Explainable AI for Resource-Efficient Microservice Management in Cloud-Native Networks

As the evolution from monolithic service deployments to microservices architectures extends to edge locations with constrained resources, efficient resource management becomes of paramount importance. While AI-driven solutions enable proactive decision-making to satisfy Quality of Service (QoS) requirements, their inherent black-box nature is a limitation that can often lead to overprovisioning and inefficiencies. To address this challenge, we propose a novel framework that leverages eXplainable AI (XAI), specifically counterfactual explanations, to provide insights into the correlation between resources utilization of specific microservices and potential QoS violations. By identifying the microservices most likely to cause issues, our framework enables precise and informed resource allocation decisions. Through extensive simulations, we compare our approach with benchmark schemes, demonstrating that our method achieves more efficient resource utilization while maintaining QoS requirements.