Benchmarking high performance HVAC Rule-Based controls with advanced intelligent Controllers: A case study in a Multi-Zone system in Modelica

Lu, Xing; Fu, Yangyang; O’Neill, Zheng

doi:10.1016/j.enbuild.2023.112854

Cited by 21 publications

(6 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 1 depicts conceptual diagrams for the conventional HVAC systems (e.g., CAV or VAV) and the DOAS. The conventional HVAC systems, which represent the typical systems of commercial buildings in the U.S., draw outside air, mix it with return air at the mixing box, and then use cooling and heating coils within the system units to condition the air before distributing it to occupied zones [10] . In such cases, a single air handling unit is designed to cover all the sensible load (by mixing with return air, a cooling coil, and heating coils), latent load (by removing moisture using a cooling coil), and ventilation requirement (by outdoor air).…”

Section: Figurementioning

confidence: 99%

“…These kinds of controls are easy to implement but are likely to be inferior to other more advanced control techniques (e.g., model predictive control, reinforcement learning-based control) in terms of energy performance [27] . In this regard, many studies have been conducted to determine how HVAC systems can be controlled optimally using model predictive controls (MPC) [28] or reinforcement learning (RL)-based controls [29] , [30] , [31] . The aforementioned optimal control strategies (i.e., MPC, RL) often demonstrate promising energy-saving potential.…”

Section: Figurementioning

confidence: 99%

“…In the studies, simple rule extraction (RE)-based controls have been formed to mimic optimal controls. It has been proven that such RE-based controls are almost as energy-efficient as the optimal controls (i.e., near-optimal) while still being straightforward for simple implementations [30] .…”

Section: Figurementioning

confidence: 99%

See 2 more Smart Citations

Optimization-informed rule extraction for HVAC system: A case study of dedicated outdoor air system control in a mixed-humid climate zone

Choi

O’Neill

et al. 2023

Energy and Buildings

Self Cite

View full text Add to dashboard Cite

Section: Figurementioning

confidence: 99%

Section: Figurementioning

confidence: 99%

See 1 more Smart Citation

Optimization-informed rule extraction for HVAC system: A case study of dedicated outdoor air system control in a mixed-humid climate zone

Choi

O’Neill

et al. 2023

Energy and Buildings

Self Cite

View full text Add to dashboard Cite

“…Additionally, RBC was primarily centered on upholding comfort standards, neglecting energy conservation or financial efficiency. The absence of a holistic understanding of the interplay between various HVAC elements also resulted in less ideal outcomes [16][17][18].…”

Section: Introduction 1motivationmentioning

confidence: 99%

Evaluating Reinforcement Learning Algorithms in Residential Energy Saving and Comfort Management

Lazaridis,

Michailidis,

Karatzinis

et al. 2024

Energies

View full text Add to dashboard Cite

The challenge of maintaining optimal comfort in residents while minimizing energy consumption has long been a focal point for researchers and practitioners. As technology advances, reinforcement learning (RL)—a branch of machine learning where algorithms learn by interacting with the environment—has emerged as a prominent solution to this challenge. However, the modern literature exhibits a plethora of RL methodologies, rendering the selection of the most suitable one a significant challenge. This work focuses on evaluating various RL methodologies for saving energy while maintaining adequate comfort levels in a residential setting. Five prominent RL algorithms—Proximal Policy Optimization (PPO), Deep Deterministic Policy Gradient (DDPG), Deep Q-Network (DQN), Advantage Actor-Critic (A2C), and Soft Actor-Critic (SAC)—are being thoroughly compared towards a baseline conventional control approach, exhibiting their potential to improve energy use while ensuring a comfortable living environment. The integrated comparison between the different RL methodologies emphasizes the subtle strengths and weaknesses of each algorithm, indicating that the best selection relies heavily on particular energy and comfort objectives.

show abstract

“…Also, Lu et al [140] compared the G36 sequences of operation to an optimization-based controller (OBC) and a deep reinforcement-learning-based controller (DRLC) in terms of energy efficiency and thermal comfort. A medium-sized office building with a VAV cooling system was simulated in Modelica, and the baseline control system was implemented with the airside and waterside G36 sequences.…”

Section: Background and Previous Workmentioning

confidence: 99%

Fault Detection and Diagnostics in Single-Duct Multiple-Zone Variable Air Volume Air Handling Unit Systems

Torabi

View full text Add to dashboard Cite

Variable air volume (VAV) air handling unit (AHU) systems are the most common heating, ventilation, and air conditioning (HVAC) configuration in North America's commercial buildings. They account for a large fraction of sensors and actuators and are prone to faults due to their control systems' complexity. This research fills the gap in VAV AHU fault detection and diagnostics (FDD) through four parts. First, inverse model-based virtual sensors are developed to detect actuator faults in AHUs. Three algorithms are explored to compensate for the lack of reliable intermediate sensor data for five AHUs. Results indicate that although generated models can act as virtual sensors to identify hard faults, they cannot isolate faults' root causes. To address this uncertainty, the second part introduces a holistic sequential hierarchical FDD framework considering the significance of zone-to-system hard and sequencing logic fault interactions in AHUs and VAVs. The proposed framework follows this fault-checking order: AHU hard faults, VAV hard faults, AHU sequencing logic faults, and VAV sequencing logic faults. Faults are detected by visualizing the discrepancies between the expected and measured operational behaviour. The third part focuses on VAV AHU control systems (sensors, actuators, and sequencing logic), studying human errors during design, installation, and operation. Human errors are identified through a literature review and interviews with control specialists. The most common errors are classified, and interview examples are listed for different building life cycle phases. Since a commonly reported error by interviewees is thermostat misplacement, resulting in negative impacts on AHU supply air temperature (SAT) setpoint, the last step of this research investigates the robustness of sequences of operation to such errors. Fault tolerance of the most vulnerable sequences: SAT setpoint, duct static pressure (DSP) ix

show abstract

Benchmarking high performance HVAC Rule-Based controls with advanced intelligent Controllers: A case study in a Multi-Zone system in Modelica

Cited by 21 publications

References 38 publications

Optimization-informed rule extraction for HVAC system: A case study of dedicated outdoor air system control in a mixed-humid climate zone

Optimization-informed rule extraction for HVAC system: A case study of dedicated outdoor air system control in a mixed-humid climate zone

Evaluating Reinforcement Learning Algorithms in Residential Energy Saving and Comfort Management

Fault Detection and Diagnostics in Single-Duct Multiple-Zone Variable Air Volume Air Handling Unit Systems

Contact Info

Product

Resources

About