Anomaly Detection of Energy Consumption in Cloud Computing and Buildings Using Artificial Intelligence as a Tool of Sustainability: A Systematic Review of Current Trends, Applications, and Challenges

Document Type

Article

Publication Title

Signals and Communication Technology

Abstract

The increased energy consumption around the globe has consequently led to a high amount of energy waste. While people need energy in various forms, such as electricity, fossil fuels, and natural gas, energy wastage and abnormal consumption are alarming for their day-to-day activities. Building and cloud computing are among the leading energy consumption and wastage fields following the increased number of residential and commercial buildings and the recent growth in cloud computing. Energy waste and abnormal consumption lead to increased gas emissions, which threaten the sustainability of the global climate. Using artificial intelligence as a sustainability tool, this study’s author researched anomaly detection of energy consumption in cloud computing and buildings. Using qualitative research methodologies, the researcher established that artificial intelligence methods and techniques, such as machine learning, are more effective and efficient in detecting abnormalities in data consumption. Though various researchers have established frameworks to solve and militate abnormalities in energy consumption, they face serious challenges such as increased cost, lack of efficiency for large data, and lack of skilled detectors. Intending to overcome these challenges, the researcher developed a new framework that employs machine and deep learning technologies to determine anomalies in cloud and building energy consumption.

First Page

177

Last Page

210

DOI

10.1007/978-3-031-45214-7_9

Publication Date

1-1-2024

Keywords

Anomaly, Anomaly detection, Artificial intelligence, Cloud computing, Energy consumption, Machine learning

This document is currently not available here.

Share

COinS