LSTM- and GRU-Based Time Series Models for Market Clearing Price Forecasting of Indian Deregulated Electricity Markets

  • Ashish UbraniEmail author
  • Simran Motwani
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 898)


In a deregulated electricity market scenario, formulation of bidding strategies and investment decisions depends majorly on forecasting of Market Clearing Price (MCP). This research proposes and compares models based on Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks to achieve the same. Data for training and testing of the proposed models is collected from Indian Energy Exchange (IEX). Trained models are used to perform day-ahead and week-ahead predictions. Mean Absolute Percentage Error (MAPE) for each model in each case is calculated. Results show that both LSTM- and GRU-based models deliver a reasonably good overall performance with LSTM performing slightly better.


Market clearing price (MCP) Deregulated electricity markets Long short-term memory (LSTM) networks Gated recurrent unit (GRU) networks 


  1. 1.
    Rodriguez, C., Anders, G.: Bidding strategy design for different types of electric power market participants. IEEE Trans. Power Syst. 19, 964–971 (2004)CrossRefGoogle Scholar
  2. 2.
    Bunn, D., Karakatsani, N.: Forecasting electricity prices. Review paper. London Business School Working Paper (2003)Google Scholar
  3. 3.
    Gonzalez, A., Roque, A., Garcia-Gonzalez, J.: Modeling and forecasting electricity prices with input/output hidden Markov models. IEEE Trans. Power Syst. 20, 13–24 (2005)CrossRefGoogle Scholar
  4. 4.
    Box, G., Jenkins, G., Reinsel, G.: Time Series Analysis. Prentice Hall, Englewood Cliffs (1994)zbMATHGoogle Scholar
  5. 5.
    Pindoriya, N., Singh, S., Singh, S.: An adaptive wavelet neural network-based energy price forecasting in electricity markets. IEEE Trans. Power Syst. 23, 1423–1432 (2008)CrossRefGoogle Scholar
  6. 6.
    Khan, G., Arshad, R., Khan, N.: Efficient prediction of dynamic tariff in smart grid using CGP evolved artificial neural networks. In: 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 493–498. IEEE, Cancun (2017)Google Scholar
  7. 7.
    Alshejari, A., Kodogiannis, V.: Electricity price forecasting using asymmetric fuzzy neural network systems. In: IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1–6. IEEE, Naples (2017)Google Scholar
  8. 8.
    Yang, H., Duan, X.: Chaotic characteristics of electricity price and its forecasting model. In: Canadian Conference on Electrical and Computer Engineering—CCECE 2003, pp. 659–662. IEEE (2003)Google Scholar
  9. 9.
    Anamika, Kumar, N.: Market clearing price prediction using ANN in Indian electricity markets. In: International Conference on Energy Efficient Technologies for Sustainability (ICEETS), pp. 454–458. IEEE, Nagercoil, India (2016)Google Scholar
  10. 10.
    Indian Energy Exchange.
  11. 11.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRefGoogle Scholar
  12. 12.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. NIPS 2014 Workshop on Deep Learning, December 2014 (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Electrical DepartmentVeermata Jijabai Technological InstituteMumbaiIndia
  2. 2.Computer DepartmentVeermata Jijabai Technological InstituteMumbaiIndia

Personalised recommendations