Improving load forecast in energy markets during COVID-19

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.

[1]  M. Dahleh,et al.  A Cross-Domain Approach to Analyzing the Short-Run Impact of COVID-19 on the US Electricity Sector , 2020, Joule.

[2]  Weiwei Yang,et al.  Using Mobility for Electrical Load Forecasting During the COVID-19 Pandemic , 2020, 2006.08826.

[3]  Shahzad Muzaffar,et al.  Short-Term Load Forecasts Using LSTM Networks , 2019, Energy Procedia.

[4]  Derya Eryilmaz,et al.  Assessment of the COVID-19 pandemic effect on regional electricity generation mix in NYISO, MISO, and PJM markets⋆ , 2020, The Electricity Journal.

[5]  Kai Zhao,et al.  A pneumonia outbreak associated with a new coronavirus of probable bat origin , 2020, Nature.

[6]  Patrick Hosein,et al.  Load forecasting using deep neural networks , 2017, 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[7]  Chien-fei Chen,et al.  Coronavirus comes home? Energy use, home energy management, and the social-psychological factors of COVID-19 , 2020, Energy Research & Social Science.

[8]  I. Dincer,et al.  Analysis of the electricity demand trends amidst the COVID-19 coronavirus pandemic , 2020, Energy Research & Social Science.

[9]  Hisham Mahmood,et al.  Short-Term Load Forecasting Using an LSTM Neural Network , 2020, 2020 IEEE Power and Energy Conference at Illinois (PECI).

[10]  Xifan Wang,et al.  Operating reserve model in the power market , 2005, IEEE Transactions on Power Systems.

[11]  A. J. Pires,et al.  Load forecasting, the importance of the probability “tails” in the definition of the input vector , 2013, 4th International Conference on Power Engineering, Energy and Electrical Drives.

[12]  Yizhen Wang,et al.  A Short-Term Residential Load Forecasting Model Based on LSTM Recurrent Neural Network Considering Weather Features , 2021, Energies.

[13]  I. Santiago,et al.  Electricity demand during pandemic times: The case of the COVID-19 in Spain , 2020, Energy Policy.

[14]  A. Nešović,et al.  Impact of people's behavior on the energy sustainability of the residential sector in emergency situations caused by COVID-19 , 2020, Energy and Buildings.

[15]  Ali Cheshmehzangi,et al.  COVID-19 and household energy implications: what are the main impacts on energy use? , 2020, Heliyon.

[16]  Jing Wu,et al.  COVID-19 pandemic in China: Context, experience and lessons , 2020, Health Policy and Technology.

[17]  Sahm Kim,et al.  Short term electricity load forecasting for institutional buildings , 2019, Energy Reports.

[18]  Norbert Edomah,et al.  Energy transition in a lockdown: An analysis of the impact of COVID-19 on changes in electricity demand in Lagos Nigeria , 2020, Global Transitions.

[19]  A. Gundlapalli,et al.  Timing of State and Territorial COVID-19 Stay-at-Home Orders and Changes in Population Movement — United States, March 1–May 31, 2020 , 2020, MMWR. Morbidity and mortality weekly report.