Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Benchmarking Evaluation of Building Energy Consumption Based on Data Mining
University building energy consumption is an important proportion of the total energy consumption of society. In order to work out the problem of poor practicability of the existing benchmarking management method of campus building energy consumption, this study proposes an evaluation model of campus building energy consumption benchmarking management. By analyzing several types of feature data of buildings, this study uses random forest method to determine the building features that have outstanding contributions to building energy consumption intensity and building classification, and uses the K-means method to reclassify buildings based on the building features obtained after screening, to obtain a building category that is more in line with the actual use situation and to solve the problem that the existing building classification is not in line with the reality. Compared with the original classification method, the new classification method showed significant improvement in many indexes, among which DBI decreased by 60.8% and CH increased by 3.73 times. Finally, the quart lines of buildings in the category of new buildings are calculated to obtain the low energy consumption line, medium energy consumption line and high energy consumption line of buildings, so as to improve the accuracy and practicability of energy consumption line classification.
Benchmarking Evaluation of Building Energy Consumption Based on Data Mining
University building energy consumption is an important proportion of the total energy consumption of society. In order to work out the problem of poor practicability of the existing benchmarking management method of campus building energy consumption, this study proposes an evaluation model of campus building energy consumption benchmarking management. By analyzing several types of feature data of buildings, this study uses random forest method to determine the building features that have outstanding contributions to building energy consumption intensity and building classification, and uses the K-means method to reclassify buildings based on the building features obtained after screening, to obtain a building category that is more in line with the actual use situation and to solve the problem that the existing building classification is not in line with the reality. Compared with the original classification method, the new classification method showed significant improvement in many indexes, among which DBI decreased by 60.8% and CH increased by 3.73 times. Finally, the quart lines of buildings in the category of new buildings are calculated to obtain the low energy consumption line, medium energy consumption line and high energy consumption line of buildings, so as to improve the accuracy and practicability of energy consumption line classification.
Benchmarking Evaluation of Building Energy Consumption Based on Data Mining
Thomas Wu (Autor:in) / Bo Wang (Autor:in) / Dongdong Zhang (Autor:in) / Ziwei Zhao (Autor:in) / Hongyu Zhu (Autor:in)
2023
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
Bulk data for benchmarking non domestic building energy consumption
| British Library Conference Proceedings | 1996
Knowledge is Power: Benchmarking and prediction of building energy consumption
| British Library Online Contents | 2013
Knowledge is Power: Benchmarking and prediction of building energy consumption
| SAGE Publications | 2013