Assessment of Building Automation and Control Systems in Danish Healthcare Facilities in the COVID-19 Era

A well-designed and properly operated building automation and control system (BACS) is key to attaining energy-efficient operation and optimal indoor conditions. In this study, three healthcare facilities of a different type, age, and use are considered as case studies to investigate the functionalities of BACS in providing optimal air quality and thermal comfort. IBACSA, the first-of-its-kind instrument for BACS assessment and smartness evaluation, is used to evaluate the current systems and their control functionalities. The BACS assessment is reported and analyzed. Then, three packages of improvements were implemented in the three cases, focusing on (1) technical systems enhancement, (2) indoor air quality and comfort, and (3) energy efficiency. It was found that the ventilation system domain is the best performer in the three considered cases with an overall score of 52%, 89% and 91% in Case A, B, and C,, respectively. On the other hand, domestic hot water domain scores are relatively low, indicating that this is an area where Danish healthcare facilities need to provide more concentration on. A key finding indicated by the assessment performed is that the three buildings score relatively very low when it comes to the impact criteria of energy flexibility and storage.

Temporal Consistency-Based Loss Function for Both Deep Q-Networks and Deep Deterministic Policy Gradients for Continuous Actions

Artificial intelligence (AI) techniques in power grid control and energy management in building automation require both deep Q-networks (DQNs) and deep deterministic policy gradients (DDPGs) in deep reinforcement learning (DRL) as off-policy algorithms. Most studies on improving the stability of DRL have addressed these with replay buffers and a target network using a delayed temporal difference (TD) backup, which is known for minimizing a loss function at every iteration. The loss functions were developed for DQN and DDPG, and it is well-known that there have been few studies on improving the techniques of the loss functions used in both DQN and DDPG. Therefore, we modified the loss function based on a temporal consistency (TC) loss and adapted the proposed TC loss function for the target network update in both DQN and DDPG. The proposed TC loss function showed effective results, particularly in a critic network in DDPG. In this work, we demonstrate that, in OpenAI Gym, both “cart-pole” and “pendulum”, the proposed TC loss function shows enormously improved convergence speed and performance, particularly in the critic network in DDPG.

Special Issue on Electronic Systems and Energy Harvesting Methods for Automation, Mechatronics and Automotive

Electronic apparatus have become essential components of civil and industrial systems, including the automotive, home and building automation, Industrial IoT (Internet of Things) and control applications, and playing an essential role in improving security, efficiency, manageability, and rapid feedback [...]