Search

The HVAC (Heating, Ventilation, and Air Conditioning) system is an important component of a building's energy consumption, and its primary function is to provide a comfortable thermal environment for occupants. Accurate prediction of occupant thermal comfort is essential for improving building energy utilization as well as health and work efficiency. Therefore, the development of accurate thermal comfort prediction models is of great value. Deep learning based on data-driven techniques has excellent potential for predicting thermal comfort due to the development of artificial intelligence. However, the inability to obtain large quantities of detailed thermal comfort labeling data from residents presents a substantial challenge to the modeling endeavor. This paper proposes a building-to-building transfer learning framework to make deep learning models applicable in data-limited interior building environments, thereby resolving the issue and enhancing model predictive performance. The transfer learning method (TL) is applied to a novel technology dubbed the Transformer model, which has demonstrated outstanding performance in data trend prediction. The model exploits the spatiotemporal relationship of data regarding thermal comfort. Experiments are conducted using the source dataset (Scales project dataset and ASHRAE RP-884 dataset) and the target dataset (Medium US office dataset), and the results show that the proposed TL-Transformer achieves 62.6% accuracy, 57% precision, and a 59% F1 score, and the prediction performance is better than other existing methods. The model is useful for predicting indoor thermal comfort in buildings with limited data, and its validity is verified by experimental results. [ABSTRACT FROM AUTHOR]

A sustainable use of active heating, ventilation, and air conditioning (HVAC) systems is crucial for minimum energy consumption. Currently, research studies are increasingly applying adaptive setpoint temperatures, thus reducing considerably the energy consumption without influencing comfort levels excessively. Most of them, however, are focused on the limit values of adaptive comfort standards without considering the tolerance in users' adaptation capacity. This research study analyzed various tolerance ranges in the recent adaptive thermal comfort model from EN 16798-1:2019 used in setpoint temperatures. The study focused on the south of Europe, considering 47 cities in Spain, 18 cities in Portugal, 13 cities in Greece, and 20 cities in Italy. In addition, such cities were analyzed in three climate scenarios: present time, 2050, and 2100. The results showed that values prefixed by EN 16798-1:2019 for new buildings (tolerance of 0.00 °C) produced significant savings with respect to the static model and that each progressive improvement in users' thermal expectations in 0.25 °C increased the energy consumption between 6.57 and 9.31% in all scenarios analyzed. Even applying a thermal tolerance of 1.50 °C, energy savings are currently produced with respect to the static model. This tendency increases in future scenarios until a thermal tolerance of 1.75 °C. The results of this paper provide greater knowledge about the possible energy increase that the improvement in users' expectations would produce. [ABSTRACT FROM AUTHOR]

Abstract: Air conditioning is essential for maintaining thermal comfort in indoor environments, particularly for hot and humid climates. Today, air conditioning, comprising cooling and dehumidification, has become a necessity in commercial and residential buildings and industrial processes. It accounts for a major share of the energy consumption of a building or facility. In tropical climates, the energy consumed by heating, ventilation and air-conditioning (HVAC) can exceed 50% of the total energy consumption of a building. This significant figure is primarily due to the heavy duty placed on cooling technologies to remove both sensible and latent heat loads. Therefore, there is tremendous potential to improve the overall efficiency of the air-conditioning systems in buildings. Based on today’s practical technology for cooling, the major components of a chiller plant are (1) compressors, (2) cooling towers, (3) pumps (chilled and cooling water) and (4) fans in air handling units. They all consume mainly electricity to operate. When specifying the kW/Rton of a plant, there are two levels of monitoring cooling efficiency: (1) at the efficiency of the chiller machines or the compressors which consume a major amount of electricity; and (2) at the overall efficiency of cooling plants which include the cooling towers, pumps for moving coolant (chilled and cooling water) to all air-handling units. Pragmatically, a holistic approach is necessary towards achieving a low energy input per cooling achieved such as 0.6kW/Rton cooling or lower by considering all aspects of the cooling plant. In this paper, we present a review of recent innovative cooling technology and strategies that could potentially lower the kW/Rton of cooling systems – from the existing mean of 0.9kW/Rton towards 0.6kW/Rton or lower. The paper, broadly divided into three key sections (see Fig. 2), begins with a review of the recent novel devices that enhances the energy efficiency of cooling systems at the component level. This is followed by a review of innovative cooling systems designs that reduces energy use for air conditioning. Lastly, the paper presents recent developments in intelligent air-control strategies and smart chiller sequencing methodologies that reduce the primary energy utilization for cooling. The energy efficient cooling technology, innovative systems designs, and intelligent control strategies described in the paper have been recently researched or are on-going studies. Several have been implemented on a larger scale and, therefore, are examples of practical solutions that can be readily applied to suit specific needs. [Copyright &y& Elsevier]

Generally, conventional controllers for comfort are designed by using on/off control or proportional-integral (PI) control, with little consideration of energy consumption of the system. This paper presents a multi-input-multi-output (MIMO) model predictive control (MPC) for a direct expansion (DX) air conditioning (A/C) system to improve both indoor thermal comfort and air quality, whereas the energy consumption is minimised. The DX A/C system is modelled into a nonlinear system, with a varying speed of compressor and varying speed of supply fan and volume flow rate of supply air being regarded as inputs. We first propose an open loop controller based on an optimisation of energy consumption with the advantage of a unique set of steady states. The MPC controller is proposed to optimise the transient processes reaching the steady state. To facilitate the MPC design, the nonlinear model is linearised around its steady state. MPC is designed for the linearised model. The advantages of the proposed energy-optimised open loop controller and the closed-loop regulation of the MIMO MPC scheme are verified by simulation results. [ABSTRACT FROM AUTHOR]