A Deep Q-Network for Balancing Energy Savings and Occupant Comfort in an Air Conditioned Environment

AI-driven optimization: revolutionizing energy efficiency in modern buildings.

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.

Safe Deep Reinforcement Learning for Energy-Efficient HVAC Control in Multi-Zone Residential Buildings

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.

Research on air conditioning load regulation and energy saving in public buildings based on reinforcement learning

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.

Enhancing energy management in multi-zone buildings using the on-policy reinforcement learning algorithm SARSA

Design of a Smart HVAC System Using AI-Based Controls

A Smart HVAC system that integrates Artificial Intelligence (AI), Internet of Things (IoT) sensors, cloud-based analytics, and machine learning to enhance energy efficiency, thermal comfort, and reliability is presented.

Enhanced Energy Efficiency and Adaptive Indoor Temperature Management for Residential Buildings Using Advanced Model Predictive Control Strategy

In addressing the imperative need to optimize heating, ventilation, and air-conditioning (HVAC) systems for improved indoor comfort and reduced energy expenditures within buildings, Model Predictive Control (MPC) emerges as a highly effective algorithm for the proactive management of intricate HVAC systems. This article introduces an MPC model designed with the dual objectives of guaranteeing thermal comfort and minimizing energy consumption in residential heating contexts. The model, developed and simulated using the MATLAB Simulink platform, achieves these objectives through meticulous adjustments of MPC parameters, ensuring optimal heating energy consumption while sustaining comfort levels. Compared to a traditional PID controller, the proposed MPC demonstrated superior energy efficiency, achieving up to 22.7% in energy savings. These findings underscore the promising potential of MPC for intelligent management of residential heating systems, striking a balance between comfort and energy efficiency. The results highlight the practical advantages of adopting MPC in residential settings, paving the way for more sustainable and comfortable living environments.