Hybrid Learning for Orchestrating Deep Learning Inference in Multi-user Edge-cloud Networks

TL;DR

This paper introduces a Hybrid Learning framework that combines model-based and model-free reinforcement learning to optimize deep learning inference orchestration in multi-user edge-cloud networks, significantly reducing learning time.

Contribution

The paper proposes a novel Hybrid Learning approach that accelerates RL-based inference orchestration, addressing the trial-and-error inefficiency of traditional RL methods in dynamic edge-cloud environments.

Findings

Accelerates RL learning by up to 166.6 times

Reduces system interactions during learning process

Improves inference orchestration efficiency in edge-cloud networks

Abstract

Deep-learning-based intelligent services have become prevalent in cyber-physical applications including smart cities and health-care. Collaborative end-edge-cloud computing for deep learning provides a range of performance and efficiency that can address application requirements through computation offloading. The decision to offload computation is a communication-computation co-optimization problem that varies with both system parameters (e.g., network condition) and workload characteristics (e.g., inputs). Identifying optimal orchestration considering the cross-layer opportunities and requirements in the face of varying system dynamics is a challenging multi-dimensional problem. While Reinforcement Learning (RL) approaches have been proposed earlier, they suffer from a large number of trial-and-errors during the learning process resulting in excessive time and resource consumption. We present a Hybrid Learning orchestration framework that reduces the number of interactions with the system environment by combining model-based and model-free reinforcement learning. Our Deep Learning inference orchestration strategy employs reinforcement learning to find the optimal orchestration policy. Furthermore, we deploy Hybrid Learning (HL) to accelerate the RL learning process and reduce the number of direct samplings. We demonstrate efficacy of our HL strategy through experimental comparison with state-of-the-art RL-based inference orchestration, demonstrating that our HL strategy accelerates the learning process by up to 166.6x.