The growth of the number of connected devices and network densification is driving an increasing demand for radio network resources, particularly Radio Frequency (RF) spectrum. Given the dynamic and complex nature of contemporary wireless environments, characterized by a wide variety of devices and multiple RATs, spectrum sensing is envisioned to become a building component of future 6G, including as a components within O-RAN or digital twins. However, the current SotA research for RAT classification predominantly revolves around supervised Convolutional Neural Network (CNN)- based approach that require extensive labeled dataset. Due to this, it is unclear how existing models behave in environments for which training data is unavailable thus leaving open questions regarding their generalization capabilities. In this paper, we propose a new spectrum sensing workflow in which the model training does not require any prior knowledge of the RATs transmitting in that area (i.e., no labelled data) and the class assignment can be easily done through manual mapping. Furthermore, we adaptat a SSL deep clustering architecture capable of autonomously extracting spectrum features from raw 1D Fast Fourier Transform (FFT) data. We evaluate the proposed architecture on three real-world datasets from three European cities, in the 868 MHz, 2.4 GHz and 5.9 GHz bands containing over 10 RATs and show that the developed model achieves superior performance by up to 35 percentage points with 22% fewer trainable parameters and 50% less floating-point operations per second (FLOPS) compared to an SotA AE-based reference architecture.
{"title":"Spectrum Sensing With Deep Clustering: Label-Free Radio Access Technology Recognition","authors":"Ljupcho Milosheski;Mihael Mohorčič;Carolina Fortuna","doi":"10.1109/OJCOMS.2024.3436601","DOIUrl":"10.1109/OJCOMS.2024.3436601","url":null,"abstract":"The growth of the number of connected devices and network densification is driving an increasing demand for radio network resources, particularly Radio Frequency (RF) spectrum. Given the dynamic and complex nature of contemporary wireless environments, characterized by a wide variety of devices and multiple RATs, spectrum sensing is envisioned to become a building component of future 6G, including as a components within O-RAN or digital twins. However, the current SotA research for RAT classification predominantly revolves around supervised Convolutional Neural Network (CNN)- based approach that require extensive labeled dataset. Due to this, it is unclear how existing models behave in environments for which training data is unavailable thus leaving open questions regarding their generalization capabilities. In this paper, we propose a new spectrum sensing workflow in which the model training does not require any prior knowledge of the RATs transmitting in that area (i.e., no labelled data) and the class assignment can be easily done through manual mapping. Furthermore, we adaptat a SSL deep clustering architecture capable of autonomously extracting spectrum features from raw 1D Fast Fourier Transform (FFT) data. We evaluate the proposed architecture on three real-world datasets from three European cities, in the 868 MHz, 2.4 GHz and 5.9 GHz bands containing over 10 RATs and show that the developed model achieves superior performance by up to 35 percentage points with 22% fewer trainable parameters and 50% less floating-point operations per second (FLOPS) compared to an SotA AE-based reference architecture.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":null,"pages":null},"PeriodicalIF":6.3,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10623390","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141942604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-02DOI: 10.1109/OJCOMS.2024.3437357
Wenqian Tang;Ronghua Liu;Qiang Li;Zian Meng;Ashish Pandharipande;Xiaohu Ge
In this paper, a semantic-assisted hybrid non-orthogonal multiple access (NOMA) is investigated, in which a secondary far user (F-user) wishes to transmit to a common access point simultaneously with a primary near user (N-user) in the same frequency band. In order to take advantages of both semantic communication (SemCom) and traditional bit communication (BitCom), a SemCom/BitCom mode switching is proposed at the F-user, by adapting to the varying fading states of the channel. On this basis, in order to optimize the performance of F-user while providing adequate protection to the primary N-user, an optimization problem of maximizing the ergodic semantic rate of F-user is formulated, subject to an instantaneous bit rate constraint of N-user. This problem is non-convex and requires a joint design on the SemCom/BitCom mode switching and power adaptation over different fading states. To provide insights, it is first proved that the formulated problem satisfies the time-sharing condition, indicating that there exists a dual problem with zero duality gap to the original problem. A Lagrangian Sub-Gradient Algorithm is then proposed to solve the dual problem. Simulation results demonstrate that in the proposed semantic-assisted hybrid NOMA, significant performance improvement can be achieved for the F-user while meeting the instantaneous bit rate requirement of N-user. Furthermore, by adapting to the varying fading states, the proposed joint SemCom/BitCom mode switching and power adaptation scheme outperforms both BitCom and SemCom.
