Hakan Aydin

Dynamic and aggressive scheduling techniques for power-aware real-time systems

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) solution to compute the optimal speed, assuming worst-case workload for each arrival, (b) an on-line speed reduction mechanism to reclaim energy by adapting to the actual workload, and (c) an online, adaptive and speculative speed adjustment mechanism to anticipate early completions of future executions by using the average-case workload information. All these solutions still guarantee that all deadlines are met. Our simulation results show that the reclaiming algorithm saves a striking 50% of the energy, over the static algorithm. Further our speculative techniques allow for an additional approximately 20% savings over the reclaiming algorithm. In this study, we also establish that solving an instance of the static power-aware scheduling problem is equivalent to solving an instance of the reward-based scheduling problem [1, 4] with concave reward functions.

Power-aware scheduling for periodic real-time tasks

We address power-aware scheduling of periodic tasks to reduce CPU energy consumption in hard real-time systems through dynamic voltage scaling. Our intertask voltage scheduling solution includes three components: 1) a static (offline) solution to compute the optimal speed, assuming worst-case workload for each arrival, 2) an online speed reduction mechanism to reclaim energy by adapting to the actual workload, and 3) an online, adaptive and speculative speed adjustment mechanism to anticipate early completions of future executions by using the average-case workload information. All these solutions still guarantee that all deadlines are met. Our simulation results show that our reclaiming algorithm alone outperforms other recently proposed intertask voltage scheduling schemes. Our speculative techniques are shown to provide additional gains, approaching the theoretical lower-bound by a margin of 10 percent.In this paper, we address power-aware scheduling of periodic tasks to reduce CPU energy consumption in hard real-time systems through dynamic voltage scaling. Our intertask voltage scheduling solut...

Energy-aware partitioning for multiprocessor real-time systems

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 the feasible partitioning that results in minimum energy consumption on multiple identical processors by using variable voltage earliest-deadline-first scheduling. We show that the problem is NP-hard in the strong sense on m /spl ges/ 2 processors even when feasibility is guaranteed a priori. Then, we develop our framework where load balancing plays a major role in producing energy-efficient partitionings. We evaluate the feasibility and energy-efficiency performances of partitioning heuristics experimentally.

Determining optimal processor speeds for periodic real-time tasks with different power characteristics

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 a constant speed S/sub i/ at every instance without hurting optimality. We sketch an O(n/sup 2/ log n) algorithm to compute the optimal S/sub i/ values. We also prove that the EDF (Earliest Deadline First) scheduling policy can be used to obtain a feasible schedule with these optimal speed values.

Energy-aware task allocation for rate monotonic scheduling

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. We adopt partitioned scheduling and assume that the tasks are assigned rate-monotonic priorities. We show that the problem is NP-hard in the strong sense on m /spl ges/ 2 processors even when the feasibility is guaranteed a priori. Because of the intractability of the problem, we propose an integrated approach that consists of three different components: RMS admission control test, the partitioning heuristic and the speed assignment algorithm. We discuss possible options for each component by considering state-of-the-art solutions. Then, we experimentally investigate the impact of heuristics on feasibility, energy and feasibility/energy performance dimensions. In offline settings where tasks can be ordered according to the utilization values, we show that worst-fit dominates other well-known heuristics. For online settings, we propose an algorithm that is based on reserving a subset of processors for light tasks to guarantee a consistent performance.

System-Level Energy Management for Periodic Real-Time Tasks

In this paper, we consider the system-wide energy management problem for a set of periodic real-time tasks running on a DVS-enabled processor. Our solution uses a generalized power model, in which frequency-dependent and frequency-independent power components are explicitly considered. Further, variations in power dissipations and on-chip/off-chip access patterns of different tasks are encoded in the problem formulation. Using this generalized power model, we show that it is possible to obtain analytically the task-level energy-efficient speed below which DVS starts to affect overall energy consumption negatively. Then, we formulate the system-wide energy management problem as a non-linear optimization problem and provide a polynomial-time solution. We also provide a dynamic slack reclaiming extension which considers the effects of slow-down on the system-wide energy consumption. Our experimental evaluation shows that the optimal solution provides significant (up to 50%) gains over the previous solutions that focused on dynamic CPU power at the expense of ignoring other power components

