Search

Smart buildings are rapidly becoming more prevalent, aiming to create energy-efficient and comfortable living spaces. Nevertheless, the design of a smart building is a multifaceted approach that faces numerous challenges, with the primary one being the algorithm needed for energy management. In this paper, the design of a smart building, with a particular emphasis on the algorithm for controlling the indoor environment, is addressed. The implementation and evaluation of the Advantage-Weighted Actor-Critic algorithm is examined in a four-unit residential simulated building. Moreover, a novel self-adapted Advantage-Weighted Actor-Critic algorithm is proposed, tested, and evaluated in both the simulated and real building. The results underscore the effectiveness of the proposed control strategy compared to Rule-Based Controllers, Deep Deterministic Policy Gradient, and Advantage-Weighted Actor-Critic. Experimental results demonstrate a 34.91% improvement compared to the Deep Deterministic Policy Gradient and a 2.50% increase compared to the best Advantage-Weighted Actor-Critic method in the first epoch during a real-life scenario. These findings solidify the Self-Adapted Advantage-Weighted Actor-Critic algorithm's efficacy, positioning it as a promising and advanced solution in the realm of smart building optimization. [ABSTRACT FROM AUTHOR]

Abstract: This paper traces the developments of Building Controls in the 1980s to the present-day focus not only on public health and safety, but also on quality, productivity and sustainability in Singapore. The administrative aspects of Building Controls from a predominately paper-based platform to the current e-platform are also highlighted as part of the nation-wide efforts in Singapore to enhance efficacy and transparency in the application, appeal and approval process. The key important legislations relating to workplace safety and health, buildability and environmental sustainability are presented to demonstrate the government''s resolve in these areas. [Copyright &y& Elsevier]

Highlights • Hardware-in-the-loop (HIL) simulation is increasingly used for building controls. • HIL simulation combines the advantages of pure simulation and field tests. • The agent-based framework for HIL simulation has several distinctive advantages. • An example was used to illustrate the use of the HIL simulation framework. Abstract In general, a hardware-in-the-loop (HIL) building simulation has lower cost and fewer practical limitations (e.g., scheduling issues) than field tests in occupied buildings, while also overcoming limitations of simulations alone by capturing the full behavior of some physical systems, equipment, and components. However, the implementation of an HIL can be difficult due to the scarcity of appropriate tools. This paper presents an agent-based framework for HIL simulation. It can be used for investigation of controller performance via controller-in-the-loop simulations and also HIL for system synthesis. In the latter case, both controllers and major equipment participate in tests to ensure that dynamics of equipment operation are correctly captured in addition to controller performance. The HIL simulation framework presented allows such actual physical parts to be included in the framework while representing others for which behaviors are better known and modeled in simulation models. The mechanism implemented in the framework to synchronize simulations in software with real-time operation of physical equipment is described. As an example, use of the HIL simulation framework is illustrated through a brief study of speed control of the supply fan in the air handling unit of a variable-air-volume building heating, ventilating and air-conditioning system. [ABSTRACT FROM AUTHOR]

Abstract: Adequate indoor illuminance is accepted as one important determinant of conditions for comfort and productivity in offices. This paper uses the results of field surveys in 26 offices in five European countries (France, Greece, Portugal, Sweden and the UK) to investigate what illuminance levels are actually achieved on office desks, what light level is considered ‘best’ by occupants, and how this is affected by outdoor sky conditions and illuminance. The paper also explores how blinds and lights are used by occupants to modify light levels at their desks. The office workers show a remarkable degree of adaptation to different light intensities. They use controls to modify the light level at their desks to almost the same mean level irrespective of the sky conditions outside. There is a small but significant effect of lighting on self-reported productivity which seems to be higher when offices are daylit. [Copyright &y& Elsevier]

• Long term field evaluation of forecast control of heating. • Easy integration with existing installations in buildings. • Widely applicable measure for energy savings around 10%. • Payback time below one heating season. The priority for reaching carbon neutral buildings by 2050 is to first increase energy efficiency in existing buildings by use of easily and widely applicable measures that are verified based on long-term field research. One such solution is a forecast control of heating systems, which can be quickly and easily integrated to existing weather based controls. However, there are still no long-term field evaluation and detailed analyses of the main features of such a system, which would provide a clear picture about the system's energetical and economical features and thus increase their wide application in existing buildings. This paper provides the data from a long term field evaluation of an innovative forecast control of heating systems (forHEAT), which can be easily installed (in less than 2 h) and integrated with existing installations in millions of existing buildings in Europe and throughout the world. The energy consumption for heating was evaluated in seven residential buildings and three public office buildings before and after the installation and use of the forecast control. The resulting energy savings averaged 13.4% in the residential and 10.7% in the public buildings located in continental European climate, with very cold winters. The payback time averaged a 0.6 heating season and in most case studies does not exceed a single heating season. [ABSTRACT FROM AUTHOR]

