Arnab Sarkar

Scheduling Dynamic Hard Real-Time Task Sets on Fully and Partially Reconfigurable Platforms

Reconfigurable systems are increasingly being employed in a large class of todays heterogeneous real-time embedded systems which often demand satisfaction of stringent timeliness constraints. However, executing a set of hard real-time applications on reconfigurable systems such that all timing constraints are satisfied while also allowing efficient resource utilization requires effective scheduling, mapping and admission control strategies. This letter presents methodologies for scheduling periodic hard real-time dynamic task sets on fully and partially reconfigurable field-programmable gate arrays (FPGAs). The floor of the FPGA is assumed to be statically equipartitioned into a set of homogeneous tiles (each of which act as individual processing elements or PEs) such that any arbitrary task of the given task set may be feasibly mapped into the area of a given tile. Experimental results reveal that the proposed algorithms are able to achieve high resource utilization with low task rejection rates over a variety of simulation scenarios.

Frame-Based Proportional Round-Robin

All known real-time proportional fair scheduling mechanisms either have high scheduling overheads (O(lg n) per time-slot) or do not efficiently handle dynamic task sets. This paper presents frame-based proportional round-robin (FBPRR), a real-time fair scheduler providing high and bounded proportional fairness accuracy and O(1) scheduling overhead with the ability to efficiently handle a set of dynamic tasks. FBPRR achieves this by applying the benefits of virtual-time round-robin (VTRR) scheduling mechanism within a frame-based scheduling approach. Simulation results show that the algorithm gains a speedup of 5 to 20 times (over O(lg n) complexity schedulers) with fairly high fairness

A three level LTE downlink scheduling framework for RT VBR traffic

Abstract In recent literature, it has been observed that obtaining low overhead LTE downlink scheduling mechanisms that ensure a descent QoS is a challenging task especially in the presence of transient overloads. This paper proposes a novel three level LTE downlink scheduling framework (called TLS ). The three major objectives of the proposed framework includes low overall traffic flow selection and mapping overheads at each Transmission Time Interval (TTI), maintaining acceptable QoS levels for various real-time (RT) variable bit rate (VBR) flows even during transient overloads through graceful degradation, and maximizing spectral efficiency by effectively exploiting multi-user diversity. Both the outermost and the second level of TLS employs a novel adjustable frame-based approach to provide efficient service even in the face of ever changing wireless channel conditions, system workloads, traffic bit rates etc. A low-overhead O (1) look-up based scheme is used in the innermost layer of the framework to physically allocate bandwidth resources to the traffic flows at each TTI. Simulation results clearly reveal that TLS outperforms the existing schedulers with respect to QoS, goodput and spectral efficiency.

Sticky-ERfair: a task-processor affinity aware proportional fair scheduler

A drawback of current proportional fair schedulers is that they ignore task-to-processor mutual affinities, thereby causing frequent inter-processor task migrations and cache misses. This paper presents the Sticky-ERfair Scheduler, an Early-Release Fair (ERfair) scheduler that attempts to minimize task migrations and preemptions. Given any processor Vi, Sticky-ERfair allocates to it the most recently executed ready task that previously executed on Vi (thus restricting migrations and preemptions) in such a way that this allocation does not cause any ERfairness violations in the system at any time during the schedule length. Experimental results reveal that Sticky-ERfair can achieve upto over 40 times reduction both in the number of migrations and preemptions suffered with respect to Basic-ERfair (for a set of 25 to 100 tasks running on 2 to 10 processors) while simultaneously guaranteeing ERfairness at each time slot.

A resource allocation framework for adaptive video streaming over LTE

Abstract The ever-increasing demand for multimedia applications on mobile devices is set to pose considerable challenges on the bandwidth allocation mechanisms in LTE and future networks. In this work, we present “Adaptive Video Streaming Architecture”, an efficient resource allocation framework that attempts to maximize Quality of Experience (QoE) for a set of users by simultaneously balancing three important QoE verticals: (i) providing stutter-free viewing experience by dynamically throttling video streaming data-rates; (ii) minimizing flickers in video outputs by controlling and stabilizing the rates of encoding quality switches over time; (iii) maximizing aggregate video quality over all users. We have posed the resource allocation problem through an Integer Linear Programming (ILP) formulation and showed that solution strategies such as conventional dynamic programming (DP) impose substantial overheads. Next, we have proposed the Streamlined DP-based Quality-level Allocator (SDQA) which utilizes the discrete nature in the data-rate scalability of video flows to retain a far lower number of non-dominating partial DP-solutions and thereby generates far quicker solutions. Further, SDQA has been extended to provide a tunable approximation scheme called SDQA-AA that can accelerate the speed of generating solutions at multiple scales with distinct bounds on solution quality. Analytical and simulation based experimental results are promising.

