Search

Assessing building energy consumption is of paramount significance in sustainability and energy efficiency (EE) studies. The development of an accurate EE prediction model is pivotal for optimizing energy resources and facilitating effective building planning. Traditional physical modeling approaches are encumbered by high complexity and protracted modeling cycles. In this paper, we introduce a novel evolutionary dendritic neural regression (EDNR) model tailored to forecasting residential building EE. Acknowledging the vast landscape and complexity of the EDNR weight space, coupled with the inherent susceptibility of traditional optimization algorithms to local optima, we propose a complex network-guided strategy-based differential evolution algorithm for training the EDNR model. This strategy adeptly strikes a balance between exploration and exploitation during the search process, significantly enhancing the predictive and generalization capacities of EDNR. To our knowledge, this study represents the inaugural application of dendritic neural regression in real-world prediction scenarios. Extensive experimental findings demonstrate the efficacy of EDNR in accurately predicting building EE with commendable performance. Furthermore, the results of two nonparametric statistical tests affirm the validity and stability of EDNR. Consequently, our proposed methodology exhibits high potential and competitiveness in machine learning applications within the energy domain. [ABSTRACT FROM AUTHOR]

Global warming, climate change and the energy crisis are trending topics around the world, especially within the energy sector. The rising cost of energy, greenhouse gas (GHG) emissions and global temperatures stem from the over-reliance on fossil fuel as the major energy resource. These challenges have highlighted the need for alternative energy resources and urgent intervention strategies like energy consumption reduction and improving energy efficiency. The heating, ventilation, and air-conditioning (HVAC) system in a building accounts for about 70% of energy consumption, and a decision to reduce energy consumption may impact the indoor environmental quality (IEQ) of the building. It is important to adequately balance the tradeoff between IEQ and energy management. Artificial intelligence (AI)-based solutions are being explored for improving building energy performance without compromising IEQ. This paper systematically reviews recent studies on AI and machine learning (ML) for building energy management and IEQ by exploring common use areas, the methods or algorithms applied and the results obtained. The overall purpose of this research is to add to the existing body of work and to highlight energy-related AI applications in buildings and the related gaps. The result shows five common application areas: thermal comfort and indoor air quality (IAQ) control; energy management and energy consumption prediction; indoor temperature prediction; anomaly detection; and HVAC controls. Gaps involving policy, real-life scenario applications, and insufficient study of the visual and acoustic comfort areas are also identified. Very few studies take into consideration the need to follow IEQ standards in the selection process and positioning of sensors in AI applications for IEQ in buildings. This study reveals a need for more systematically summarized research. [ABSTRACT FROM AUTHOR]

Non-residential buildings are responsible for more than a third of global energy consumption. Estimating building energy consumption is the first step towards identifying inefficiencies and optimizing energy management policies. This paper presents a study of Deep Learning techniques for time series analysis applied to building energy prediction with real environments. We collected multisource sensor data from an actual office building under normal operating conditions, pre-processed them, and performed a comprehensive evaluation of the accuracy of feed-forward and recurrent neural networks to predict energy consumption. The results show that memory-based architectures (LSTMs) perform better than stateless ones (MLPs) even without data aggregation (CNNs), although the lack of ample usable data in this type of problem avoids making the most of recent techniques such as sequence-to-sequence (Seq2Seq). [ABSTRACT FROM AUTHOR]

In areas with a deep floor plan, the distribution of natural light is not uniform. Consequently, relying solely on daylight may not suffice to meet the space's lighting requirements, necessitating the use of artificial lighting in darker areas. Therefore, a lighting system is needed that not only controls the glare near the windows but also increases the light at the end of the room and provides uniform daylight. One of the widely used systems is the "light shelf", which has three main functions: shading, increasing the depth of light penetration, and reducing glare. Review articles about light shelves were published in 2015 and 2017, while more than 80% of the studies have been carried out since 2016, and light shelves with more diverse forms and dynamic elements and many consolidations have been proposed. Therefore, there is a need for a more comprehensive review. The main question of this research is how different parameters (including climate, material, ceiling, and integrated systems) can help to increase the efficiency of light shelves. By using a systematic review, studies in the past three decades were classified in order to determine the effect of these parameters on improving lighting performance and controlling solar heat gain. [ABSTRACT FROM AUTHOR]

Thermal comfort is a complex issue in the built environment due to the physiological and psychological differences of each individual in a building. There is a growing worry over the environmental implications of energy use as a result of the warming of the global climate and the growth in the number of instances of extreme weather events. Many review articles have been written, but these reviews have focused on a specific aspect of occupant behavior and thermal comfort. To research the trends of thermal comfort and energy, this research adopted mixed reviews, i.e., quantitative and qualitative, to understand the state-of-the-art factors affecting the thermal comfort of occupants concerning energy, different occupant modeling approaches, functions, and limitations. The in-depth qualitative discussion provides deeper insights into the impacts of occupant behaviors, factors affecting thermal comfort, and occupant behavior modeling approaches. This study classified occupant behaviors into five categories: occupant characteristics, perceptions of the occupant, realistic behaviors, heat gain, and occupant interactions with the system. It also went further to classify the factors affecting the thermal comfort of users based on past works of literature. These include structural, environmental, and human factors. It was concluded that factors that have the most significant impact on energy are human, structural, and environmental factors, respectively. In addition, most of the occupant behavior modeling approaches that have been used in past studies have pros and cons and cannot accurately predict human behaviors because they are stochastic. Future research should be conducted on thermal comfort for different building functions by examining the varied activity intensity levels of users, especially in educational or commercial buildings. Additionally, a proper investigation should be carried out on how thermal insulation of structural members influences thermal comfort. These should be compared in two similar buildings to understand occupant behavioral actions and energy consumption. [ABSTRACT FROM AUTHOR]

