Predicting Power Deviation in the Turkish Power Market Based on Adaptive Factor Impacts

Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 614)


Energy market models are generally focused on energy balancing using the optimum energy mix. In countries where the energy markets are not fully liberalised, the State Regulators reflect any cost of being off-balance on the utility companies and this affects the consumers as well. The right short term prediction of the market trends is beneficial both to optimise the physical energy flow and commercial revenue balance for suppliers and utility companies. This study is aimed to predict the sign trends in the power market by selecting the influencing factors adaptive to the conditions of the day ahead, 10 h, 5 h, 2 h and 1 h before the electricity balance is active. There are numerous factors consisting of weather conditions, resource costs, operation costs, renewable energy conditions, regulations, etc. with a considerable impact on the predictions. The contribution of this paper is to choose the factors with the highest impacts using the Genetic Algorithm (GA) with Akaike Information Criteria (AIC), which are then used as input of a Recursive Neural Network (RNN) model for forecasting the deviation trends. The proposed hybrid method does not only reduce the prediction errors but also avoid dependency on expert knowledge. Hence this paper will allow both the market regulator and the suppliers to take precautions based on a confident prediction.


Energy market balancing Auxiliary power market modeling Turkish power market Adaptive prediction Genetic algorithm and recursive neural networks 


  1. 1.
    Weron, R.: Electricity price forecasting: a review of the state-of-the-art with a look into the future. Int. J. Forecast. 30(4), 10 (2014)CrossRefGoogle Scholar
  2. 2.
    Lago, J., Poplavskaya, K., Suryanarayana, G., De Schutter, B.: A market framework for grid balancing support through imbalances trading. Renew. Sustain. Energy Rev. 137, 110467 (2020)CrossRefGoogle Scholar
  3. 3.
    Schillinger, M.: Balancing-market design and opportunity cost: the Swiss case. Util. Policy 64, 101045 (2020)CrossRefGoogle Scholar
  4. 4.
    Nobel, F.A.: On balancing market design. Technische Universiteit Eindhoven: Eindhoven, The Netherlands (2016)Google Scholar
  5. 5.
    [Data] EXIST- Energy Exchange Istanbul: Real Time Generation, 01 January 2020–31 December 2020. Accessed 29 Jan 2021
  6. 6.
    [Data] TETC- Turkish Electricity Transmission Company: Electricity Generation and Transmission Statistics. Accessed 31 Jan 2021
  7. 7.
    [Data] TETC- Turkish Electricity Transmission Company: Installed Power Plant Capacity Report, December 2020. Accessed 11 Feb 2021
  8. 8.
    Cetintas, H., Bicil, I.M.: Elektrik Piyasalarında Yeniden Yapılanma ve Türkiye Elektrik Piyasasında Yapısal Dönüşüm. Optimum Ekonomi ve Yönetim Bilimleri Dergisi 2(2), 1–15 (2015)CrossRefGoogle Scholar
  9. 9.
    Ortner, A., Totschnig, G.: The future relevance of electricity balancing markets in Europe-a 2030 case study. Energ. Strat. Rev. 24, 111–120 (2019)CrossRefGoogle Scholar
  10. 10.
    Borggrefe, F., Neuhoff, K.: Balancing and intraday market design: options for wind integration. DIW Berlin Discussion Paper No. 1162. SSRN (2011). or
  11. 11.
    Goodarzi, S., Perera, H.N., Bunn, D.: The impact of renewable energy forecast errors on imbalance volumes and electricity spot prices. Energy Policy 134, 110827 (2019)CrossRefGoogle Scholar
  12. 12.
    Sirin, S.M., Yilmaz, B.N.: The impact of variable renewable energy technologies on electricity markets: an analysis of the Turkish balancing market. Energy Policy 151, 112093 (2021)CrossRefGoogle Scholar
  13. 13.
    Kölmek, M.A., Navruz, I.: Forecasting the day-ahead price in electricity balancing and settlement market of Turkey by using artificial neural networks. Turk. J. Electr. Eng. Comput. Sci. 23(3), 841–852 (2015)CrossRefGoogle Scholar
  14. 14.
    Mordasiewicz, Ł.: Price forecasting in the balancing mechanism. Rynek Energii (3), 94 (2011)Google Scholar
  15. 15.
    Lucas, A., Pegios, K., Kotsakis, E., Clarke, D.: Price forecasting for the balancing energy market using machine-learning regression. Energies 13(20), 5420 (2020)CrossRefGoogle Scholar
  16. 16.
    Garcia, M.P., Kirschen, D.S.: Forecasting system imbalance volumes in competitive electricity markets. IEEE Trans. Power Syst. 21(1), 240–248 (2006)CrossRefGoogle Scholar
  17. 17.
    Kratochvíl, Š.: System imbalance forecast. Doctoral dissertation. Czech Technical University, Prague, Czech Republic (2016)Google Scholar
  18. 18.
    Contreras, C.: System imbalance forecasting and short-term bidding strategy to minimize imbalance costs of transacting in the Spanish electricity market. Doctoral dissertation. Universidad Pontifıcia Comillas, Madrid, Spain (2016)Google Scholar
