COVID-19 impact on wind and solar energy sector and cost of energy prediction based on machine learning

Abstract

This study examines the impact of the COVID-19 pandemic on renewable energy sectors across seven countries through techno-economic analysis and machine learning (ML). In China, the renewable fraction decreased in grid-connected systems due to 14.6 % higher diesel fuel prices. They reduced grid electricity prices, with Cost of Energy (COE) reductions driven by a 2.8 % inflation decrease and a 3 % discount rate cut. The increase in renewable energy adoption in the USA during the pandemic was driven by decreased initial and operational costs of renewable components, a significant rise in diesel fuel prices, and government policy changes, despite a reduction in renewable energy sell-back prices and rising capital and annual costs due to expanded renewable capacity. Canada noted a shift to standalone systems with 50 % lower PV sell-back prices, 2 % lower WT prices, and a 48 % fuel cost rise, reducing COE except in grid/WT scenarios. Germany managed rising electricity and fuel costs, decreasing COE despite inflation. India expanded standalone HRESs driven by a sevenfold PV capacity increase, lowering COE. Japan saw stable COE with minimal variation. Iran faced economic challenges with a 104 % inflation increase, impacting COE despite a grid-connected COE decrease. Machine learning forecasts suggest that COVID-19 may cause an increase in COE in China and India due to pandemic effects.

Highlights

• •

  Economic impacts of the COVID-19 lockdown on the renewable energy sector are investigated.

• •

  Techno-economic analysis is used to investigate the impact of COVID-19 on the cost of energy.

• •

  The impacts of inflation and discount changes on renewable systems are investigated.

• •

  A database containing details of renewable systems was gathered using published papers.

• •

  Machine Learning is used to predict renewable COE changes related to COVID-19.