Privacy-preserving Decision-focused Learning for Multi-energy Systems

TL;DR

This work tackles privacy in decision-focused learning for multi-energy systems (MES) dispatch by introducing a privacy-preserving framework based on information masking (IM). It couples forward-dispatch computations on masked data with gradient recovery for training through an OptNet/KKT-based approach, and strengthens security with a safety protocol using matrix blocking and homomorphic encryption. An adaptive load-pattern recognition (LPR) module enables pattern-specific DFL to address load heterogeneity without leaking sensitive profiles. Case studies on real MES data demonstrate that privacy-preserving DFL can reliably reduce average dispatch costs while protecting sector data and model parameters.

Abstract

Decision-making for multi-energy system (MES) dispatch depends on accurate load forecasting. Traditionally, load forecasting and decision-making for MES are implemented separately. Forecasting models are typically trained to minimize forecasting errors, overlooking their impact on downstream decision-making. To address this, decision-focused learning (DFL) has been studied to minimize decision-making costs instead. However, practical adoption of DFL in MES faces significant challenges: the process requires sharing sensitive load data and model parameters across multiple sectors, raising serious privacy issues. To this end, we propose a privacy-preserving DFL framework tailored for MES. Our approach introduces information masking to safeguard private data while enabling recovery of decision variables and gradients required for model training. To further enhance security for DFL, we design a safety protocol combining matrix decomposition and homomorphic encryption, effectively preventing collusion and unauthorized data access. Additionally, we developed a privacy-preserving load pattern recognition algorithm, enabling the training of specialized DFL models for heterogeneous load patterns. Theoretical analysis and comprehensive case studies, including real-world MES data, demonstrate that our framework not only protects privacy but also consistently achieves lower average daily dispatch costs compared to existing methods.

Figures (7)

• Figure 1: Illustration of DFL for MES
• Figure 2: The basic idea of IM. The super-plane illustrates the mapping from decision variables ($x$, $y$) to the objective ($z$) for both the original and masked optimization problems, where masking is achieved by scaling and rotating the variable
• Figure 3: Illustration of IM-based DFL framework
• Figure 4: Proposed safety protocol for privacy-preserving DFL
• Figure 5: Original and masked cluster centers