# Distributed and Application-aware Task Scheduling in Edge-clouds

## TL;DR

Petrel is a distributed, application-aware task scheduling framework for edge-clouds that improves load balancing and QoE by adaptive policies and sample-based load balancing, outperforming existing strategies.

## Contribution

Introduces Petrel, a novel distributed scheduling framework that enhances load balancing and QoE in edge-clouds through adaptive, application-aware policies.

## Key findings

- Significant performance improvements over existing strategies.
- Effective load balancing without centralized control.
- Enhanced user QoE through application-aware scheduling.

## Abstract

Edge computing is an emerging technology which places computing at the edge of the network to provide an ultra-low latency. Computation offloading, a paradigm that migrates computing from mobile devices to remote servers, can now use the power of edge computing by offloading computation to cloudlets in edge-clouds. However, the task scheduling of computation offloading in edge-clouds faces a two-fold challenge. First, as cloudlets are geographically distributed, it is difficult for each cloudlet to perform load balancing without centralized control. Second, as tasks of computation offloading have a wide variety of types, to guarantee the user quality of experience (QoE) in terms of task types is challenging. In this paper, we present Petrel, a distributed and application-aware task scheduling framework for edge-clouds. Petrel implements a sample-based load balancing technology and further adopts adaptive scheduling policies according to task types. This application-aware scheduling not only provides QoE guarantee but also improves the overall scheduling performance. Trace-driven simulations show that Petrel achieves a significant improvement over existing scheduling strategies.