A Kernel-Based Approach for Accurate Steady-State Detection in Performance Time Series

TL;DR

This paper presents a kernel-based online method for accurately detecting the transition to steady state in performance time series, improving benchmarking precision especially in noisy data.

Contribution

It introduces a novel approach adapting chemical reactor techniques for real-time steady-state detection in performance metrics, enhancing accuracy and robustness.

Findings

Reduces total error by 14.5% compared to existing methods

Provides more reliable and precise steady-state detection

Handles noisy and irregular time series effectively

Abstract

This paper addresses the challenge of accurately detecting the transition from the warmup phase to the steady state in performance metric time series, which is a critical step for effective benchmarking. The goal is to introduce a method that avoids premature or delayed detection, which can lead to inaccurate or inefficient performance analysis. The proposed approach adapts techniques from the chemical reactors domain, detecting steady states online through the combination of kernel-based step detection and statistical methods. By using a window-based approach, it provides detailed information and improves the accuracy of identifying phase transitions, even in noisy or irregular time series. Results show that the new approach reduces total error by 14.5% compared to the state-of-the-art method. It offers more reliable detection of the steady-state onset, delivering greater precision for benchmarking tasks. For users, the new approach enhances the accuracy and stability of performance benchmarking, efficiently handling diverse time series data. Its robustness and adaptability make it a valuable tool for real-world performance evaluation, ensuring consistent and reproducible results.