Electricity Day-Ahead Market Price Forecasting by Using Artificial Neural Networks: An Application for Turkey


KABAK M., Tasdemir T.

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, vol.45, no.3, pp.2317-2326, 2020 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 45 Issue: 3
  • Publication Date: 2020
  • Doi Number: 10.1007/s13369-020-04349-1
  • Journal Name: ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Communication Abstracts, Metadex, Pollution Abstracts, zbMATH, Civil Engineering Abstracts
  • Page Numbers: pp.2317-2326
  • Keywords: Day-ahead market, Electricity spot market, Price forecasting, Market clearing price, Artificial neural networks, ENERGY-CONSUMPTION
  • Gazi University Affiliated: Yes

Abstract

The reference price is the most important signal for market participant to have position of selling or buying in the trade of electricity. The electricity price has a dynamic structure and is directly and/or indirectly affected by many factors. All of the market participants' transaction is carried out in a contract based on forecasting. These transactions are for day-ahead market (DAM) and balancing power market 1 day before, intraday market 60 min before and short, mid, long term for derivatives market. The price is forecasted that is determined as far as cost. The price forecasting has benefits which are maximizing profit, protecting from all of the crisis and constrictions and mitigation of loses. All of the market participants highly affected from the price. For this reason, such an important topic should be conducted scientifically. This study aims to develop a price forecasting tool for short term which is calculated day by day in DAM at Turkish electricity market. This forecasting tool is developed based on artificial neural networks. All of the market participants take the price, which is calculated in DAM, as reference. There are many direct and/or indirect factors affecting the reference price used by market players. In this study, a short-term price forecasting model was formed by analyzing historical data and all of the data, which are affecting the price most correctly, are correlated by using artificial neural network method. The basis of the forecasting model used is supply and demand curves. All the factors affecting different points on supply and demand curves by artificial neural network model provide the most correct reference price. In the study, January, April, July and October 2017 values were taken and estimated for randomly selected days of the months. The randomly selected supply and demand curves of April 19 is affected from renewable energy production, natural gas and coal production. In this scope of conclusion, the forecasted price is below 5% deviation on average per day compared to the actual price. As for hourly error deviation, it was seen that deviation is below 10% for 13 h. The suggested artificial neural network model scientifically supports market participant to make short-term transaction.