In this paper, we propose an improved anomaly detection algorithm for O-RAN Near-RT RIC environments by enhancing the Isolation Forest-based xApp deployed for traffic steering. Conventional implementations rely on arbitrary or correlation-based feature selection and (semi-)supervised-like hyperparameter tuning, which can result in suboptimal performance. To address these issues, we introduce a proxy label generation method grounded domain expertise, enabling evaluation-driven hyperparameter optimization. We further propose a three-step feature selection framework to produce interpretable and effective feature subsets. Experimental results demonstrate that our proposed method consistently improves F1-score performance, with Bayesian optimization showing the most robust results. Furthermore, our analysis highlights the value of retaining certain correlated features that may be beneficial for tree-based models like Isolation Forest, counter to common practices in feature selection. These findings validate the proposed framework’s applicability in O-RAN anomaly detection and offer new directions for interpretable xApp development.

Deep learning (DL) techniques have been intensively studied for the optimization of multi-user multiple-input single-output (MU-MISO) downlink systems owing to the capability of handling nonconvex formulations. However, the fixed computation structure of existing deep neural networks (DNNs) lacks flexibility with respect to the system size, i.e., the number of antennas or users. This paper develops a bipartite graph neural network (BGNN) framework, a scalable DL solution designed for multi-antenna beamforming optimization. The MU-MISO system is first characterized by a bipartite graph where two disjoint vertex sets, each of which consists of transmit antennas and users, are connected via pairwise edges. These vertex interconnection states are modeled by channel fading coefficients. Thus, a generic beamforming optimization process is interpreted as a computation task over a weighted bipartite graph. This approach partitions the beamforming optimization procedure into multiple suboperations dedicated to individual antenna vertices and user vertices. Separated vertex operations lead to scalable beamforming calculations that are invariant to the system size. The vertex operations are realized by a group of DNN modules that collectively form the BGNN architecture. Identical DNNs are reused at all antennas and users so that the resultant learning structure becomes flexible to the network size. Component DNNs of the BGNN are trained jointly over numerous MU-MISO configurations with randomly varying network sizes. As a result, the trained BGNN can be universally applied to arbitrary MU-MISO systems. Numerical results validate the advantages of the BGNN framework over conventional methods.

Uplink and downlink cloud radio access networks are modeled as two-hop K-user L-relay networks, whereby small base-stations act as relays for end-to-end communications and are connected to a central processor via orthogonal fronthaul links of finite capacities. Simplified versions of network compress-forward (or noisy network coding) and distributed decode-forward are presented to establish inner bounds on the capacity region for uplink and downlink communications, that match the respective cutset bounds to within a finite gap independent of the channel gains and signal to noise ratios. These approximate capacity regions are then compared with the capacity regions for networks with no capacity limit on the fronthaul. Although it takes infinite fronthaul link capacities to achieve these “fronthaul-unlimited” capacity regions exactly, these capacity regions can be approached approximately with finite-capacity fronthaul. The total fronthaul link capacities required to approach the fronthaul-unlimited sum-rates (for uplink and downlink) are characterized. Based on these results, the capacity scaling law in the large network size limit is established under certain uplink and downlink network models, both theoretically and via simulations.

Cell-free Massive MIMO (multiple-input multiple output), where all the access nodes (ANs) cooperate to coherently serve all the user equipments (UEs) and to overcome the inter-cell interference limitation in ultra-dense network environments, has attracted significant attention from both academia and industry as a promising technology for 5G and future wireless communication. In this paper, we investigate the impacts of RF beamforming schemes to be combined with zero-forcing baseband precoding on cell-free mmWave massive MIMO UDN systems.

This work proposes an energy-efficient design of transmit power control and relaying strategies for the uplink of a cloud radio access network (C-RAN) with wireless fronthaul link. In the system, a set of single-antenna user equipments (UEs) send independent messages to a multi-antenna baseband processing unit (BBU) through a set of parallel multi-antenna remote radio heads (RRHs). The radio access link from the UEs to the RRHs is assumed to be orthogonal to the fronthaul link from the RRHs to the BBU. Since the overall performance of the system may be limited by the battery constraints of the UEs, this work tackles the problem of maximizing the worst energy efficiency of the UEs subject to the transmit power constraints at the UEs and the RRHs. Numerical results are provided to validate the advantages of the proposed energy-efficient scheme.

