A comprehensive review of predictive control strategies in heating, ventilation, and air-conditioning (HVAC): Model-free VS model

X **n, Z Zhang, Y Zhou, Y Liu, D Wang… - Journal of Building …, 2024 - Elsevier
Predictive control offers significant advantages in nonlinear control, high thermal inertia, and
dynamic control. This article uses a Systematic Reviews and Meta-Analyses methodology to …

Prospects and challenges of reinforcement learning-based HVAC control

A Iyanu, H Chang, CS Lee, S Chang - Journal of Building Engineering, 2024 - Elsevier
Increasing worldwide energy demand and the resulting escalations in greenhouse gas
emissions require a reassessment of energy usage in many sectors. The building industry …

Comparative study of model-based and model-free reinforcement learning control performance in HVAC systems

C Gao, D Wang - Journal of Building Engineering, 2023 - Elsevier
Reinforcement learning (RL) shows the potential to address drawbacks of rule-based control
and model predictive control and exhibits great effectiveness in heating, ventilation and air …

[HTML][HTML] Optimization of building demand flexibility using reinforcement learning and rule-based expert systems

X Zhou, S Xue, H Du, Z Ma - Applied Energy, 2023 - Elsevier
The increasing use of renewable energy in buildings requires optimization of building
demand flexibility to reduce energy costs and carbon emissions. Nevertheless, the …

Long-term experimental evaluation and comparison of advanced controls for HVAC systems

X Wang, B Dong - Applied Energy, 2024 - Elsevier
The tremendous energy usage from buildings leads to research studies on their
improvement, among which advanced building control plays an important role. In advanced …

Expert-guided imitation learning for energy management: Evaluating GAIL's performance in building control applications

M Liu, M Guo, Y Fu, Z O'Neill, Y Gao - Applied Energy, 2024 - Elsevier
Abstract The use of Deep Reinforcement Learning (DRL) in building energy management is
often hampered by data efficiency and computational challenges. The long training time …

Safe deep reinforcement learning for building energy management

X Wang, P Wang, R Huang, X Zhu, J Arroyo, N Li - Applied Energy, 2025 - Elsevier
The optimization of building energy systems poses a complex challenge due to the dynamic
nature of building environments and the need for ensuring both energy efficiency and …

Reinforcement learning approach for optimal control of ice-based thermal energy storage (TES) systems in commercial buildings

X Wang, X Kang, J An, H Chen, D Yan - Energy and Buildings, 2023 - Elsevier
Ice-based thermal energy storage (TES) system is effective on load shifting and demand
response in public buildings under time-of-use (TOU) tariffs. The management and …

[HTML][HTML] Heuristic model predictive control implementation to activate energy flexibility in a fully electric school building

N Morovat, AK Athienitis, JA Candanedo… - Energy, 2024 - Elsevier
This paper presents a heuristic model predictive control (MPC) methodology to activate
energy flexibility in fully electric school buildings in cold climates to reduce electricity …

A novel multi-energy load forecasting method based on building flexibility feature recognition technology and multi-task learning model integrating LSTM

P Fan, D Wang, W Wang, X Zhang, Y Sun - Energy, 2024 - Elsevier
Accurate multi-energy load forecasting is prerequisite for achieving balance between supply
and demand in building energy system. The continuous development of building flexibility …