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

2025-10-23

AI Summary

To address the suboptimality arising from the decoupling of load forecasting and scheduling decisions in multi-energy systems, this paper proposes a privacy-preserving Decision-Forward Learning (DFL) framework. Methodologically, DFL departs from conventional prediction-error minimization by optimizing end-to-end scheduling cost directly. It introduces an information-masking mechanism integrating matrix factorization with partial homomorphic encryption, enabling secure cross-departmental collaborative modeling of sensitive load data—resistant to collusion attacks while supporting recoverable computation of decision variables and gradients. Additionally, it incorporates load pattern recognition and personalized model training. Experiments on real-world multi-energy system data demonstrate that, under strict privacy guarantees, the proposed framework achieves significantly lower average daily scheduling costs compared to state-of-the-art methods, validating its effectiveness and practicality.

Technology Category

• Machine Learning: Privacy
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Addresses privacy risks in decision-focused learning for multi-energy systems
• Protects sensitive data during cross-sector model training and optimization
• Reduces dispatch costs while maintaining privacy through encryption techniques

Innovation

• Information masking protects private data during training
• Matrix decomposition and homomorphic encryption prevent unauthorized access
• Privacy-preserving algorithm trains specialized models for load patterns