Citation: Skala, R.; Elgalhud,
M.A.T.A.; Grolinger, K.; Mir, S.
Interval Load Forecasting for
Individual Households in the
Presence of Electric Vehicle Charging.
Energies 2023, 16, 4093. https://
doi.org/10.3390/en16104093
Academic Editors: Antonio
Gabaldón, María Carmen
Ruiz-Abellón and Luis Alfredo
Fernández-Jiménez
Received: 20 March 2023
Revised: 8 May 2023
Accepted: 10 May 2023
Published: 15 May 2023
Copyright: © 2023 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
energies
Article
Interval Load Forecasting for Individual Households in the
Presence of Electric Vehicle Charging
Raiden Skala
1
, Mohamed Ahmed T. A. Elgalhud
1
, Katarina Grolinger
1,
* and Syed Mir
2
1
Department of Electrical and Computer Engineering, Western University, London, ON N6A 5B9, Canada
2
London Hydro, London, ON N6A 4H6, Canada
* Correspondence: kgroling@uwo.ca; Tel.: +1-519-661-2111 (ext. 81407)
Abstract: The transition to Electric Vehicles (EV) in place of traditional internal combustion engines
is increasing societal demand for electricity. The ability to integrate the additional demand from EV
charging into forecasting electricity demand is critical for maintaining the reliability of electricity
generation and distribution. Load forecasting studies typically exclude households with home EV
charging, focusing on offices, schools, and public charging stations. Moreover, they provide point
forecasts which do not offer information about prediction uncertainty. Consequently, this paper
proposes the Long Short-Term Memory Bayesian Neural Networks (LSTM-BNNs) for household
load forecasting in presence of EV charging. The approach takes advantage of the LSTM model
to capture the time dependencies and uses the dropout layer with Bayesian inference to generate
prediction intervals. Results show that the proposed LSTM-BNNs achieve accuracy similar to point
forecasts with the advantage of prediction intervals. Moreover, the impact of lockdowns related to the
COVID-19 pandemic on the load forecasting model is examined, and the analysis shows that there is
no major change in the model performance as, for the considered households, the randomness of the
EV charging outweighs the change due to pandemic.
Keywords: residential load forecasting; Long Short-Term Memory; Bayesian Neural Network;
Bayesian optimization; interval forecasting; EV charging; analysis of variance
1. Introduction
Affordable and reliable sources of electricity enable the sustainable growth of strong
economies and can improve the average person’s quality of life [1] by providing reliable
access to appliances, medical equipment, communication, entertainment, and other devices.
The dependence on power grids to provide electricity is increasing due to the continuous
integration of novel electronic devices into every aspect of modern life [2] as these devices
rely on a reliable source of electricity. The mainstream adoption of electric vehicles (EVs)
away from traditional internal combustion engine (ICE) vehicles for consumer use is
set further to entrench reliance on access to electricity due to the increased electricity
demand for charging. While this transition can be a positive step in reducing carbon
emissions [3], embracing EVs will shift transportation energy requirements from petroleum-
based products to electric grids. Of specific interest to this paper, is the demand created
by charging EVs in residential households, which is frequently utilized due to its relative
affordability and convenience.
As countries, such as Canada, plan to ban the sale of new ICE vehicles by 2035 [4],
preparations are required to ensure the success of this shift. This includes actions such
as installing charging stations, increasing electricity generation capacity, investing into
battery technologies, and improving infrastructure throughout the grid to handle the
higher loads required by EV charging. The capability of electricity distribution companies
to accurately forecast the hourly electricity consumption of residential households that
own EVs is instrumental in the transition to EVs as it assists the utility companies to
Energies 2023, 16, 4093. https://doi.org/10.3390/en16104093 https://www.mdpi.com/journal/energies