Paper: arXiv 2602.10071

Authors: Runyao Yu, Derek W. Bunn, Julia Lin, Jochen Stiasny, Fabian Leimgruber, Tara Esterl, Yuchen Tao, Lianlian Qi, Yujie Chen, Wentao Wang, Jochen L. Cremer

Abstract

Electricity price forecasting (EPF) plays a critical role in power system operation and market decision making. While existing review studies have provided valuable insights into forecasting horizons, market mechanisms, and evaluation practices, the rapid adoption of deep learning has introduced increasingly diverse model architectures, output structures, and training objectives that remain insufficiently analyzed in depth. This paper presents a structured review of deep learning methods for EPF in day-ahead, intraday, and balancing markets. Specifically, We introduce a unified taxonomy that decomposes deep learning models into backbone, head, and loss components, providing a consistent evaluation perspective across studies. Using this framework, we analyze recent trends in deep learning components across markets. Our study highlights the shift toward probabilistic, microstructure-centric, and market-aware designs. We further identify key gaps in the literature, including limited attention to intraday and balancing markets and the need for market-specific modeling strategies, thereby helping to consolidate and advance existing review studies.

Complexity vs Empirical Score

  • Math Complexity: 3.5/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: This paper presents a structured review and unified taxonomy (backbone, head, loss) for deep learning in electricity price forecasting across day-ahead, intraday, and balancing markets. While it lacks heavy mathematical derivations, it provides a highly clear synthesis and thorough literature mapping of empirical deep learning applications in European energy markets.

Research Flowchart

  flowchart TD
    A[Research Goal: Review Deep Learning in Day-Ahead, Intraday & Balancing EPF] --> B[Data Inputs: Recent Literature on DL-based Electricity Price Forecasting]
    B --> C[Methodology: Develop Unified Taxonomy]
    C --> D[Computational Analysis: Deconstruct Models into Backbone, Head & Loss Components]
    D --> E[Outcome 1: Identified Shift to Probabilistic & Market-Aware Designs]
    D --> F[Outcome 2: Revealed Key Gaps in Intraday & Balancing Market Research]

Cited References (115)

