TY - GEN
T1 - Hyperparameter study of machine learning solutions for the edge server deployment problem
AU - Rodrigues, Tiago Koketsu
AU - Suto, Katsuya
AU - Kato, Nei
N1 - Funding Information:
This work was supported by JSPS KAKENHI Grant Number 18J10020 and by “Research and Development on Intellectual ICT System for Disaster Response and Recovery”, the Commissioned Research of the National Institute of Information and Communications Technology (NICT), Japan.
Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - Edge Cloud Computing is a key technology for enhancing mobile functionalities and real-time applications in devices with limited resources. This is done by sharing the resources of edge servers and offloading jobs to the edge cloud. In order to ensure a high-quality service and more efficient usage of resources, it is important not only to correctly configure the edge servers but also to carefully select where to deploy them. However, in Edge Cloud Computing there is a high amount of servers and, with the advent of 5G and Internet of Things, there will be a massive number of client devices as well. This would make the edge server deployment too complex to solve through convex techniques. In this situation, Machine Learning is the most appropriate approach. In this paper, we provide a deep analysis of the usage of k-Means Clustering and Particle Swarm Optimization in the edge cloud deployment problem. Our results show that the hyperparameters for these algorithms can significantly impact their running time as well as the efficiency of their results. Finally, we also provide how to best configure these algorithms for this specific problem.
AB - Edge Cloud Computing is a key technology for enhancing mobile functionalities and real-time applications in devices with limited resources. This is done by sharing the resources of edge servers and offloading jobs to the edge cloud. In order to ensure a high-quality service and more efficient usage of resources, it is important not only to correctly configure the edge servers but also to carefully select where to deploy them. However, in Edge Cloud Computing there is a high amount of servers and, with the advent of 5G and Internet of Things, there will be a massive number of client devices as well. This would make the edge server deployment too complex to solve through convex techniques. In this situation, Machine Learning is the most appropriate approach. In this paper, we provide a deep analysis of the usage of k-Means Clustering and Particle Swarm Optimization in the edge cloud deployment problem. Our results show that the hyperparameters for these algorithms can significantly impact their running time as well as the efficiency of their results. Finally, we also provide how to best configure these algorithms for this specific problem.
UR - http://www.scopus.com/inward/record.url?scp=85075242937&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075242937&partnerID=8YFLogxK
U2 - 10.1109/VTCFall.2019.8891500
DO - 10.1109/VTCFall.2019.8891500
M3 - Conference contribution
AN - SCOPUS:85075242937
T3 - IEEE Vehicular Technology Conference
BT - 2019 IEEE 90th Vehicular Technology Conference, VTC 2019 Fall - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 90th IEEE Vehicular Technology Conference, VTC 2019 Fall
Y2 - 22 September 2019 through 25 September 2019
ER -