Experimental comparison of graph-based approximate nearest neighbor search algorithms on edge devices

TL;DR

This paper provides a comprehensive experimental comparison of graph-based approximate nearest neighbor search algorithms on edge devices, focusing on real-time applications like smart city infrastructure and autonomous vehicles.

Contribution

It offers the first detailed analysis of multiple graph-based ANN algorithms on edge hardware, including metrics like latency and power consumption, for real-time applications.

Findings

Different algorithms vary significantly in latency and power efficiency.

Edge device deployment impacts algorithm performance and suitability.

Insights guide selection of ANN algorithms for real-time edge applications.

Abstract

In this paper, we present an experimental comparison of various graph-based approximate nearest neighbor (ANN) search algorithms deployed on edge devices for real-time nearest neighbor search applications, such as smart city infrastructure and autonomous vehicles. To the best of our knowledge, this specific comparative analysis has not been previously conducted. While existing research has explored graph-based ANN algorithms, it has often been limited to single-threaded implementations on standard commodity hardware. Our study leverages the full computational and storage capabilities of edge devices, incorporating additional metrics such as insertion and deletion latency of new vectors and power consumption. This comprehensive evaluation aims to provide valuable insights into the performance and suitability of these algorithms for edge-based real-time tracking systems enhanced by nearest-neighbor search algorithms.