Ranking and benchmarking framework for sampling algorithms on synthetic data streams
This provides a benchmarking tool for researchers and practitioners working on sampling algorithms in distributed streaming systems, though it is incremental as it builds on existing concepts.
The paper tackles the lack of standardized testing for sampling algorithms used in dynamic partitioning of non-uniform data streams, by developing an extensible ranking framework with benchmark and hyperparameter optimization capabilities, and includes a data generator for concept drifts.
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.