Energy efficiency is a principle of architectural design that reduces environmental impact. Generative design can offer alternative options to improve energy efficiency in buildings, but significant gaps exist in the application due to accessing complex knowledge. This study aimed to explore publications on generative design and energy efficiency in buildings and identify generative methods for energy efficiency topics. This study conducted a systematic review using the PRISMA methodology in December 2023 by searching publications from databases including Scopus, Google Scholar, and Thai Journals Online. Descriptive analysis examined 34 articles, showing the publication year, source, and citations. Comparative qualitative and descriptive analysis identified generative methods. Publications are increasing over time, and further growth is expected related to the accessibility of computational design and practical applications. Tools and frameworks demonstrated reduced energy usage compared to prototypes or traditional design approaches. The most studied is thermal performance, which was reduced by 28%. Energy performance achieved up to a 23.30% reduction, followed by others and daylighting. In addition to single-topic studies, there are also studies with multiple topics. Evolutionary algorithms are standard. Parametric search strategies have increased. Exploration reveals rule-based and mixed methods. Machine learning and AI garner attention. [ABSTRACT FROM AUTHOR]

It is crucial to consider structural design issues in Trombe wall (T-wall) buildings to promote more suitable indoor climates and thermal comfort standards. Therefore, the present study examined the impact of two different T-wall designs and six different roof types on the energy and operational efficiency of a building located in a low-temperature and high-humidity winter climate. Ansys-CFX 15.0 software was employed to simulate the thermal and fluid dynamics behavior of the T-wall system, and flow, thermal comfort, energy, and exergy analyses were conducted. Three-dimensional simulation results and the pertinent literature data showed a good level of agreement, and the accuracy of the model was ensured. Outcomes revealed an average air velocity variation of 0.186 m/s and maximum average indoor air temperature variation of 3.3 °C between the six roof geometries. The highest air speed (0.988 m/s) was recorded for the gambrel roof while the lowest one (0.802 m/s) was recorded for the typical flat roof. The shed roof right with a rounded T-wall was more comfortable for standing and sitting activity than the others for the two T-wall shapes, and, at Y = 0.6 m and Y = 1.1 m, the average predicted percentages of dissatisfied (PPD) values were 31 and 28%, respectively. Furthermore, it was determined in the study that solar radiation intensity and T-wall and roof geometries had a significant effect on energy and exergy efficiency, and high energy and exergy efficiencies were achieved at higher solar intensity values. The best energy and exergy efficiencies were obtained for the butterfly and shed roof configurations. This study can serve as a reference for the thermal environment design of buildings with T-walls. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

An increasing number of federal and state regulations and financial incentive programs have been enacted in recent years to promote renewable energy systems integration in new buildings. This requires designers to analyze the initial and lifecycle costs of feasible renewable energy systems in order to optimize their integration in buildings during all design phases. The goal of this study is to support designers in generating optimal building schematic designs to maximize the integration and generation of onsite renewable energy. To accomplish this goal, this paper presents the development of a novel multi-objective optimization model that can be used during the schematic design phase to identify optimal building design decisions including dimensions, orientation, location on site, solid-to-void ratio, and the type and size of onsite renewable energy systems. The optimization objectives of the developed model focus on maximizing the generation of onsite renewable energy, maximizing savings-to-investment ratio of all integrated renewable energy, and minimizing both construction and renewable energy costs. An application example of optimizing the schematic design of a 6500 m2 building was analyzed to highlight the model original contributions and its novel capabilities. The results of this analysis highlight the original contributions of the developed model and its novel capabilities that can be used to maximize the generation of onsite renewable energy and its savings-to-investment ratio while minimizing building cost by optimizing building schematic design and renewable energy (RE) technology decisions. • Optimizing building schematic design with renewable energy integration. • Maximizing RE generation, savings-to-investment ration, and minimizing bilding costs. • Complying with building design requirements and renewable energy constraints. • Optimal building design parameters and renewable energy technologies. • Analyzing the impact of design decisions on renewable energy and building costs. [ABSTRACT FROM AUTHOR]

The buildings sector is the single most important end-user of final energy in the European Union and a significant contributor to carbon and greenhouse gas emissions. This work focuses on a review of available data that are used to calculate the annual emissions from electricity generation in the European Union and quantify indirect emissions from the use of electricity in the buildings sector. Historical data since 1990 are used to derive simple empirical correlations for the time evolution of emissions factors related to electricity production in each Member State of the European Union. More recent trajectories using data from the last ten years are also presented. The derived correlations can be easily integrated in building stock modeling and national studies to facilitate forward-looking projections of emissions from electricity use in buildings. The EU-27 averages 0.2883 kgCO2-eq/kWhel, ranging from 0.0456 kgCO2-eq/kWhel in Sweden up to 1.0595 kgCO2-eq/kWhel in Poland. As a case study, the derived coefficients are then used to quantify the indirect emissions from the electricity consumption attributed to the building stock in each EU Member State. The calculated total EU-27 GHG indirect emissions attributed to electricity consumption amounted to 215 MtCO2-eq for residential buildings and 201 MtCO2-eq for non-residential buildings. In addition, the proposed correlations are used to demonstrate how they can be used for more realistic future projections of emissions towards the national targets in Greece and Poland. [ABSTRACT FROM AUTHOR]