are changing human mobility patterns; however, the effects on power systems remain unclear. Previous loads and timings along with weather features are often used in literature as input features in load forecasting, but these may be insufficient during COVID-19. As a result, this paper proposes an analytical framework to assess the impact of COVID-19 on power system operation as well as day-ahead electricity prices in Ireland. To improve peak demand forecasting during pandemics, we incorporate mobility, NPIs, and COVID-19 cases as complementary input features and representative of human behaviour changes. By defining different combinations of these explanatory features, several Machine Learning (ML) algorithms are applied and their performance is compared with the baseline scenario currently used in the literature. Using SHapley Additive Explanations (SHAP), we interpret the best performing model, Light Gradient Boosted Machine, to determine the influence of each feature on the predicted outcomes. We discover that typical load forecasting features still influence ML outcomes the most, but mobility-related changes are also significant. Our finding shows that NPIs impact human behaviour and electricity consumption during times of crisis and can be used in the context of load forecasting to assist policymakers and energy distributors.

No abstract

Abstract. With COVID-19’s prevalence and government efforts to curb its spread, urban travel behaviour has significantly altered, resulting in a significant shift in traffic congestion. Rather than predicting traffic congestion based on historical data, we aim to model the correlation between travel behaviour and external mobility-related urban features and use Dublin in Ireland as a case study. This study incorporates four categories of urban data, including 1) Mobility-based features, including the government’s interventions and mobility pattern changes in different locations, 2) Environmental features such as weather and urban street-waste, 3) COVID-19- related features such as the positivity and vaccination rates, and 4) Time-related features such as public holidays. First, we examine the impact of COVID-19 on traffic congestion and street-waste to understand the city’s dynamic. Then, multiple machine learning (ML) models, such as random forests, support vector regression, light gradient boosting machine, and multiple linear regression are trained, and their performance optimized to predict traffic congestion changes. We compare the outcomes of the models with several evaluation metrics and interpret the best performing model. The results indicate that mobility changes in grocery and pharmacy, retail and recreation, workplaces sectors, and the amount of urban street-waste significantly contribute to the model outcomes. Findings could predict traffic dynamics in times of crisis and allow authorities to comprehend the effects of their intervention measures on mobility, which would ultimately benefit developing smart cities and intelligent transportation systems.