本文研究了一种语义辅助混合非正交多址接入(NOMA),在这种接入中,次远用户(F-user)希望与主近用户(N-user)在同一频段同时向一个共同接入点传输信号。为了同时利用语义通信(SemCom)和传统比特通信(BitCom)的优势,建议在 F 用户处进行 SemCom/BitCom 模式切换,以适应信道的不同衰减状态。在此基础上,为了优化 F 用户的性能,同时为主要 N 用户提供足够的保护,提出了一个优化问题,即在 N 用户瞬时比特率约束条件下,最大化 F 用户的遍历语义速率。这个问题是非凸的,需要在不同衰减状态下对 SemCom/BitCom 模式切换和功率适应进行联合设计。为了提供深入见解,首先证明了所提出的问题满足分时条件,表明存在一个与原始问题具有零对偶差距的对偶问题。然后提出了一种拉格朗日子梯度算法来求解对偶问题。仿真结果表明,在所提出的语义辅助混合 NOMA 中,在满足 N 用户瞬时比特率要求的同时,还能显著提高 F 用户的性能。此外,通过适应不同的衰减状态,所提出的 SemCom/BitCom 联合模式切换和功率适应方案的性能优于 BitCom 和 SemCom。
{"title":"Joint Optimization on Mode Switching and Power Adaptation in Semantic-Assisted Hybrid NOMA","authors":"Wenqian Tang;Ronghua Liu;Qiang Li;Zian Meng;Ashish Pandharipande;Xiaohu Ge","doi":"10.1109/OJCOMS.2024.3437357","DOIUrl":"10.1109/OJCOMS.2024.3437357","url":null,"abstract":"In this paper, a semantic-assisted hybrid non-orthogonal multiple access (NOMA) is investigated, in which a secondary far user (F-user) wishes to transmit to a common access point simultaneously with a primary near user (N-user) in the same frequency band. In order to take advantages of both semantic communication (SemCom) and traditional bit communication (BitCom), a SemCom/BitCom mode switching is proposed at the F-user, by adapting to the varying fading states of the channel. On this basis, in order to optimize the performance of F-user while providing adequate protection to the primary N-user, an optimization problem of maximizing the ergodic semantic rate of F-user is formulated, subject to an instantaneous bit rate constraint of N-user. This problem is non-convex and requires a joint design on the SemCom/BitCom mode switching and power adaptation over different fading states. To provide insights, it is first proved that the formulated problem satisfies the time-sharing condition, indicating that there exists a dual problem with zero duality gap to the original problem. A Lagrangian Sub-Gradient Algorithm is then proposed to solve the dual problem. Simulation results demonstrate that in the proposed semantic-assisted hybrid NOMA, significant performance improvement can be achieved for the F-user while meeting the instantaneous bit rate requirement of N-user. Furthermore, by adapting to the varying fading states, the proposed joint SemCom/BitCom mode switching and power adaptation scheme outperforms both BitCom and SemCom.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":null,"pages":null},"PeriodicalIF":6.3,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10620678","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper considers an OFDM-based wireless cellular network operating at millimeter waves and studies the problem of estimating the position and orientation of a mobile station (MS) upon relying on the pilot symbols emitted by the serving base station (BS), which are received via a direct link and an indirect link provided by a reconfigurable intelligent surface (RIS). To counterbalance the multiplicative pathloss in the indirect link, an active RIS is employed, which is able to reflect and amplify the incident signal. Upon introducing a convenient signal model, which accounts for the additional noise generated by the reflective amplifiers in the active RIS, we derive the ML estimators of the MS position and orientation and the corresponding Cramér Rao Lower Bounds under three levels of system cognition at the MS concerning the BS beamforming matrix, the RIS response, and the channel amplitudes on the direct and indirect links. In two cases, we also derive a suboptimal estimator with a reduced implementation complexity. Finally, we provide a numerical analysis to show the merits of the proposed estimators, assess the achievable gains granted by the use of an active RIS (as compared to a passive one), and investigate the impact of the main system parameters, including the BS-RIS distance and the amplification gain at the RIS.
