We address power-aware scheduling of periodic tasks to reduce CPU energy consumption in hard real-time systems through dynamic voltage scaling. Our intertask solution includes three components: 1) a static (offline) compute the optimal speed, assuming worst-case workload for each arrival, 2) an online speed reduction mechanism reclaim by adapting actual workload, and 3) online, adaptive speculative adjustment anticipate early completions future executions using average-case information. All...

In this paper we address power-aware scheduling of periodic hard real-time tasks using dynamic voltage scaling. Our solution includes three parts: (a) a static (off-line) to compute the optimal speed, assuming worst-case workload for each arrival, (b) an on-line speed reduction mechanism reclaim energy by adapting actual workload, and (c) online, adaptive speculative adjustment anticipate early completions future executions average-case information. All these solutions still guarantee that...

In this paper, we address the problem of partitioning periodic real-time tasks in a multiprocessor platform by considering both feasibility and energy-awareness perspectives: our objective is to compute feasible that results minimum energy consumption on multiple identical processors using variable voltage earliest-deadline-first scheduling. We show NP-hard strong sense m /spl ges/ 2 even when guaranteed priori. Then, develop framework where load balancing plays major role producing...

In this paper, we provide an efficient solution for periodic real-time tasks with (potentially) different power consumption characteristics. We show that a task T/sub i/ can run at constant speed S/sub every instance without hurting optimality. sketch O(n/sup 2/ log n) algorithm to compute the optimal values. also prove EDF (Earliest Deadline First) scheduling policy be used obtain feasible schedule these

Dynamic voltage and frequency scaling (DVFS) has been widely used to manage energy in real-time embedded systems. However, it was recently shown that DVFS direct adverse effects on system reliability. In this work, we investigate static dynamic reliability-aware management schemes minimize consumption for periodic systems while preserving Focusing earliest deadline first (EDF) scheduling, show the version of problem is NP-hard propose two task-level utilization-based heuristics. Then,...

This article presents a survey of energy-aware scheduling algorithms proposed for real-time systems. The analysis the main results starting from middle 1990s until today, showing how solutions evolved to address evolution platform's features and needs. first taxonomy classify existing approaches uniprocessor systems, distinguishing them according technology exploited reducing energy consumption, that is, Dynamic Voltage Frequency Scaling (DVFS), Power Management (DPM), or both. Then,...

On emerging multicore systems, task replication is a powerful way to achieve high reliability targets. In this paper, we consider the problem of achieving given target for set periodic real-time tasks running on system with minimum energy consumption. Our framework explicitly takes into account coverage factor fault detection techniques and negative impact Dynamic Voltage Scaling (DVS) rate transient faults leading soft errors. We characterize subtle interplay between processing frequency,...

We consider the problem of energy minimization for periodic preemptive hard real-time tasks that are scheduled on an identical multiprocessor platform with dynamic voltage scaling capability. adopt partitioned scheduling and assume assigned rate-monotonic priorities. show is NP-hard in strong sense m /spl ges/ 2 processors even when feasibility guaranteed a priori. Because intractability problem, we propose integrated approach consists three different components: RMS admission control test,...

The dynamic voltage and frequency scaling (DVFS) technique is the basis of numerous state-of-the-art energy management schemes proposed for real-time embedded systems. However, recent research has illustrated alarmingly negative impact DVFS on task system reliability. In this paper, we consider problem assigning processing frequencies to a set tasks in order maximize overall reliability, under given time constraints. First, frame-based model, formulate as nonlinear optimization show how...

Voltage/Frequency Scaling (VFS) and Device Power Management (DPM) are two popular techniques commonly employed to save energy in real-time embedded systems. VFS policies aim at reducing the CPU energy, while DPM-based solutions involve putting system components (e.g., memory or I/O devices) low-power/sleep states runtime, when sufficiently long idle intervals can be predicted. Despite numerous research papers that tackled minimization problem using DPM separately, interactions of these not...

The negative impact of the popular energy management technique Dynamic Voltage and Frequency Scaling (DVFS) on reliability real-time embedded systems, in terms increased transient fault rates, has been recently identified. As a result, recent research literature includes number solutions within so-called Reliability-Aware Power Management (RA-PM) framework, where aim is to preserve system's original reliability. In this effort, we propose more general framework achieve arbitrary levels that...

