Adaptive resource management using many-core processing for fault tolerance based on cyber-physical cloud systems

摘要

With the increasing utilization of cloud computing and cyber-physical systems (CPSs), which allow the expression and control of the real world in a virtual environment, researches related to these subjects are being actively conducted in various areas. The convergence of CPS and cloud computing is being researched primarily because of their high availability, high-performance computing, and high-throughput computing. CPS consisting of numerous sensors, actuators, controllers, and control managers requires optimized modeling, simulation, and resource management technologies to integrate physical elements with computing elements for processing, which will provide high-throughput computing and high-reliability services. But the main problem of sensor resource management is that information of sensors cannot be approached in case that a sensor failure occurs at the sensing target area. Thus, various researches have been done to reconstruct the topology, but the self-topology configuration of sensors causes unnecessary events and battery consumption from various sensor nodes. In this paper, adaptive resource management (ARM) is proposed to 1) minimize information loss due to the irregular lifespan of resources, such as sensors and actuators; and 2) quickly respond to any problems. ARM uses the many-core of GPU to speed up fault handling, parallelizes the sensor information to select an alternate node of the fault node, and presents the performance evaluation results of the execution time of CPU and GPU.