Building Energy Management

Follow this topic Ask about this topic

Building energy management studies how to operate heating, cooling, ventilation, storage, and flexible loads to reduce costs and emissions while maintaining comfort and indoor air quality. Common approaches include model predictive control with thermal or resistance-capacitance models, forecasting and transfer learning, and reinforcement learning with reward shaping or safety filters; occupancy sensing and human preferences increasingly inform these controls. Researchers evaluate methods using building simulators, real operational data, and benchmarks for forecasting, energy use, comfort, and grid flexibility. A central challenge is making simulated improvements transfer safely across buildings and operating conditions, especially when comfort, equipment limits, occupant needs, and deployment reliability can conflict with energy savings.

Latest papers

45 papers4 papers in the last four weeks, down 43% on the four weeks before. 0.0% of all new papers.

PIRS: Physics-Informed Reward Shaping for SAC-Based Building Energy Management
May 27, 2026Shadmehr Zaregarizi, Khashayar YavariMulti-Objective Reinforcement Learning Reward Shaping
Politecnico di Torino Turin, Italy
OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
May 27, 2026Shadmehr Zaregarizi, Khashayar YavariReward Shaping Algorithmic Fairness
Politecnico di Torino Turin, Italy
A Unified Python Framework for Direct PPO-based Control of AHUs with Economizer Logic and CO2-Constrained Ventilation
May 23, 2026Erfan Haghighat Damavandi, Davide Papurello, Mahdi Alibeigi +3RL Control Constrained RL
a Research and Development Department Owtana Tech- Turin, Italy · b Department of Energy Politecnico di Torino- Turin, Italy · c Department of Energy University of Tehran- Tehran, Iran +1
Counter-Dyna: Data-Efficient RL-Based HVAC Control using Counterfactual Building Models
May 6, 2026Jan Marco Ruiz de Vargas, Fabian Raisch, Zoltan Nagy +2Neural Surrogate Modeling Building Energy Management
Technical University of Munich Munich, Germany · Technical University of Applied Sciences Rosenheim Rosenheim, Germany · Eindhoven University of Technology Eindhoven, Netherlands +1
Safe Deep Reinforcement Learning for Building Heating Control and Demand-side Flexibility
Apr 17, 2026Colin Jüni, Mina Montazeri, Yi Guo +3RL Control Building Energy Management
Urban Energy Systems Laboratory, Swiss Federal Laboratories for Materials Science and Technology, Dubendorf, Switzerland. · School of Automation, Beijing Institute of Technology, Haidian District, Beijing, China · Reliability and Risk Engineering Laboratory, ETH Zürich, CH-8092, Switzerland.
Neural Parameter Estimation of RC Thermal Building Models for Model Predictive Control
Apr 7, 2026Fabian Raisch, Timo Germann, Sang-Woo Ham +3Parameter Estimation Building Energy Management
Technical University of Applied Sciences Rosenheim, Rosenheim, Germany · Technical University of Munich, Munich, Germany · Ludwig Maximilian University of Munich, Munich, Germany +2
Thermal-GEMs: Generalized Models for Building Thermal Dynamics
Apr 7, 2026Felix Koch, Fabian Raisch, Benjamin TischlerTime Series Forecasting Multi-Source Domain Adaptation
Technical University of Applied Sciences Rosenheim, Rosenheim, Germany · Technical University of Munich, Munich, Germany
End-to-End Learning-based Operation of Integrated Energy Systems for Buildings and Data Centers
Mar 31, 2026Zhenyu Pu, Yu Yang, Liang Yu +1Data Center Energy Management Learning to Optimize
School of Automation Science and Engineering, Xi’an Jiaotong University, Shaanxi, China · College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China · Center for Intelligent and Networked Systems, Department of Automation, Tsinghua University, Beijing 100084, China +1
An Optimal Battery-Free Approach for Emission Reduction by Storing Solar Surplus in Building Thermal Mass
Mar 30, 2026Michela Boffi, Jessica Leoni, Fabrizio Leonforte +2Building Energy Management Heating, Ventilation, and Air Conditioning Control
Politecnico di Milano, Piazza Leonardo da Vinci, Milano, 20133, Milano, Italy
Experimental study on surveillance video-based indoor occupancy measurement with occupant-centric control
Mar 27, 2026Irfan Qaisar, Kailai Sun, Qingshan Jia +1Video Surveillance Building Energy Management
Center for Intelligent and Networked Systems, Department of Automation, BNRist, Tsinghua University, Beijing, 100084, China · Urban Mobility Lab, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Singapore-MIT Alliance for Research and Technology Centre, Massachusetts Institute of Technology, 138602, Singapore
HeatPrompt: Zero-Shot Vision-Language Modeling of Urban Heat Demand from Satellite Images
Feb 23, 2026Kundan Thota, Xuanhao Mu, Thorsten Schlachter +1Building Energy Management Vision-Language Models
Institute for Automation and Applied Informatics (IAI), Karlsruhe Institute of Technology (KIT), Germany
Multimodal Modular Chain of Thoughts in Energy Performance Certificate Assessment
Feb 20, 2026Zhen Peng, Peter J. BentleyMultimodal CoT Reasoning Building Energy Management
Department of Physics and Astronomy, University College London, Gower Street, London WC1E 6BT, UK · Department of Computer Science, University College London, Gower Street, London WC1E 6BT, UK
Catalyzing Informed Residential Energy Retrofit Decisions via Domain-Specific LLM
Feb 19, 2026Lei Shu, Dong Zhao, Jianli Chen +3LLM Decision-Making Building Energy Management
School of Planning, Design, and Construction, Michigan State University, East Lansing, Michigan, USA. · Human-Building Systems Lab, Michigan State University, East Lansing, Michigan, USA. · Department of Civil and Environmental Engineering, Michigan State University, East Lansing, Michigan, USA. +2
Human-AI Collaboration in Large Language Model-Integrated Building Energy Management Systems: The Role of User Domain Knowledge and AI Literacy
Feb 18, 2026Wooyoung Jung, Kahyun Jeon, Prosper Babon-AyengHuman-AI Collaboration Human-AI Interaction
The University of Arizona · Illinois Institute of Technology
Constrained Reinforcement Learning for Safe Heat Pump Control
Sep 29, 2024Baohe Zhang, Lilli Frison, Thomas Brox +1RL Control Constrained RL
Faculty of Computer Science, University of Freiburg, Germany · Systems Control and Optimization Laboratory, Department of Microsystems Engineering, University of Freiburg, Germany

