arXiv subjects

Marina Petrova

Publications and source records attributed to Marina Petrova.

At least 37 records · Page 2Linked to original sources

arXiv2024

Wireless MAC Protocol Synthesis and Optimization with Multi-Agent Distributed Reinforcement Learning

In this letter, we propose a novel Multi-Agent Deep Reinforcement Learning (MADRL) framework for Medium Access Control (MAC) protocol design. Unlike centralized approaches, which rely on a single entity for decision-making, MADRL empowers individual network nodes to autonomously learn and optimize their MAC based on local observations. Leveraging ns3-ai and RLlib, as far as we are aware of, our framework is the first of a kind that enables distributed multi-agent learning within the ns-3 environment, facilitating the design and synthesis of adaptive MAC protocols tailored to specific environmental conditions. We demonstrate the effectiveness of the MADRL MAC framework through extensive simulations, showcasing superior performance compared to legacy protocols across diverse scenarios. Our findings highlight the potential of MADRL-based MAC protocols to significantly enhance Quality of Service (QoS) requirements for future wireless applications.

eess.SY↗

arXiv2024

Empowering 5G PRS-Based ISAC with Compressed Sensing

To enable widespread use of Integrated Sensing and Communication (ISAC) in future communication systems, an important requirement is the ease of integration. A possible way to achieve this is to use existing communication reference signals for sensing, such as the 5G Positioning Reference Signal (PRS). Existing works have demonstrated promising results by using the PRS with classical signal processing techniques. However, this approach suffers from a loss of SNR due to the sparse resource allocation. In this work, we improve upon existing results by combining the 5G PRS with compressed sensing methods. We demonstrate that our method achieves better noise robustness compared to the existing works and has superresolution properties, making it an ideal choice for range-Doppler map generation and target detection even in noisy environments.

eess.SP↗

arXiv2024

Unknown Interference Modeling for Rate Adaptation in Cell-Free Massive MIMO Networks

Co-channel interference poses a challenge in any wireless communication network where the time-frequency resources are reused over different geographical areas. The interference is particularly diverse in cell-free massive multiple-input multiple-output (MIMO) networks, where a large number of user equipments (UEs) are multiplexed by a multitude of access points (APs) on the same time-frequency resources. For realistic and scalable network operation, only the interference from UEs belonging to the same serving cluster of APs can be estimated in real-time and suppressed by precoding/combining. As a result, the unknown interference arising from scheduling variations in neighboring clusters makes the rate adaptation hard and can lead to outages. This paper aims to model the unknown interference power in the uplink of a cell-free massive MIMO network. The results show that the proposed method effectively describes the distribution of the unknown interference power and provides a tool for rate adaptation with guaranteed target outage.

eess.SP↗

arXiv2024

HBF MU-MIMO with Interference-Aware Beam Pair Link Allocation for Beyond-5G mm-Wave Networks

Hybrid beamforming (HBF) multi-user multiple-input multiple-output (MU-MIMO) is a key technology for unlocking the directional millimeter-wave (mm-wave) nature for spatial multiplexing beyond current codebook-based 5G-NR networks. In order to suppress co-scheduled users' interference, HBF MU-MIMO is predicated on having sufficient radio frequency chains and accurate channel state information (CSI), which can otherwise lead to performance losses due to imperfect interference cancellation. In this work, we propose IABA, a 5G-NR standard-compliant beam pair link (BPL) allocation scheme for mitigating spatial interference in practical HBF MU-MIMO networks. IABA solves the network sum throughput optimization via either a distributed or a centralized BPL allocation using dedicated CSI reference signals for candidate BPL monitoring. We present a comprehensive study of practical multi-cell mm-wave networks and demonstrate that HBF MU-MIMO without interference-aware BPL allocation experiences strong residual interference which limits the achievable network performance. Our results show that IABA offers significant performance gains over the default interference-agnostic 5G-NR BPL allocation, and even allows HBF MU-MIMO to outperform the fully digital MU-MIMO baseline, by facilitating allocation of secondary BPLs other than the strongest BPL found during initial access. We further demonstrate the scalability of IABA with increased gNB antennas and densification for beyond-5G mm-wave networks.

