Scenario generation of intraday electricity price paths for optimal trading in continuous markets

TL;DR

This paper introduces a novel ensemble forecasting framework using Support Vector Regression and scenario generation for intraday electricity prices, enhancing trading decisions and risk management.

Contribution

It extends point forecasts to probabilistic trajectories with a new scenario selection method, improving accuracy and economic outcomes in intraday electricity trading.

Findings

Ensemble forecasts outperform benchmark methods in statistical accuracy.

Fundamental scenarios improve median trajectory accuracy.

Scenario reweighting enhances trading profitability.

Abstract

Continuous intraday electricity markets play an increasingly important role in short-term trading and balancing, yet decision-making under rapidly evolving price dynamics remains challenging. This paper proposes a comprehensive framework for ensemble forecasting of intraday electricity price trajectories and their translation into adaptive trading decisions. Building on a corrected Support Vector Regression model, the approach extends point predictions to probabilistic trajectory forecasts by introducing scenario generation based on forecast errors of fundamental variables and proposing a novel Support Vector Sorting procedure for the efficient selection of representative scenarios. The framework is evaluated using transaction level data from the German intraday continuous market. Empirical results show improvements over benchmark methods in both statistical and economic terms. Fundamental scenarios enhance median trajectory accuracy but produce more concentrated predictive distributions, while historical simulation with scenario selection better captures tail risk. From an economic perspective, ensemble-based forecasts outperform naive benchmarks across most of the trading strategies. Dynamic updating through scenario reweighting further improves profitability with limited impact on downside risk. Overall, the results demonstrate that combining kernel-based learning with scenario driven uncertainty and adaptive updating provides a flexible and effective approach for forecasting and trading in continuous electricity markets.