This work studies distributed uplink reception for a device-to-device (D2D) underlaid cloud radio access network (C-RAN) system, in which cellular user equipments (UEs) communicate with a baseband processing unit (BBU) through a set of distributed remote radio heads (RRHs) that are connected to the BBU via finite-capacity fronthaul links. The uplink of C-RAN system is interfered by a number of D2D communication links that operate in the same frequency band. Most of prior works on C-RAN uplink systems prescribe that the noise signals of different RRHs do not have statistical correlation. However, in the D2D underlaid C-RAN uplink systems, the effective noise signals that contain the D2D interference signals may have inter-RRH cross correlation. This work proposes an improved distributed reception scheme which leverages the noise correlation information. To tackle non-convex sum-rate maximization problem, a successive convex approximation (SCA) based iterative algorithm is derived that guarantees monotonically non-decreasing sum-rates. Some numerical results are presented that validate the advantages of the proposed scheme.

Today, MIMO has become an indispensable scheme for providing significant spectral efficiency in wireless communication and for future wireless system, recently, it goes to two extremes: massive MIMO and single-RF MIMO. This paper, which is put in the latter, utilizes load-modulated arrays with only reactance loads for single-RF transmission of spatially multiplexed QAM signals. To alleviate the need for iterative processes while considering mutual coupling in the compact antenna, we present a novel design methodology for the loading network, which enables the exact computation of the three reactance loads per antenna element and also the perfect matching to the source with the opportunity to select appropriate analog tunable loads. We verify the design methodology by comparing the calculated values for some key parameters with the values from the circuit simulation. In addition, as an evaluation of the proposed architecture, we perform the bit error rate (BER) comparison which shows that our scheme with ideal loading is comparable to the conventional MIMO.

This article deals with the study on the performance of the hybrid transmission scheme combining both beamforming and spatial multiplexing. Specifically, the capacity of the hybrid scheme is evaluated and compared to that of the just beamforming scheme in line-of-sight and multi-path channels. Two kinds of the hybrid schemes are considered: the shared antenna architecture where each antenna processes all data streams and the split antenna architecture where each antenna processes only one data stream. The effects of the channel parameters such as the antenna spacing, the existence of reflecting paths, etc. on the capacity and the optimal beams and powers are examined. The frequency-selectivity property of the capacity and the optimal beams and powers is also investigated. In this study, a scenario is considered where the same analog RF beamformer is applied to all subcarriers but the digital baseband power allocation is executed individually at each subcarrier.

The 57-66GHz millimeter-wave (mmWave) spectrum has been dramatically drawing interest due to the worldwide availability of the extremely wide and unlicensed bandwidth which enable us to build up multi-gigabit wireless system (MGWS). The MGWS provides the opportunity to deliver high-quality uncompressed video wirelessly. In order to realize the uncompressed video transmission, we investigate the impact of unequal error protection (UEP) scheme which can be effectively used for graceful quality degradation under harsh wireless link conditions. To allow for improved quality maintenance and efficient wireless resource usage, this paper proposes a flexible UEP method with awareness of the uncompressed video context, which offers better visual-quality and resource usage over conventional UEP and equal error protection (EEP). Computer simulations using real uncompressed high-definition images indicate that the proposed UEP scheme outperforms conventional UEP and EEP schemes in terms of average weighted peak-signal-to-noise-ration (PSNR) under both poor channel and good channel condition.

Data-over-cable service interface specification (DOCSIS) MAC protocol is the de facto standard for hybrid fiber coax (HFC) network, and has also given leverage to IEEE 802.16 MAC protocol. The primary medium access control (MAC) function is contention resolution algorithm (CRA), called frame-based truncated binary exponential back-off (F-TBEB), for bandwidth requests from cable modems. The DOCSIS MAC is on the upgrade by introducing channel bonding concept in that the multiple channels can be combined together to get greater aggregate bandwidth. This paper provides a simple analytical model to compute the F-TBEB delay and throughput in single DOCSIS channel. Furthermore, we give two solutions to the problem of CRA on multiple channels and use the analytical model to determine which solution is superior.

IEEE 802.16 defines the air interface standard for fixed/mobile broadband wireless access (BWA) metropolitan area networks (MANs), which is expected to support quality of service (QoS) for real time application such as voice over IP (VoIP). However, three major technical problems that stand in the way are: 1) absence of MAC scheduling for supporting codecs with voice activity detector (VAD); 2) absence of mapping procedure between IEEE 802.16 service flow and network flow; 3) absence of efficient admission control for VoIP. This paper proposes two schemes, statistical UGS and UGS-rtPS combined scheduling, of MAC scheduling, addresses mapping RSVP FlowSpecs parameter into IEEE 802.16 QoS parameter, and devises simple admission control algorithm for VoIP services