End-to-End Delay Minimization based on Joint Optimization of DNN Partitioning and Resource Allocation for Cooperative Edge Inference

TL;DR

This paper proposes a joint optimization framework using Lyapunov-guided algorithms and deep reinforcement learning to minimize end-to-end delay in cooperative edge inference with dynamic AI tasks.

Contribution

It introduces a novel multi-slot stochastic delay optimization model and a Lyapunov-guided algorithm for joint DNN partitioning and resource allocation in MEC.

Findings

Significant delay reduction demonstrated in simulations.

Effective long-term resource management achieved.

Joint optimization outperforms baseline methods.

Abstract

Cooperative inference in Mobile Edge Computing (MEC), achieved by deploying partitioned Deep Neural Network (DNN) models between resource-constrained user equipments (UEs) and edge servers (ESs), has emerged as a promising paradigm. Firstly, we consider scenarios of continuous Artificial Intelligence (AI) task arrivals, like the object detection for video streams, and utilize a serial queuing model for the accurate evaluation of End-to-End (E2E) delay in cooperative edge inference. Secondly, to enhance the long-term performance of inference systems, we formulate a multi-slot stochastic E2E delay optimization problem that jointly considers model partitioning and multi-dimensional resource allocation. Finally, to solve this problem, we introduce a Lyapunov-guided Multi-Dimensional Optimization algorithm (LyMDO) that decouples the original problem into per-slot deterministic problems, where Deep Reinforcement Learning (DRL) and convex optimization are used for joint optimization of partitioning decisions and complementary resource allocation. Simulation results show that our approach effectively improves E2E delay while balancing long-term resource constraints.