Partition oriented frame based fair scheduler

Proportionate fair schedulers provide an effective methodology for scheduling recurrent real-time tasks on multiprocessors. However, a drawback in these schedulers is that they ignore a tasks affinity towards the processor where it was executed last, causing frequent inter-processor task migrations which ultimately results in increased execution times. This paper presents Partition Oriented Frame Based Fair Scheduler (POFBFS), an efficient proportional fair scheduler for periodic firm and soft real-time tasks that ensures a bounded number of task migrations. Experimental results reveal that POFBFS can achieve 3 to 100 times reduction in the number of migrations suffered with respect to the General-ERfair algorithm (for a set of 25 to 100 tasks running on 2 to 8 processors) while simultaneously maintaining high fairness accuracy.

A Low-Overhead Partition-Oriented ERfair Scheduler for Hard Real-Time Embedded Systems

This letter presents partition-oriented ERfair scheduler (POES), a low-overhead proportional fair scheduler for hard real-time multiprocessor embedded systems. POES achieves lower overheads using an online partitioning/merging mechanism that retains the optimal schedulability of a fully global scheduler by merging processor groups as resources become critical while using partitioning for fast scheduling at other times. The principal objective is to remain only just as global at any given instant of time as is necessary to maintain ERfair schedulability of the system throughout the schedule length. Experimental results reveal that POES incurs almost no migrations at low workloads and achieves up to 32 times reduction in the number of migrations suffered with respect to the global ERfair scheduler on a set of two to 16 processors even when the average system load is as high as 85%. Theoretical analysis proves that POES typically has the same amortized complexity as that of the global ERfair algorithm.

Buffer aware three level scheduler for video streaming over LTE

The ever increasing demand for high bandwidth, low latency multimedia applications on mobile devices is set to pose a considerable challenge on the bandwidth allocation and multiplexing mechanisms in LTE and future wireless networks. One of the most important factors that diminish the quality of viewing experience of delivered videos is frequent client side rebuffering events. This paper proposes a buffer-aware downlink scheduling framework (called BA-TLS) for streaming video applications. The problem of scheduling a set of video streams over LTE has first been formulated as an Integer Linear Programming (ILP) problem. It has been shown that a conventional dynamic programming solution for the ILP imposes prohibitive online overheads. Then, by utilizing analytical properties of the problem, a genetic algorithm based fast and efficient radio resource allocation heuristic has been implemented over the proposed framework. Experimental results reveal that the developed framework is able to provide significant reductions in rebuffering events and thus allow video transmission with high and acceptable quality of service.

Comments on “Supervisory control for real-time scheduling of periodic and sporadic tasks with resource constraints” [Automatica 45 (2009) 2597–2604]

Abstract In the article “ Supervisory control for real-time scheduling of periodic and sporadic tasks with resource constraints ”, the authors presented an approach for the design of a uniprocessor real-time scheduler for task sets consisting of a mix of periodic and sporadic tasks with support for exclusive shared resource accessibility. The scheduler design is founded on the synthesis process presented in their paper. However, it is unable to correctly model the fixed inter-arrival periodicity of a periodic task.

A three level adaptive video streaming framework over LTE

The ever increasing demand for high bandwidth, low latency multimedia applications on mobile devices is set to pose a considerable challenge on the bandwidth allocation and multiplexing mechanisms in LTE and future wireless networks. This paper proposes a low overhead Scalable Video Coding (SVC) based dynamic adaptive streaming framework (called TLS-AV) which attempt to maintain a minimum satisfactory Quality of Experience (QoE) for all end users even during transient network overloads. Two fast and efficient radio resource allocation heuristics namely, the TLS-AV Water-Filling Heuristic (TWH) and TLS-AV Balanced Water-Filling Heuristic (TBWH) have been implemented over the proposed framework. Experimental results reveal that both the developed heuristics are able to restrict packet loss rate below ∼ 10% while simultaneously achieving high video qualities and fairness among the transmitted qualities of video flows, on average.