Customizable Mapping of Virtualized Network Services in Multi-datacenter Environments Based on Genetic Metaheuristics

One of the major challenges Network Functions Virtualization paradigm is to properly deploy functions and services across network. In particular, current solutions for multi-datacenter service mapping present several restrictions in terms choice optimization models metrics. This lack flexibility ultimately leads sub-optimized mappings that do not meet (often conflicting) requirements all parties involved deployment process (e.g., network operators, clients, providers). work proposes Genetic Service Mapping (GeSeMa), a new intelligent solution based on genetic algorithms. GeSeMa enables flexible configuration evaluation setup, which used generate candidate mappings. The allows specification arbitrary metrics, constraints, different policies. A algorithm processes requests iteratively creates/evolves We evaluate through comprehensive case studies, including comparison with other classic state-of-the-art alternatives.