Mixed-Integer Modeling for Multi-Criteria Optimization of 6G Service Placement

With software-only core networks, a new level of flexibility has been achieved in how network services can be distributed and where they can be deployed. The 6 G network is foreseen to become increasingly heterogeneous regarding compute resources and their interconnectivity by incorporating new deployments such as fixed and nomadic campus networks, onpremise edge networks, and non-terrestrial networks. In this new environment, service placement is one of the key mechanisms to improve the system's response time, performance, resource utilization, scalability, and robustness. This paper presents a study on network service placement for 6G networks, employing MixedInteger Programming (MIP) and Multi-Criteria Optimization (MCO) for efficient resource allocation. We propose two MIP models addressing minimizing latency, installation costs, and maximizing success rate. Our models evaluate network service placement considering constraints such as node capacities, link bandwidth, and failure scenarios. Numerical results demonstrate the scalability and effectiveness of our approaches, providing insights into optimal network service deployment strategies for future 6G-ready networks.