Request distribution with pre-learning for distributed SSL reverse proxies

Haitao Dong; Jun Yang; Yiqiang Sheng

doi:10.1109/SNPD.2016.7515895

Request distribution with pre-learning for distributed SSL reverse proxies

Haitao Dong, Jun Yang, Yiqiang Sheng

CAS - Institute of Acoustics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

As network data security becoming more and more universalized, distributed Secure Sockets Layer (SSL) reverse proxies are often used in Web systems to offload CPU exhausting SSL operations from Web servers and improve the execution performance of the SSL protocol. The distribution strategy of user requests to the SSL reverse proxies is a significant factor affecting the system's performance in processing SSL operations. Aiming at improving the quality of request distribution decisions, this paper proposes a new approach for SSL reverse proxy load estimation, i.e. the family of algorithms called Load Estimation with Pre-Learning (LEPL), which estimates load using pre-learned machine learning models. Using LEPL, high accuracy of load estimation can be achieved, so that better request distribution decisions can be made. Our experimental results show that by using pre-learning, the SSL reverse proxy system's average response time can be shortened by about 30% - 50%.

Original language	English
Title of host publication	2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016
Editors	Yihai Chen
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	161-167
Number of pages	7
ISBN (Electronic)	9781509022397
DOIs	https://doi.org/10.1109/SNPD.2016.7515895
Publication status	Published - Jul 18 2016
Externally published	Yes
Event	17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016 - Shanghai, China Duration: May 30 2016 → Jun 1 2016

Publication series

Name	2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016

Conference

Conference	17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016
Country/Territory	China
City	Shanghai
Period	5/30/16 → 6/1/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

ASJC Scopus Subject Areas

Artificial Intelligence
Computer Networks and Communications
Software

Keywords

distributed system
load estimation
machine learning
request distribution
SSL reverse proxy
Web system

Access to Document

10.1109/SNPD.2016.7515895

Cite this

Dong, H., Yang, J., & Sheng, Y. (2016). Request distribution with pre-learning for distributed SSL reverse proxies. In Y. Chen (Ed.), 2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016 (pp. 161-167). Article 7515895 (2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SNPD.2016.7515895

Dong, Haitao ; Yang, Jun ; Sheng, Yiqiang. / Request distribution with pre-learning for distributed SSL reverse proxies. 2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016. editor / Yihai Chen. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 161-167 (2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016).

@inproceedings{0b8da7db563d45b1a93074479178d8ba,

title = "Request distribution with pre-learning for distributed SSL reverse proxies",

abstract = "As network data security becoming more and more universalized, distributed Secure Sockets Layer (SSL) reverse proxies are often used in Web systems to offload CPU exhausting SSL operations from Web servers and improve the execution performance of the SSL protocol. The distribution strategy of user requests to the SSL reverse proxies is a significant factor affecting the system's performance in processing SSL operations. Aiming at improving the quality of request distribution decisions, this paper proposes a new approach for SSL reverse proxy load estimation, i.e. the family of algorithms called Load Estimation with Pre-Learning (LEPL), which estimates load using pre-learned machine learning models. Using LEPL, high accuracy of load estimation can be achieved, so that better request distribution decisions can be made. Our experimental results show that by using pre-learning, the SSL reverse proxy system's average response time can be shortened by about 30% - 50%.",

keywords = "distributed system, load estimation, machine learning, request distribution, SSL reverse proxy, Web system",

author = "Haitao Dong and Jun Yang and Yiqiang Sheng",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016 ; Conference date: 30-05-2016 Through 01-06-2016",

year = "2016",

month = jul,

day = "18",

doi = "10.1109/SNPD.2016.7515895",

language = "English",

series = "2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "161--167",

editor = "Yihai Chen",

booktitle = "2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016",

address = "United States",

}

Dong, H, Yang, J & Sheng, Y 2016, Request distribution with pre-learning for distributed SSL reverse proxies. in Y Chen (ed.), 2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016., 7515895, 2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016, Institute of Electrical and Electronics Engineers Inc., pp. 161-167, 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016, Shanghai, China, 5/30/16. https://doi.org/10.1109/SNPD.2016.7515895

Request distribution with pre-learning for distributed SSL reverse proxies. / Dong, Haitao; Yang, Jun; Sheng, Yiqiang.
2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016. ed. / Yihai Chen. Institute of Electrical and Electronics Engineers Inc., 2016. p. 161-167 7515895 (2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Request distribution with pre-learning for distributed SSL reverse proxies

AU - Dong, Haitao

AU - Yang, Jun

AU - Sheng, Yiqiang

PY - 2016/7/18

Y1 - 2016/7/18

N2 - As network data security becoming more and more universalized, distributed Secure Sockets Layer (SSL) reverse proxies are often used in Web systems to offload CPU exhausting SSL operations from Web servers and improve the execution performance of the SSL protocol. The distribution strategy of user requests to the SSL reverse proxies is a significant factor affecting the system's performance in processing SSL operations. Aiming at improving the quality of request distribution decisions, this paper proposes a new approach for SSL reverse proxy load estimation, i.e. the family of algorithms called Load Estimation with Pre-Learning (LEPL), which estimates load using pre-learned machine learning models. Using LEPL, high accuracy of load estimation can be achieved, so that better request distribution decisions can be made. Our experimental results show that by using pre-learning, the SSL reverse proxy system's average response time can be shortened by about 30% - 50%.

AB - As network data security becoming more and more universalized, distributed Secure Sockets Layer (SSL) reverse proxies are often used in Web systems to offload CPU exhausting SSL operations from Web servers and improve the execution performance of the SSL protocol. The distribution strategy of user requests to the SSL reverse proxies is a significant factor affecting the system's performance in processing SSL operations. Aiming at improving the quality of request distribution decisions, this paper proposes a new approach for SSL reverse proxy load estimation, i.e. the family of algorithms called Load Estimation with Pre-Learning (LEPL), which estimates load using pre-learned machine learning models. Using LEPL, high accuracy of load estimation can be achieved, so that better request distribution decisions can be made. Our experimental results show that by using pre-learning, the SSL reverse proxy system's average response time can be shortened by about 30% - 50%.

KW - distributed system

KW - load estimation

KW - machine learning

KW - request distribution

KW - SSL reverse proxy

KW - Web system

UR - http://www.scopus.com/inward/record.url?scp=84983372402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983372402&partnerID=8YFLogxK

U2 - 10.1109/SNPD.2016.7515895

DO - 10.1109/SNPD.2016.7515895

M3 - Conference contribution

AN - SCOPUS:84983372402

T3 - 2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016

SP - 161

EP - 167

BT - 2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016

A2 - Chen, Yihai

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016

Y2 - 30 May 2016 through 1 June 2016

ER -

Dong H, Yang J, Sheng Y. Request distribution with pre-learning for distributed SSL reverse proxies. In Chen Y, editor, 2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 161-167. 7515895. (2016 IEEE/ACIS 17th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, SNPD 2016). doi: 10.1109/SNPD.2016.7515895

Request distribution with pre-learning for distributed SSL reverse proxies

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Cite this