Industrial 5G Service Quality Assurance via Markov Decision Process Mapping
Ajay Kattepur, Anil Ramachandran Nair, Merve Saimler, Yunus Donmez · 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA) · 2022
Industry 4.0 applications require robust and reliable connectivity to ensure optimal performance. The emergence of 5G private networks attempts to provide differentiated services for various industrial traffic requirements. To guarantee service quality, it is crucial to correctly map metrics of the Industry 4.0 domain to the 5G Network domain. Mapping the metrics will ensure optimal system performance without the need for network over-provisioning or requirement violations. In this work, we make use of a Partially Observable Markov Decision Process (POMDP) formulation to map Industry 4.0 metrics to 5G requirements. The optimal mapping is shown to generate policies to reconfigure the 5G network and satisfy Industry 4.0 process requirements. The system is demonstrated over use cases from the industrial project 5G SMART.