The effect of behavior changes caused by the covid-19 pandemic on electricity consumptions and feeder loads: a case study on an electricity distribution feeder
No Thumbnail Available
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The COVID-19 (Sars CoV-2) virus, which emerged in Wuhan city of Hubei province of China in December 2019, affected the whole world in a short time and was declared a global epidemic by the World Health Organization (WHO) as of March 11, 2020. After this date, closure measures have been implemented all over the world to prevent the spread of the virus. Due to the provisions taken, there have been changes in electrical energy consumption compared to previous years. In March, April and May 2020, when the restrictions affected human life the most, dynamic changes occurred in energy demand all over the world. This has affected international energy markets, energy production and grid load planning. Although the total electricity consumption in Turkey increased compared to the previous year, there was a decrease in the consumption in the commercial tariff. In this study, the effects of the COVID-19 pandemic on electricity consumption were analyzed by analyzing the electricity consumption of Turkey and Izmir, depending on the tariffs, based on time. A case study was conducted on an electricity distribution feeder to see the impact of COVID-19 on electricity distribution networks. For the case study, an electricity distribution feeder with 99% of the subscriber density in the residential and commercial tariff group was selected. For the feeder, load forecasting was made using artificial neural networks machine learning method according to 2018, 2019 and 2020 data. In the load forecasting study, 75% of the data was selected for learning and 25% for testing. As a result of the study, the actual and forecasted load data of 2020 were compared. The effects of the COVID-19 pandemic on the lad of an electricity distribution feeder were investigated. In the study, the best performance values of load forecasting were found mse as 0.0024 and R2 as 0.83.