[Display omitted] Reinforcement learning (RL) based control is widely considered a promising approach in building automation and control as it has demonstrated the potential to deal with complex objectives in adjacent domains like robotics, autonomous vehicles, gaming applications, and advertisement recommendations. When applied to any environment, model-free RL learns to improve its control performance over time without requiring a control model, by receiving and then analyzing feedback from the building environment after each control action. Operational objectives are becoming increasingly complex through the simultaneous consideration of thermal comfort, carbon emissions, grid services, and indoor air quality. In this context, conventional rule-based control approaches are proving sub-optimal, mostly heuristic, and inadequate. The model-free and self learning nature of RL appears promising and attractive as it may address the scalability issues associated with advanced control approaches. However, it suffers from long training times and unstable control behavior during the early stages of its learning process, which makes it unsuitable to be applied directly to buildings. This paper addresses these issues using an inverse reinforcement learning approach (IRL), a technique utilized to learn the objective of a controller agent which is considered an expert in its respective domain. Here, we consider a rule-based control as the expert demonstrator. IRL is different from a direct imitation (i.e., direct mapping of states to actions) of control actions as it tries to find the underlying intent of an expert's policy, providing the controller with a better-generalized policy for unseen states or environments with slightly different dynamics. This approach propels the RL controller's policy to levels similar to or better than that of a rule-based policy before it starts learning by interacting with the building. This makes RL for building energy management applications more practical as it prevents the erratic and exploratory behavior in the initial training period, simultaneously speeding up the learning process when compared to applying an untrained RL agent directly to a building environment. [ABSTRACT FROM AUTHOR]

Smart buildings are rapidly becoming more prevalent, aiming to create energy-efficient and comfortable living spaces. Nevertheless, the design of a smart building is a multifaceted approach that faces numerous challenges, with the primary one being the algorithm needed for energy management. In this paper, the design of a smart building, with a particular emphasis on the algorithm for controlling the indoor environment, is addressed. The implementation and evaluation of the Advantage-Weighted Actor-Critic algorithm is examined in a four-unit residential simulated building. Moreover, a novel self-adapted Advantage-Weighted Actor-Critic algorithm is proposed, tested, and evaluated in both the simulated and real building. The results underscore the effectiveness of the proposed control strategy compared to Rule-Based Controllers, Deep Deterministic Policy Gradient, and Advantage-Weighted Actor-Critic. Experimental results demonstrate a 34.91% improvement compared to the Deep Deterministic Policy Gradient and a 2.50% increase compared to the best Advantage-Weighted Actor-Critic method in the first epoch during a real-life scenario. These findings solidify the Self-Adapted Advantage-Weighted Actor-Critic algorithm’s efficacy, positioning it as a promising and advanced solution in the realm of smart building optimization.

Abstract: Windows are one of the major means by which building occupants control the indoor environment. This research uses results from field surveys to formulate a method for simulation of office buildings to include the effects of window opening behaviour on comfort and energy use. The paper focuses on: (1) what is general window opening behaviour? (2) how can we frame an “adaptive algorithm” to predict whether windows are open? (3) how can the algorithm be used within a simulation to allow the effects of window opening on comfort and energy use to be quantified? We have found that: (1) the proportion of windows open depends on indoor and outdoor conditions, (2) logistic regression analysis can be used to formulate an adaptive algorithm to predict the likelihood that windows are open, (3) the algorithm when embedded in simulation software provides insights not available using more usual simulation methods and allows the quantification of the effect of building design on window opening behaviour, occupant comfort and building energy use. [Copyright &y& Elsevier]

An adaptive control algorithm (ACA) has been developed as an alternative to fixed temperature setpoint controls within buildings. This paper describes both the theory behind the ACA and the findings from an EU-funded research project, smart controls and thermal comfort (SCATs), from which the form of the ACA was developed. The ACA was also tested in two air-conditioned buildings as part of the SCATs project and the results are presented. The results show that use of the ACA has potential for energy savings in the climate-control services of a building with no reduction in the perceived thermal comfort levels of that building’s occupants. Further refinement and testing of the ACA is required before it can be marketed. [Copyright &y& Elsevier]

In the last few decades, researchers have shown that advanced building controllers can reduce energy consumption without negatively impacting occupants' wellbeing and help to manage building systems, which are becoming increasingly complex. Nevertheless, the lack of benefit awareness and demonstration projects undermines stakeholders' trust, justifying the reluctance to approve new controls in the industry. Therefore, it is necessary to support the development of controls through solid arguments testifying to the performance gain that can be achieved. However, the absence of standardized and systematic testing methods limits the generalization of results and the ability to make fair cross-study comparisons. This study presents an overview of the different benchmarking approaches used to assess control performance. Our goal is to highlight trends, limitations, and controversies through analytics to support the definition of best practices, which remains a widely discussed topic in this research area. We aim to focus on simulation-based benchmarking, which is regarded as a promising solution to overcome the time and cost requirements related to field or hardware-in-the-loop testing. We identify and investigate four key steps relating to virtual benchmarking: defining the key performance indicators, specifying the reference control, characterizing the test scenarios, and post-processing the results. This work confirmed the expected heterogeneity, underlined recurrent features with the help of analytics, and recognized limits and open challenges. [ABSTRACT FROM AUTHOR]