Adaptive Composition of Machine Learning as a Service (MLaaS) for IoT Environments
This work addresses the problem of adapting MLaaS compositions for IoT systems, which is incremental as it builds on existing MLaaS and IoT concepts.
This paper tackles the challenge of maintaining effective Machine Learning as a Service (MLaaS) compositions in dynamic IoT environments by proposing an adaptive framework that integrates service assessment and selection models with a contextual multi-armed bandit optimization strategy, resulting in maintained Quality of Service (QoS) and reduced computational costs.
The dynamic nature of Internet of Things (IoT) environments challenges the long-term effectiveness of Machine Learning as a Service (MLaaS) compositions. The uncertainty and variability of IoT environments lead to fluctuations in data distribution, e.g., concept drift and data heterogeneity, and evolving system requirements, e.g., scalability demands and resource limitations. This paper proposes an adaptive MLaaS composition framework to ensure a seamless, efficient, and scalable MLaaS composition. The framework integrates a service assessment model to identify underperforming MLaaS services and a candidate selection model to filter optimal replacements. An adaptive composition mechanism is developed that incrementally updates MLaaS compositions using a contextual multi-armed bandit optimization strategy. By continuously adapting to evolving IoT constraints, the approach maintains Quality of Service (QoS) while reducing the computational cost associated with recomposition from scratch. Experimental results on a real-world dataset demonstrate the efficiency of our proposed approach.