Abstract:Reconfigurable Intelligent Surfaces (RISs) are a promising technique for enhancing the performance of Next Generation (NextG) wireless communication systems in terms of both spectral and energy efficiency, as well as resource utilization. However, current RIS research has primarily focused on theoretical modeling and Physical (PHY) layer considerations only. Full protocol stack emulation and accurate modeling of the propagation characteristics of the wireless channel are necessary for studying the benefits introduced by RIS technology across various spectrum bands and use-cases. In this paper, we propose, for the first time: (i) accurate PHY layer RIS-enabled channel modeling through Geometry-Based Stochastic Models (GBSMs), leveraging the QUAsi Deterministic RadIo channel GenerAtor (QuaDRiGa) open-source statistical ray-tracer; (ii) optimized resource allocation with RISs by comprehensively studying energy efficiency and power control on different portions of the spectrum through a single-leader multiple-followers Stackelberg game theoretical approach; (iii) full-stack emulation and performance evaluation of RIS-assisted channels with SCOPE/srsRAN for Enhanced Mobile Broadband (eMBB) and Ultra Reliable and Low Latency Communications (URLLC) applications in the worlds largest emulator of wireless systems with hardware-in-the-loop, namely Colosseum. Our findings indicate (i) the significant power savings in terms of energy efficiency achieved with RIS-assisted topologies, especially in the millimeter wave (mmWave) band; and (ii) the benefits introduced for Sub-6 GHz band User Equipments (UEs), where the deployment of a relatively small RIS (e.g., in the order of 100 RIS elements) can result in decreased levels of latency for URLLC services in resource-constrained environments.
Abstract:The highly heterogeneous ecosystem of Next Generation (NextG) wireless communication systems calls for novel networking paradigms where functionalities and operations can be dynamically and optimally reconfigured in real time to adapt to changing traffic conditions and satisfy stringent and diverse Quality of Service (QoS) demands. Open Radio Access Network (RAN) technologies, and specifically those being standardized by the O-RAN Alliance, make it possible to integrate network intelligence into the once monolithic RAN via intelligent applications, namely, xApps and rApps. These applications enable flexible control of the network resources and functionalities, network management, and orchestration through data-driven control loops. Despite recent work demonstrating the effectiveness of Deep Reinforcement Learning (DRL) in controlling O-RAN systems, how to design these solutions in a way that does not create conflicts and unfair resource allocation policies is still an open challenge. In this paper, we perform a comparative analysis where we dissect the impact of different DRL-based xApp designs on network performance. Specifically, we benchmark 12 different xApps that embed DRL agents trained using different reward functions, with different action spaces and with the ability to hierarchically control different network parameters. We prototype and evaluate these xApps on Colosseum, the world's largest O-RAN-compliant wireless network emulator with hardware-in-the-loop. We share the lessons learned and discuss our experimental results, which demonstrate how certain design choices deliver the highest performance while others might result in a competitive behavior between different classes of traffic with similar objectives.