Identifying Energy Inefficiencies Using Self-Organizing Maps: Case of A Highly Efficient Certified Office Building

Living and working in comfort while a building’s energy consumption is kept under control requires monitoring a system’s consumption to optimize the energy performance. The way energy is generally used is often far from optimal, which requires the use of smart meters that can record the energy consu...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences 2023-02, Vol.13 (3), p.1666
Main Authors: Talei, Hanaa, Benhaddou, Driss, Gamarra, Carlos, Benhaddou, Mohamed, Essaaidi, Mohamed
Format: Article
Language:English
Subjects:
Air conditioning
Algorithms
Artificial intelligence
Buildings
Clustering
Electricity
Electricity distribution
Energy conservation
Energy consumption
Energy efficiency
HVAC
LEED building
Literature reviews
Machine learning
Neurons
Office buildings
Self organizing maps
smart building
smart meter
time series
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Living and working in comfort while a building’s energy consumption is kept under control requires monitoring a system’s consumption to optimize the energy performance. The way energy is generally used is often far from optimal, which requires the use of smart meters that can record the energy consumption and communicate the information to an energy manager who can analyze the consumption behavior, monitor, and optimize energy performance. Given that the heating, ventilation, and air conditioning (HVAC) systems are the largest electricity consumers in buildings, this paper discusses the importance of incorporating occupancy data in the energy efficiency analysis and unveils energy inefficiencies in the way the system operates. This paper uses 1-year data of a highly efficient certified office building located in the Houston area and shows the power of self-organizing maps and data analysis in identifying up to 4.6% possible savings in energy. The use of time series analysis and machine-learning techniques is conducive to helping energy managers discover more energy savings.
ISSN:2076-3417
2076-3417
DOI:10.3390/app13031666