Dynamic CU-DU Selection for Resource Allocation in O-RAN Using Actor-Critic Learning

Recently, there has been tremendous efforts by network operators and equipment vendors to adopt intelligence and openness in the next generation radio access network (RAN). The goal is to reach a RAN that can self-optimize in a highly complex setting with multiple platforms, technologies and vendors in a converged compute and connect architecture. In this paper, we propose two nested actor-critic learning based techniques to optimize the placement of resource allocation function, and as well, the decisions for resource allocation. By this, we investigate the impact of observability on the performance of the reinforcement learning based resource allocation. We show that when a network function (NF) is dynamically relocated based on service requirements, using reinforcement learning techniques, latency and throughput gains are obtained.

[1]  Melike Erol-Kantarci,et al.  Actor-Critic Learning Based QoS-Aware Scheduler for Reconfigurable Wireless Networks , 2021, IEEE Transactions on Network Science and Engineering.

[2]  Christos Verikoukis,et al.  Offline SLA-Constrained Deep Learning for 5G Networks Reliable and Dynamic End-to-End Slicing , 2020, IEEE Journal on Selected Areas in Communications.

[3]  Melike Erol-Kantarci,et al.  AI-Enabled Future Wireless Networks: Challenges, Opportunities, and Open Issues , 2019, IEEE Vehicular Technology Magazine.

[4]  Walid Saad,et al.  A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems , 2019, IEEE Network.

[5]  Bin Han,et al.  A Comprehensive Survey of RAN Architectures Toward 5G Mobile Communication System , 2019, IEEE Access.

[6]  Bruno Chatras,et al.  NFV enabling network slicing for 5G , 2017, 2017 20th Conference on Innovations in Clouds, Internet and Networks (ICIN).

[7]  Mohit Sewak,et al.  Actor-Critic Models and the A3C , 2019, Deep Reinforcement Learning.

[8]  Anatolij Zubow,et al.  ns-3 meets OpenAI Gym: The Playground for Machine Learning in Networking Research , 2019, MSWiM.

[9]  Saied Abedi.  Efficient radio resource management for wireless multimedia communications: a multidimensional QoS-based packet scheduler , 2005, IEEE Transactions on Wireless Communications.

[10]  Mate Boban,et al.  Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications Outside Coverage , 2018, 2018 IEEE Vehicular Networking Conference (VNC).

[11]  Melike Erol-Kantarci,et al.  Reinforcement Learning Based Dynamic Function Splitting in Disaggregated Green Open RANs , 2020, ICC 2021 - IEEE International Conference on Communications.

[12]  Giuseppe Piro,et al.  Two-Level Downlink Scheduling for Real-Time Multimedia Services in LTE Networks , 2011, IEEE Transactions on Multimedia.

[13]  Wei Chen,et al.  The Roadmap to 6G: AI Empowered Wireless Networks , 2019, IEEE Communications Magazine.

[14]  Fatimah Audah Md. Zaki,et al.  Towards Efficient and Scalable Machine Learning-Based QoS Traffic Classification in Software-Defined Network , 2019, MobiWIS.

[15]  Dipak Ghosal,et al.  A Deep Deterministic Policy Gradient Based Network Scheduler For Deadline-Driven Data Transfers , 2020, 2020 IFIP Networking Conference (Networking).