cs.NI↗

arXiv2024

Power Allocation Scheme for Device-Free Localization in 6G ISAC Networks

Integrated Sensing and Communication (ISAC) is considered one of the crucial technologies in the upcoming sixth-generation (6G) mobile communication systems that could facilitate ultra-precise positioning of passive and active targets and extremely high data rates through spectrum coexistence and hardware sharing. Such an ISAC network offers a lot of benefits, but comes with the challenge of managing the mutual interference between the sensing and communication services. In this paper, we investigate the problem of localization accuracy in a monostatic ISAC network under consideration of inter-BS interference due to communication signal and sensing echoes, and self-interference at the respective BS. We propose a power allocation algorithm that minimizes BS's maximum range estimate error while considering minimum communication signal-to-interference-plus-noise ratio (SINR) and total power constraint. Our numerical results demonstrate the effectiveness of the proposed algorithm and indicate that it can enhance the sensing performance when the self-interference is effectively suppressed.

eess.SP↗

arXiv2024

ML Framework for Wireless MAC Protocol Design

Adaptivity, reconfigurability and intelligence are key features of the next-generation wireless networks to meet the increasingly diverse quality of service (QoS) requirements of the future applications. Conventional protocol designs, however, struggle to provide flexibility and agility to changing radio environments, traffic types and different user service requirements. In this paper, we explore the potential of deep reinforcement learning (DRL), in particular Proximal Policy Optimization (PPO), to design and configure intelligent and application-specific medium access control (MAC) protocols. We propose a framework that enables the addition, removal, or modification of protocol features to meet individual application needs. The DRL channel access policy design empowers the protocol to adapt and optimize in accordance with the network and radio environment. Through extensive simulations, we demonstrate the superior performance of the learned protocols over legacy IEEE 802.11ac in terms of throughput and latency.

cs.NI↗

arXiv2024

Modeling and Performance Analysis of CSMA-Based JCAS Networks

Joint communication and sensing (JCAS) networks are envisioned as a key enabler for a variety of applications which demand reliable wireless connectivity along with accurate and robust sensing capability. When sensing and communication share the same spectrum, the communication links in the JCAS networks experience interference from both sensing and communication signals. Therefore, it is crucial to analyze the interference caused by the uncoordinated transmission of either sensing or communication signals, so that effective interference mitigation techniques could be put in place. We consider a JCAS network consisting of dual-functional nodes operating in radar and communication modes. To gain access to the shared communication channel, each node follows carrier sense multiple access (CSMA)-based protocol. For this setting, we study the radar and communication performances defined in terms of maximum unambiguous range and aggregated network throughput, respectively. Leveraging on the stochastic geometry approach, we model the interference of the network and derive a closed-form expression for both radar and communication performance metrics. Finally, we verify our analytical results through extensive simulation.

eess.SY↗

arXiv2024

Cooperative Multi-Monostatic Sensing for Object Localization in 6G Networks

Enabling passive sensing of the environment using cellular base stations (BSs) will be one of the disruptive features of the sixth-generation (6G) networks. However, accurate localization and positioning of objects are challenging to achieve as multipath significantly degrades the reflected echos. Existing localization techniques perform well under the assumption of large bandwidth available but perform poorly in bandwidth-limited scenarios. To alleviate this problem, in this work, we introduce a 5G New Radio (NR)-based cooperative multi-monostatic sensing framework for passive target localization that operates in the Frequency Range 1 (FR1) band. We propose a novel fusion-based estimation process that can mitigate the effect of multipath by assigning appropriate weight to the range estimation of each BS. Extensive simulation results using ray-tracing demonstrate the efficacy of the proposed multi-sensing framework in bandwidth-limited scenarios.

eess.SP↗

arXiv2023

Soft Handover Procedures in mmWave Cell-Free Massive MIMO Networks

This paper considers a mmWave cell-free massive MIMO (multiple-input multiple-output) network composed of a large number of geographically distributed access points (APs) simultaneously serving multiple user equipments (UEs) via coherent joint transmission. We address UE mobility in the downlink (DL) with imperfect channel state information (CSI) and pilot training. Aiming at extending traditional handover concepts to the challenging AP-UE association strategies of cell-free networks, distributed algorithms for joint pilot assignment and cluster formation are proposed in a dynamic environment considering UE mobility. The algorithms provide a systematic procedure for initial access and update of the serving APs and assigned pilot sequence to each UE. The principal goal is to limit the necessary number of AP and pilot changes, while limiting computational complexity. We evaluate the performance, in terms of spectral efficiency (SE), with maximum ratio and regularized zero-forcing precoding. Results show that our proposed distributed algorithms effectively identify the essential AP-UE association refinements with orders-of-magnitude lower computational time compared to the state-of-the-art. It also provides a significantly lower average number of pilot changes compared to an ultra-dense network (UDN). Moreover, we develop an improved pilot assignment procedure that facilitates massive access to the network in highly loaded scenarios.

