Resource management for multi-service coexistence in 5 G/6 G NFV-MEC networks

Enabling the coexistence of multiple services on the same NFV-MEC network is challenging due to conflicting resource requirements, virtualization overhead, and potential processing failures, all within the strict resource constraints of the NFV-MEC node. Additionally, the critical nature of URLLC services often necessitates service prioritization, which can adversely impact the performance of eMBB applications. This paper addresses these challenges by designing a continuous-time Markov chain (CTMC)-based model that incorporates these features to analyze resource allocation for multiple coexisting services in an NFV-MEC system. Extensive analyses of energy consumption, availability, response time, and memory consumption are conducted across various system configurations. Results reveal that higher loads of URLLC services decrease system availability and increase response times for both service types. The study also finds that an increase in the number of containers does not necessarily lead to a proportional increase in energy consumption, and energy and memory consumption exhibit similar patterns due to their common usage during setup and active processing states. While increasing buffer size slightly improves service availability with minimal impact on energy consumption (as buffered requests do not use resources while in the queue), it negatively affects service response times.