4.6 Article

Examining the Relationships between Stationary Occupancy and Building Energy Loads in US Educational Buildings-Case Study

Journal

SUSTAINABILITY
Volume 12, Issue 3, Pages -

Publisher

MDPI
DOI: 10.3390/su12030893

Keywords

building energy loads; network traffic; building occupancy; electricity consumption

Ask authors/readers for more resources

Building energy systems are designed to handle both permanent and temporary occupants. Permanent occupants are considered the base energy load while temporary occupants are considered a temporary or additional load. Temporary occupancy is potentially the most difficult to design as the number of temporary occupants varies more significantly than permanent occupants. This case study was designed to investigate the effect of occupancy on energy loads, i.e., the relationship between occupancy and building energy loads. This study estimated the building occupancy by using existing network infrastructure, such as Wi-Fi and wired Ethernet based on the assumption that the number of Wi-Fi connections and the wired Ethernet traffic were used as a proxy for total and stationary occupancy. The relationships were then examined using correlations and regression analyses. The results showed the following: 1. Stationary occupancy was successfully estimated using the network infrastructure; 2. There was a linear relationship between electricity use and total occupancy (and, thus, the use of network infrastructure); 3. Permanent occupants generated a higher impact on the electricity load than the temporary occupants; 4. There was a logarithmic relationship between electricity use and the Ethernet data traffic (a proxy of permanent occupants); and 5. The statistical and qualitative analyses indicated that there was no significant relationship between occupancy and thermal loads, such as cooling and heating loads.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Operations Research & Management Science

Optimizing non-unit repetitive project resource and scheduling by evolutionary algorithms

Duc-Hoc Tran, Jui-Sheng Chou, Duc-Long Luong

Summary: This work presents a new hybrid evolutionary approach, called the fuzzy clustering artificial bee colony approach (FABC), to optimize resource assignment and scheduling for non-unit repetitive projects (NRP). The proposed method outperforms benchmark algorithms in terms of project duration and optimal solution deviation.

OPERATIONAL RESEARCH (2022)

Article Computer Science, Interdisciplinary Applications

Cloud evolutionary computation system for advanced engineering analytics

Jui-Sheng Chou, Jeffisa Delaosia Kosasih, Wai K. Chong

Summary: The study developed a cloud evolutionary machine learning system aimed at providing user-friendly web analytics for solving engineering problems. The system successfully addressed classification and regression problems with high accuracy and improved performance metrics.

ENGINEERING WITH COMPUTERS (2022)

Article Energy & Fuels

Automated prediction system of household energy consumption in cities using web crawler and optimized artificial intelligence

Jui-Sheng Chou, Sheng-Ming Hsu

Summary: This study established an automated platform using machine learning and optimization methods to predict residential electricity demand in each city in Taiwan, generating an accurate and effective model. By providing monthly electricity consumption information through a web-based system, it helps power providers and government discuss policies and set energy use goals.

INTERNATIONAL JOURNAL OF ENERGY RESEARCH (2022)

Article Construction & Building Technology

Multiobjective forensic-based investigation algorithm for solving structural design problems

Jui-Sheng Chou, Dinh-Nhat Truong

Summary: The MOFBI algorithm utilizes chaotic maps and elite populations to explore and exploit multi-objective search spaces, providing more accurate approximations of Pareto-optimal solutions compared to other algorithms.

AUTOMATION IN CONSTRUCTION (2022)

Article Computer Science, Artificial Intelligence

Integrating a novel multiple-objective FBI with BIM to determine tradeoff among resources in project scheduling

Dang-Trinh Nguyen, Jui-Sheng Chou, Duc-Hoc Tran

Summary: Project managers face challenges in balancing various resource factors, and this study proposes a framework that integrates BIM, MOO, and MCDM to find the best resource scheduling solution through modeling, multi-objective optimization, and multi-criteria decision analysis.

KNOWLEDGE-BASED SYSTEMS (2022)

Article Construction & Building Technology

Identifying deflections of reinforced concrete beams under seismic loads by bio-inspired optimization of deep residual learning

Jui-Sheng Chou, Misael Algape Karundeng, Dinh-Nhat Truong, Min-Yuan Cheng

Summary: This study proposes a method that combines deep learning and bio-inspired optimization to measure the deflection of reinforced concrete beams. The hybrid model achieves higher accuracy than traditional models and provides insights in similar visual surveillance tasks.

STRUCTURAL CONTROL & HEALTH MONITORING (2022)

Article Environmental Studies

Comparison of machine learning models to provide preliminary forecasts of real estate prices

Jui-Sheng Chou, Dillon-Brandon Fleshman, Dinh-Nhat Truong

Summary: This research reviews machine learning techniques for predicting house prices and compares their performance using four popular artificial intelligence methods. The study finds that the proposed particle swarm optimization-Bagging-ANNs hybrid model outperforms others in predicting house prices. The availability of multiple prediction models allows users to choose the most suitable one based on their needs and understanding of machine learning.

