AdapShare: An RL-Based Dynamic Spectrum Sharing Solution for O-RAN

The Open Radio Access Network (O-RAN) initiative, characterized by open interfaces and AI/ML-capable RAN Intelligent Controller (RIC), facilitates effective spectrum sharing among RANs. In this context, we introduce AdapShare, an ORAN-compatible solution leveraging Reinforcement Learning (RL) for intent-based spectrum management, with the primary goal of minimizing resource surpluses or deficits in RANs. By employing RL agents, AdapShare intelligently learns network demand patterns and uses them to allocate resources. We demonstrate the efficacy of AdapShare in the spectrum sharing scenario between LTE and NR networks, incorporating real-world LTE resource usage data and synthetic NR usage data to demonstrate its practical use. We use the average surplus or deficit and fairness index to measure the system's performance in various scenarios. AdapShare outperforms a quasi-static resource allocation scheme based on long-term network demand statistics, particularly when available resources are scarce or exceed the aggregate demand from the networks. Lastly, we present a high-level O-RAN compatible architecture using RL agents, which demonstrates the seamless integration of AdapShare into real-world deployment scenarios.

ProSAS: An O-RAN Approach to Spectrum Sharing between NR and LTE

The Open Radio Access Network (O-RAN), an industry-driven initiative, utilizes intelligent Radio Access Network (RAN) controllers and open interfaces to facilitate efficient spectrum sharing between LTE and NR RANs. In this paper, we introduce the Proactive Spectrum Adaptation Scheme (ProSAS), a data-driven, O-RAN-compatible spectrum sharing solution. ProSAS is an intelligent radio resource demand prediction and management scheme for intent-driven spectrum management that minimizes surplus or deficit experienced by both RANs. We illustrate the effectiveness of this solution using real-world LTE resource usage data and synthetically generated NR data. Lastly, we discuss a high-level O-RAN-compatible architecture of the proposed solution.

Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AI

Building on the remarkable achievements in generative sampling of natural images, we propose an innovative challenge, potentially overly ambitious, which involves generating samples of entire multivariate time series that resemble images. However, the statistical challenge lies in the small sample size, sometimes consisting of a few hundred subjects. This issue is especially problematic for deep generative models that follow the conventional approach of generating samples from a canonical distribution and then decoding or denoising them to match the true data distribution. In contrast, our method is grounded in information theory and aims to implicitly characterize the distribution of images, particularly the (global and local) dependency structure between pixels. We achieve this by empirically estimating its KL-divergence in the dual form with respect to the respective marginal distribution. This enables us to perform generative sampling directly in the optimized 1-D dual divergence space. Specifically, in the dual space, training samples representing the data distribution are embedded in the form of various clusters between two end points. In theory, any sample embedded between those two end points is in-distribution w.r.t. the data distribution. Our key idea for generating novel samples of images is to interpolate between the clusters via a walk as per gradients of the dual function w.r.t. the data dimensions. In addition to the data efficiency gained from direct sampling, we propose an algorithm that offers a significant reduction in sample complexity for estimating the divergence of the data distribution with respect to the marginal distribution. We provide strong theoretical guarantees along with an extensive empirical evaluation using many real-world datasets from diverse domains, establishing the superiority of our approach w.r.t. state-of-the-art deep learning methods.

5G NR-LTE Coexistence: Opportunities, Challenges, and Solutions

5G New Radio (NR) promises to support diverse services such as enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), and massive machine-type communication (mMTC). This requires spectrum, most of which is occupied by 4G Long Term Evolution (LTE). Hence, network operators are expected to deploy 5G using the existing LTE infrastructure while migrating to NR. In addition, operators must support legacy LTE devices during the migration, so LTE and NR systems will coexist for the foreseeable future. In this article, we address LTE-NR coexistence starting with a review of both radio access technologies. We then describe the contributions by the 3rd Generation Partnership Project (3GPP) to solving the coexistence issue and catalog the major coexistence scenarios. Lastly, we introduce a novel spectrum sharing scheme that can be applied to the coexistence scenarios under study.