Reliability-Aware Online Scheduling for DNN Inference Tasks in Mobile-Edge Computing

Mobile-edge computing (MEC) is widely envisioned as a promising technique for provisioning artificial intelligence (AI) capability for resource-limited Internet of Things (IoT) devices by leveraging edge servers (ESs) for executing deep neural network (DNN) inference tasks in proximity. However, scheduling DNN inference tasks at the network edge under unknown system dynamics (e.g., uncertain availability of ESs) may suffer from failures, making it difficult to guarantee reliable services for the IoT device. To overcome this challenge, we propose a reliability-aware online scheduling scheme for DNN inference tasks in MEC by leveraging both online feedback and offline data to learn the uncertain availability of ESs to maximize both the inference accuracy and service reliability of DNN inference tasks (i.e., the number of DNN inference tasks processed during the system span). We first formulate the reliability-aware DNN inference tasks scheduling problem as a novel constrained combinatorial multiarmed bandit (CMAB) problem. Then by integrating the Lyapunov optimization technique, bandit learning, approximated submodular maximization, and historical data organically, we design a reliability-aware task scheduling scheme with a bandit learning (RTBL) algorithm to solve this problem. Unfortunately, even with an accurate prediction of the system uncertainties, the task scheduling problem is still NP-hard. To deal with it, we, therefore, design an advanced approximation algorithm based on the submodularity of the scheduling problem which obtains a near-optimal solution and provides a satisfactory performance guarantee. Finally, we conduct rigorous theoretical analysis and race-driven simulations to show RTBL's brilliant performance.

Automated summary

Mobile-edge computing is a promising technique for IoT devices with limited resources to access AI capabilities. We propose a reliability-aware online scheduling scheme that utilizes online feedback and offline data to learn the uncertain availability of edge servers, maximizing both inference accuracy and service reliability of DNN inference tasks.