Article: Software Systems Engineering

Prof. Dr. Andreas Metzger

Self-learning software is able to improve its behavior at runtime by using modern AI algorithms. In his talk, Prof. Metzger will illustrate the relevance of the quality of the data based on which the software learns.

The “2nd International Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems/Internet of Things (SEA4DQ)” will be held in Singapore on November 17,2022 as part of the “ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)”. It will provide researchers and practitioners a forum for exchanging ideas, experiences, understanding of the problems, visions for the future, and promising solutions to the problems in data quality in CPS/IoT.

Andreas Metzger: Data Quality Issues in Online Reinforcement Learning for Self-adaptive Systems

A self-adaptive system can modify its structure and behavior at runtime based on its perception of the environment, itself, and its requirements. By adapting itself at runtime, the system can maintain its requirements in the presence of dynamic environment changes. Examples are elastic cloud systems, intelligent IoT systems as well as proactive process management systems. One key element of a self-adaptive system is its self-adaptation logic, which encodes when and how the system should adapt itself.

When developing the adaptation logic, developers face the challenge of design time uncertainty. This means they have to anticipate potential environment states and the precise effect of adaptation in a given environment state, while the knowledge available at design time may not be sufficient to do so. A recent industrial survey determined design-time uncertainty as one of the most frequently observed difficulties in designing self-adaptation logic in practice.

This talk will explore the opportunities but also challenges that modern machine learning algorithms offer in building the self-adaptation logic in the presence of design-time uncertainty. It will focus on online reinforcement learning as an emerging approach, which means that during operation the system learns from interactions with its environment, thereby effectively leveraging data only available at run time. In particular, the talk will focus on three different issues related to data quality and will introduce initial solutions for these issues: (1) data non-stationarity, (2) data sparsity, and (3) data intransparency. The talk will close with a critical discussion of limitations and an outlook on future research opportunities.

Andreas Metzger. 2022. Data quality issues in online reinforcement learning for self-adaptive systems (keynote). In Proceedings of the 2nd International Workshop on Software Engineering and AI for Data Quality in Cyber-Physical Systems/Internet of Things (SEA4DQ 2022). Association for Computing Machinery, New York, NY, USA, 1. https://doi.org/10.1145/3549037.3570194