eess.SP↗

arXiv2023

Communication-Efficient Orchestrations for URLLC Service via Hierarchical Reinforcement Learning

Ultra-reliable low latency communications (URLLC) service is envisioned to enable use cases with strict reliability and latency requirements in 5G. One approach for enabling URLLC services is to leverage Reinforcement Learning (RL) to efficiently allocate wireless resources. However, with conventional RL methods, the decision variables (though being deployed at various network layers) are typically optimized in the same control loop, leading to significant practical limitations on the control loop's delay as well as excessive signaling and energy consumption. In this paper, we propose a multi-agent Hierarchical RL (HRL) framework that enables the implementation of multi-level policies with different control loop timescales. Agents with faster control loops are deployed closer to the base station, while the ones with slower control loops are at the edge or closer to the core network providing high-level guidelines for low-level actions. On a use case from the prior art, with our HRL framework, we optimized the maximum number of retransmissions and transmission power of industrial devices. Our extensive simulation results on the factory automation scenario show that the HRL framework achieves better performance as the baseline single-agent RL method, with significantly less overhead of signal transmissions and delay compared to the one-agent RL methods.

eess.SY↗

arXiv2023

A Bayesian Approach to Characterize Unknown Interference Power in Wireless Networks

The existence of unknown interference is a prevalent problem in wireless communication networks. Especially in multi-user multiple-input multiple-output (MIMO) networks, where a large number of user equipments are served on the same time-frequency resources, the outage performance may be dominated by the unknown interference arising from scheduling variations in neighboring cells. In this letter, we propose a Bayesian method for modeling the unknown interference power in the uplink of a cellular network. Numerical results show that our method accurately models the distribution of the unknown interference power and can be effectively used for rate adaptation with guaranteed target outage performance.

eess.SP↗

arXiv2023

Beam Alignment Using Trajectory Information in Mobile Millimeter-wave Networks

Millimeter-wave and terahertz systems rely on beamforming/combining codebooks to determine the best beam directions during the initial access and data transmission. Existing approaches suffer from large codebook sizes and high beam searching overhead in the presence of mobile devices. To address this issue, we utilize the similarity of the channel in adjacent locations to divide the user trajectory into a set of separate regions and maintain a set of candidate beams for each region in a database. Due to the tradeoff between the number of regions and the signalling overhead, i.e., the greater number of regions results in a higher signal-to-noise ratio (SNR) but also a larger signalling overhead for the database, we propose an optimization framework to find the minimum number of regions based on the trajectory of a mobile device. Using a ray tracing tool, we demonstrate that the proposed method provides high SNR while being more robust to the location information accuracy in comparison to the lookup table baseline and fixed size region baseline.

cs.IT↗

arXiv2023

Reinforcement Learning-based Joint Handover and Beam Tracking in Millimeter-wave Networks

In this paper, we develop an algorithm for joint handover and beam tracking in millimeter-wave (mmWave) networks. The aim is to provide a reliable connection in terms of the achieved throughput along the trajectory of the mobile user while preventing frequent handovers. We model the association problem as an optimization problem and propose a reinforcement learning-based solution. Our approach learns whether and when beam tracking and handover should be performed and chooses the target base stations. In the case of beam tracking, we propose a tracking algorithm based on measuring a small spatial neighbourhood of the optimal beams in the previous time slot. Simulation results in an outdoor environment show the superior performance of our proposed solution in achievable throughput and the number of handovers needed in comparison to a multi-connectivity baseline and a learning-based handover baseline.

eess.SY↗

arXiv2022

Learning-Based Downlink Power Allocation in Cell-Free Massive MIMO Systems

This paper considers a cell-free massive multiple-input multiple-output (MIMO) system that consists of a large number of geographically distributed access points (APs) serving multiple users via coherent joint transmission. The downlink performance of the system is evaluated, with maximum ratio and regularized zero-forcing precoding, under two optimization objectives for power allocation: sum spectral efficiency (SE) maximization and proportional fairness. We present iterative centralized algorithms for solving these problems. Aiming at a less computationally complex and also distributed scalable solution, we train a deep neural network (DNN) to approximate the same network-wide power allocation. Instead of training our DNN to mimic the actual optimization procedure, we use a heuristic power allocation, based on large-scale fading (LSF) parameters, as the pre-processed input to the DNN. We train the DNN to refine the heuristic scheme, thereby providing higher SE, using only local information at each AP. Another distributed DNN that exploits side information assumed to be available at the central processing unit is designed for improved performance. Further, we develop a clustered DNN model where the LSF parameters of a small number of APs, forming a cluster within a relatively large network, are used to jointly approximate the power coefficients of the cluster.