  19. 19.
    Pires Ferreira, P.: Volume and price in the Nordic balancing power market. Master’s thesis. Norwegian University of Science and Technology, Trondheim, Norway (2016)Google Scholar
  20. 20.
    Salem, T.S., Kathuria, K., Ramampiaro, H., Langseth, H.: Forecasting intra-hour imbalances in electric power systems. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 9595–9600 (2019)Google Scholar
  21. 21.
    van der Veen, R.A., Abbasy, A., Hakvoort, R.A.: Agent-based analysis of the impact of the imbalance pricing mechanism on market behavior in electricity balancing markets. Energy Econ. 34(4), 874–881 (2012)CrossRefGoogle Scholar
  22. 22.
    Bueno-Lorenzo, M., Moreno, M.Á., Usaola, J.: Analysis of the imbalance price scheme in the Spanish electricity market: a wind power test case. Energy Policy 62, 1010–1019 (2013)CrossRefGoogle Scholar
  23. 23.
    Hirth, L., Ziegenhagen, I.: Balancing power and variable renewables: three links. Renew. Sustain. Energy Rev. 50, 1035–1051 (2015)CrossRefGoogle Scholar
  24. 24.
    Klæboe, G., Eriksrud, A.L., Fleten, S.-E.: Benchmarking time series based forecasting models for electricity balancing market prices. Energy Syst. 6(1), 43–61 (2013). Scholar
  25. 25.
    Koch, C., Hirth, L.: Short-term electricity trading for system balancing: an empirical analysis of the role of intraday trading in balancing Germany’s electricity system. Renew. Sustain. Energy Rev. 113, 109275 (2019)CrossRefGoogle Scholar
  26. 26.
    Huang, P., Xu, T., Sun, Y.: A genetic algorithm based dynamic pricing for improving bi-directional interactions with reduced power imbalance. Energy Build. 199, 275–286 (2019)CrossRefGoogle Scholar
  27. 27.
    Schäfer, P., Westerholt, H.G., Schweidtmann, A.M., Ilieva, S., Mitsos, A.: Model-based bidding strategies on the primary balancing market for energy-intense processes. Comput. Chem. Eng. 120, 4–14 (2019)CrossRefGoogle Scholar
  28. 28.
    Wu, Z., Zhou, M., Zhang, T., Li, G., Zhang, Y., Liu, X.: Imbalance settlement evaluation for China’s balancing market design via an agent-based model with a multiple criteria decision analysis method. Energy Policy 139, 111297 (2020)CrossRefGoogle Scholar
  29. 29.
    Poplavskaya, K., Lago, J., De Vries, L.: Effect of market design on strategic bidding behavior: model-based analysis of European electricity balancing markets. Appl. Energy 270, 115130 (2020)CrossRefGoogle Scholar
  30. 30.
    Vural, M.: Genetik algoritma yöntemi ile toplu üretim planlama. Doctoral dissertation. Istanbul Technical University, Istanbul, Turkey (2005)Google Scholar
  31. 31.
    Ozturk, H.K., Canyurt, O.E., Hepbasli, A., Utlu, Z.: Residential-commercial energy input estimation based on genetic algorithm approaches: an application of Turkey. Energy Build. 36, 175–183 (2004)CrossRefGoogle Scholar
  32. 32.
    Haldenbilen, S., Ceylan, H.: Genetic algorithm approach to estimate transport energy demand in Turkey. Energy Policy 33, 89–98 (2005)CrossRefGoogle Scholar
  33. 33.
    Man, K.F., Tang, K.S., Kwong, S.: Genetic Algorithms: Concepts and Designs. Springer, London (2001)zbMATHGoogle Scholar
  34. 34.
    Hewamalage, H., Bergmeir, C., Bandara, K.: Recurrent neural networks for time series forecasting: current status and future directions. Int. J. Forecast. 37(1), 388–427 (2021)CrossRefGoogle Scholar
  35. 35.
    Achanta, S., Gangashetty, S.V.: Deep Elman recurrent neural networks for statistical parametric speech synthesis. Speech Commun. 93, 31–42 (2017)CrossRefGoogle Scholar
  36. 36.
    Wang, J., Wang, J., Fang, W., Niu, H.: Financial time series prediction using Elman recurrent random neural networks. Comput. Intell. Neurosci. (2016).
  37. 37.
    Jiang, Y., Chen, M., You, S.: A unified trading model based on robust optimization for day-ahead and real-time markets with wind power integration. Energies 10(4), 554 (2017)CrossRefGoogle Scholar
  38. 38.
    Qiu, J., Zhao, J., Wang, D., Zheng, Y.: Two-stage coordinated operational strategy for distributed energy resources considering wind power curtailment penalty cost. Energies 10(7), 965 (2017)CrossRefGoogle Scholar
  39. 39.
    Gligoric, Z., Savic, S.S., Grujic, A., Negovanovic, M., Music, O.: Short-term electricity price forecasting model using interval-valued autoregressive process. Energies 11(7), 1911 (2018)CrossRefGoogle Scholar
  40. 40.
    Sun, P., Li, J., Chen, J., Lei, X.: A short-term outage model of wind turbines with doubly fed induction generators based on supervisory control and data acquisition. Energies 9(11), 882 (2016)CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2021

Authors and Affiliations

  1. 1.Eurasia Institute of Earth SciencesIstanbul Technical UniversityIstanbulTurkey
  2. 2.Axpo TurkeyBesiktas, IstanbulTurkey
  3. 3.Energy InstituteIstanbul Technical UniversityIstanbulTurkey

Personalised recommendations