本文考虑了基于 OFDM 的毫米波无线蜂窝网络,研究了依靠服务基站(BS)发射的先导符号估计移动站(MS)位置和方向的问题,这些先导符号通过可重构智能表面(RIS)提供的直接链路和间接链路接收。为了抵消间接链路中的乘法路径损耗,采用了主动式 RIS,它能够反射和放大入射信号。在引入一个方便的信号模型(该模型考虑了主动 RIS 中反射放大器产生的额外噪声)后,我们推导出了 MS 位置和方向的 ML 估计器,以及在 MS 对 BS 波束成形矩阵、RIS 响应以及直接和间接链路上的信道振幅的三个系统认知水平下相应的 Cramér Rao 下界。在两种情况下,我们还推导出了一个次优估计器,其实现复杂度有所降低。最后,我们通过数值分析展示了所提估计器的优点,评估了使用主动 RIS(与被动 RIS 相比)可实现的增益,并研究了主要系统参数(包括 BS-RIS 距离和 RIS 放大增益)的影响。
{"title":"Estimation of the User Position and Orientation in mmWave Cellular Networks Aided by an Active RIS","authors":"Georgios Mylonopoulos;Luca Venturino;Stefano Buzzi;Carmen D’Andrea","doi":"10.1109/OJCOMS.2024.3437661","DOIUrl":"10.1109/OJCOMS.2024.3437661","url":null,"abstract":"This paper considers an OFDM-based wireless cellular network operating at millimeter waves and studies the problem of estimating the position and orientation of a mobile station (MS) upon relying on the pilot symbols emitted by the serving base station (BS), which are received via a direct link and an indirect link provided by a reconfigurable intelligent surface (RIS). To counterbalance the multiplicative pathloss in the indirect link, an active RIS is employed, which is able to reflect and amplify the incident signal. Upon introducing a convenient signal model, which accounts for the additional noise generated by the reflective amplifiers in the active RIS, we derive the ML estimators of the MS position and orientation and the corresponding Cramér Rao Lower Bounds under three levels of system cognition at the MS concerning the BS beamforming matrix, the RIS response, and the channel amplitudes on the direct and indirect links. In two cases, we also derive a suboptimal estimator with a reduced implementation complexity. Finally, we provide a numerical analysis to show the merits of the proposed estimators, assess the achievable gains granted by the use of an active RIS (as compared to a passive one), and investigate the impact of the main system parameters, including the BS-RIS distance and the amplification gain at the RIS.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":null,"pages":null},"PeriodicalIF":6.3,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10621044","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-02DOI: 10.1109/OJCOMS.2024.3437681
Andra Blaga;Federico Campolo;Maurizio Rea;Xavier Costa-Pérez
Every year millions of lives are lost in emergency situations. Localizing missing people in the shortest possible timeframe is the most effective tool to reduce such a death toll. However, this is challenging when the victims are unable to communicate by themselves or located in large and difficult-toreach areas. Current technological approaches for victim localization are often rendered inoperable under obstacles or low visibility conditions, or due to the lack of cellular networking infrastructure. Toward addressing these issues, we present 3DSAR+, a pioneering single-drone three-dimensional (3D) cellular search-and-rescue (SAR) solution leveraging 5G-new radio (NR) technology. 3DSAR+ system introduces dynamic autonomous 3D UAV trajectories in diverse and challenging environments, offering a robust tool for first responders in SAR missions. The main novelty of the proposed approach lies in advanced distance and angle estimation combined with machine learning (ML) algorithms for position prediction and correction. The approach is able to estimate victims’ locations through their mobile phones without requiring extra equipment and improves localization accuracy by an order of magnitude compared to baseline solutions.
{"title":"3DSAR+: A Single-Drone 3D Cellular Search and Rescue Solution Leveraging 5G-NR","authors":"Andra Blaga;Federico Campolo;Maurizio Rea;Xavier Costa-Pérez","doi":"10.1109/OJCOMS.2024.3437681","DOIUrl":"10.1109/OJCOMS.2024.3437681","url":null,"abstract":"Every year millions of lives are lost in emergency situations. Localizing missing people in the shortest possible timeframe is the most effective tool to reduce such a death toll. However, this is challenging when the victims are unable to communicate by themselves or located in large and difficult-toreach areas. Current technological approaches for victim localization are often rendered inoperable under obstacles or low visibility conditions, or due to the lack of cellular networking infrastructure. Toward addressing these issues, we present 3DSAR+, a pioneering single-drone three-dimensional (3D) cellular search-and-rescue (SAR) solution leveraging 5G-new radio (NR) technology. 3DSAR+ system introduces dynamic autonomous 3D UAV trajectories in diverse and challenging environments, offering a robust tool for first responders in SAR missions. The main novelty of the proposed approach lies in advanced distance and angle estimation combined with machine learning (ML) algorithms for position prediction and correction. The approach is able to estimate victims’ locations through their mobile phones without requiring extra equipment and improves localization accuracy by an order of magnitude compared to baseline solutions.","PeriodicalId":33803,"journal":{"name":"IEEE Open Journal of the Communications Society","volume":null,"pages":null},"PeriodicalIF":6.3,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10621056","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}