A New Soccer Game Optimization Modeling For Flexible Functional Splitting Dimensioning in CF-RAN Networks

The baseband processing centralization enabled by the Cloud Radio Access Network generates stringent latency and high bandwidth requirements. Therefore, some studies proposed using hybrid architectures and baseband functional splitting to ease such requirements. In the literature, the ideal functional splitting in hybrid RAN architectures has been tackled using integer linear programming. Such approaches guarantee optimality, but they have low scalability, making them infeasible for real deployments. On the other hand, Meta Heuristics can provide practical solutions to large combinatorial problems with a good level of accuracy (not rarely achieving optimality). This paper proposes new modeling of the functional splitting problem in Cloud Fog RANs using the meta-heuristic optimization named Soccer Game Optimization. We compared our solution to an integer linear programming formulation evaluating the correctness, energy efficiency, and network coverage. Results show that meta-heuristic achieve statistically optimality equal to the ILP in coverage and energy-efficiency.