JOURNAL OF HOUSING AND THE BUILT ENVIRONMENT (2022)

Article Construction & Building Technology

Scour depth prediction at bridge piers using metaheuristics-optimized stacking system

Jui-Sheng Chou, Ngoc-Mai Nguyen

Summary: This paper proposes a novel artificial intelligence-based approach, called MOSS, for estimating scour depth at bridge piers. MOSS combines a metaheuristic optimization algorithm with efficient machine learning models to achieve the most effective system. The efficiency of MOSS is verified through three case studies and is found to outperform other approaches. The results show that MOSS is the most reliable and accurate method for predicting scour depth.

AUTOMATION IN CONSTRUCTION (2022)

Article Mathematical & Computational Biology

Jellyfish Search-Optimized Deep Learning for Compressive Strength Prediction in Images of Ready-Mixed Concrete

Jui-Sheng Chou, Stela Tjandrakusuma, Chi-Yun Liu

Summary: This study uses deep learning models to predict the compressive strength of concrete. By comparing computer vision and conventional numerical data methods, it is found that computer vision methods outperform the traditional methods in terms of accuracy and reliability. The computer vision models were further optimized using a bio-inspired metaheuristic algorithm, resulting in the best prediction models.

COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE (2022)

Article Construction & Building Technology

Bayesian-optimized deep learning model to segment deterioration patterns underneath bridge decks photographed by unmanned aerial vehicle

Chi-Yun Liu, Jui-Sheng Chou

Summary: Bridge collapses and fractures have occurred due to lack of inspection and maintenance, and traditional visual inspection methods have limitations. This study presents an unmanned aerial vehicle (UAV) equipped with a Bayesian-optimized deep learning model for computer vision-based identification of deterioration patterns and segmented areas in composite bridge decks. The proposed module improves inspection accuracy, reduces labor safety hazards, and can be embedded in an artificial intelligence chip for consumer-grade UAVs dedicated to external bridge inspections.

AUTOMATION IN CONSTRUCTION (2023)

Article Computer Science, Interdisciplinary Applications

Forensic-based investigation-optimized extreme gradient boosting system for predicting compressive strength of ready-mixed concrete

Jui-Sheng Chou, Li-Ying Chen, Chi-Yun Liu

Summary: A baseline model for predicting the compressive strength of concrete was constructed using machine-learning methods. The model was optimized using a newly developed algorithm and historical data from concrete plants. An expert system was developed to facilitate quality management and improve the safety of concrete structures.

JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING (2023)

Article Engineering, Civil

QUALITY MANAGEMENT PLATFORM INSPIRED DURING COVID-19 PANDEMIC FOR USE BY SUBCONTRACTORS IN PRIVATE HOUSING PROJECTS

Jui-Sheng Chou, Yu-Hsuan Chen, Chi-Yun Liu, Wai Oswald Chong

Summary: Due to the COVID-19 pandemic, construction sites in Taiwan have implemented measures such as limiting the number of workers and conducting independent work to prevent the spread of the virus. Unclear job handover and the presence of infected workers pose challenges to construction quality. Neglecting inspection processes can result in errors and poor quality. To address these issues, a literature analysis and in-depth interviews with subcontractors were conducted to identify quality management problems in private housing projects. Improvement measures and a simplified checklist were formulated based on practical feedback. An inspection application was also developed to facilitate construction practice, especially during the pandemic.

JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT (2023)

Article Energy & Fuels

Forecasting Regional Energy Consumption via Jellyfish Search-Optimized Convolutional-Based Deep Learning

Jui-Sheng Chou, Ngoc-Quang Nguyen

Summary: The energy sector needs to find a delicate balance between energy supply and demand. Accurate energy consumption forecasts can assist plant operators in achieving this goal. This study explores the application of various techniques from three categories of artificial intelligence, namely convolutional neural networks (CNNs), machine learning (ML), and time-series deep learning (DL), to predict short-term regional energy consumption.

INTERNATIONAL JOURNAL OF ENERGY RESEARCH (2023)

Article Computer Science, Interdisciplinary Applications

Fuzzy adaptive forensic-based investigation algorithm for optimizing frequency-constrained structural dome design

Dinh-Nhat Truong, Jui-Sheng Chou

Summary: This study develops a novel fuzzy adaptive forensic-based investigation algorithm (FAFBI) to optimize frequency-constrained structural dome design. The results show that FAFBI outperforms other compared algorithms in finding optimal values. The proposed FAFBI algorithm is an effective tool for solving mathematical optimization problems and for use in the design phase of structural construction.

MATHEMATICS AND COMPUTERS IN SIMULATION (2023)

Article Construction & Building Technology

Determining critical success factors for residential reconstruction in the urban city from the perspective of developers

Jui-Sheng Chou, Yu-Hsiu Chang, Asmare Molla, Wai Oswald Chong

Summary: Urban renewal involves different stakeholders with different expectations, such as residents and developers. This study analyzed completed and ongoing urban renewal projects and found that land integration is a crucial factor for success. Developers need to consider factors such as resident approval rates, complexity of ownership, environmental friendliness, high rewards, case review duration, and providing a vision of the community after renewal. Urban renewal also relies on government assistance and cooperation among developers, government, and landowners.

SUSTAINABLE CITIES AND SOCIETY (2023)

No Data Available