Context-aware Container Orchestration in Serverless Edge Computing
Peiyuan Guan, Chen Chen, Ziru Chen, Lin X. Cai, Xing Hao, Amir Taherkordi
TL;DR
This work tackles latency-sensitive serverless edge computing by jointly allocating wireless bandwidth and edge compute resources under heterogeneous conditions. It formulates a MILP to minimize latency, proves NP-hardness via a reduction from the Generalized Assignment Problem, and benchmarks three scheduling approaches: MIDACO, a Genetic Algorithm, and a context-aware neural network (CANN). The proposed CANN, a two-layer LSTM trained on MIDACO results, achieves near-optimal latency with substantially faster convergence than the heuristic baselines, reducing convergence time by about 95% while maintaining competitive end-to-end delay. The findings demonstrate a practical pathway to fast, resource-fragmentation-avoiding orchestration in edge networks for bursty serverless workloads.
Abstract
Adopting serverless computing to edge networks benefits end-users from the pay-as-you-use billing model and flexible scaling of applications. This paradigm extends the boundaries of edge computing and remarkably improves the quality of services. However, due to the heterogeneous nature of computing and bandwidth resources in edge networks, it is challenging to dynamically allocate different resources while adapting to the burstiness and high concurrency in serverless workloads. This article focuses on serverless function provisioning in edge networks to optimize end-to-end latency, where the challenge lies in jointly allocating wireless bandwidth and computing resources among heterogeneous computing nodes. To address this challenge, We devised a context-aware learning framework that adaptively orchestrates a wide spectrum of resources and jointly considers them to avoid resource fragmentation. Extensive simulation results justified that the proposed algorithm reduces over 95% of converge time while the end-to-end delay is comparable to the state of the art.