Ranking and benchmarking framework for sampling algorithms on synthetic data streams

TL;DR

This paper introduces an extensible benchmarking framework with a data generator for evaluating sampling algorithms used in dynamic data stream partitioning, addressing the lack of standardized testing methods.

Contribution

It provides a novel, flexible ranking and benchmarking framework with hyperparameter optimization and a concept drift-aware data generator for sampling algorithms.

Findings

The framework effectively compares state-of-the-art algorithms.

It includes a data generator capable of simulating concept drifts.

Benchmarking results highlight the strengths and weaknesses of different algorithms.

Abstract

In the fields of big data, AI, and streaming processing, we work with large amounts of data from multiple sources. Due to memory and network limitations, we process data streams on distributed systems to alleviate computational and network loads. When data streams with non-uniform distributions are processed, we often observe overloaded partitions due to the use of simple hash partitioning. To tackle this imbalance, we can use dynamic partitioning algorithms that require a sampling algorithm to precisely estimate the underlying distribution of the data stream. There is no standardized way to test these algorithms. We offer an extensible ranking framework with benchmark and hyperparameter optimization capabilities and supply our framework with a data generator that can handle concept drifts. Our work includes a generator for dynamic micro-bursts that we can apply to any data stream. We provide algorithms that react to concept drifts and compare those against the state-of-the-art algorithms using our framework.