Regime-Aware Conditional Neural Processes with Multi-Criteria Decision Support for Operational Electricity Price Forecasting
This work addresses electricity price forecasting for market participants in the German electricity market, representing an incremental improvement with domain-specific application.
This paper tackles 24-hour electricity price forecasting in the German market by integrating Bayesian regime detection with conditional neural processes, and evaluates models through operational utility assessments. The proposed R-NP model emerged as the most balanced and preferred solution across 2021-2023 in multi-criteria evaluation, though LEAR sometimes yielded superior absolute profits.
This work integrates Bayesian regime detection with conditional neural processes for 24-hour electricity price prediction in the German market. Our methodology integrates regime detection using a disentangled sticky hierarchical Dirichlet process hidden Markov model (DS-HDP-HMM) applied to daily electricity prices. Each identified regime is subsequently modeled by an independent conditional neural process (CNP), trained to learn localized mappings from input contexts to 24-dimensional hourly price trajectories, with final predictions computed as regime-weighted mixtures of these CNP outputs. We rigorously evaluate R-NP against deep neural networks (DNN) and Lasso estimated auto-regressive (LEAR) models by integrating their forecasts into diverse battery storage optimization frameworks, including price arbitrage, risk management, grid services, and cost minimization. This operational utility assessment revealed complex performance trade-offs: LEAR often yielded superior absolute profits or lower costs, while DNN showed exceptional optimality in specific cost-minimization contexts. Recognizing that raw prediction accuracy doesn't always translate to optimal operational outcomes, we employed TOPSIS as a comprehensive multi-criteria evaluation layer. Our TOPSIS analysis identified LEAR as the top-ranked model for 2021, but crucially, our proposed R-NP model emerged as the most balanced and preferred solution for 2021, 2022 and 2023.