Incentive-Vacation Queueing in Extreme Edge Computing: An Analytical Reward-Based Framework

Abstract

Edge Computing (EC) emerged to address the cloud’s shortcomings in meeting demand and latency requirements, leading to a shift in computation closer to the end-user. Extreme Edge Computing (XEC) extends this approach by utilizing nearby user-owned computational resources to support latency-sensitive applications in a distributed manner. In this study, we introduce Reward Edge Computing (REC), a variant of XEC, where service providers recruit user devices for infrastructure support, offering rewards in return. We explore the use of Incentive-Vacation Queueing (IVQ) to manage REC and analyze both its long-term and short-term performance. Our analysis focuses on the choice of an Incentive-Vacation Function (IVF), a contractual function between workers and service providers, proposing a tunable model favoring either party. We provide closed-form expressions for long-term worker behavior under uniform workload pricing and analyze the system’s overall short-term operation, including the time a worker spends in the system. REC and IVQ aim to commodify computational resources for edge services, akin to sharing economy models like Uber and Airbnb, utilizing user-owned infrastructure.

Keywords

• Extreme edge computing
• distributed crowd computing
• incentive vacation queueing
• incentive mechanisms
• performance modeling