Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning

TL;DR

DHDA is an online framework that adaptively learns configuration performance models in dynamic environments by capturing both local and global concept drifts, improving accuracy and efficiency over existing methods.

Contribution

The paper introduces DHDA, a novel dually hierarchical online adaptation framework that effectively handles multi-level concept drifts in software configuration performance learning.

Findings

DHDA achieves up to 2x accuracy improvements over state-of-the-art methods.

DHDA effectively detects and adapts to both local and global concept drifts.

DHDA maintains reasonable computational overhead while improving adaptation quality.

Abstract

Modern configurable software systems need to learn models that correlate configuration and performance. However, when the system operates in dynamic environments, the workload variations, hardware changes, and system updates will inevitably introduce concept drifts at different levels - global drifts, which reshape the performance landscape of the entire configuration space; and local drifts, which only affect certain sub-regions of that space. As such, existing offline and transfer learning approaches can struggle to adapt to these implicit and unpredictable changes in real-time, rendering configuration performance learning challenging. To address this, we propose DHDA, an online configuration performance learning framework designed to capture and adapt to these drifts at different levels. The key idea is that DHDA adapts to both the local and global drifts using dually hierarchical adaptation: at the upper level, we redivide the data into different divisions, within each of which the local model is retrained, to handle global drifts only when necessary. At the lower level, the local models of the divisions can detect local drifts and adapt themselves asynchronously. To balance responsiveness and efficiency, DHDA combines incremental updates with periodic full retraining to minimize redundant computation when no drifts are detected. Through evaluating eight software systems and against state-of-the-art approaches, we show that DHDA achieves considerably better accuracy and can effectively adapt to drifts with up to 2x improvements, while incurring reasonable overhead and is able to improve different local models in handling concept drift.