Search for: All records

The open radio access network (O-RAN) architecture introduces RAN intelligent controllers (RICs) to facilitate the management and optimization of the disaggregated RAN. Reinforcement learning (RL) and its advanced form, deep RL (DRL), are increasingly employed for designing intelligent controllers, or xApps, to be deployed in the near-real time (near-RT) RIC. These models often encounter local optima, which raise concerns about their reliability for RAN intelligent control. We therefore introduce Federated O-RAN enabled Neuroevolution (NE)-enhanced DRL (F-ONRL) that deploys an NE-based optimizer xApp in parallel to the RAN controller xApps. This NE-DRL xApp framework enables effective exploration and exploitation in the near-RT RIC without disrupting RAN operations. We implement the NE xApp along with a DRL xApp and deploy them on Open AI Cellular (OAIC) platform and present numerical results that demonstrate the improved robustness of xApps while effectively balancing the additional computational load. 

In the rapidly evolving landscape of 5G technology, safeguarding Radio Frequency (RF) environments against sophisticated intrusions is paramount, especially in dynamic spectrum access and management. This paper presents an enhanced experimental model that integrates a self-attention mechanism with a Recurrent Neural Network (RNN)-based autoencoder for the detection of anomalous spectral activities in 5G networks at the waveform level. Our approach, grounded in time-series analysis, processes in-phase and quadrature (I/Q) samples to identify irregularities that could indicate potential jamming attacks. The model's architecture, augmented with a self-attention layer, extends the capabilities of RNN autoen-coders, enabling a more nuanced understanding of temporal dependencies and contextual relationships within the RF spectrum. Utilizing a simulated 5G Radio Access Network (RAN) test-bed constructed with srsRAN 5G and Software Defined Radios (SDRs), we generated a comprehensive stream of data that reflects real-world RF spectrum conditions and attack scenarios. The model is trained to reconstruct standard signal behavior, establishing a normative baseline against which deviations, indicative of security threats, are identified. The proposed architecture is designed to balance between detection precision and computational efficiency, so the LSTM network, enriched with self-attention, continues to optimize for minimal execution latency and power consumption. Conducted on a real-world SDR-based testbed, our results demonstrate the model's improved performance and accuracy in threat detection. 

The open radio access network (O-RAN) represents a paradigm shift in RAN architecture, integrating intelligence into communication networks via xApps -- control applications for managing RAN resources. This integration facilitates the adoption of AI for network optimization and resource management. However, there is a notable gap in practical network performance analyzers capable of assessing the functionality and efficiency of xApps in near real-time within operational networks. Addressing this gap, this article introduces a comprehensive network performance analyzer, tailored for the near-real time RAN intelligent controller. We present the design, development, and application scenarios for this testing framework, including its components, software, and tools, providing an end-to-end solution for evaluating the performance of xApps in O-RAN environments. 

The evolution of open architectures for Radio Ac-cess Networks (RANs) is revolutionizing network management and optimization. This transformation, fostered by O-RAN, expedites data acquisition and examination by exploiting newly established open interfaces. Moreover, it has led to the rise of near real-time RAN Intelligent Controllers (RICs), instigating a wave of AI-driven applications, or xApps, that employ Artificial Intelligence (AI)/Machine Learning (ML) methods. Nevertheless, deploying xApps as centralized applications presents substantial challenges, such as handling vast data transactions, potential delays, and security vulnerabilities, which are notably prominent within the multifaceted, decentralized, multivendor, and trustless nature of open networks. To alleviate these predicaments, a transition from centralized apps operating in near real-time to distributed real-time apps is imperative for augmented security and efficiency. This paper addresses these complexities by introducing an open platform that integrates a federated reinforcement learning algorithm to operate as distributed Apps (dApps) within the next-generation O-RAN architecture. We present evaluation results in a specific test environment. 

Open Radio Access Network (O-RAN) has introduced an emerging RAN architecture that enables openness, intelligence, and automated control. The RAN Intelligent Controller (RIC) provides the platform to design and deploy network controllers. xApps are the applications that can leverage machine learning (ML) algorithms for near-real time control. Despite the opportunities provided by this new architecture, the progress of practical artificial intelligence (AI)-based solutions for network control and automation has been slow. There is a lack of end-to-end solutions for designing, deploying, and testing AI-based xApps in production-like network settings. This paper introduces an end-to-end O-RAN design and evaluation procedure using the latest O-RAN architecture and interface releases. We provide details on the development of a reinforcement learning (RL)-based xApp, considering two RL approaches and present numerical results to validate the xApp.