Conference Paper

Delay Analysis in Temperature-Constrained Hard Real-Time Systems with General Task Arrivals

Michigan Univ., Dearborn, MI
DOI: 10.1109/RTSS.2006.16 Conference: Proceedings of the 27th IEEE Real-Time Systems Symposium (RTSS 2006), 5-8 December 2006, Rio de Janeiro, Brazil
Source: DBLP


In this paper, we study temperature-constrained hard real- time systems, where real-time guarantees must be met with- out exceeding safe temperature levels within the proces- sor. Dynamic speed scaling is one of the major techniques to manage power so as to maintain safe temperature lev- els. As example, we adopt a simple reactive speed con- trol technique in our work. We design a methodology to perform delay analysis for general task arrivals under re- active speed control with First-In-First-Out (FIFO) sche- duling and Static-Priority (SP) scheduling. As a special case, we obtain a close-form delay formula for the leaky- bucket task arrival model. Our data show how simple reac- tive speed control can decrease the delay of tasks compared with any constant-speed scheme.

  • Source
    • "The difference between these two approaches is that reactive schemes adapt to the temperature of the system when it reaches the maximum temperature or a specific trigger by switching the CPU speed or by changing scheduling decisions. In this scope, Wang et al. proposed a schedulability analysis for speed scaling scheme for framebased task model in [23], and they completed this with a worst-case response time analysis for FIFO and fixed priority scheduling in [22] [23]. In contrast, proactive approaches set the configuration of the system judiciously beforehand (CPU speed and scheduling decisions ) so that the maximum temperature is never reached [10] [16] [17]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper investigates schedulability analysis for thermal-aware real-time systems. Thermal constraints are becoming more and more critical in new generation miniaturized embedded systems, e.g. medical implants. As part of this work, we adapt the $PFP_{ASAP}$ algorithm proposed in \cite{Abdeddaim2013} for energy-harvesting systems to thermal-aware ones. We prove its optimality for non-concrete fixed-priority task sets and propose a response-time analysis based on worst-case upper bounds. We evaluate the efficacy of the proposed bounds via extensive simulation over randomly-generated task systems.
    Preview · Article · Jun 2014
  • Source
    • "We assume that the environment has a fixed temperature, and that temperature is scaled so that the ambient temperature is zero. Previous real-time research with thermal constraints [10] [11] [12] "
    [Show abstract] [Hide abstract]
    ABSTRACT: Over the years, thermal-aware designs have become a prominent research issue for real-time application development. A drastic increase in energy consumption of modern processors makes devices running real-time 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 thermal-aware 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, polynomial-time 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 earliest-deadline first (EDF). The proposed algorithms only incur bounded error (based on a user-defined 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 thermal-aware 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 trade-off between the accuracy and the efficiency of the algorithms.
    Full-text · Article · Sep 2011 · Sustainable Computing: Informatics and Systems
  • Source
    • "For uniprocessor systems, thermal-aware scheduling has been explored to optimize the performance by exploiting the DTM [3] [4] [5] to prevent the system from overheating by adopting Dynamic Voltage Scaling (DVS) [9] [10]. Wang et al. [11] [12] [13] developed reactive speed control with schedulability tests and delay analysis, while Chen et al. [14] developed proactive speed control to improve the schedulability. Bansal et al. [15] developed an algorithm to maximize the workload that can complete in a specified time window without violating the thermal constraints. "
    [Show abstract] [Hide abstract]
    ABSTRACT: As the power density of modern electronic circuits increases dramatically, systems are prone to overheating. Thermal management has become a prominent issue in system design. This paper explores thermal-aware scheduling for sporadic real-time tasks to minimize the peak temperature in a homogeneous multicore system, in which heat might transfer among some cores. By deriving an ideally preferred speed for each core, we propose global scheduling algorithms which can exploit the flexibility of multicore platforms at low temperature. We perform simulations to evaluate the performance of the proposed approach.
    Preview · Article · May 2011 · Journal of Systems Architecture
Show more