  1. Multivariate simulation-based forecasting for intraday power markets: Modeling cross-product price effects (2024)
  2. Directional Price Forecasting in the Continuous Intraday Market under Consideration of Neighboring Products and Limit Order Books — → 2509.04452
  3. Simulation-based forecasting for intraday power markets: Modelling fundamental drivers for location, shape and scale of the price distribution (2024)
  4. Learning representations by back-propagating errors (1986)
  5. Gradient-based learning applied to document recognition (2002)
  6. Finding structure in time (1990)
  7. Long short-term memory (1997)
  8. Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014) — link
and 107 more
  1. Attention is all you need (2017)
  2. Semi-supervised classification with graph convolutional networks (2016) — link
  3. Auto-encoding variational bayes (2013) — link
  4. Generative adversarial nets (2014)
  5. Density estimation using real nvp (2016) — link
  6. Kan: Kolmogorov-arnold networks (2024) — link
  7. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer (2017) — link
  8. A dual-stage attention-based recurrent neural network for time series prediction (2017) — link
  9. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting (2019)
  10. A hybrid model for GEFCom2014 probabilistic electricity price forecasting (2016) — link
  11. Statistical and economic evaluation of forecasts in electricity markets: beyond RMSE and MAE (2025) — link
  12. Forecasting imbalance price densities with statistical methods and neural networks (2023)
  13. Short-term electricity price forecasting with recurrent regimes and structural breaks (2020)
  14. PriceFM: Foundation Model for Probabilistic Electricity Price Forecasting (2025) — link
  15. Forecasting spot electricity prices: Deep learning approaches and empirical comparison of traditional algorithms (2018) — link
  16. Electricity Price Forecasting with Neural Networks on EPEX Order Books (2020) — link
  17. Electricity price forecasting for nord pool data (2018)
  18. Deep neural networks (DNN) for day-ahead electricity price markets (2018)
  19. An electricity price forecasting model by hybrid structured deep neural networks (2018)
  20. Effective adam-optimized LSTM neural network for electricity price forecasting (2018)
  21. Power market price forecasting via deep learning (2018)
  22. An optimized heterogeneous structure LSTM network for electricity price forecasting (2019)
  23. Day-ahead price forecasting for electricity market using long-short term memory recurrent neural network (2018)
  24. Day-ahead price forecasting in ERCOT market using neural network approaches (2019)
  25. Electricity price and load forecasting using enhanced convolutional neural network and enhanced support vector regression in smart grids (2019)
  26. Bayesian hierarchical probabilistic forecasting of intraday electricity prices (2025) — link
  27. A two-stage supervised learning approach for electricity price forecasting by leveraging different data sources (2019)
  28. Electricity price forecasting in the Danish day-ahead market using the TBATS, ANN and ARIMA methods (2019)
  29. Neural network based model comparison for intraday electricity price forecasting (2019)
  30. Short term electricity price forecasting through convolutional neural network (cnn) (2020)
  31. Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling (2021)
  32. Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark (2021)
  33. Probabilistic forecasting of German electricity imbalance prices (2022)
  34. Electricity price forecasting on the day-ahead market using machine learning (2022)
  35. A hybrid model based on bidirectional long short-term memory neural network and Catboost for short-term electricity spot price forecasting (2022)
  36. Electricity price forecasting with high penetration of renewable energy using attention-based LSTM network trained by crisscross optimization (2022)
  37. Short-term electricity price forecasting based on graph convolution network and attention mechanism (2022)
  38. Optimized Gated Recurrent Unit for Mid-Term Electricity Price Forecasting. (2022)
  39. Framework for collaborative intelligence in forecasting day-ahead electricity price (2022)
  40. Day-ahead electricity price forecasting based on hybrid regression model (2022)
  41. Electricity price forecasting: The dawn of machine learning (2022)
  42. Electricity price forecasting model based on gated recurrent units (2022)
  43. QCAE: A quadruple branch CNN autoencoder for real-time electricity price forecasting (2022)
  44. Daily electricity price forecasting using artificial intelligence models in the Iranian electricity market (2023)
  45. A hybrid day-ahead electricity price forecasting framework based on time series (2023)
  46. Distributional neural networks for electricity price forecasting (2023)
  47. Application of bagging in day-ahead electricity price forecasting and factor augmentation (2021)
  48. Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx (2023)
  49. Transfer learning for electricity price forecasting (2023)
  50. Aggregating prophet and seasonal trend decomposition for time series forecasting of Italian electricity spot prices (2023)
  51. Forecasting day-ahead electricity prices with spatial dependence (2024)
  52. Intraday electricity price forecasting via LSTM and trading strategy for the power market: A case study of the West Denmark DK1 grid region (2024)
  53. Two-step deep learning framework with error compensation technique for short-term, half-hourly electricity price forecasting (2024)
  54. An optimized deep learning approach for forecasting day-ahead electricity prices (2024)
  55. An ensemble approach for enhanced Day-Ahead price forecasting in electricity markets (2024)
