A Stochastic Optimization Framework for Joint RAN Intelligent Controller Placement and RAN Nodes Assignment in O-RAN Networks

<p>O-RAN Architecture is consolidating the concept of software-defined cellular networks (SDCNs) for beyond 5G networks, mainly through the introduction of the Near-Real-Time RAN Intelligent Controller (Near-RT RIC) and the xApps. In this context, the deployment of the Near-RT RIC faces the traditional controller placement problem in an SDCN, which considers the number of controllers, their placement, and the assignment of RAN nodes to the controllers. In this paper, we study the controller placement problem in SDCNs, considering the uncertainty in user locations. Specifically, our contributions are as follows. First, we develop C3P2, a robust static joint controller placement and RAN node-controller assignment scheme. The objective of C3P2 is to minimize the number of controllers needed to control all RAN nodes while ensuring that the response time to each RAN node will not exceed delta seconds with a probability greater than beta?. Second, we develop CPPA, a robust joint controller placement and adaptive RAN node-controller assignment scheme. In contrast to C3P2, CPPA enjoys a recourse capability, where the RAN node-controller assignment adapts to the variations in the user locations. We use chance-constrained stochastic optimization combined with several linearization techniques to develop a mixed-integer linear (MIL) formulation for C3P2. Two-stage stochastic optimization with recourse, combined with several linearization techniques, is used to develop an MIL formulation for CPPA. The optimal performance of C3P2 and CPPA has been examined under various system parameter values. Furthermore, sample average approximation has been employed to design efficient approximate algorithms for solving C3P2 and CPPA. Our results demonstrate the robustness of the proposed stochastic resource allocation schemes for SDCNs compared to existing deterministic allocation schemes. They also show the merits of adapting the allocation of resources to the network uncertainties compared to statically allocating them.</p>