Most of the scheduling algorithms proposed for real-time embedded systems, with energy constraints, try to reduce power consumption. However, reducing the power consumption may decrease the computation speed and impact the makespan. Therefore, for real-time embedded systems, makespan and power consumption need to be considered simultaneously. Since task scheduling is an NP-hard problem, most of the proposed scheduling algorithms are not able to find the multi-objective optimal solution. In this paper, we propose a two-phase hybrid task scheduling algorithm based on decomposition of the input task graph, by applying spectral partitioning. The proposed algorithm, called G-SP, assigns each part of the task graph to a low power processor in order to minimize power consumption. Through experiments, we compare the makespan and power consumption of the G-SP against well-known algorithms of this area for a large set of randomly generated and real-world task graphs with different characteristics. The obtained results show that the G-SP outperforms other algorithms in both metrics, under various conditions, involving different numbers of processors and considering several system configurations.

针对具有能量约束的实时嵌入式系统提出的大多数调度算法都试图降低功耗。但是，降低功耗可能会降低计算速度并影响制造时间。因此，对于实时嵌入式系统，需要同时考虑制造时间和功耗。由于任务调度是一个难解决的NP问题，因此大多数提出的调度算法都无法找到多目标最优解。在本文中，我们提出了一种基于输入任务图分解的两阶段混合任务调度算法，通过应用频谱划分。提出的称为G-SP的算法将任务图的每个部分分配给低功耗处理器，以最大程度地降低功耗。通过实验，对于大量随机生成的，具有不同特征的真实任务图，我们将G-SP的制造时间和功耗与该区域的著名算法进行比较。获得的结果表明，在各种条件下，涉及不同数量的处理器并考虑了几种系统配置的情况下，G-SP的性能均优于其他两种算法。