  56. A new modeling framework for real-time extreme electricity price forecasting (2024)
  57. A hybrid framework for day-ahead electricity spot-price forecasting: A case study in China (2024)
  58. A new framework for electricity price forecasting via multi-head self-attention and CNN-based techniques in the competitive electricity market (2024)
  59. A robust electricity price forecasting framework based on heteroscedastic temporal Convolutional Network (2024)
  60. Electricity price forecasting in the irish balancing market (2024)
  61. An optimized deep learning approach for forecasting day-ahead electricity prices (2024)
  62. Day-ahead electricity price prediction in multi-price zones based on multi-view fusion spatio-temporal graph neural network (2024)
  63. Seasonality in deep learning forecasts of electricity imbalance prices (2024)
  64. Probabilistic electricity price forecasting based on penalized temporal fusion transformer (2024)
  65. A hybrid forecasting method considering the long-term dependence of day-ahead electricity price series (2024)
  66. A whale optimization algorithm-based multivariate exponential smoothing grey-holt model for electricity price forecasting (2024)
  67. A hybrid stacking method for short-term price forecasting in electricity trading market (2024)
  68. Data-driven techniques for short-term electricity price forecasting through novel deep learning approaches with attention mechanisms (2024)
  69. Price forecasting in the Ontario electricity market via TriConvGRU hybrid model: Univariate vs. multivariate frameworks (2024)
  70. Day-Ahead electricity price forecasting using a CNN-BiLSTM model in conjunction with autoregressive modeling and hyperparameter optimization (2024)
  71. A Market-Rule-Informed Neural Network for Efficient Imbalance Electricity Price Forecasting (2026) — link
  72. A transformer-BILSTM based hybrid deep learning approach for day-ahead electricity price forecasting (2024)
  73. A novel multivariate electrical price bi-forecasting system based on deep learning, a multi-input multi-output structure and an operator combination mechanism (2024)
  74. A Novel Hybrid Deep learning Model for Electricity Price Forecasting (2024)
  75. Multivariate probabilistic forecasting of electricity prices with trading applications (2025)
  76. Optimising quantile-based trading strategies in electricity arbitrage (2025)
  77. Outlier-adaptive-based non-crossing quantiles method for day-ahead electricity price forecasting (2025)
  78. A novel mid-and long-term time-series forecasting framework for electricity price based on hierarchical recurrent neural networks (2025)
  79. A Time Series Decomposition-Based Interpretable Electricity Price Forecasting Method (2025)
  80. Forecasting imbalance price densities with statistical methods and neural networks (2023)
  81. Prediction of Imbalance Prices through Gradient Boosting Algorithms: An Application to the Greek Balancing Market (2025)
  82. Interpretable transformer model for capturing regime switching effects of real-time electricity prices (2022)
  83. Price forecasting for the balancing energy market using machine-learning regression (2020)
  84. OrderFusion: Encoding Orderbook for End-to-End Probabilistic Intraday Electricity Price Forecasting (2026) — link
  85. Electricity Price Forecasting: Bridging Linear Models, Neural Networks and Online Learning (2026) — link
  86. Recurrent neural networks with linear structures for electricity price forecasting (2026) — link
  87. Neural networks in day-ahead electricity price forecasting: single vs. multiple outputs (2020) — link
  88. Trading on short-term path forecasts of intraday electricity prices. Part II–Distributional Deep Neural Networks (2023)
  89. Orderbook Feature Learning and Asymmetric Generalization in Intraday Electricity Markets (2026) — link
  90. Probabilistic intraday electricity price forecasting using generative machine learning (2025) — link
  91. Combining predictive distributions of electricity prices: Does minimizing the CRPS lead to optimal decisions in day-ahead bidding? — → 2308.15443
  92. Probabilistic electricity price forecasting with NARX networks: Combine point or probabilistic forecasts? (2020) — link
  93. On the importance of the long-term seasonal component in day-ahead electricity price forecasting with NARX neural networks (2019) — link
  94. Short term electricity spot price forecasting using catboost and bidirectional long short term memory neural network (2019)
  95. Benchmarking Pre-Trained Time Series Models for Electricity Price Forecasting — → 2506.08113
  96. Electricity price forecasting for Norwegian day-ahead market using hybrid AI models (2022)
  97. Probabilistic forecasting of imbalance prices in the belgian context (2019)
  98. Electricity price forecasting: The dawn of machine learning (2022)
  99. A Review of Electricity Price Forecasting Models in the Day-Ahead, Intra-Day, and Balancing Markets (2025)
  100. Energy forecasting: A review and outlook (2020)
  101. Forecasting day-ahead electricity prices: A review of state-of-the-art algorithms, best practices and an open-access benchmark (2021)
  102. Recent advances in electricity price forecasting: A review of probabilistic forecasting (2018)
  103. Electricity price forecasting: A review of the state-of-the-art with a look into the future (2014)
  104. A review on short-term electricity price forecasting techniques for energy markets (2018)
  105. Forecasting electricity price in different time horizons: an application to the Italian electricity market (2021)
  106. Causal Impact of Wind Energy on the UK Day-Ahead Market (2025) — link
  107. The electricity balancing market: Exploring the design challenge (2016) — link

3 of 115 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.