Cooperative-Competitive Task Allocation in Edge Computing for Delay-Sensitive Social Sensing

With the ever-increasing data processing capabilities of edge computing devices and the growing acceptance of running social sensing applications on such cloud-edge systems, effectively allocating processing tasks between the server and the edge devices has emerged as a critical undertaking for maximizing the performance of such systems. Task allocation in such an environment faces several unique challenges: (i) the objectives of applications and edge devices may be inconsistent or even conflicting with each other, and (ii) edge devices may only be partially collaborative in finishing the computation tasks due to the "rational actor" nature and trust constraints of these devices, and (iii) an edge device's availability to participate in computation can change over time and the application is often unaware of such availability dynamics. Many social sensing applications are also delay-sensitive, which further exacerbates the problem. To overcome these challenges, this paper introduces a novel game-theoretic task allocation framework. The framework includes a dynamic feedback incentive mechanism, a decentralized fictitious play with a new negotiation scheme, and a judiciously-designed private payoff function. The proposed framework was implemented on a testbed that consists of heterogeneous edge devices (Jetson TX1, TK1, Raspberry Pi3) and Amazon elastic cloud. Evaluations based on two real-world social sensing applications show that the new framework can well satisfy real-time Quality-of-Service requirements of the applications and provide much higher payoffs to edge devices compared to the state-of-the-arts.