Your browser doesn't support javascript.
A machine learning framework to quantify and assess the impact of COVID-19 on the power sector: An Indian context
Advances in Applied Energy ; : 100078, 2021.
Article in English | ScienceDirect | ID: covidwho-1559510
ABSTRACT
As the COVID-19 continues to disrupt the global norms, there is the requirement of modelling frameworks to accurately assess and quantify the impact of the pandemic on the electricity sector and its emissions. In this study, we devise machine learning models to estimate the pandemic induced reduction in electricity consumption based on weather, econometrics, and social-distancing parameters for seven major Indian states. As per our baseline electricity consumption model, we find that the electricity consumption dropped by 15-33% in 2020 (March-May) during the complete lockdown phase, followed by 6-13% (June-August) during the unlock phases and gradually reached the norms by September 2020. As a result, the net CO2 emissions from power generation in 2020 dropped by 7% and 5% compared to 2018 and 2019 respectively. Amidst the ongoing second wave since mid-April 2021, we projected the electricity consumption across states from May-August by accounting for two scenarios. Under the reference and worst-case scenarios, the electricity consumption approximates 106% and 96% of the non-pandemic situation, respectively. The modelling framework developed in this study is purely data-oriented, cross-deployable across spatio-temporal scales and can serve as a valuable tool to inform current and future energy policies amidst and post COVID-19.
Keywords

Full text: Available Collection: Databases of international organizations Database: ScienceDirect Type of study: Randomized controlled trials Topics: Long Covid Language: English Journal: Advances in Applied Energy Year: 2021 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: ScienceDirect Type of study: Randomized controlled trials Topics: Long Covid Language: English Journal: Advances in Applied Energy Year: 2021 Document Type: Article