Online ML Self-adaptation in Face of Traps

TL;DR

This paper discusses the challenges and limitations of applying online machine learning for self-adaptation in systems, based on real-world experiments in smart farming, highlighting traps and lessons learned.

Contribution

It identifies and analyzes specific traps encountered when using online ML for self-adaptation, providing guidance for future research and practice.

Findings

Identification of several traps affecting online ML in self-adaptation

Impact of traps on system performance and estimation accuracy

Lessons learned for better application of online ML in adaptive systems

Abstract

Online machine learning (ML) is often used in self-adaptive systems to strengthen the adaptation mechanism and improve the system utility. Despite such benefits, applying online ML for self-adaptation can be challenging, and not many papers report its limitations. Recently, we experimented with applying online ML for self-adaptation of a smart farming scenario and we had faced several unexpected difficulties -- traps -- that, to our knowledge, are not discussed enough in the community. In this paper, we report our experience with these traps. Specifically, we discuss several traps that relate to the specification and online training of the ML-based estimators, their impact on self-adaptation, and the approach used to evaluate the estimators. Our overview of these traps provides a list of lessons learned, which can serve as guidance for other researchers and practitioners when applying online ML for self-adaptation.