Optimization of Multitenant Radio Admission Control Through a Semi-Markov Decision Process

Abstract

Network slicing in future 5G systems enables the provision of multitenant networks in which a network infrastructure owned by an operator is shared among different tenants, such as mobile virtual operators, over-the-top providers or vertical market players. The support of network slicing within the radio access network requires the introduction of appropriate radio resource management functions to ensure that each tenant gets the required radio resources in accordance with the expected service level agreement (SLA). This paper addresses radio admission control (RAC) functionality in multiservice and multitenant scenarios as a mechanism for regulating the acceptance of new guaranteed bit rate service requests of different tenants. This paper proposes an optimization framework that models the RAC as a semi-Markov decision process and, as a result, derives an optimal decision-making policy that maximizes an average long-term function representing the desired optimization target. A reward function is proposed to capture the degree of tenant satisfaction with the received service in relation to the expected SLA, accounting for both the provision of excess capacity beyond the SLA and the cost associated with sporadic SLA breaches. The proposed approach is evaluated by means of simulations, and its superiority to other reference schemes in terms of reward and other key performance indicators is analyzed.