ECMS: An Edge Intelligent Energy Efficient Model in Mobile Edge Computing

With the increasing popularity of mobile edge computing (MEC) for processing intensive and delay sensitive IoT applications, the problem of high energy consumption of MEC has become a significant concern. Energy consumption prediction and monitoring of edge servers are crucial for reducing MEC'...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on green communications and networking 2022-03, Vol.6 (1), p.238-247
Main Authors: Zhou, Zhou, Shojafar, Mohammad, Abawajy, Jemal, Yin, Hui, Lu, Hongming
Format: Article
Language:English
Subjects:
Computational modeling
Data models
Edge computing
Elman Neural Network (ENN)
Energy consumption
Energy Prediction and Measurement
Feature extraction
Green Computing
Internet of Things
Load fluctuation
Load modeling
Mobile computing
Mobile Edge Computing (MEC)
Neural networks
Servers
Sustainable development
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:With the increasing popularity of mobile edge computing (MEC) for processing intensive and delay sensitive IoT applications, the problem of high energy consumption of MEC has become a significant concern. Energy consumption prediction and monitoring of edge servers are crucial for reducing MEC's carbon footprint in accordance with green computing and sustainable development. However, predicting energy consumption of edge servers is a nontrivial problem due to the fluctuation and variation of different loads. To address this problem, we propose ECMS, a new edge intelligent energy modeling approach that jointly adopts Elman Neural Network (ENN) and feature selection to optimize the consumption of energy on edge servers. ECMS considers 29 parameters relevant to edge server energy consumption and uses the ENN to develop an energy consumption model. Unlike other energy consumption models, ECMS can successfully deal with load fluctuation and various sorts of tasks, such as CPU-intensive, online transaction-intensive, and I/O-intensive. We have validated ECMS through extensive experiments and compared its performance in terms of accuracy and training time to several baseline approaches. The experimental results show the superiority of ECMS to the baseline models. We believe that the proposed model can be used by the MEC resource providers to forecast and optimize energy use.
ISSN:2473-2400
2473-2400
DOI:10.1109/TGCN.2021.3121961