eess.SP↗

arXiv2022

Interplay between Distributed AI Workflow and URLLC

Distributed artificial intelligence (AI) has recently accomplished tremendous breakthroughs in various communication services, ranging from fault-tolerant factory automation to smart cities. When distributed learning is run over a set of wireless connected devices, random channel fluctuations, and the incumbent services simultaneously running on the same network affect the performance of distributed learning. In this paper, we investigate the interplay between distributed AI workflow and ultra-reliable low latency communication (URLLC) services running concurrently over a network. Using 3GPP compliant simulations in a factory automation use case, we show the impact of various distributed AI settings (e.g., model size and the number of participating devices) on the convergence time of distributed AI and the application layer performance of URLLC. Unless we leverage the existing 5G-NR quality of service handling mechanisms to separate the traffic from the two services, our simulation results show that the impact of distributed AI on the availability of the URLLC devices is significant. Moreover, with proper setting of distributed AI (e.g., proper user selection), we can substantially reduce network resource utilization, leading to lower latency for distributed AI and higher availability for the URLLC users. Our results provide important insights for future 6G and AI standardization.

cs.NI↗

arXiv2022

Location-Aided Beamforming in Mobile Millimeter-Wave Networks

Due to the large bandwidth available, millimeter-Wave (mmWave) bands are considered a viable opportunity to significantly increase the data rate in cellular and wireless networks. Nevertheless, the need for beamforming and directional communication between the transmitter and the receiver increases the complexity of the channel estimation and link establishment phase. Location-aided beamforming approaches have the potential to enable fast link establishment in mmWave networks. However, these are often very sensitive to location errors. In this work, we propose a beamforming algorithm based on tracking spatial correlation of the available strong paths between the transmitter and the receiver. We show that our method is robust to uncertainty in location information, i.e., location error and can provide a reliable connection to a moving user along a trajectory. The numerical results show that our approach outperforms benchmarks on various levels of error in the location information accuracy. The gain is more prominent in high location error scenarios.

eess.SY↗

arXiv2021

Towards Global and Limitless Connectivity: The Role of Private NGSO Satellite Constellations for Future Space-Terrestrial Networks

Satellite networks are expected to support global connectivity and services via future integrated 6G space-terrestrial networks (STNs), as well as private non-geostationary satellite orbit (NGSO) constellations. In the past few years, many such private constellations have been launched or are in planning, e.g. SpaceX and OneWeb to name a few. In this article we take a closer look at the private constellations and give a comprehensive overview of their features. We then discuss major technical challenges resulting from their design and briefly review the recent literature addressing these challenges. Studying the emerging private constellations gives us useful insights for engineering the future STNs. To this end, we study the satellite mobility and evaluate the impact of two handover strategies on the space-to-ground link performance of four real private NGSO constellations. We show that the link capacity, delay, and handover rate vary across the constellations, so the optimal handover strategy depends on the constellation design. Consequently, the communications solutions of future STNs should be compliant with the constellation specifics, and the STN standards need to be flexible enough to support satellite operation with the large parameter space observed in the emerging private constellations.

cs.NI↗

arXiv2021

NeuroRAN: Rethinking Virtualization for AI-native Radio Access Networks in 6G

Network softwarization has revolutionized the architecture of cellular wireless networks. State-of-the-art container based virtual radio access networks (vRAN) provide enormous flexibility and reduced life cycle management costs, but they also come with prohibitive energy consumption. We argue that for future AI-native wireless networks to be flexible and energy efficient, there is a need for a new abstraction in network softwarization that caters for neural network type of workloads and allows a large degree of service composability. In this paper we present the NeuroRAN architecture, which leverages stateful function as a user facing execution model, and is complemented with virtualized resources and decentralized resource management. We show that neural network based implementations of common transceiver functional blocks fit the proposed architecture, and we discuss key research challenges related to compilation and code generation, resource management, reliability and security.

cs.NI↗