May 27, 2026J/K move · Enter open · S save

PIRS: Physics-Informed Reward Shaping for SAC-Based Building Energy Management

Shadmehr Zaregarizi, Khashayar Yavari

Politecnico di Torino Turin, Italy

Multi-Objective Reinforcement Learning Reward Shaping Building Energy Management Heating, Ventilation, and Air Conditioning Control

Open paper AskPDF arXiv

Occupant comfort and grid-aware energy efficiency are competing objectives whose joint optimization depends critically on how reward functions are specified in deep reinforcement learning (DRL) controllers for buildings. Yet reward design remains largely ad hoc: comfort terms are either hand-tuned heuristics or simple temperature-deviation proxies without explicit grounding in thermal-comfort physics. We present PIRS (Physics-Informed Reward Shaping), which replaces these ad-hoc comfort proxies with the ISO 7730 Predicted Mean Vote (PMV) formulation inside a weighted multi-objective reward for Soft Actor-Critic (SAC). By anchoring the comfort signal in the ISO 7730 PMV formulation, PIRS improves reward interpretability and provides a standards-grounded comfort proxy without changing any other component of the learning pipeline. We evaluate PIRS in CityLearn v2.1.2 (challenge 2022 phase 1) with a central SAC agent trained for 50k steps over five random seeds, and compare against a rule-based controller (RBC), a manually engineered reward (E2), an energy-only reward (E3), and a naive temperature-deviation comfort reward (E4). District-level key performance indicators (KPIs), reported as ratios versus RBC, show that PIRS attains cost, carbon, and electricity metrics on par with the manual baseline while substantially outperforming non-physics-grounded designs -- particularly on load ramping (1.78x vs. ~2.4x RBC) and daily peak demand. All DRL policies remain above RBC at this training budget; we interpret this gap honestly and position PIRS as an interpretable, standards-aligned foundation for reward design rather than a claim of dominance over classical control at limited compute.