Li Xiangyu, Xie Nijie, Tian Xinyue
Tsinghua National Laboratory for Information Science and Technology, Institute of Microelectronics, Tsinghua University, Beijing 100084, China.
Sensors (Basel). 2017 Feb 8;17(2):310. doi: 10.3390/s17020310.
This paper proposes a scheduling and power management solution for energy harvesting heterogeneous multi-core WSN node SoC such that the system continues to operate perennially and uses the harvested energy efficiently. The solution consists of a heterogeneous multi-core system oriented task scheduling algorithm and a low-complexity dynamic workload scaling and configuration optimization algorithm suitable for light-weight platforms. Moreover, considering the power consumption of most WSN applications have the characteristic of data dependent behavior, we introduce branches handling mechanism into the solution as well. The experimental result shows that the proposed algorithm can operate in real-time on a lightweight embedded processor (MSP430), and that it can make a system do more valuable works and make more than 99.9% use of the power budget.
本文提出了一种用于能量收集异构多核无线传感器网络（WSN）节点片上系统（SoC）的调度与功率管理解决方案，以使系统能够常年持续运行并高效利用收集到的能量。该解决方案包括一种面向异构多核系统的任务调度算法以及一种适用于轻量级平台的低复杂度动态工作负载缩放和配置优化算法。此外，考虑到大多数WSN应用的功耗具有数据依赖行为的特点，我们还在解决方案中引入了分支处理机制。实验结果表明，所提出的算法能够在轻量级嵌入式处理器（MSP430）上实时运行，并且能够使系统完成更多有价值的工作，同时使功率预算的利用率超过99.9%。
