A Resource Management Algorithm for Real-Time Response of Mobile Ad Hoc Cloud in Swarm Robotic System

摘要

Mobile ad hoc cloud enables swarm robots to share idle computing resources on-demand. It aims at delivering high functionalities for computing-intensive applications without relying on a cloud server or developed communication infrastructures. However, mobile ad hoc cloud cannot be directly deployed in swarm robots since constraints such as limited network resources and heterogeneous computing resources. This paper proposes a resource management algorithm, called Utility of Computation (UoC) bandwidth allocation algorithm, for real-time response when processing computing-intensive tasks. The algorithm ensures real-time response while considering both computation delays and communication delays, and it maximizes utilization of idle computing resources, which is achieved by a tradeoff between network resources and idle computing resources. Simulations with comparisons are performed to validate the effectiveness of the proposed algorithm.