Results 1 
4 of
4
Utility Accrual RealTime Scheduling Under Variable Cost Functions
, 2005
"... We present a utility accrual realtime scheduling algorithm called CICVCUA, for tasks whose execution times are functions of their starting times. We model such variable execution times employing variable cost functions (or VCFs). The algorithm considers application activities that are subject to t ..."
Abstract

Cited by 4 (0 self)
 Add to MetaCart
(Show Context)
We present a utility accrual realtime scheduling algorithm called CICVCUA, for tasks whose execution times are functions of their starting times. We model such variable execution times employing variable cost functions (or VCFs). The algorithm considers application activities that are subject to time/utility function time constraints (or TUFs), execution times described using VCFs, and concurrent, mutually exclusive sharing of nonCPU resources. We consider the multicriteria scheduling objective of (1) assuring that the maximum interval between any two consecutive, successful completions of jobs of a task must not exceed a specified upper bound, and (2) maximizing the system’s total accrued utility, while satisfying mutual exclusion resource constraints. Since the scheduling problem is intractable, CICVCUA statically computes worstcase sojourn times of tasks, selects tasks for execution based on their potential utility density, and completes them at specific times, in polynomialtime. We establish that CICVCUA achieves optimal timeliness during underloads. Further, we identify the conditions under which timeliness assurances hold. Our simulation experiments illustrate CICVCUA’s effectiveness and superiority. Acknowledgments
unknown title
"... Tasks in many realtime applications can be scheduled by variations of rate monotonic or earliest deadline first algorithms. When this is possible, it is satisfying to have formal analysis and performance bounds underlying the use of these algorithms. However, in many applications the simultaneous s ..."
Abstract
 Add to MetaCart
(Show Context)
Tasks in many realtime applications can be scheduled by variations of rate monotonic or earliest deadline first algorithms. When this is possible, it is satisfying to have formal analysis and performance bounds underlying the use of these algorithms. However, in many applications the simultaneous set of constraints that must be satisfied makes these traditional solutions unsuitable. Practical solutions for these more complicated applications are important. In this paper we develop a novel integrated scheduling and allocation heuristic for a dual face phased array radar system. The realistic features of the radar system that must be simultaneously addressed include timeliness (worst case execution time, period, deadline), semantic importance, and physical constraints such as beam selection and frequency harmonics. The heuristic function we develop provides a very flexible way to incorporate these requirements into one single equation. Since scheduling high semantic importance tasks is paramount, we use the highest semantic importance tasks ’ success ratio as the major performance metric. Based on simulation results, we show that our static heuristic algorithm can schedule more than 91 % of the highest semantic importance tasks at high frequency conflict degree even at heavy workloads. The result is 50 % better than EDF and 31 % better than an importance (IMP) based static priority scheduling algorithm where IMP is similar to various current approaches. For the online scheduling algorithm, our heuristic algorithm is 30 % better than EDF and 20 % better than IMP in terms of highest semantic importance tasks ’ success ratio at heavy workloads.
DWELL SCHEDULING OF MULTIFUNCTION PHASED ARRAY RADARS BASED ON GENETIC ALGORITHM
"... ..."
(Show Context)
Minimizing Peak Temperature in Embedded RealTime Systems via ThermalAware Periodic Resources
"... Over the years, thermalaware designs have become a prominent research issue for realtime application development. A drastic increase in energy consumption of modern processors makes devices running realtime applications more prone to overheating and also decreases the lifespan. As a result, obta ..."
Abstract
 Add to MetaCart
(Show Context)
Over the years, thermalaware designs have become a prominent research issue for realtime application development. A drastic increase in energy consumption of modern processors makes devices running realtime applications more prone to overheating and also decreases the lifespan. As a result, obtaining a reduction in peak temperature is considered the most desirable design aspect in developing such devices as it not only decreases the packaging cost, but also increases the lifetime of a device substantially. In this article, the thermalaware periodic resource model is proposed which is a proactive scheme for minimizing peak temperature in a system with a microprocessor having basic energy saving features. For this model, polynomialtime algorithms are proposed to determine the lowest processing time (i.e., bandwidth) in periodic intervals with the minimum peak temperature for a specified sporadic task system scheduled by earliestdeadline first (EDF). The proposed algorithms only incur bounded error (based on a userdefined parameter) in determining temperature in exchange for a significant improvement in running time over exact algorithms. Furthermore, we derive the thermal equations to calculate the asymptotic temperature bound for a given thermalaware periodic resource. These equations, along with the algorithm presented, will give a system designer not only a guarantee of schedulability for a given workload with minimum peak temperature, but also the freedom of choosing a tradeoff between the accuracy and the efficiency of the algorithms.