End-to-End Differentiable Predictive Control with Probabilistic Constraint-Satisfaction Guarantees for Building Demand Response

[2603.22104] End-to-End Differentiable Predictive Control with Probabilistic Constraint-Satisfaction Guarantees for Building Demand Response Skip to main content Search Submit Donate Log in Electrical Engineering and Systems Science > Systems and Control arXiv:2603.22104 (eess) [Submitted on 23 Mar 2026 ( v1 ), last revised 24 Aug 2026 (this version, v2)] Title: End-to-End Differentiable Predictive Control with Probabilistic Constraint-Satisfaction Guarantees for Building Demand Response Authors: Kaipeng Xu , Zhuo Zhi , Ruixuan Zhao , Keyue Jiang View PDF HTML (experimental) Abstract: Building Demand Response (DR) benefits from Model Predictive Control (MPC) because thermal flexibility can be optimized over a future horizon while enforcing operational constraints, but the repeated online optimization required by MPC motivates Differentiable Predictive Control (DPC) as a computationally efficient explicit-policy alternative. Conventional DPC, however, separates model identification from policy optimization and remains sensitive to plant-model mismatch. This paper proposes an End-to-End DPC (E2E-DPC) framework that jointly optimizes the learned dynamics model and control policy using prediction, constraint, and economic objectives. Stage-wise conformal prediction (CP) calibrates recursive prediction errors to construct horizon-dependent tightened state constraints, while independent Hoeffding certification provides a high-confidence lower bound on plant-level satisfaction of the original state and input constraints under receding-horizon deployment. The framework is evaluated in a high-fidelity residential building simulation using EnergyPlus through the Energym interface and compared with online MPC and conventional DPC. Constraint tightening eliminates thermal violations for both DPC variants in the stress test and reduces violations by 99.4 percent for online MPC. Compared with conventional DPC, E2E-DPC reduces the mean constraint-tightening margin at the first prediction stage by 31.0 percent and increases the median certified plant-level lower bound from 0 to 0.814. The results further reveal a trade-off between stronger certification of plant-level constraint satisfaction and the ability to maintain nonempty tightened state sets as the prediction horizon increases, with stronger multi-step identification mitigating this trade-off. Comments: 18 pages, 5 figures. Substantially revised version: replaced the previous deterministic tube-based constraint-tightening formulation with stage-wise conformal prediction and independent Hoeffding certification; expanded theoretical analysis, experiments, and comparisons Subjects: Systems and Control (eess.SY) Cite as: arXiv:2603.22104 [eess.SY] (or arXiv:2603.22104v2 [eess.SY] for this version) https://doi.org/10.48550/arXiv.2603.22104 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Kaipeng Xu [ view email ] [v1] Mon, 23 Mar 2026 15:34:49 UTC (6,485 KB) [v2] Mon, 24 Aug 2026 21:34:39 UTC (6,701 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: eess.SY < prev | next > new | recent | 2026-03 Change to browse by: cs cs.SY eess References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• End-to-End Differentiable Predictive Control with Probabilistic Constraint-Satisfaction Guarantees for Building Demand Response#670531
• Mixed-Integer Nonlinear Differentiable Predictive Control for Underground Pumped Hydro Energy Storage Systems#1011676
• Abstraction and Hierarchy Emerge from Control Feasibility Constraints#223255
• Anchor-and-Resume Concession Under Dynamic Pricing for LLM-Augmented Freight Negotiation#124086
• Artificial Intelligence Based Estimation of Offsite Panel Requirements in Building Construction: Challenges and Opportunities#458213