Optimal reward-based scheduling for periodic real-time tasks

Reward-based scheduling refers to the problem in which there is a reward associated with the execution of a task. In our framework, each real-time task comprises a mandatory and an optional part. The mandatory part must complete before the tasks deadline, while a nondecreasing reward function is associated with the execution of the optional part, which can be interrupted at any time. Imprecise computation and Increased-Reward-with-Increased-Service models fall within the scope of this-framework. In this paper, we address the reward-based scheduling problem for periodic tasks. An optimal schedule is one where mandatory-parts complete in a timely manner and the weighted average reward is maximized. For linear and concave reward functions, which are most common, we 1) show the existence of an optimal schedule where the optional service time of a task is constant at every instance and 2) show how to efficiently compute this service time. We also prove the optimality of Rate Monotonic Scheduling (with harmonic periods), Earliest Deadline First, and Least Laxity First policies for the case of uniprocessors when used with the optimal service times we computed. Moreover, we extend our result by showing that any policy which can fully utilize all the processors is also optimal for the multiprocessor periodic reward-based scheduling. To show-that our optimal solution is pushing the limits of reward-based scheduling, we further prove that, when the reward functions are convex, the problem becomes NP-Hard. Our static optimal solution, besides providing considerable reward improvements over the previous suboptimal strategies, also has a major practical benefit. Run-time overhead is eliminated and existing scheduling disciplines may be used without modification with the computed optimal service times.

Reliability-Aware Energy Management for Periodic Real-Time Tasks

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 has direct and adverse effects on system reliability. In this work, we investigate static and dynamic reliability-aware energy management schemes to minimize energy consumption for periodic real-time systems while preserving system reliability. Focusing on earliest deadline first (EDF) scheduling, we first show that the static version of the problem is NP-hard and propose two task-level utilization-based heuristics. Then, we develop a job-level online scheme by building on the idea of wrapper-tasks, to monitor and manage dynamic slack efficiently in reliability-aware settings. The feasibility of the dynamic scheme is formally proved. Finally, we present two integrated approaches to reclaim both static and dynamic slack at runtime. To preserve system reliability, the proposed schemes incorporate recovery tasks/jobs into the schedule as needed, while still using the remaining slack for energy savings. The proposed schemes are evaluated through extensive simulations. The results confirm that all the proposed schemes can preserve the system reliability, while the ordinary (but reliability-ignorant) energy management schemes result in drastically decreased system reliability. For the static heuristics, the energy savings are close to what can be achieved by an optimal solution by a margin of 5 percent. By effectively exploiting the runtime slack, the dynamic schemes can achieve additional energy savings while preserving system reliability.

Optimal reward-based scheduling of periodic real-time tasks

Reward-based scheduling refers to the problem in which there is a reward associated with the execution of a task. In our framework, each real-time task comprises a mandatory and an optional part, with which a nondecreasing reward function is associated. Imprecise Computation and Increased-Reward-with-Increased-Service models fall within the scope of this framework. In this paper we address the reward-based scheduling problem for periodic tasks. For linear and concave reward functions we show: (a) the existence of an optimal schedule where the optional service time of a task is constant at every instance and (b) how to efficiently compute this service time. We also prove that RMS-h (RMS with harmonic periods), EDF and LLF policies are optimal when used with the optimal service times we computed, and that the problem becomes NP-Hard, when the reward functions are convex. Further, our solution eliminates run-time overhead, and makes possible the use of existing scheduling disciplines.

On the Interplay of Voltage/Frequency Scaling and Device Power Management for Frame-Based Real-Time Embedded Applications

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 the system components (e.g., memory or I/O devices) to low-power/sleep states at runtime, when sufficiently long idle intervals can be predicted. Despite numerous research papers that tackled the energy minimization problem using VFS or DPM separately, the interactions of these two popular techniques are not yet well understood. In this paper, we undertake an exact analysis of the problem for a real-time embedded application running on a VFS-enabled CPU and using multiple devices. Specifically, by adopting a generalized system-level energy model, we characterize the variations in different components of the system energy as a function of the CPU processing frequency. Then, we propose a provably optimal and efficient algorithm to determine the optimal CPU frequency as well as device state transition decisions to minimize the system-level energy. We also extend our solution to deal with workload variability. The experimental evaluations confirm that substantial energy savings can be obtained through our solution that combines VFS and DPM optimally under the given task and energy models.