Scale: Deep Reinforcement Learning for Container Scheduling in Serverless Edge Computing

TL;DR

This paper introduces Scale, a deep reinforcement learning framework for container scheduling in serverless edge computing, optimizing resource allocation while respecting SLOs and reducing decision time.

Contribution

The paper presents a novel DRL-based scheduling framework that incorporates SLOs, latency, and data locality for edge serverless systems, outperforming traditional methods.

Findings

Scale achieves near-optimal solutions within 1.15 times the ILP solver.

Reduces decision-making time by up to 99%.

Demonstrates effectiveness on large-scale real-world datasets.

Abstract

Serverless computing has emerged as a promising computing paradigm for edge computing. However, adopting the event driven model in highly dynamic, heterogeneous, and distributed edge systems poses significant challenges in request placement and resource management. Efficiently allocating requests to containers is therefore critical to reduce resource over provisioning and unnecessary data movement. This paper proposes Scale, a Service Level Objective aware container scheduling and resource allocation framework designed for serverless edge computing. Scale employs a policy based deep reinforcement learning algorithm to balance system stability and performance under dynamic workloads. The design jointly incorporates SLO constraints, end to end latency, and data locality into the scheduling decision process. Extensive simulations using large scale real world datasets from Huawei Cloud demonstrate that Scale achieves solutions within a factor of 1.11 to 1.15 of a state of the art Integer Linear Programming solver, while reducing decision making time by up to 99%.