 1) models were fitted to the demand data under study. Based on the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) approach, the best heteroscedastic model was the ARCH (2). The study thus used the ARIMA (3, 0, 4)-ARCH (2) model for a two-point forecast of electricity load demand.

Original language	English
Title of host publication	2021 International Conference on Cyber Security and Internet of Things
Subtitle of host publication	ICSIoT 2021
Publisher	IEEE
Pages	37-42
ISBN (Print)	978-1-6654-7878-6
DOIs	https://doi.org/10.1109/icsiot55070.2021.00016
Publication status	Published - 11 Feb 2022
Event	2021 International Conference on Cyber Security and Internet of Things - , France Duration: 15 Dec 2021 → 17 Dec 2021

Publication series

Name	2021 International Conference on Cyber Security and Internet of Things (ICSIoT)
Publisher	IEEE

Conference

Conference	2021 International Conference on Cyber Security and Internet of Things
Abbreviated title	ICSIoT
Country/Territory	France
Period	15/12/21 → 17/12/21

Access to Document

10.1109/icsiot55070.2021.00016

Cite this

Oduro-Gyimah, F. K., Boateng, M. A., Abdallah, U., Boateng, K. O., Adjin, D. M. O., & Azasoo, J. Q. (2022). Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana. In 2021 International Conference on Cyber Security and Internet of Things: ICSIoT 2021 (pp. 37-42). (2021 International Conference on Cyber Security and Internet of Things (ICSIoT)). IEEE. https://doi.org/10.1109/icsiot55070.2021.00016

@inproceedings{9f14e9f98d1240108498bfb0ae53aac3,

title = "Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana",

abstract = "The study considered providing the best model among competing models for forecasting electricity load demand. Data from Helios Towers was used for this purpose. The study applied the Autoregressive Integrated Moving Average (ARIMA) model and residuals from the model tested for heteroscedasticity. The residuals were found to be heteroscedastic, thus, the Autoregressive Conditional Heteroscedastic (ARCH) and the Generalized Autoregressive Conditional Heteroscedastic (GARCH) models were applied to the data set. Competing models namely, ARCH (1), ARCH (2), ARCH (3) and GARCH (1, 1) models were fitted to the demand data under study. Based on the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) approach, the best heteroscedastic model was the ARCH (2). The study thus used the ARIMA (3, 0, 4)-ARCH (2) model for a two-point forecast of electricity load demand.",

author = "Oduro-Gyimah, {Francis Kwabena} and Boateng, {Maxwell Akwasi} and Usman Abdallah and Boateng, {Kwame Osei} and Adjin, {Daniel M. O.} and Azasoo, {Julius Quarshie}",

year = "2022",

month = feb,

day = "11",

doi = "10.1109/icsiot55070.2021.00016",

language = "English",

isbn = "978-1-6654-7878-6",

series = "2021 International Conference on Cyber Security and Internet of Things (ICSIoT)",

publisher = "IEEE",

pages = "37--42",

booktitle = "2021 International Conference on Cyber Security and Internet of Things",

note = "2021 International Conference on Cyber Security and Internet of Things, ICSIoT ; Conference date: 15-12-2021 Through 17-12-2021",

}

Oduro-Gyimah, FK, Boateng, MA, Abdallah, U, Boateng, KO, Adjin, DMO & Azasoo, JQ 2022, Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana. in 2021 International Conference on Cyber Security and Internet of Things: ICSIoT 2021. 2021 International Conference on Cyber Security and Internet of Things (ICSIoT), IEEE, pp. 37-42, 2021 International Conference on Cyber Security and Internet of Things, France, 15/12/21. https://doi.org/10.1109/icsiot55070.2021.00016

Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana. / Oduro-Gyimah, Francis Kwabena; Boateng, Maxwell Akwasi; Abdallah, Usman et al.
2021 International Conference on Cyber Security and Internet of Things: ICSIoT 2021. IEEE, 2022. p. 37-42 (2021 International Conference on Cyber Security and Internet of Things (ICSIoT)).

Research output: Contribution to Book/Report › Conference Contribution › peer-review

TY - GEN

T1 - Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana

AU - Oduro-Gyimah, Francis Kwabena

AU - Boateng, Maxwell Akwasi

AU - Abdallah, Usman

AU - Boateng, Kwame Osei

AU - Adjin, Daniel M. O.

AU - Azasoo, Julius Quarshie

PY - 2022/2/11

Y1 - 2022/2/11

N2 - The study considered providing the best model among competing models for forecasting electricity load demand. Data from Helios Towers was used for this purpose. The study applied the Autoregressive Integrated Moving Average (ARIMA) model and residuals from the model tested for heteroscedasticity. The residuals were found to be heteroscedastic, thus, the Autoregressive Conditional Heteroscedastic (ARCH) and the Generalized Autoregressive Conditional Heteroscedastic (GARCH) models were applied to the data set. Competing models namely, ARCH (1), ARCH (2), ARCH (3) and GARCH (1, 1) models were fitted to the demand data under study. Based on the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) approach, the best heteroscedastic model was the ARCH (2). The study thus used the ARIMA (3, 0, 4)-ARCH (2) model for a two-point forecast of electricity load demand.

AB - The study considered providing the best model among competing models for forecasting electricity load demand. Data from Helios Towers was used for this purpose. The study applied the Autoregressive Integrated Moving Average (ARIMA) model and residuals from the model tested for heteroscedasticity. The residuals were found to be heteroscedastic, thus, the Autoregressive Conditional Heteroscedastic (ARCH) and the Generalized Autoregressive Conditional Heteroscedastic (GARCH) models were applied to the data set. Competing models namely, ARCH (1), ARCH (2), ARCH (3) and GARCH (1, 1) models were fitted to the demand data under study. Based on the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) approach, the best heteroscedastic model was the ARCH (2). The study thus used the ARIMA (3, 0, 4)-ARCH (2) model for a two-point forecast of electricity load demand.

U2 - 10.1109/icsiot55070.2021.00016

DO - 10.1109/icsiot55070.2021.00016

M3 - Conference Contribution

SN - 978-1-6654-7878-6

T3 - 2021 International Conference on Cyber Security and Internet of Things (ICSIoT)

SP - 37

EP - 42

BT - 2021 International Conference on Cyber Security and Internet of Things

PB - IEEE

T2 - 2021 International Conference on Cyber Security and Internet of Things

Y2 - 15 December 2021 through 17 December 2021

ER -

Oduro-Gyimah FK, Boateng MA, Abdallah U, Boateng KO, Adjin DMO, Azasoo JQ. Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana. In 2021 International Conference on Cyber Security and Internet of Things: ICSIoT 2021. IEEE. 2022. p. 37-42. (2021 International Conference on Cyber Security and Internet of Things (ICSIoT)). doi: 10.1109/icsiot55070.2021.00016

Forecasting Electricity Load of Network Infrastructure Sharing Mobile Sites in Ghana

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this