This work establishes a novel continuous-time dynamic-policy learning paradigm that integrates predictive modeling with real-time adaptive control, advancing data-driven intelligent building operation toward sustainable and autonomous energy management.
Abstract
Rising global energy demand and increasing decarbonization requirements have intensified the need for intelligent building energy management capable of handling nonlinear dynamics and multi-objective operational trade-offs. Conventional discrete-time and simulation-dependent control strategies often struggle to maintain temporal continuity, adaptive responsiveness, and consistent performance across heterogeneous building environments. Addressing these limitations, NODE-RL-BEM (Neural Ordinary Differential Equation Reinforcement Learning for Building Energy Management) introduces a unified continuous-time optimization paradigm that jointly models system dynamics and learns adaptive control policies. The approach integrates heterogeneous operational data, temporal state embeddings, neural differential equation modeling, and multi-objective reinforcement learning within a cohesive architecture designed for predictive and responsive energy optimization. Performance evaluation conducted on the ASHRAE Great Energy Predictor III dataset and the Intelligent Indoor Environment Dataset demonstrates the effectiveness of the proposed framework, achieving 42-48% energy savings, maintaining comfort violations below 0.5%, and improving indoor air quality by 28-35%. The framework further achieves a generalization score of 0.91 across diverse building operational scenarios, confirming strong transferability and stability. Continuous-time dynamics learning improves predictive fidelity and ensures smooth state evolution, while adaptive reinforcement learning enables robust decision-making under dynamic environmental and occupancy variations. Scalable applicability to multi-zone building environments highlights practical deployment feasibility. This work establishes a novel continuous-time dynamic-policy learning paradigm that integrates predictive modeling with real-time adaptive control, advancing data-driven intelligent building operation toward sustainable and autonomous energy management.
A Smart Air Conditioning Management System based on a Deep Q-Network agent capable of dynamically balancing energy use and thermal comfort and demonstrates that reinforcement learning enables adaptive AC control, offering a scalable approach to energy-efficient building management.
Jason Harvey Lorenzo, Justin Kyle O. Ricafort, E. Q. Macabebe· IOP Conference Series: Earth...· 0 citations
Sustainable solutions in the built environment have become essential due to rapid urbanization and rising energy demands. Buildings account for nearly 40% of global energy consumption, making them a critical focus for energy efficiency and environmental sustainability. This paper explores AI-driven energy management systems in smart buildings, highlighting their ability to optimize energy use, reduce costs, and minimize environmental impact while maintaining occupant comfort. By integrating technologies such as IoT, machine learning, predictive analytics, and automation, these systems enable real-time monitoring and adaptive energy optimization. The study reviews traditional building management systems and identifies their limitations, proposing a layered architecture involving data acquisition, processing, prediction, and control. Machine learning techniques like ANN, SVM, and Reinforcement Learning are evaluated for energy forecasting and optimization. Findings indicate that AI-based systems can significantly improve energy efficiency, reduce carbon emissions, and enhance comfort, though challenges such as data privacy, system complexity, and initial costs remain. The research provides a practical framework for developing sustainable, energy-efficient smart buildings.
Meena Krishnan· International Journal of Mod...· 0 citations
HVAC systems represent a major share of building energy consumption. Traditional control strategies are limited in coordinating energy-comfort tradeoffs across multiple zones simultaneously. Reinforcement learning (RL) offers adaptive, data-driven control that optimizes performance over time. However, deploying learned neural network controllers in safety-critical building systems remains challenging due to lack of formal safety guarantees. We propose a safety-certified deep RL framework for multi-zone residential HVAC control. Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) agents are trained in an EnergyPlus/Sinergym simulation to minimize energy consumption while maintaining thermal comfort. Post-training safety certification is performed on the PPO policy using Lipschitz-based forward invariance analysis, building on existing tools for the computation of Lipschitz constants for neural networks, to guarantee constraint satisfaction. Both agents are evaluated over an annual simulation cycle in an eight-zone variable refrigerant flow (VRF) testbed. The PPO agent achieves 67\% comfort violation reduction compared to rule-based control, while the SAC agent achieves 27.6\% energy savings. The PPO policy satisfies formal safety certification with a margin of $2.003^\circ$C. These results demonstrate the feasibility of combining reinforcement learning with post-training safety verification for multi-zone building control.
Oussama Ziadi, A. Rochd, S. I. Kaitouni et al.· 0 citations
Green-building energy-efficiency evaluation requires dynamic integration of spatial topology, environmental sensing, and design-optimization feedback. This study constructs an artificial-intelligence-driven evaluation system that combines BIM, IoT monitoring data, graph neural networks, deep reinforcement learning, and interpretable analysis. Building spaces are modeled as graph nodes, while heat-transfer paths, ventilation channels, equipment zoning, and personnel movement are represented as graph edges. A temporal graph attention network extracts environment–space coupling features, and a soft actor-critic reinforcement-learning model dynamically generates multi-objective evaluation weights under energy-efficiency, thermal-comfort, daylighting, and carbon-emission constraints. An interpretable module integrating attention weights and Shapley values forms an assessment–diagnosis–optimization loop. Experiments on eight operational green-building projects show that the system achieves an RMSE of 2.91 kWh/m2·a, reduces prediction error by 66.3% compared with static indicators, and improves energy-efficiency optimization from 12.4% to 28.6%. The framework supports IoT-based environmental sensing, intelligent energy management, and design decision optimization.
Weiwei Zhang, Xiaojuan Liu, Yi Sun et al.· Advanced Electromagnetics· 0 citations
Microgrids play a critical role in enhancing the flexibility, reliability, and sustainability of modern power systems by integrating distributed energy resources, energy storage systems, and controllable loads. However, the inherent uncertainty of renewable generation and the stochastic nature of load demand pose significant challenges to optimal energy management. To address these issues, this paper proposes a deep reinforcement learning (DRL)-based optimal energy management framework for microgrids. The problem is formulated as a Markov decision process, where the system state captures renewable generation, load demand, and storage status, while the control actions determine power dispatch and energy storage operation. A deep reinforcement learning model is developed to learn optimal control policies through continuous interaction with the environment, enabling adaptive decision-making under dynamic and uncertain conditions. To improve learning efficiency and policy stability, state normalization and reward shaping strategies are incorporated. Furthermore, a constrained optimization mechanism is introduced to ensure operational safety and economic feasibility. Experimental results on benchmark microgrid scenarios demonstrate that the proposed method outperforms conventional rule-based strategies and model-based optimization approaches in terms of operational cost reduction, energy utilization efficiency, and robustness under uncertainty. The results indicate that the proposed DRL-based framework provides an effective and scalable solution for intelligent microgrid energy management.
Li Chen, Hong-Qiao Li, Zhen-Xing Chen et al.· European Conference on Elect...· 0 citations
To address the limitations of existing central air conditioning energy-saving algorithms—such as their inability to achieve conventional optimization or adapt to grid peak shaving, coupled with nonlinear system dynamics, environmental uncertainties, and high-dimensional optimization challenges—we propose an integrated optimization method combining environmental forecasting and DDPG reinforcement learning. This approach employs dual constraints of demand response and thermal comfort to enable adaptive continuous control without prior knowledge models, using an actual office building air conditioning system at a research institute as the test case. Experimental results demonstrate that with adjustable loads of 135 kW (25% of total load), the optimized system achieves approximately 24% annual electricity savings, 31% peak shaving efficiency, and demand response compliance exceeding 91%. By balancing energy conservation, peak load reduction, and comfort requirements, this solution provides robust support for public buildings participating in demand response programs.
Junjie Lin, Zhuofu Deng· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
