Energy-Efficient Resource Utilization for Heterogeneous Embedded Computing Systems
Energy-Efficient Resource Utilization for Heterogeneous Embedded Computing Systems
复制标题
异构嵌入式计算系统的节能资源利用
DOI：
10.1109/tc.2017.2693186
复制
发表时间：
2017-09-01
影响因子：
3.7
通讯作者：
Li, Keqin
中科院分区：
文献类型：
--
作者：
Huang, Jing;Li, Renfa;Li, Keqin
针对异构分布式多核嵌入式系统，研究了能量有效利用和资源有效利用的联合优化问题。该系统模型被认为是一个完全异构的模型，也就是说，所有的节点有不同的最大速度和功耗水平，从硬件的角度来看，而他们可以采用不同的调度策略，从应用程序的角度。由于该问题本质上是一个多约束、多变量的优化问题，无法得到封闭解，因此本文提出了一种基于拉格朗日理论的功率分配和负载均衡策略。当拉格朗日法不能完全解决负载均衡问题时，首先采用数据拟合的方法得到核心速率，然后采用拉格朗日法求解负载均衡调度问题。几个数值例子来显示所提出的方法的有效性，并证明本优化系统的每个因素的影响。最后，通过仿真和实际应用验证了理论分析结果与实际结果的一致性.据我们所知，这是第一个在异构和分布式嵌入式系统中结合负载平衡、能源效率、硬件异构性和应用程序异构性的工作。
In this paper, the joint optimization problem with energy efficiency and effective resource utilization is investigated for heterogeneous and distributed multi-core embedded systems. The system model is considered to be fully a heterogeneous model, that is, all nodes have different maximum speeds and power consumption levels from the perspective of hardware while they can employ different scheduling strategies from the perspective of applications. Since the concerned problem by nature is a multi-constrained and multi-variable optimization problem in which a closed-form solution cannot be obtained, our aim is to propose a power allocation and load balancing strategy based on Lagrange theory. Furthermore, when the problem cannot be fully solved by Lagrange approach, a data fitting method is employed to obtain core speed first, and then load balancing schedule is solved by Lagrange method. Several numerical examples are given to show the effectiveness of the proposed method and to demonstrate the impact of each factor to the present optimization system. Finally, simulation and practical evaluations show that the theoretical results are consistent with the practical results. To the best of our knowledge, this is the first work that combines load balancing, energy efficiency, hardware heterogeneity and application heterogeneity in heterogeneous and distributed embedded systems.