Mikail Purlu, B. Turkay, Cenk Andic, E. Aydin, Bilal Canol, Burak Kucukaslan
{"title":"Market-Clearing Price Forecasting Using Keras in Turkish Day-Ahead Electricity Market","authors":"Mikail Purlu, B. Turkay, Cenk Andic, E. Aydin, Bilal Canol, Burak Kucukaslan","doi":"10.1109/gpecom55404.2022.9815603","DOIUrl":null,"url":null,"abstract":"The market-clearing price determined in the electricity market is of great importance for the market players trading in electricity. The market-clearing price constitutes the core of the buying and selling transactions in the electricity market. Knowing what the price of the product, service or commodity to be bought and / or sold would be, provides a great competitive advantage to the relevant party over the person or organization carrying out the relevant commercial activity. It is important to successfully predict the market-clearing price in the market in order to set strategy and game plan and implement risk management. For this purpose, in this study, a model using only publicly available input data on Keras, a deep learning library, is used to predict hourly market-clearing price in Turkish Day-Ahead Electricity Market. Despite the high economic and financial uncertainty and price fluctuations in 2021, the proposed model showed a high performance with a MAPE value of 2.5% and it is clear that the model is successful and applicable in real market conditions.","PeriodicalId":441321,"journal":{"name":"2022 4th Global Power, Energy and Communication Conference (GPECOM)","volume":"63 15","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 4th Global Power, Energy and Communication Conference (GPECOM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/gpecom55404.2022.9815603","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
The market-clearing price determined in the electricity market is of great importance for the market players trading in electricity. The market-clearing price constitutes the core of the buying and selling transactions in the electricity market. Knowing what the price of the product, service or commodity to be bought and / or sold would be, provides a great competitive advantage to the relevant party over the person or organization carrying out the relevant commercial activity. It is important to successfully predict the market-clearing price in the market in order to set strategy and game plan and implement risk management. For this purpose, in this study, a model using only publicly available input data on Keras, a deep learning library, is used to predict hourly market-clearing price in Turkish Day-Ahead Electricity Market. Despite the high economic and financial uncertainty and price fluctuations in 2021, the proposed model showed a high performance with a MAPE value of 2.5% and it is clear that the model is successful and applicable in real market conditions.