Multi-objective Optimisation for Slice-aware Resource Orchestration in 5G Networks

5G networks will enable new services and use cases for industries and vertical markets. The concepts of network elasticity and slicing will be essential for 5G realization, enabling reduction of capital and operational expenses while allowing more services to be simultaneously hosted using the same pool of resources. This leads to the challenge of automatically handling slices with heterogeneous resource demands in an efficient manner. Based on an evolutionary algorithm, this paper proposes a multi-objective approach to accomplish optimized resource orchestration between cloud-based slices in a 5G network. Finally, we provide numerical results to demonstrate the gains of the proposed approach, compared to other allocation schemes.