When Network Slicing Meets Prospect Theory: A Service Provider Revenue Maximization Framework

摘要

Recently, the network slicing technology has emerged enabling network operators to provide dedicated virtual networks to customers, over a common network infrastructure. This paper addresses the service provider maximization revenue problem in network slicing, aiming at offering customized services for different users' classes and heterogeneous requirements. In particular, the slicing of the network is performed here on the basis of the end users' perspective, considered at different levels. The customers demand forecasting is pursuit for service classes through the application of the federated learning framework according to which the end users act as clients. Then, considering the forecast service demands, the virtual network functions placement strategy is performed by taking into account that different network zones are characterized by diverse provision costs and prices, and it is realized by resorting to the application of matching theory principles. Furthermore, with the aim at taking into consideration the customers perspectives to obtain a realistic users' decisions process, the prospect theory principles are applied. Finally, the goodness of the proposed framework is investigated and validated by providing numerical results derived by extensive computer simulations and proposing performance comparisons with the Kolkata game and the potential game.