Forecasting Electricity Generation and Shares by Energy Resources by Time Series Analysis: A Case-Study of Turkey


Konyalıoğlu A. K. , Çelik N.

International Symposium for Production Research, ISPR 2020, Antalya, Turkey, 24 - 26 September 2020, pp.115-120 identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1007/978-3-030-62784-3_10
  • City: Antalya
  • Country: Turkey
  • Page Numbers: pp.115-120
  • Keywords: Box-Jenkins models, Electricity forecasting, Electricity generation, Time series analysis

Abstract

© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.Electricity generation has always been a debatable topic to investigate since industrialization grows up day by day. The accurate planning and directing of the system of supplying electricity depends on reliable modelling and forecasting. Better forecasting and modelling provide more efficient planning, more suitable investments of time, cost and performance and more satisfied customers and citizens. A suitable forecast model for electricity generation is a difficult process to perform, since it involves many parameters such as climate conditions, population, industrial tendency and habitualness of each country or region. In this paper, we tried to forecast electricity generation and shares by energy resources in Turkey by using Time Series Analysis in R software. The study provides not only an effective forecasting for electricity consumption in order to meet the demand in Turkey, but also an efficient segmentation according to the shares by energy resources since the usage of electricity differs from resources. The data, which correspond to the period 1970–2018, are used to forecast the electricity generation in Turkey.