Autonomous fault detection in self-healing systems using Restricted Boltzmann Machines

Christopher Schneider; Adam David Barker; Simon Andrew Dobson

Autonomous fault detection in self-healing systems using Restricted Boltzmann Machines

Christopher Schneider, Adam David Barker, Simon Andrew Dobson

School of Computer Science

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

Abstract

Autonomously detecting and recovering from faults is one approach for reducing the operational complexity and costs associated with managing computing environments. We present a novel methodology for autonomously generating
investigation leads that help identify systems faults, and extends our previous work in this area by leveraging Restricted Boltzmann Machines (RBMs) and contrastive divergence learning to analyse changes in historical feature data. This allows us to
heuristically identify the root cause of a fault, and demonstrate an improvement to the state of the art by showing feature data can be predicted heuristically beyond a single instance to include entire sequences of information.

Original language	English
Title of host publication	Proceedings of the 11th IEEE International Conference and Workshops on Engineering of Autonomic and Autonomous Systems (EASe 2014)
Place of Publication	Laurel, MD
Publication status	Accepted/In press - 24 Sept 2014
Event	11th IEEE International Conference and Workshops on the Engineering of Autonomic and Autonomous Systems - John Hopkins Applied Physics Laboratory , Laurel, Maryland, United States Duration: 24 Sept 2014 → 26 Sept 2014

Conference

Conference	11th IEEE International Conference and Workshops on the Engineering of Autonomic and Autonomous Systems
Country/Territory	United States
City	Laurel, Maryland
Period	24/09/14 → 26/09/14

Keywords

Self-healing systems
Fault detection
Machine learning
Computational intelligence
Autonomic computing
Artificial neural networks
Restricted Boltzmann Machines

Access to Document

faults-ease-14
© © 2014. IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 237 KB

Cite this

@inproceedings{86a13b076bb6455aa9ba7560baad2327,

title = "Autonomous fault detection in self-healing systems using Restricted Boltzmann Machines",

abstract = "Autonomously detecting and recovering from faults is one approach for reducing the operational complexity and costs associated with managing computing environments. We present a novel methodology for autonomously generatinginvestigation leads that help identify systems faults, and extends our previous work in this area by leveraging Restricted Boltzmann Machines (RBMs) and contrastive divergence learning to analyse changes in historical feature data. This allows us toheuristically identify the root cause of a fault, and demonstrate an improvement to the state of the art by showing feature data can be predicted heuristically beyond a single instance to include entire sequences of information.",

keywords = "Self-healing systems, Fault detection, Machine learning, Computational intelligence, Autonomic computing, Artificial neural networks, Restricted Boltzmann Machines",

author = "Christopher Schneider and Barker, {Adam David} and Dobson, {Simon Andrew}",

note = "Funding for this research was provided by the Scottish Informatics and Computer Science Alliance (SICSA).; 11th IEEE International Conference and Workshops on the Engineering of Autonomic and Autonomous Systems ; Conference date: 24-09-2014 Through 26-09-2014",

year = "2014",

month = sep,

day = "24",

language = "English",

booktitle = "Proceedings of the 11th IEEE International Conference and Workshops on Engineering of Autonomic and Autonomous Systems (EASe 2014)",

}

Schneider, C, Barker, AD & Dobson, SA 2014, Autonomous fault detection in self-healing systems using Restricted Boltzmann Machines. in Proceedings of the 11th IEEE International Conference and Workshops on Engineering of Autonomic and Autonomous Systems (EASe 2014). Laurel, MD, 11th IEEE International Conference and Workshops on the Engineering of Autonomic and Autonomous Systems, Laurel, Maryland, United States, 24/09/14.

Autonomous fault detection in self-healing systems using Restricted Boltzmann Machines. / Schneider, Christopher; Barker, Adam David; Dobson, Simon Andrew.
Proceedings of the 11th IEEE International Conference and Workshops on Engineering of Autonomic and Autonomous Systems (EASe 2014). Laurel, MD, 2014.

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

TY - GEN

T1 - Autonomous fault detection in self-healing systems using Restricted Boltzmann Machines

AU - Schneider, Christopher

AU - Barker, Adam David

AU - Dobson, Simon Andrew

N1 - Funding for this research was provided by the Scottish Informatics and Computer Science Alliance (SICSA).

PY - 2014/9/24

Y1 - 2014/9/24

N2 - Autonomously detecting and recovering from faults is one approach for reducing the operational complexity and costs associated with managing computing environments. We present a novel methodology for autonomously generatinginvestigation leads that help identify systems faults, and extends our previous work in this area by leveraging Restricted Boltzmann Machines (RBMs) and contrastive divergence learning to analyse changes in historical feature data. This allows us toheuristically identify the root cause of a fault, and demonstrate an improvement to the state of the art by showing feature data can be predicted heuristically beyond a single instance to include entire sequences of information.

AB - Autonomously detecting and recovering from faults is one approach for reducing the operational complexity and costs associated with managing computing environments. We present a novel methodology for autonomously generatinginvestigation leads that help identify systems faults, and extends our previous work in this area by leveraging Restricted Boltzmann Machines (RBMs) and contrastive divergence learning to analyse changes in historical feature data. This allows us toheuristically identify the root cause of a fault, and demonstrate an improvement to the state of the art by showing feature data can be predicted heuristically beyond a single instance to include entire sequences of information.

KW - Self-healing systems

KW - Fault detection

KW - Machine learning

KW - Computational intelligence

KW - Autonomic computing

KW - Artificial neural networks

KW - Restricted Boltzmann Machines

UR - http://tab.computer.org/aas/ease/2014/index.html

M3 - Conference contribution

BT - Proceedings of the 11th IEEE International Conference and Workshops on Engineering of Autonomic and Autonomous Systems (EASe 2014)

CY - Laurel, MD

T2 - 11th IEEE International Conference and Workshops on the Engineering of Autonomic and Autonomous Systems

Y2 - 24 September 2014 through 26 September 2014

ER -

Autonomous fault detection in self-healing systems using Restricted Boltzmann Machines

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this