Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Electricity Price Forecasting in the Irish Balancing Market

Ciaran O'Connor, Joseph Collins, Steven Prestwich, Andrea Visentin

TL;DR

This paper tackles the challenge of forecasting Balancing Market prices in the Irish BM within I-SEM, a setting characterized by extreme volatility and limited public BM data. It adapts successful Day-Ahead Market forecasting approaches into a replicable BM benchmarking framework, employing walk-forward validation and an open dataset/codebase to ensure reproducibility. The study benchmarks a spectrum of models—statistical (LEAR), tree ensembles (RF, XGB), and deep learning (SH-DNN, MH-RNN-DNN)—and finds that LEAR and ensemble methods typically outperform DL models in BM forecasting, with BM-DAM differences underscoring the need for BM-specific modeling choices. The work offers practical baselines for BM participants, demonstrates the fundamental differences between BM and DAM dynamics, and provides a valuable open-resource platform for future BM forecast research and method development.

Abstract

Short-term electricity markets are becoming more relevant due to less-predictable renewable energy sources, attracting considerable attention from the industry. The balancing market is the closest to real-time and the most volatile among them. Its price forecasting literature is limited, inconsistent and outdated, with few deep learning attempts and no public dataset. This work applies to the Irish balancing market a variety of price prediction techniques proven successful in the widely studied day-ahead market. We compare statistical, machine learning, and deep learning models using a framework that investigates the impact of different training sizes. The framework defines hyperparameters and calibration settings; the dataset and models are made public to ensure reproducibility and to be used as benchmarks for future works. An extensive numerical study shows that well-performing models in the day-ahead market do not perform well in the balancing one, highlighting that these markets are fundamentally different constructs. The best model is LEAR, a statistical approach based on LASSO, which outperforms more complex and computationally demanding approaches.

Electricity Price Forecasting in the Irish Balancing Market

TL;DR

This paper tackles the challenge of forecasting Balancing Market prices in the Irish BM within I-SEM, a setting characterized by extreme volatility and limited public BM data. It adapts successful Day-Ahead Market forecasting approaches into a replicable BM benchmarking framework, employing walk-forward validation and an open dataset/codebase to ensure reproducibility. The study benchmarks a spectrum of models—statistical (LEAR), tree ensembles (RF, XGB), and deep learning (SH-DNN, MH-RNN-DNN)—and finds that LEAR and ensemble methods typically outperform DL models in BM forecasting, with BM-DAM differences underscoring the need for BM-specific modeling choices. The work offers practical baselines for BM participants, demonstrates the fundamental differences between BM and DAM dynamics, and provides a valuable open-resource platform for future BM forecast research and method development.

Abstract

Short-term electricity markets are becoming more relevant due to less-predictable renewable energy sources, attracting considerable attention from the industry. The balancing market is the closest to real-time and the most volatile among them. Its price forecasting literature is limited, inconsistent and outdated, with few deep learning attempts and no public dataset. This work applies to the Irish balancing market a variety of price prediction techniques proven successful in the widely studied day-ahead market. We compare statistical, machine learning, and deep learning models using a framework that investigates the impact of different training sizes. The framework defines hyperparameters and calibration settings; the dataset and models are made public to ensure reproducibility and to be used as benchmarks for future works. An extensive numerical study shows that well-performing models in the day-ahead market do not perform well in the balancing one, highlighting that these markets are fundamentally different constructs. The best model is LEAR, a statistical approach based on LASSO, which outperforms more complex and computationally demanding approaches.
Paper Structure (17 sections, 2 equations, 8 figures, 1 table)

This paper contains 17 sections, 2 equations, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Motivation and contributions
  3. Literature Review
  4. Day Ahead Market Forecasting
  5. Balancing Market
  6. Electricity Market Structure
  7. Analytical Framework
  8. Dataset
  9. Experimental Configuration
  10. Metrics
  11. Models
  12. Single-Headed DNN model
  13. Multi-Headed LSTM-DNN model
  14. Results
  15. Accuracy
  16. ...and 2 more sections

Figures (8)

  • Figure 1: Schematic overview of the typical sequence of existing electricity markets in the EU. Markets in dotted lines are optional meeus2020evolution
  • Figure 2: MH RNN DNN Model
  • Figure 3: LEAR Forecast for BM
  • Figure 4: MH RNN DNN Forecasts for BM
  • Figure 5: Hourly breakdown of the BM prices and the models' forecast error.
  • ...and 3 more figures