Effects of COVID-19 on electric energy consumption in Turkey and ANN-based short-term forecasting

Abstract

Due to the coronavirus, millions of people worldwide carry out their work, education, shopping, culture, and entertainment activities from their homes using the advantages of today's technology now. Apart from this, patient care and follow-up are carried out with the help of electronic equipment especially in the institutions where health services are provided. It is important for humanity to perform all these services by providing a reliable electricity supply. In this study, outlook of the energy in Turkey were examined. The current energy consumption and investments were examined. Then, the precautions by the government against the pandemic period according to the occurrence and spread of COVID-19 in the country are given in chronological order. The actual electricity consumption data were obtained daily across the country, after all these precautions. It was observed that electricity consumption decreased significantly, especially on restricted days. It is inevitable that energy consumption estimation should be made in the short term so that the energy sector is not adversely affected by this situation. In this study, a more accurate short-term consumption forecasting methods were developed during the COVID-19 pandemic period, non-linear autoregressive (NARX) and long short term memory (LSTM) artificial neural networks. Between January-April 2019 electrical consumption data were used to train and validate the forecast prediction. The NARX and LSTM is a potential candidate for effective forecasting of electricity energy consumption. However, the obtained LSTM results suggest that the proposed method performed better results than NARX ANN.

The Impact of the COVID-19 Pandemic on Electricity Consumption and Economic Growth in Romania

“…Some researchers have studied the prospects for energy consumption during the pandemic and government-imposed restrictions and made various forecasts using various forecasting techniques [37,38].…”

Manta ray foraging optimization algorithm–based feedforward neural network for electric energy consumption forecasting

“…Figure 1 shows the installed power of Turkey according to the year. 40,41 The data published for 2021 (96 207.7 MW) are for the month of January and show that the installed electric power is increasing steadily in order to ensure the energy supply (Figure 1). Figure 2 reveals the detailed data as of January 2021 for a total of 9524 power plants and their installed power according to primary sources.…”

“…To meet this demand, Turkey also has been steadily increasing its installed power. Figure 1 shows the installed power of Turkey according to the year 40,41 …”

“…Moreover, 75% of all power plants are private power plants 41 . More detailed reviews can be found in the 40 study.…”

New normal: cooperative paradigm for COVID-19 timely detection and containment using Internet of things and deep learning

“…The research discusses post-COVID analysis to identify and reduce the health challenges. Authors in [15] present short-term forecasting for electric energy considering COVID-19 and health centers using artificial neural networks. The study focuses on the availability of electricity in hospitals and health centers to ensure pervasive medical care to COVID-19 patients.…”