Improving Load Forecast in Energy Markets During COVID-19

TL;DR

This paper evaluates and enhances load forecasting models during COVID-19 by incorporating novel COVID-related features and simulating stay-at-home conditions, using real-world data from NYISO.

Contribution

It systematically assesses deep learning models and introduces COVID-specific features and simulation techniques to improve load forecasting during the pandemic.

Findings

COVID-related features improve forecasting accuracy

Simulating stay-at-home conditions enhances model performance

Deep learning models outperform traditional methods

Abstract

The abrupt outbreak of the COVID-19 pandemic was the most significant event in 2020, which had profound and lasting impacts across the world. Studies on energy markets observed a decline in energy demand and changes in energy consumption behaviors during COVID-19. However, as an essential part of system operation, how the load forecasting performs amid COVID-19 is not well understood. This paper aims to bridge the research gap by systematically evaluating models and features that can be used to improve the load forecasting performance amid COVID-19. Using real-world data from the New York Independent System Operator, our analysis employs three deep learning models and adopts both novel COVID-related features as well as classical weather-related features. We also propose simulating the stay-at-home situation with pre-stay-at-home weekend data and demonstrate its effectiveness in improving load forecasting accuracy during COVID-19.