Information Fusion Architecture for Variable-Load Scheduling in a Cloud-Assisted CPS
This paper addresses the problem of devising an effective information fusion architecture for a task scheduling algorithm which facilitates data processing of a Cyber Physical System (CPS) under bounded latency for bursty or lossy traffic. Task scheduling traditionally caters to real-time systems where a feedback loop does not exist allowing the serviced application to be independent of the inputs from the server. However, owing to the nature of a near real-time CPS, such liberties cannot be entertained. Additionally, the advent of big data in CPS has necessitated the use of Cloud Computing as a scalable and cost effective alternative. Task scheduling in such CPSs, where inputs from the Cloud complete the feedback loop is a major research issue. Therefore, in this paper, we propose a multi-layered information fusion architecture which integrates such a task scheduling mechanism by accommodating both traffic bursts and packet losses. Our scheduling algorithm ensures that the overall latency always remains under an acceptable upper bound as required by the CPS application.
B. K. Chejerla and S. K. Madria, "Information Fusion Architecture for Variable-Load Scheduling in a Cloud-Assisted CPS," Proceedings of the 2nd IEEE International Conference on Collaboration and Internet Computing (2016, Pittsburgh, PA), Institute of Electrical and Electronics Engineers (IEEE), Nov 2016.
The definitive version is available at https://doi.org/10.1109/CIC.2016.034
2nd IEEE International Conference on Collaboration and Internet Computing, CIC 2016 (2016: Nov. 1-3, Pittsburgh, PA)
Intelligent Systems Center
Keywords and Phrases
Cyber Physical System; Cloud; Scheduling
International Standard Book Number (ISBN)
Article - Conference proceedings
© 2016 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.