Scaling Serverless Functions in Edge Networks: A Reinforcement Learning Approach

TL;DR

This paper presents a reinforcement learning-based auto-scaling solution for serverless functions in edge networks, significantly reducing delay and improving resource allocation for delay-sensitive applications.

Contribution

It introduces a novel RL approach for auto-scaling in edge serverless environments, outperforming traditional heuristics in delay reduction.

Findings

RL outperforms heuristics in delay metrics

Delay reduction of up to 50% achieved

Effective resource allocation in distributed edge networks

Abstract

With rapid advances in containerization techniques, the serverless computing model is becoming a valid candidate execution model in edge networking, similar to the widely used cloud model for applications that are stateless, single purpose and event-driven, and in particular for delay-sensitive applications. One of the cloud serverless processes, i.e., the auto-scaling mechanism, cannot be however directly applied at the edge, due to the distributed nature of edge nodes, the difficulty of optimal resource allocation, and the delay sensitivity of workloads. We propose a solution to the auto-scaling problem by applying reinforcement learning (RL) approach to solving problem of efficient scaling and resource allocation of serverless functions in edge networks. We compare RL and Deep RL algorithms with empirical, monitoring-based heuristics, considering delay-sensitive applications. The simulation results shows that RL algorithm outperforms the standard, monitoring-based algorithms in terms of total delay of function requests, while achieving an improvement in delay performance by up to 50%.