To conserve building energy, optimal operation of a building’s energy systems, especially heating, ventilation and air-conditioning (HVAC) systems, is important. This study focuses on the optimization of the central chiller plant, which accounts for a large portion of the HVAC system’s energy consumption. Classic optimal control methods for central chiller plants are mostly based on system performance models which takes much effort and cost to establish. In addition, inevitable model error could cause control risk to the applied system. To mitigate the model dependency of HVAC optimal control, reinforcement learning (RL) algorithms have been drawing attention in the HVAC control domain due to its model-free feature. Currently, the RL-based optimization of central chiller plants faces several challenges: (1) existing model-free control methods based on RL typically adopt single-agent scheme, which brings high training cost and long training period when optimizing multiple controllable variables for large-scaled systems; (2) multi-agent scheme could overcome the former problem, but it also requires a proper coordination mechanism to harmonize the potential conflicts among all involved RL agents; (3) previous agent coordination frameworks (identified by distributed control or decentralized control) are mainly designed for model-based control methods instead of model-free controllers. To tackle the problems above, this article proposes a multi-agent, model-free optimal control approach for central chiller plants. This approach utilizes game theory and the RL algorithm SARSA for agent coordination and learning, respectively. A data-driven system model is set up using measured field data of a real HVAC system for simulation. The simulation case study results suggest that the energy saving performance (both short- and long-term) of the proposed approach (over 10% in a cooling season compared to the rule-based baseline controller) is close to the classic multi-agent reinforcement learning (MARL) algorithm WoLF-PHC; moreover, the proposed approach’s nature of few pending parameters makes it more feasible and robust for engineering practices than the WoLF-PHC algorithm.

As a space for daily life, the community directly affects residents’ lives and has a significant impact on residents’ health. Integrating the concept of health into community construction can promote comprehensive and full-cycle health protection. This study explored the potential contribution of the DGNB system to community health and well-being and collected residents’ perceptions. A community assessment model was established to analyze how the community environment would affect residents’ health. The results show that compared with other community evaluation systems, the DGNB system has a more balanced weight and more comprehensive content, covering many factors that influence physical health, mental health, and social health. Residents pay more attention to personal safety, lifestyle, physical environment, community service, and management, which are related to their well-being and health. The assessment model is helpful to improve the community healthy environment and residents’ life quality.

Model-free reinforcement learning (RL) techniques are currently drawing attention in the control of heating, ventilation, and air-conditioning (HVAC) systems due to their minor pre-conditions and fast online optimization. The simultaneous optimal control of multiple HVAC appliances is a high-dimensional optimization problem, which single-agent RL schemes can barely handle. Hence, it is necessary to investigate how to address high-dimensional control problems with multiple agents. To realize this, different multi-agent reinforcement learning (MARL) mechanisms are available. This study intends to compare and evaluate three MARL mechanisms: Division, Multiplication, and Interaction. For comparison, quantitative simulations are conducted based on a virtual environment established using measured data of a real condenser water system. The system operation simulation results indicate that (1) Multiplication is not effective for high-dimensional RL-based control problems in HVAC systems due to its low learning speed and high training cost; (2) the performance of Division is close to that of the Interaction mechanism during the initial stage, while Division’s neglect of agent mutual inference limits its performance upper bound; (3) compared to the other two, Interaction is more suitable for multi-equipment HVAC control problems given its performance in both short-term (10% annual energy conservation compared to baseline) and long-term scenarios (over 11% energy conservation).

In building HVAC systems, a chilled water flowmeter is an important sensor. Its reading can be used to measure the real-time cooling load, which is a critical variable for the automated control of building HVAC systems, especially central chiller plants. To maintain accurate reading data, fault detection and diagnosis (FDD) of flowmeters is necessary. The available FD/FDD methods for chilled water flowmeters have several common disadvantages: (1) high requirements on sensor integrity: multiple sensors are usually involved in the construction of energy balance models; (2) complex methodology: the fault of any monitored sensor could trigger a detection hit, and a diagnosis procedure must be used to isolate the faulty sensor; and (3) the more sensors that are involved, the more difficult it is to collect fault-free historical data for the establishment of a fault-free benchmark. To address these problems, a user-friendly fault detection (FD) method for building chilled water flowmeters is proposed in this study. The proposed method requires three types of variables to function: the pump frequency, the pump power, and the measured chilled water flow rate on the header pipe. The real-time pump frequency and electrical power data that are collected by VFDs/power meters are used to estimate the true value of the chilled water flow rate with random forest regressor. An auxiliary alarm rule is proposed to tackle the trade-off issue between detector sensitivity and false alarm rate. Field data of a real HVAC system are used in a case study to evaluate the performance of the proposed method in comparison with three existing FD methods. The results of the validation case study suggest that compared to existing FD methods, which are based on the physical pump model, ensemble learning and clustering techniques, the proposed method could realize higher hit rates and higher alarm rates when confronting different faults (bias, noise and drift) at various levels. Besides, due to the proposed alarm rule, false alarms caused by occasional data errors are completely evaded. Sensitivity analysis to the proposed method indicates that the random forest with default hyperparameters is good enough for the FD task. In brief, the good features of the proposed method (i.e., the simple workflow, low sensor requirements, accessible robust input variable data, handy estimation model, auxiliary alarm rule with tight detection threshold) render the proposed method feasible and user-friendly for engineering practice.

To realize building energy conservation, appropriate operation of building energy systems is necessary. A chilled water pump, an essential component for chilled water transportation in building cooling systems, consumes substantial energy. Hence, its operation should be optimized. Previous studies on optimal pump control mostly focused on pump speed/frequency control, while the control of pump running number is usually too passive to realize energy-saving objectives. Moreover, existing relevant studies have some disadvantages, such as (1) too complex a workflow for maintenance; (2) dependence on accurate system performance models that take substantial data and labor to establish; and (3) high requirements on monitoring and sensors. To tackle those problems, this article proposes a simple, feasible approach to optimize the running number (on/off status) of chilled water pumps for building energy conservation. The proposed method is merely based on similarity/affinity laws and pump performance curves feasible for engineering practices. It has been implemented on a real cooling system in a battery factory. Our results suggest that: (1) based on similarity/affinity laws and pump performance curves, the estimation of potential targeted pump working points is accurate enough for optimal control (the flow rate estimation error is less than 2%, the frequency estimation error is less than 1 Hz); (2) the energy-saving effect of this control method is evident (20% of pump energy is saved by the proposed method compared to the former control logic); (3) the water grid operation condition is maintained well: cooling supply is not sacrificed by the control intervention (compared to the working condition before the intervention, grid pressure difference changed by 1.4%, flow rate changed by 2.6%). Regarding the low preconditions, simple workflow, and acceptable energy-saving performance of the proposed method, it is suitable for energy conservation in building cooling systems.