A Unified Methodology for Scheduling in Distributed Cyber-Physical Systems

Abstract

A Distributed Cyber-Physical System (DCPS) may receive and induce energy-based interference from and to its environment. This paper presents a model and an associated methodology that can be used to: i) schedule tasks in DCPSs to ensure that the thermal effects of the task execution are within acceptable levels; and ii) verify that a given schedule meets the constraints. The model uses coarse discretization of space and linearity of interference. The methodology involves characterizing the interference of the task execution and fitting it into the model, then using the fitted model to verify a solution or explore the solution space.

GDCSim

“…Analytical models include queuing models (e.g., M/M/n or GI/G/n) [Ahmad and Vijaykumar 2010;Urgaonkar et al 2008;Kusic et al 2009]. For example, Ahmad and Vijaykumar [2010] expressed the average response time of a server, modeled as a GI/G/1 queue, as follows:…”

“…Permissions may be requested from Publications Dept., ACM, Inc., 2 Penn Plaza, Suite 701, New York, NY 10121-0701 USA, fax +1 (212) 869-0481, or permissions@acm.org. c 2014 ACM 1049-3301/2014/01-ART3 $15.00 DOI: http://dx.doi.org/10.1145/2553083 cost of running a data center is avoidable through an intelligent understanding and management of the cyber-physical [Lee 2008;Tang et al 2012; interactions within them. The predominant way that data center owners deal with idle power usage is to turn the equipment off when it is not needed.…”

Integrating cooling awareness with thermal aware workload placement for HPC data centers

“…However, such an analysis again falls short of considering cooling behavior and thermal profiles of heterogeneous data center. Qinghui et al [34] proposes a theoretical framework for the development and evaluation of scheduling algorithms for distributed cyber physical systems with data center as a specific example. Although it incorporates the thermal profiles of the data center in the algorithm development, cooling behavior is still ignored.…”

Analyzing Isolation in Mobile Systems

“…Task scheduling theories, e.g, [25], [6], [31], [38], [23], [24], [33], have been studied for decades under the strong assumption that each scheduled task is independent of the others. The later research on scheduling theories, e.g., [38], [23], [24], [33], [27], [22], dives deep into task scheduling and schedulability analysis, especially in cyber-physical systems [20].…”

“…Task scheduling theories, e.g, [25], [6], [31], [38], [23], [24], [33], have been studied for decades under the strong assumption that each scheduled task is independent of the others. The later research on scheduling theories, e.g., [38], [23], [24], [33], [27], [22], dives deep into task scheduling and schedulability analysis, especially in cyber-physical systems [20]. Task scheduling mainly considers how to generate the optimal scheduling policies while schedulability analysis aims to check if there exists the possibility of constraint violations during the system's evolvement process.…”