Locality, Latency and Spatial-Aware Data Placement Strategies at the Edge

TL;DR

This paper compares different data placement strategies at the edge, showing that spatial-awareness-based strategies can match latency-based methods in quality of service and outperform distance-based approaches.

Contribution

It introduces a framework to compare various data placement strategies considering locality, latency, and spatial-awareness at the edge.

Findings

Spatial-awareness-based strategy achieves comparable QoS to latency-based methods.

Spatial-awareness outperforms distance-based data placement.

Simulation results validate the effectiveness of spatial-awareness in edge data placement.

Abstract

The vast data deluge at the network's edge is raising multiple challenges for the edge computing community. One of them is identifying edge storage servers where data from edge devices/sensors have to be stored to ensure low latency access services to emerging edge applications. Existing data placement algorithms mainly focus on locality, latency, and zoning to select edge storage servers under multiple environmental constraints. This paper uses a data placement framework to compare distance-based, latency-based, and spatial-awareness-based data placement strategies, which all share a decision-making system with similar constraints. Based on simulation experiments, we observed that the spatial-awareness-based strategy could provide a quality of service on par with the latency-based and better than the distance-based strategy.