Electricity price forecasting using recurrent neural networks

Umut Ugurlu, Ilkay Oksuz*, Oktay Tas

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

197 Citations (Scopus)
165 Downloads (Pure)


Accurate electricity price forecasting has become a substantial requirement since the liberalization of the electricity markets. Due to the challenging nature of electricity prices, which includes high volatility, sharp price spikes and seasonality, various types of electricity price forecasting models still compete and cannot outperform each other consistently. Neural Networks have been successfully used in machine learning problems and Recurrent Neural Networks (RNNs) have been proposed to address time-dependent learning problems. In particular, Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU) are tailor-made for time series price estimation. In this paper, we propose to use multi-layer Gated Recurrent Units as a new technique for electricity price forecasting. We have trained a variety of algorithms with three-year rolling window and compared the results with the RNNs. In our experiments, three-layered GRUs outperformed all other neural network structures and state-of-the-art statistical techniques in a statistically significant manner in the Turkish day-ahead market.

Original languageEnglish
Article number1255
Issue number5
Publication statusPublished - 14 May 2018


  • Artificial intelligence
  • Deep learning
  • Electricity price forecasting
  • Gated recurrent units
  • Long short term memory
  • Turkish day-ahead market


Dive into the research topics of 'Electricity price forecasting using recurrent neural networks'. Together they form a unique fingerprint.

Cite this