Thermal-aware service rate adjustment for cyber-physical systems

Abstract

The thermal-aware service rate assignment problem is a major challenge in cyber-physical systems. This problem is complex because of the severe temperature changes in uncertain physical environments and variable power consumption for each application, and these two effects might cause the system to overheat. This study proposes a dynamic-programming based service rate assignment with a feedback control framework. With configurable computational overhead, the proposed algorithm prevents the system from overheating and maximizes the system benefit under the given service level. This study also evaluates the capability of the proposed methodology using a series of experiments and presenting encouraging results.