Practical issues in implementing machine-learning models for building energy efficiency: Moving beyond obstacles

PurposeThe changes brought by Industry 4.0 go beyond transformations in the industrial environment. The increasingly frequent digitization and robotization of activities is not only restricted to the industrial environment, but also to people's daily routine. People spend a large part of their time inside buildings, and maintaining adequate Indoor Environmental Quality (IEQ) is an essential factor for a healthy and productive environment. In this sense, the purpose of this study is to verify how the Internet of Things (IoT) is being used to improve the indoor environment, through sensors that instantly measure the conditions of the environment.Design/methodology/approachThe aim of this paper is to verify, through a literature review, how IoT is being used for building control (for energy saving purposes) and to monitor IEQ conditions inside buildings, in order to provide a better environment for occupants, in terms of health and comfort. By combining keywords in databases, PRISMA method was used to select the articles for analysis, and 91 articles were analyzed.FindingsThe main findings in this research are: (1) the main purpose for applying IoT inside buildings is to reduce energy consumption; (2) there is an interest in developing low-cost sensoring devices with a learning approach; (3) Machine Learning methods are mainly used for energy saving purposes and to learn about occupants' behavior inside buildings, focusing on thermal comfort; (4) sensors in the IoT era are a requirement to help improve people's comfort and well-being.Originality/valueStudies directly correlating IoT and IEQ are limited. This paper emphasises the link between them, through the presentation of recent methods to control the built environment.

show abstract

“…According to Wang et al. (2021), ML-based MPC research is one of the most common fields in ML-based building energy efficiency research.…”

Section: Resultsmentioning

confidence: 99%

The role of internet of things (IoT) in the assessment and communication of indoor environmental quality (IEQ) in buildings: a review

Broday

Silva

2022

SASBE

View full text Add to dashboard Cite

show abstract

“…ML is a reliable approach for pattern identification, especially when it does not require constructing and solving physical models. 8,9 Therefore, the model presented in the next section will focus on bypassing the complex physical phenomena involved in the fatigue damage process for numerical efficiency by focusing on a nonphysical general-purpose algorithm and its formulation. In addition, the density functional theory (DFT) community has been using ML to examine combinations of elements and crystal structures to discover new materials.…”

Section: In Materials Processing and Engineeringmentioning

confidence: 99%

“…Traditional numerical and analytical models are difficult to establish a process‐structure–property‐performance connection for AM. ML is a reliable approach for pattern identification, especially when it does not require constructing and solving physical models 8,9 . Therefore, the model presented in the next section will focus on bypassing the complex physical phenomena involved in the fatigue damage process for numerical efficiency by focusing on a nonphysical general‐purpose algorithm and its formulation.…”

Section: Introductionmentioning

confidence: 99%

Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

Awd

Münstermann

Walther

2022

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

The posterior statistical distributions of fatigue strength are determined using Bayesian inferential statistics and the Metropolis Monte Carlo method.This study explores how structural heterogeneity affects ultrahigh cycle fatigue strength in additive manufacturing. Monte Carlo methods and procedures may assist estimate fatigue strength posteriors and scatter. The acceptable probability in Metropolis Monte Carlo relies on the Markov chain's random microstructure state. In addition to commonly studied variables, the proportion of chemical composition was demonstrated to substantially impact fatigue strength if fatigue lifetime in crack propagation did not prevail due to high threshold internal notches. The study utilizes an algorithm typically used for quantum mechanics to solve the complicated multifactorial fatigue problem. The inputs and outputs are modified by fitting the microstructural heterogeneities into the Metropolis Monte Carlo algorithm. The main advantage here is applying a general-purpose nonphenomenological model that can be applied to multiple influencing factors without high numerical penalty.

show abstract

“…Inventors across the country have long used various installations to heat water. In the summer, when the temperature inside the car, such as closed rooms and garages, can reach 65 degrees Celsius, a toxic substance called antimony is formed inside the bed bottle [14,15]. Thus this toxicity mixes with the water.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Smart Hybrid Solar Water Heater Erection Model to Extract Maximum Energy

Bharathi

Sripriya

Muthuraj³

et al. 2022

International Journal of Photoenergy

View full text Add to dashboard Cite

Currently, we are trying to get electricity in alternative ways. Many solar powered water heaters have come up to use water heaters. However, these tools are not 100 percent fully effective. The device we have manufactured is an automatic device that runs in the direction of sunlight. The device runs automatically in the morning facing east and in the evening facing west. In this instrument, the defective one-inch tube lamp and the three-quarter-inch tube lamp are put together and connected in series. In this paper, a smart deep learning model was proposed to improve the performance of the solar water heater. The gap between the tube lights is filled with methane gas, and the tube inside is filled with water. The water thus filled is heated by sunlight. Methane gas acts as a fast conductor of solar heat. An electronic control device is placed to determine the temperature of the hot water and to expel the hot water. This device can heat at least 10 liters of water in 15 minutes. Increasing the number of incandescent tube lights can heat up a large amount of water when this device is set up, or it can be designed by replacing tube lights with a series of large glass tubes using the same technology. This tool can be manufactured at low cost so that people from all walks of life can use it.

show abstract

Practical issues in implementing machine-learning models for building energy efficiency: Moving beyond obstacles

Cited by 73 publications

References 123 publications

The role of internet of things (IoT) in the assessment and communication of indoor environmental quality (IEQ) in buildings: a review

The role of internet of things (IoT) in the assessment and communication of indoor environmental quality (IEQ) in buildings: a review

Effect of microstructural heterogeneity on fatigue strength predicted by reinforcement machine learning

Deep Learning-Based Smart Hybrid Solar Water Heater Erection Model to Extract Maximum Energy

Contact Info

Product

Resources

About