Perturbed Decision-Focused Learning for Modeling Strategic Energy Storage

TL;DR

This paper introduces a decision-focused learning framework with perturbation techniques for modeling energy storage, effectively integrating physical models into machine learning for improved arbitrage and behavior prediction.

Contribution

It develops a novel end-to-end decision-focused approach with perturbation-based loss functions that incorporate physical energy storage models into machine learning pipelines.

Findings

Achieves highest profit in energy arbitrage tasks.

Outperforms benchmarks in energy storage behavior prediction.

Demonstrates effectiveness on real and synthetic data.

Abstract

This paper presents a novel decision-focused framework integrating the physical energy storage model into machine learning pipelines. Motivated by the model predictive control for energy storage, our end-to-end method incorporates the prior knowledge of the storage model and infers the hidden reward that incentivizes energy storage decisions. This is achieved through a dual-layer framework, combining a prediction layer with an optimization layer. We introduce the perturbation idea into the designed decision-focused loss function to ensure the differentiability over linear storage models, supported by a theoretical analysis of the perturbed loss function. We also develop a hybrid loss function for effective model training. We provide two challenging applications for our proposed framework: energy storage arbitrage, and energy storage behavior prediction. The numerical experiments on real price data demonstrate that our arbitrage approach achieves the highest profit against existing methods. The numerical experiments on synthetic and real-world energy storage data show that our approach achieves the best behavior prediction performance against existing benchmark methods, which shows the effectiveness of our method.