Towards More Explainable and Traceable AI: Gray-boxed Design in a Case of Microservice Allocation

There is great potential in leveraging Artificial Intelligence (AI) systems to optimize complex infrastructures, automate difficult tasks, or support autonomy and coordination between networked devices. However, advances in state-of-the-art AI often neglect features and/or requirements that businesses care deeply about, namely traceability and explainability. While majority of research concerning Explainable AI remains focused on weight modelling and timid gray-box approaches, the state-of-the-art has not explored much the deployment of semi-physical architectures combining fuzzy rule-based systems with more opaque models to improve explainability. This contribution aims to explore and make the case for a middle ground of mixed AI architectures that combine the performance of black-box AI models with a more explainable overall architecture, enabling operators to use them, while still retaining the core aspects of explainability, when compared to full black-box AI systems. This work contextualizes a potential application of such approach to the problem of Service Level Agreement compliance, in a case of microservice allocation decision over cloud (and cloud-like) infrastructures.