Multi-Objective Provisioning of Network Slices using Deep Reinforcement Learning

Network Slicing (NS) is crucial for efficiently enabling divergent network applications in nextgeneration networks. Nonetheless, the complex Quality of Service (QoS) requirements and diverse heterogeneity in network services entail high complexity for Network Slice Provisioning (NSP) optimization. The legacy optimization methods are challenging to meet various low latency and highreliability requirements from network applications. Specifically, we formulate the ONSP problem as an Multi-Objective Integer Programming Optimization (MOIPO) problem. Our simulation results show the effectiveness of the proposed method compared to the state-of-the-art methods with a lower SLA violation rate and network operation cost. Network Slicing (NS) is essential in the next-generation mobile wireless networks [1]. It enables efficient connectivity to various services with diverse requirements by instantiating multiple logical networks on top of the substrate, i.e., the physical network infrastructure. Note that some emerging 5G services, such as those related to the Ultra-Reliable Low Latency Communication (URLLC), require dedicated network resources to achieve the stringent quality of service (QoS) requirements.