(Machine) learning from the COVID-19 lockdown about electricity market performance with a large share of renewables

Christoph Graf, Federico Quaglia, Frank A. Wolak

Research output: Contribution to journalReview ArticleResearchpeer-review

22 Citations (Scopus)

Abstract

The negative demand shock due to the COVID-19 lockdown has reduced net demand for electricity—system demand less amount of energy produced by intermittent renewables, hydroelectric units, and net imports—that must be served by controllable generation units. Under normal demand conditions, introducing additional renewable generation capacity reduces net demand. Consequently, the lockdown can provide insights about electricity market performance with a large share of renewables. We find that although the lockdown reduced average day-ahead prices in Italy by 45%, re-dispatch costs increased by 73%, both relative to the average of the same magnitude for the same period in previous years. We estimate a deep-learning model using data from 2017 to 2019 and find that predicted re-dispatch costs during the lockdown period are only 26% higher than the same period in previous years. We argue that the difference between actual and predicted lockdown period re-dispatch costs is the result of increased opportunities for suppliers with controllable units to exercise market power in the re-dispatch market in these persistently low net demand conditions. Our results imply that without grid investments and other technologies to manage low net demand conditions, an increased share of intermittent renewables is likely to increase the costs of maintaining a reliable grid.

Original languageEnglish
Article number102398
Number of pages17
JournalJournal of Environmental Economics and Management
Volume105
DOIs
Publication statusPublished - Jan 2021

Keywords

  • European electricity market
  • Machine learning
  • Net demand shock
  • Re-dispatch market power
  • Real-time grid operation

Cite this