Open radio access network (O-RAN) is a paradigm shift in telecommunications, facilitating interoperability and innovation through the disaggregation of traditional monolithic architecture, empowering operators to select equipment from diverse vendors. However, within the multi-vendor O-RAN ecosystem, individual xApps may pursue conflicting objectives. While fine-tuned coordination can alleviate conflicts, it often requires extensive information exchange, raising privacy concerns among competing vendors. This paper delves into these challenges, particularly focusing on the interplay between different xApps, such as energy efficiency (EE) and load balancing (LB), and highlights the tradeoff between performance and level of coordination. To address this, we propose novel algorithms to optimize performance across varying levels of coordination. Initial findings underscore the diminishing returns of coordination, with significant performance gains from zero to partial coordination, yet a more modest increase with full coordination.

This paper addresses load balancing in open radio access networks (O-RAN), which aims to enhance network avail-ability without overloading the network when accommodating new user equipment (UEs) while ensuring an efficient allocation of resources to meet the data rate requirement of existing UEs. More precisely, we propose a resource allocation framework that balances the utilization of resource blocks (PRBs) at the radio units (RU s) as well as the computational resources at the distributed units (DUs) while maintaining the quality of service (QoS) demands of UEs. Given the combinatorial nature of the optimization problems, we propose, 1) a supermodular algorithm to find UE-RU assignments and 2) a job scheduling-inspired method to assign RUs to respective DUs. Through comprehensive simulations, we validate the effectiveness of our approach by showcasing substantial enhancements in the network load con-ditions and highlighting the superiority of the provided resource allocation scheme in terms of key performance indicators such as the call block ratio (CBR).

The Open RAN paradigm offers data-driven, intelligent optimization of the radio access network (RAN). The disaggregated nature of the Open RAN combined with virtualization on general-purpose CPUs with limited computation capacity creates different load types at multiple levels, making it more challenging to balance the load within the network. This paper proposes a learning framework that learns the assignment of users (UEs) to network nodes to balance the communication and computation load in the network. The framework incorporates communication resources consumed by the users in the radio unit (RU), and computation resources needed for baseband processing in the virtualized distributed unit (DU). The goal is thus to balance the communication load between RUs and the computation load between DUs to avoid overloading network elements or to handle higher peak data rate demands when new users arrive in the network. We apply a novel utility-based approach to jointly optimize the UE-RU and RU-DU assignments taking into account the users' QoS (quality of service) requirements. Simulations demonstrate that the proposed method generates the assignments that significantly improve the network load conditions compared to baseline schemes, thereby enabling more available communication and computation resources for incoming peak data rate users in the network.