Machine learning for occupant-behavior-sensitive cooling energy consumption prediction in office buildings

Amasyali, Kadir; El-Gohary, Nora

doi:10.1016/j.rser.2021.110714

Cited by 139 publications

(34 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreover, it allows concerned people to detect risk before happening, as used in the healthcare area, it shows an undertaking results to consider when dealing with patients [15] and in its application field in earth science shows prominent results to predict the accuracy of a variable [16]. However, existing prediction models do not sufficiently take user behavior into account [17].…”

Section: Results Predictionmentioning

confidence: 99%

Machine Learning for sport results prediction using algorithms

Lotfi

rebbouj

2021

IJITAS

View full text Add to dashboard Cite

This paper describes the use of machine learning in sports. Given the recent trend in Data science and sport analytics, the use of Machine Learning and Data Mining as techniques in sport reveals the essential contribution of technology in results and performance prediction. The purpose of this paper is to benchmark existing analysis methods used in literature, to understand the prediction processes used to model Data collection and its analysis; and determine the characteristics of the variables controlling the performance. Finally, this paper will suggest the reliable tool for Data mining analysis technique using Machine Learning.

show abstract

Section: Results Predictionmentioning

confidence: 99%

Machine Learning for sport results prediction using algorithms

Lotfi

rebbouj

2021

IJITAS

View full text Add to dashboard Cite

show abstract

“…Amasyali and El-Gohary [19] proposed an approach to predict the energy consumption of cooling in office buildings. Five sets of parameters, including window status, occupancy density, cooling setpoint, the power density of electric equipment, and density of lighting power, were considered as the model's input variables.…”

Section: Literature Reviewmentioning

confidence: 99%

A Novel Feature Selection Technique to Better Predict Climate Change Stage of Change

et al. 2021

View full text Add to dashboard Cite

Indications of people’s environmental concern are linked to transport decisions and can provide great support for policymaking on climate change. This study aims to better predict individual climate change stage of change (CC-SoC) based on different features of transport-related behavior, General Ecological Behavior, New Environmental Paradigm, and socio-demographic characteristics. Together these sources result in over 100 possible features that indicate someone’s level of environmental concern. Such a large number of features may create several analytical problems, such as overfitting, accuracy reduction, and high computational costs. To this end, a new feature selection technique, named the Coyote Optimization Algorithm-Quadratic Discriminant Analysis (COA-QDA), is first proposed to find the optimal features to predict CC-SoC with the highest accuracy. Different conventional feature selection methods (Lasso, Elastic Net, Random Forest Feature Selection, Extra Trees, and Principal Component Analysis Feature Selection) are employed to compare with the COA-QDA. Afterward, eight classification techniques are applied to solve the prediction problem. Finally, a sensitivity analysis is performed to determine the most important features affecting the prediction of CC-SoC. The results indicate that COA-QDA outperforms conventional feature selection methods by increasing average testing data accuracy from 0.7 to 5.6%. Logistic Regression surpasses other classifiers with the highest prediction accuracy.

show abstract

“…This type of management covers all traditional principles of energy management related to demand, distributed energy sources and demand management, as well as current energy issues such as energy savings, temporary load and demand reduction. Thus, smart energy management systems have developed the ability to combine smart end-use devices, distributed energy resources and improved management and communication [25].…”

Section: Fault Detection and Forecastingmentioning

confidence: 99%

Smart Grid Technologies as a Concept of Innovative Energy Development: Initial Proposals for the Development of Ukraine

Pliuhin

Teterev

Lapko

2021

LEPE

View full text Add to dashboard Cite

The formation of the concept of Smart Grid is associated with a number of issues, including theoretical and methodological. One of the main problems in forming such theory is to build its basis, the starting point for the development of which is the definition of Smart Grid as a systems of views concept on the future of power engineering, the principles of operation and technological basis of which undergoes significant changes compared to modern energy. The paper is aimed at reviewing and developing directions and approaches to the definition of Smart Grid in combination with machine learning mechanisms, highlighting their diverse and common nature to develop a holistic innovative energy development. In this paper, a study of the energy sector in Ukraine was conducted. Its efficiency and innovative development are considered. Problems with the implementation of Smart Grid technology, which arise when using alternative sources and monitoring and administration systems, were highlighted. The ways of mathematical formulation of the Smart Grid optimization problem are determined using the Data Science approach based on the machine learning system and neural networks. Big Data processing methods, Data Mining, statistical methods, artificial intelligence methods, and Machine Learning are analyzed. The design and development of databases and application software will be done using the Data Science method. Smart-technologies will take over the processes of control, accounting and diagnostics of assets, which will provide promising opportunities for self-recovery of the power system, as well as efficient operation of fixed assets. With the introduction of Smart Grid technologies for the Ukrainian power industry, significant fundamental changes will take place. This is the transition from centralized methods of generation and transmission of electricity to distributed networks with the ability to control energy production facilities and network topology at any point, including at the consumer level. Replacement of centralized demand forecasting according to the methodology of active consumer influence becomes an element and subject of the management system. A high-performance information and computing infrastructure will be built as the core of the energy system. This approach creates the preconditions for the widespread introduction of new devices that increase the maneuverability and controllability of the equipment. The creation of next-generation operational applications (SCADA/EMS/NMS) allows the use of innovative algorithms and methods of power system management, including its new active power elements.

show abstract

Machine learning for occupant-behavior-sensitive cooling energy consumption prediction in office buildings

Cited by 139 publications

References 34 publications

Machine Learning for sport results prediction using algorithms

Machine Learning for sport results prediction using algorithms

A Novel Feature Selection Technique to Better Predict Climate Change Stage of Change

Smart Grid Technologies as a Concept of Innovative Energy Development: Initial Proposals for the Development of Ukraine

Contact Info

Product

Resources

About