Statistical and Artificial Intelligence-Based Tools for Building Energy Prediction: A Systematic Literature Review

被引：2
作者：
Olu-Ajayi, Razak [1 ,2 ]
Alaka, Hafiz [1 ,2 ]
Sunmola, Funlade [1 ,2 ]
Ajayi, Saheed [3 ]
Mporas, Iosif [1 ,2 ]
机构：
[1] Univ Hertfordshire, Big Data Technol & Innovat Lab, Hatfield AL10 9AB, England
[2] Univ Hertfordshire, Sch Engn & Technol, Hatfield AL10 9AB, England
[3] Leeds Beckett Univ, Sch Built Environm Engn & Comp, Leeds LS1 3HE, England
来源：
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT | 2024年 / 71卷
关键词：
Reviews; Buildings; Systematics; Support vector machines; Predictive models; Energy consumption; Bibliographies; Artificial intelligence (AI); building energy consumption; energy efficiency; energy prediction; machine learning; statistical tools; systematic literature review; DEEP NEURAL-NETWORK; ELECTRICITY CONSUMPTION; LOAD PREDICTION; FORECASTING TECHNIQUES; RANDOM FOREST; MODELS; DEMAND; TIME; EFFICIENT; REGRESSION;
D O I：
10.1109/TEM.2024.3422821
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
The application of statistical and artificial intelligence (AI) tools in building energy prediction (BEP) is considered one of the most effective advances toward improving energy efficiency. Thus, researchers are constantly propagating the energy prediction field with many prediction models using diverse statistical and AI tools. However, many of these tools are employed in unsuitable data conditions or for wrong situations. Using the Institute of Electrical and Electronics Engineers and Scopus databases, 92 journal articles on statistical and AI tools in BEP were systematically analyzed. Furthermore, a quantitative bibliometric analysis was conducted to pinpoint the trends and examine knowledge gaps. This research reviews the performance of nine popular and promising statistical and AI tools with a primary focus on seven pertinent criteria within the building energy research domain. Although it was concluded that no one tool is best in all criteria, a diagrammatic framework is provided to serve as a guide for appropriate tool selection in various situations. This study contributes to appropriate tool selection in the development of BEP models and their related drawbacks. In addition, this study also evaluated the performance of the high-performing tools on a standard dataset.
引用
收藏
页码：14733 / 14753
页数：21
相关论文
共 199 条
[1]   Behavior Analysis of Refugees' Electricity Consumption in Developing Countries: Case of Turkey [J].
Acuner, Ebru ;
Kayalica, M. Ozgur .
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT, 2022, 69 (04) :1206-1215
[2]   A review on applications of ANN and SVM for building electrical energy consumption forecasting [J].
Ahmad, A. S. ;
Hassan, M. Y. ;
Abdullah, M. P. ;
Rahman, H. A. ;
Hussin, F. ;
Abdullah, H. ;
Saidur, R. .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2014, 33 :102-109
[3]   Deep Highway Networks and Tree-Based Ensemble for Predicting Short-Term Building Energy Consumption [J].
Ahmad, Muhammad Waseem ;
Mouraud, Anthony ;
Rezgui, Yacine ;
Mourshed, Monjur .
ENERGIES, 2018, 11 (12)
[4]   Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption [J].
Ahmad, Muhammad Waseem ;
Mourshed, Monjur ;
Rezgui, Yacine .
ENERGY AND BUILDINGS, 2017, 147 :77-89
[5]   An Ensemble Learning Approach for Accurate Energy Prediction in Residential Buildings [J].
Al-Rakhami, Mabrook ;
Gumaei, Abdu ;
Alsanad, Ahmed ;
Alamri, Atif ;
Hassan, Mohammad Mehedi .
IEEE ACCESS, 2019, 7 :48328-48338
[6]   A Big Data Analytics Approach for Construction Firms Failure Prediction Models [J].
Alaka, Hafiz ;
Oyedele, Lukumon ;
Owolabi, Hakeem ;
Akinade, Olugbenga ;
Bilal, Muhammad ;
Ajayi, Saheed .
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT, 2019, 66 (04) :689-698
[7]   Systematic review of bankruptcy prediction models: Towards a framework for tool selection [J].
Alaka, Hafiz A. ;
Oyedele, Lukumon O. ;
Owolabi, Hakeem A. ;
Kumar, Vikas ;
Ajayi, Saheed O. ;
Akinade, Olugbenga O. ;
Bilal, Muhammad .
EXPERT SYSTEMS WITH APPLICATIONS, 2018, 94 :164-184
[8]   Forecasting peak energy demand for smart buildings [J].
Alduailij, Mona A. ;
Petri, Ioan ;
Rana, Omer ;
Alduailij, Mai A. ;
Aldawood, Abdulrahman S. .
JOURNAL OF SUPERCOMPUTING, 2021, 77 (06) :6356-6380
[9]   Evolutionary Deep Learning-Based Energy Consumption Prediction for Buildings [J].
Almalaq, Abdulaziz ;
Zhang, Jun Jason .
IEEE ACCESS, 2019, 7 :1520-1531
[10]   Machine learning for occupant-behavior-sensitive cooling energy consumption prediction in office buildings [J].
Amasyali, Kadir ;
El-Gohary, Nora .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2021, 142
12345678910