Adaptation to Unknown Situations as the Holy Grail of Learning-Based Self-Adaptive Systems: Research Directions

TL;DR

This paper discusses the critical challenge of enabling self-adaptive systems to handle unknown and unforeseen situations through learning-based approaches, outlining key research directions for achieving such unanticipated adaptation.

Contribution

It identifies essential research directions for developing learning-based self-adaptive systems capable of adapting to completely unknown situations without human intervention.

Findings

Systems need to define internal representations of unseen situations on-the-fly.

Extrapolation of relationships to previously encountered situations is crucial.

Reasoning about goal feasibility in new conditions is necessary.

Abstract

Self-adaptive systems continuously adapt to changes in their execution environment. Capturing all possible changes to define suitable behaviour beforehand is unfeasible, or even impossible in the case of unknown changes, hence human intervention may be required. We argue that adapting to unknown situations is the ultimate challenge for self-adaptive systems. Learning-based approaches are used to learn the suitable behaviour to exhibit in the case of unknown situations, to minimize or fully remove human intervention. While such approaches can, to a certain extent, generalize existing adaptations to new situations, there is a number of breakthroughs that need to be achieved before systems can adapt to general unknown and unforeseen situations. We posit the research directions that need to be explored to achieve unanticipated adaptation from the perspective of learning-based self-adaptive systems. At minimum, systems need to define internal representations of previously unseen situations on-the-fly, extrapolate the relationship to the previously encountered situations to evolve existing adaptations, and reason about the feasibility of achieving their intrinsic goals in the new set of conditions. We close discussing whether, even when we can, we should indeed build systems that define their own behaviour and adapt their goals, without involving a human supervisor.