Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems

Prasanna Kannappan; Konstantinos Karydis; Herbert G. Tanner; Adam Jardine; Jeffrey Heinz

doi:10.1109/MED.2016.7535868

Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems

Prasanna Kannappan
, Konstantinos Karydis
, Herbert G. Tanner
, Adam Jardine
, Jeffrey Heinz

Linguistics

University of Delaware
University of Pennsylvania

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

3 Scopus citations

Abstract

The paper demonstrates that aspects of resilience of supervisory Cyber-Physical Systems (CPSs) can be improved through the inclusion of appropriate learning modules in the subordinate autonomous agents. During normal operation, individual agents keep track of their supervisor's commands and utilize the learning module, based on Grammatical Inference, to learn aspects of the organizational structure of the general system and role assignments. It is shown that in cases that the supervisor fails or communication to subordinates is disrupted, these agents are able to recover normalcy of operations. Guaranteeing normalcy recovery in supervisory CPSs is critical in cases of a catastrophic failure or malicious attack.

Original language	English
Title of host publication	24th Mediterranean Conference on Control and Automation, MED 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	996-1001
Number of pages	6
ISBN (Electronic)	9781467383455
DOIs	https://doi.org/10.1109/MED.2016.7535868
State	Published - Aug 5 2016
Event	24th Mediterranean Conference on Control and Automation, MED 2016 - Athens, Greece Duration: Jun 21 2016 → Jun 24 2016

Publication series

Name	24th Mediterranean Conference on Control and Automation, MED 2016

Conference

Conference	24th Mediterranean Conference on Control and Automation, MED 2016
Country/Territory	Greece
City	Athens
Period	06/21/16 → 06/24/16

Keywords

Cyber-Physical Systems
Grammatical Inference
Machine Learning
Resilience

Access to Document

10.1109/MED.2016.7535868

Cite this

Kannappan, P., Karydis, K., Tanner, H. G., Jardine, A., & Heinz, J. (2016). Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems. In 24th Mediterranean Conference on Control and Automation, MED 2016 (pp. 996-1001). Article 7535868 (24th Mediterranean Conference on Control and Automation, MED 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MED.2016.7535868

Kannappan, Prasanna ; Karydis, Konstantinos ; Tanner, Herbert G. et al. / Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems. 24th Mediterranean Conference on Control and Automation, MED 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 996-1001 (24th Mediterranean Conference on Control and Automation, MED 2016).

@inproceedings{ff83fdf420a641c7bf8dc6f6e0801117,

title = "Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems",

abstract = "The paper demonstrates that aspects of resilience of supervisory Cyber-Physical Systems (CPSs) can be improved through the inclusion of appropriate learning modules in the subordinate autonomous agents. During normal operation, individual agents keep track of their supervisor's commands and utilize the learning module, based on Grammatical Inference, to learn aspects of the organizational structure of the general system and role assignments. It is shown that in cases that the supervisor fails or communication to subordinates is disrupted, these agents are able to recover normalcy of operations. Guaranteeing normalcy recovery in supervisory CPSs is critical in cases of a catastrophic failure or malicious attack.",

keywords = "Cyber-Physical Systems, Grammatical Inference, Machine Learning, Resilience",

author = "Prasanna Kannappan and Konstantinos Karydis and Tanner, \{Herbert G.\} and Adam Jardine and Jeffrey Heinz",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 24th Mediterranean Conference on Control and Automation, MED 2016 ; Conference date: 21-06-2016 Through 24-06-2016",

year = "2016",

month = aug,

day = "5",

doi = "10.1109/MED.2016.7535868",

language = "English",

series = "24th Mediterranean Conference on Control and Automation, MED 2016",

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

pages = "996--1001",

booktitle = "24th Mediterranean Conference on Control and Automation, MED 2016",

}

Kannappan, P, Karydis, K, Tanner, HG, Jardine, A & Heinz, J 2016, Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems. in 24th Mediterranean Conference on Control and Automation, MED 2016., 7535868, 24th Mediterranean Conference on Control and Automation, MED 2016, Institute of Electrical and Electronics Engineers Inc., pp. 996-1001, 24th Mediterranean Conference on Control and Automation, MED 2016, Athens, Greece, 06/21/16. https://doi.org/10.1109/MED.2016.7535868

Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems. / Kannappan, Prasanna; Karydis, Konstantinos; Tanner, Herbert G. et al.
24th Mediterranean Conference on Control and Automation, MED 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 996-1001 7535868 (24th Mediterranean Conference on Control and Automation, MED 2016).

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

TY - GEN

T1 - Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems

AU - Kannappan, Prasanna

AU - Karydis, Konstantinos

AU - Tanner, Herbert G.

AU - Jardine, Adam

AU - Heinz, Jeffrey

PY - 2016/8/5

Y1 - 2016/8/5

N2 - The paper demonstrates that aspects of resilience of supervisory Cyber-Physical Systems (CPSs) can be improved through the inclusion of appropriate learning modules in the subordinate autonomous agents. During normal operation, individual agents keep track of their supervisor's commands and utilize the learning module, based on Grammatical Inference, to learn aspects of the organizational structure of the general system and role assignments. It is shown that in cases that the supervisor fails or communication to subordinates is disrupted, these agents are able to recover normalcy of operations. Guaranteeing normalcy recovery in supervisory CPSs is critical in cases of a catastrophic failure or malicious attack.

AB - The paper demonstrates that aspects of resilience of supervisory Cyber-Physical Systems (CPSs) can be improved through the inclusion of appropriate learning modules in the subordinate autonomous agents. During normal operation, individual agents keep track of their supervisor's commands and utilize the learning module, based on Grammatical Inference, to learn aspects of the organizational structure of the general system and role assignments. It is shown that in cases that the supervisor fails or communication to subordinates is disrupted, these agents are able to recover normalcy of operations. Guaranteeing normalcy recovery in supervisory CPSs is critical in cases of a catastrophic failure or malicious attack.

KW - Cyber-Physical Systems

KW - Grammatical Inference

KW - Machine Learning

KW - Resilience

UR - https://www.scopus.com/pages/publications/84986218399

U2 - 10.1109/MED.2016.7535868

DO - 10.1109/MED.2016.7535868

M3 - Conference contribution

AN - SCOPUS:84986218399

T3 - 24th Mediterranean Conference on Control and Automation, MED 2016

SP - 996

EP - 1001

BT - 24th Mediterranean Conference on Control and Automation, MED 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 24th Mediterranean Conference on Control and Automation, MED 2016

Y2 - 21 June 2016 through 24 June 2016

ER -

Kannappan P, Karydis K, Tanner HG, Jardine A, Heinz J. Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems. In 24th Mediterranean Conference on Control and Automation, MED 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 996-1001. 7535868. (24th Mediterranean Conference on Control and Automation, MED 2016). doi: 10.1109/MED.2016.7535868

Incorporating learning modules improves aspects of resilience of supervisory cyber-physical systems

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this