当前位置: X-MOL 学术IEEE Trans. Wirel. Commun. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Optimization of Workload Balancing and Power Allocation for Wireless Distributed Computing
IEEE Transactions on Wireless Communications ( IF 10.4 ) Pub Date : 2022-03-25 , DOI: 10.1109/twc.2022.3160493
Chen Sun , Xiqi Gao , Zhi Ding

Distributed computing systems, such as Hadoop, have been widely studied and used for executing and analyzing large data. In this paper, we investigate an emerging resource allocation problem for wireless distributed computing systems consisting of multifunctional nodes in charge of both numerical computation and wireless communication with master nodes. We focus on a computation power consumption model based on CMOS devices and a communication power consumption model involving multiple antenna transceivers against mutual interference. We present a joint optimization problem for workload scheduling and power allocation for achieving maximum computational speed under total power constraint. We simplify the joint optimization into two sub-problems. For workload scheduling as an integer programming sub-problem, we relax the integer constraint and establish the equivalence between relaxed and original problems. For the power allocation sub-problem, we maximize a difference of convex functions by utilizing the concave-convex procedure. We prove our proposed algorithm to converge to a stationary point of the original program. Simulation results confirm the efficiency and near-optimal performance of our proposed algorithms.

中文翻译:

无线分布式计算的工作负载平衡和功率分配优化

分布式计算系统,如 Hadoop,已被广泛研究并用于执行和分析大数据。在本文中,我们研究了无线分布式计算系统的新兴资源分配问题,该系统由负责数值计算和与主节点无线通信的多功能节点组成。我们专注于基于CMOS器件的计算功耗模型和涉及多个天线收发器的相互干扰的通信功耗模型。我们提出了一个工作负载调度和功率分配的联合优化问题,以在总功率约束下实现最大计算速度。我们将联合优化简化为两个子问题。对于作为整数规划子问题的工作负载调度,我们放松整数约束并建立松弛问题和原始问题之间的等价性。对于功率分配子问题,我们利用凹凸过程最大化凸函数的差异。我们证明我们提出的算法可以收敛到原始程序的固定点。仿真结果证实了我们提出的算法的效率和接近最佳的性能。
更新日期:2022-03-25
down
wechat
bug