Elsevier

Applied Energy

Volume 302, 15 November 2021, 117540
Applied Energy

Forecasting seasonal electricity generation in European countries under Covid-19-induced lockdown using fractional grey prediction models and machine learning methods

https://doi.org/10.1016/j.apenergy.2021.117540Get rights and content

Highlights

  • A novel genetic algorithm-based seasonal fractional grey model is proposed.

  • Monthly electricity generation is forecasted since the Covid-19 lockdown started.

  • Seasonal grey and machine learning models are used for forecasting.

  • The selected countries are France, Germany, Spain, Turkey, and the UK.

  • The share of renewables in total electricity generation is forecasted.

Abstract

Balances in the energy sector have changed since the implementation of the Covid-19 pandemic lockdown in Europe. This paper analyses how the lockdown affected electricity generation in European countries and how it will reshape future energy generation. Monthly electricity generation from total renewables and non-renewables in France, Germany, Spain, Turkey, and the UK from January 2017 to September 2020 were evaluated and compared. Four seasonal grey prediction models and three machine learning methods were used for forecasting; the quarterly results are presented to the end of 2021. Additionally, the share of electricity generation from renewables in total electricity generation from 2017 to 2021 for the selected countries was compared. Electricity generation from total non-renewables in the second quarter of 2020 for France, Germany, Spain, and the UK decreased by 21%–25% compared to the same period of 2019; the decline in Turkey was approximately 11%. Additionally, electricity generation from non-renewables in the third quarter of 2020 for all countries, except Turkey, decreased compared to the same period of the previous year. All grey prediction models and support vector machine method forecast that the share of renewables in total electricity generation will increase continuously in France, Germany, Spain, and the UK to the end of 2021. The forecasting methods provided by this study open new avenues for research on the impact of the Covid-19 pandemic on the future of the energy sector.

Keywords

Covid-19
Forecasting
Electricity generation
Fractional grey model
Machine learning
Seasonal fluctuations

Cited by (0)

View Abstract