Exploiting a self-learning predictor for session-based remote management systems in a large-scale environment

Kuen Min Lee, Wei-Guang Teng, Mu Kai Huang, Chih Pin Freg, Ting-Wei Hou

Research output: Contribution to journalArticle

Abstract

Session-based remote management systems, e.g., customer premises equipment (CPE) WAN management protocol (CWMP), have predictable task counts in a session and each CPE only accesses its own data. When the systems are used in large-scale environments, a static load balancing (LB) policy can be applied with fewer session migrations. Nevertheless, unexpected crash events, e.g., software bugs or improper management, would cause the LB policy to be reassigned so as to degrade the system performance. A self-learning predictor (SLP) is thus proposed in this work to predict unexpected crash events and to achieve a better system performance in terms of resource usage and throughput. Specifically, the SLP records and monitors all crash patterns to evaluate the system stability. Moreover, the relation flags and probabilities of all crash patterns are dynamically updated for quick comparisons. If the SLP finds the current pattern is similar to a crash pattern, a migration request is raised to the load balancer to prevent performance degradation caused by the incoming crash. The simulation results indicate that a better system performance is obtained in a large-scale environment with the proposed SLP, especially as the number of servers in each cluster node increases.

Original languageEnglish
Pages (from-to)657-668
Number of pages12
JournalJournal of Internet Technology
Volume19
Issue number3
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Resource allocation
Wide area networks
System stability
Servers
Throughput
Network protocols
Degradation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Networks and Communications

Cite this

@article{11ffe3e6c1734d2999c197ed1a0f4c27,
title = "Exploiting a self-learning predictor for session-based remote management systems in a large-scale environment",
abstract = "Session-based remote management systems, e.g., customer premises equipment (CPE) WAN management protocol (CWMP), have predictable task counts in a session and each CPE only accesses its own data. When the systems are used in large-scale environments, a static load balancing (LB) policy can be applied with fewer session migrations. Nevertheless, unexpected crash events, e.g., software bugs or improper management, would cause the LB policy to be reassigned so as to degrade the system performance. A self-learning predictor (SLP) is thus proposed in this work to predict unexpected crash events and to achieve a better system performance in terms of resource usage and throughput. Specifically, the SLP records and monitors all crash patterns to evaluate the system stability. Moreover, the relation flags and probabilities of all crash patterns are dynamically updated for quick comparisons. If the SLP finds the current pattern is similar to a crash pattern, a migration request is raised to the load balancer to prevent performance degradation caused by the incoming crash. The simulation results indicate that a better system performance is obtained in a large-scale environment with the proposed SLP, especially as the number of servers in each cluster node increases.",
author = "Lee, {Kuen Min} and Wei-Guang Teng and Huang, {Mu Kai} and Freg, {Chih Pin} and Ting-Wei Hou",
year = "2018",
month = "1",
day = "1",
doi = "10.3966/160792642018051903004",
language = "English",
volume = "19",
pages = "657--668",
journal = "Journal of Internet Technology",
issn = "1607-9264",
publisher = "Taiwan Academic Network Management Committee",
number = "3",

}

Exploiting a self-learning predictor for session-based remote management systems in a large-scale environment. / Lee, Kuen Min; Teng, Wei-Guang; Huang, Mu Kai; Freg, Chih Pin; Hou, Ting-Wei.

In: Journal of Internet Technology, Vol. 19, No. 3, 01.01.2018, p. 657-668.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Exploiting a self-learning predictor for session-based remote management systems in a large-scale environment

AU - Lee, Kuen Min

AU - Teng, Wei-Guang

AU - Huang, Mu Kai

AU - Freg, Chih Pin

AU - Hou, Ting-Wei

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Session-based remote management systems, e.g., customer premises equipment (CPE) WAN management protocol (CWMP), have predictable task counts in a session and each CPE only accesses its own data. When the systems are used in large-scale environments, a static load balancing (LB) policy can be applied with fewer session migrations. Nevertheless, unexpected crash events, e.g., software bugs or improper management, would cause the LB policy to be reassigned so as to degrade the system performance. A self-learning predictor (SLP) is thus proposed in this work to predict unexpected crash events and to achieve a better system performance in terms of resource usage and throughput. Specifically, the SLP records and monitors all crash patterns to evaluate the system stability. Moreover, the relation flags and probabilities of all crash patterns are dynamically updated for quick comparisons. If the SLP finds the current pattern is similar to a crash pattern, a migration request is raised to the load balancer to prevent performance degradation caused by the incoming crash. The simulation results indicate that a better system performance is obtained in a large-scale environment with the proposed SLP, especially as the number of servers in each cluster node increases.

AB - Session-based remote management systems, e.g., customer premises equipment (CPE) WAN management protocol (CWMP), have predictable task counts in a session and each CPE only accesses its own data. When the systems are used in large-scale environments, a static load balancing (LB) policy can be applied with fewer session migrations. Nevertheless, unexpected crash events, e.g., software bugs or improper management, would cause the LB policy to be reassigned so as to degrade the system performance. A self-learning predictor (SLP) is thus proposed in this work to predict unexpected crash events and to achieve a better system performance in terms of resource usage and throughput. Specifically, the SLP records and monitors all crash patterns to evaluate the system stability. Moreover, the relation flags and probabilities of all crash patterns are dynamically updated for quick comparisons. If the SLP finds the current pattern is similar to a crash pattern, a migration request is raised to the load balancer to prevent performance degradation caused by the incoming crash. The simulation results indicate that a better system performance is obtained in a large-scale environment with the proposed SLP, especially as the number of servers in each cluster node increases.

UR - http://www.scopus.com/inward/record.url?scp=85048881180&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048881180&partnerID=8YFLogxK

U2 - 10.3966/160792642018051903004

DO - 10.3966/160792642018051903004

M3 - Article

AN - SCOPUS:85048881180

VL - 19

SP - 657

EP - 668

JO - Journal of Internet Technology

JF - Journal of Internet Technology

SN - 1607-9264

IS - 3

ER -