Implementation of K-Nearest Neighbor Regression for Forecasting Electricity Demand in Power System of Republic of North Macedonia

Kostov, Mitko and Atanasovski, Metodija and Spirovski, Mile (2020) Implementation of K-Nearest Neighbor Regression for Forecasting Electricity Demand in Power System of Republic of North Macedonia. In: 15th Conference on Sustainable Development of Energy, Water and Environment Systems 2020 (SDEWES 2020), September, 01-05, 2020, Cologne, Germany.

Text SDEWES2020_FP_631.pdf Download (1MB)

Abstract

Load forecast is an important factor for operational and development planning of power system. Factors that play key role in forecasting power load consumption are the air temperature, type of the day (weekday, weekend or holiday), geographical differences, people standard, gross domestic product, demographic information, energy efficiency etc. The air temperature is one of the factors, which has significant impact on electricity consumption and power system load. This paper analyses the correlation between the power system load and the air temperature in Republic of North Macedonia. Furthermore, forecasting of the power system load is investigated. The power system load forecast is performed by applying k-nearest neighbor machine learning model. The power load depends on two variables – air temperature and date. Results show that for power load forecasts, k-nearest neighbor regression outperforms

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	This research is supported by the EU H2020 project TRINITY (Grant Agreement no. 863874) This paper reflects only the author’s views and neither the Agency nor the Commission are responsible for any use that may be made of the information contained therein.
Subjects:	Scientific Fields (Frascati) > Engineering and Technology > Electrical engineering, electronic engineering,information engineering
Divisions:	Faculty of Technical Sciences
Depositing User:	Prof. d-r. Metodija Atanasovski
Date Deposited:	22 Oct 2020 09:18
Last Modified:	22 Oct 2020 09:18
URI:	https://eprints.uklo.edu.mk/id/eprint/5823

Actions (login required)

View Item