MESSI: In-Memory Data Series Indexing

TL;DR

MESSI is a novel in-memory data series index that leverages modern hardware parallelization to enable real-time similarity search on large datasets, significantly outperforming previous methods in speed.

Contribution

This paper introduces MESSI, the first in-memory data series index optimized for modern hardware, achieving faster construction and query times for large datasets.

Findings

Up to 4x faster index construction

Up to 11x faster query answering

Real-time similarity search on 100GB datasets in under 75ms

Abstract

Data series similarity search is a core operation for several data series analysis applications across many different domains. However, the state-of-the-art techniques fail to deliver the time performance required for interactive exploration, or analysis of large data series collections. In this work, we propose MESSI, the first data series index designed for in-memory operation on modern hardware. Our index takes advantage of the modern hardware parallelization opportunities (i.e., SIMD instructions, multi-core and multi-socket architectures), in order to accelerate both index construction and similarity search processing times. Moreover, it benefits from a careful design in the setup and coordination of the parallel workers and data structures, so that it maximizes its performance for in-memory operations. Our experiments with synthetic and real datasets demonstrate that overall MESSI is up to 4x faster at index construction, and up to 11x faster at query answering than the state-of-the-art parallel approach. MESSI is the first to answer exact similarity search queries on 100GB datasets in _50msec (30-75msec across diverse datasets), which enables real-time, interactive data exploration on very large data series collections.