Adaptive Detection of Software Aging under Workload Shift

TL;DR

Software aging threatens reliability in long-running systems; the authors study how workload shifts undermine aging-detection models and propose adaptive detectors (DDM, ADWIN) to maintain accuracy. They compare a static Random Forest baseline to adaptive solutions using a controlled workload-shift framework and find ADWIN consistently preserves high F1 scores (above 0.93) across sudden, gradual, and recurring shifts. The work demonstrates the practical value of integrating drift-detection mechanisms into aging detection to sustain robustness in dynamic environments, and provides a reproducible evaluation framework. These insights inform deployment of aging-detection in production systems facing fluctuating workloads.

Abstract

Software aging is a phenomenon that affects long-running systems, leading to progressive performance degradation and increasing the risk of failures. To mitigate this problem, this work proposes an adaptive approach based on machine learning for software aging detection in environments subject to dynamic workload conditions. We evaluate and compare a static model with adaptive models that incorporate adaptive detectors, specifically the Drift Detection Method (DDM) and Adaptive Windowing (ADWIN), originally developed for concept drift scenarios and applied in this work to handle workload shifts. Experiments with simulated sudden, gradual, and recurring workload transitions show that static models suffer a notable performance drop when applied to unseen workload profiles, whereas the adaptive model with ADWIN maintains high accuracy, achieving an F1-Score above 0.93 in all analyzed scenarios.

Figures (2)

• Figure 1: Stages of the methodology adopted in this study.
• Figure 2: Memory usage and drift scenarios.