Challenges and opportunities of occupant-centric building controls in real-world implementation: A critical review

Energy and Buildings, Год журнала: 2024, Номер 308, С. 113958 - 113958

Опубликована: Фев. 14, 2024

Over the past few decades, attention in buildings’ design and operation has gradually shifted from promoting only energy efficiency objectives to also addressing human comfort well-being. Researchers have developed a wide range of control algorithms ranging rule-based controls complex learning approaches that can fully capture occupants’ personalized preferences smart buildings. This direction occupant-centric building bridge gap between satisfaction sustainability objectives. However, most these promising technologies not yet found their way into real-world applications. study will perform critical review on thermal lighting studies aiming (i) analyze strengths weaknesses different approaches; (ii) identify requirements for techniques be implemented systems; (iii) propose new research directions promote usability such catalyst towards adoption. Computational complexity, integration with Building Automation Systems (BAS), data availability quality, scalability, lack more featuring actual implementation emerge as barriers. Addressing challenges is imperative successful deployment

Язык: Английский

---

Unlabeled data selection for active learning in image classification

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Янв. 3, 2024

Abstract Active Learning has emerged as a viable solution for addressing the challenge of labeling extensive amounts data in data-intensive applications such computer vision and neural machine translation. The main objective is to automatically identify subset unlabeled samples annotation. This identification process based on an acquisition function that assesses value each sample model training. In context vision, image classification crucial task typically requires substantial training dataset. research paper introduces innovative selection methods within framework, aiming informative images from datasets while minimizing number required data. proposed methods, namely Similari-ty-based Selection, Prediction Probability-based Competence-based Learning, have been extensively evaluated through experiments conducted popular like Cifar10 Cifar100. experimental results demonstrate outperform random conventional techniques. superior performance novel underscores their effectiveness enhancing tasks.

Язык: Английский

---

Design strategies for renovation of public space in Beijing's traditional communities based on measured microclimate and thermal comfort

Sustainable Cities and Society, Год журнала: 2023, Номер 99, С. 104927 - 104927

Опубликована: Сен. 10, 2023

Язык: Английский

---

Thermal comfort in sight: Thermal affordance and its visual assessment for sustainable streetscape design

Building and Environment, Год журнала: 2025, Номер unknown, С. 112569 - 112569

Опубликована: Янв. 1, 2025

Язык: Английский

---

Digital Twin Smart City Visualization with MoE-Based Personal Thermal Comfort Analysis

Sensors, Год журнала: 2025, Номер 25(3), С. 705 - 705

Опубликована: Янв. 24, 2025

Digital twin technology us used to create accurate virtual representations of objects or systems. twins span the object’s life cycle and keep updated with real-time data. Therefore, their simulation capabilities can be combined deep learning a system that simulates scenarios, enabling analysis. As cities continue grow demand for sustainable development increases, digital technology, AI-driven analysis, will play critical role in shaping future urban environments. The ability accurately simulate manage complex systems real time opens up new possibilities optimizing energy usage, reducing costs, improving quality residents. In this study, application is built visualize smart area South Korea, utilizing model personal thermal comfort which useful managing saving building household consumption. Using Cesium Unreal, powerful tool integrating 3D geospatial data, leveraging DataSmith convert data into Unreal Engine format, study also contributes roadmap city development, currently considered lacking. By creating robust framework applications, research not only addresses current challenges but lays groundwork innovations planning management.

Язык: Английский

---

An indoor thermal environment control model based on multimodal perception and reinforcement learning

Building and Environment, Год журнала: 2025, Номер unknown, С. 112863 - 112863

Опубликована: Март 1, 2025

Язык: Английский

---

From Building Information Model to Digital Twin: A Framework for Building Thermal Comfort Monitoring, Visualizing, and Assessment

Buildings, Год журнала: 2023, Номер 13(8), С. 1971 - 1971

Опубликована: Авг. 2, 2023

The existing building stock is globally responsible for 17.5% of greenhouse gas emissions due to their operation achieve occupant satisfaction, thus requiring a vast intervention. However, reducing and optimizing energy performance cannot be considered independently by the users’ well-being. thermal comfort conditions monitoring represent central issue that could optimize usage while achieving good indoor environmental conditions. This document describes first findings ongoing research focused on development system, based integration Building Information Modeling tools sensor technology through Dynamo Visual Programming. Starting from an Asset Model, which represents virtual replica currently hosts administrative offices municipality Cagliari, step presented in this contribution shows scalable modular, allows effective gathering elaboration data about levels each building’s rooms. system proves helpful support facility managers control HVAC systems assure best operative status or plan suitable interventions it.

Язык: Английский

---

Enhancing thermal comfort through leading-edge design, monitoring, and optimization technologies: A review

SSRN Electronic Journal, Год журнала: 2023, Номер unknown

Опубликована: Янв. 1, 2023

This research paper offers a thorough examination of strategies geared towards enhancing thermal comfort within constructed spaces through the incorporation state-of-the-art design, monitoring, and optimization technologies. In light escalating challenges brought about by climate change increasing demand for sustainable energy-efficient building solutions, quest improved has emerged as central focus in architectural engineering research. The initiates its exploration delving into contemporary design principles that underscore significance passive strategies, such optimal orientation, shading devices, natural ventilation. It elucidates synergies between elements comfort, emphasizing how innovative designs can foster ideal indoor conditions while reducing reliance on energy-intensive heating, ventilation, air conditioning (HVAC) systems. A substantial segment review is dedicated to monitoring technologies enabling real-time assessment environmental parameters. integration sensors, data analytics, Building Information Modelling (BIM) facilitates nuanced comprehension dynamics, allowing adaptive responses evolving conditions. discusses role wearable devices occupant feedback systems capturing subjective perceptions, thereby enriching pool more comprehensive analysis. Moreover, delves burgeoning field technologies, encompassing utilization machine learning algorithms artificial intelligence management These empower predictive modeling optimizing HVAC operations, minimizing energy consumption. synthesis these not only enhances well-being but also aligns with global endeavours forge resilient built environments amid challenges.

Язык: Английский

---

Optimising Building Energy and Comfort Predictions with Intelligent Computational Model

Sustainability, Год журнала: 2024, Номер 16(8), С. 3432 - 3432

Опубликована: Апрель 19, 2024

Building performance prediction is a significant area of research, due to its potential enhance the efficiency building energy management systems. Its importance particularly evident when such predictions are validated against field data. This paper presents an intelligent computational model combining Monte Carlo analysis, Energy Plus, and artificial neural network (ANN) refine consumption thermal comfort predictions. addresses various combinations architectural design parameters their distributions, effectively managing complex non-linear relationships between response variables predictors. The model’s strength demonstrated through alignment with R2 values exceeding 0.97 for both discomfort hours during training testing phases. Validation investigation data further confirms accuracy, demonstrating average relative errors below 2.0% total 1.0% hours. In particular, underestimation −12.5% in discrepancies observed comparing simulation data, while presented smaller overestimation error (of +8.65%) discrepancy highlights reliability real-world metrics, marking it as valuable tool practitioners researchers sustainability.

Язык: Английский

---

Experimental evaluation of thermal adaptation and transient thermal comfort in a tropical mixed-mode ventilation context

Building and Environment, Год журнала: 2023, Номер 248, С. 111043 - 111043

Опубликована: Ноя. 21, 2023

Язык: Английский

---