With the continued scaling of CMOS technologies and reduced design margins, reliability concerns induced by transient faults have become prominent. Moreover, popular energy management technique dynamic voltage frequency (DVFS) has been shown to direct negative effects on reliability. In this work, for a set real-time tasks, we focus slack allocation problem minimize their consumption while preserving overall system Building our previous findings single application where recovery task was...

DVFS remains an important energy management technique for embedded systems. However, its negative impact on transient fault rates has been recently shown. In this paper, we propose the Generalized Shared Recovery (GSHR) to optimally use in order achieve a given reliability goal real-time applications. Our determines optimal number of recoveries deploy as well task-level processing frequencies minimize consumption while achieving and meeting timing constraints. The may be shared among tasks,...

In this paper, we present an energy-aware standby-sparing technique for periodic real-time applications. A system consists of a primary processor where the application tasks are executed using Dynamic Voltage Scaling (DVS) to save energy, and spare backup at maximum voltage/frequency, should there be need. our framework, employ Earliest-Deadline-First (EDF) Earliest-Deadline-Late (EDL) scheduling policies on CPUs, respectively. The use EDL CPU allows delaying as much possible, enabling...

Reward-based scheduling refers to the problem in which there is a reward associated with execution of task. In our framework, each real-time task comprises mandatory and an optional part, nondecreasing function associated. Imprecise Computation Increased-Reward-with-Increased-Service models fall within scope this framework. paper we address reward-based for periodic tasks. For linear concave functions show: (a) existence optimal schedule where service time constant at every instance (b) how...

While Dynamic Voltage Scaling (DVS) remains as a popular energy management technique for real-time embedded applications, recent research has identified significant and negative impact of voltage scaling on system reliability. For this reason, number reliability-aware power (RA-PM) schemes were recently proposed to preserve the reliability when DVS is used. In paper, we propose new approach, called shared recovery (SHR) technique, minimize system-level consumption while still preserving...

In this paper, we undertake the problem of minimizing system-level energy on chip-multicore processors (CMPs) executing a periodic real-time workload. Our framework has two components: i.) static phase that selects subset cores upon which workload can be executed without dissipating excessive power and performs task-to-core allocation, ii.) dynamic involves managing selected at run-time through coordinated management exploits Dynamic Voltage Frequency Scaling (DVFS) as well multiple idle...

There is currently tremendous interest in deploying energy harvesting wireless sensor networks. Engineering such systems requires striking a careful balance between sensing performance and management. Our work addresses this problem through the design analysis of aware utility-based rate allocation algorithm. Based on network utility formulation, we show that our algorithm optimal terms assigning rates to individual nodes maximize overall utility, while ensuring energy-neutral operation. To...

The dynamic voltage scaling (DVS) technique is the basis of numerous state-of-the-art energy management schemes proposed for real-time embedded systems. However, recent research has illustrated alarmingly negative impact DVS on task and system reliability. In this paper, we consider problem processing frequency assignment to a set tasks in order maximize overall reliability, under given time constraints. First, formulate as non-linear optimization show how obtain static optimal solution....

Reliability-aware power management (RAPM) schemes have been recently studied to save energy while preserving system reliability. The existing RAPM schemes, however, provision for worst-case execution scenarios and are rather conservative. In this paper, by exploiting the probabilistic time information of real-time tasks, we develop an optimistic scheme. Instead scheduling a full recovery tasks whose executions scaled down, new scheme puts aside just enough slack guarantee required...

Dynamic power management (DPM) techniques are crucial in minimizing the overall energy consumption real-time embedded systems. The timing constraints of applications and non-trivial time/energy transition overheads introduce significant challenges, as device sleep intervals should be longer than a minimum threshold (called break-even time) to ensure energy-efficiency. In this paper, we present novel approach DPM problem by explicitly enforcing long for different devices, called forbidden...

The negative effects of the Dynamic Voltage and Frequency Scaling (DVFS) technique on system reliability has recently promoted research reliability-aware power management (RAPM). RAPM aims at reducing energy consumption while preserving system's reliability. In this paper, we study problem for parallel realtime applications shared memory multiprocessor systems in presence precedence constraints. We show that is NP-hard. Depending how recoveries are scheduled utilized by a subset selected...