Article
Engineering, Electrical & Electronic
Yoel Bokobza, Ron Dabora, Kobi Cohen
Summary: This paper investigates the problem of dynamic spectrum access (DSA) in cognitive wireless networks, where secondary users (SUs) can only obtain partial observations due to narrowband sensing and transmissions. The objective is to maximize the SU's long-term throughput by developing a novel algorithm called Double Deep Q-network for Sensing and Access (DDQSA) that learns both access and sensing policies via deep Q-learning. The proposed algorithm achieves near-optimal performance and outperforms existing approaches in certain scenarios.
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Ramsha Ahmed, Yueyun Chen, Bilal Hassan
Summary: This paper addresses the opportunistic spectrum access (OSA) problem in the 5G/B5G cognitive radio (CR) network of IoTs and UAVs through the novel deep learning-based detector, dubbed as Deep-CRNet. Deep-CRNet intelligently learns and locates the spectrum holes so that secondary users (SUs) and primary users (PUs) can dynamically share network spectrum resources. The efficacy of Deep-CRNet is validated through simulation results, achieving high accuracy, precision, and recall in accurately classifying the PU status.
Article
Telecommunications
Bharath Keshavamurthy, Nicolo Michelusi
Summary: The LESSA framework introduces a novel learning-based spectrum sensing and access strategy, achieving a good balance between sensing accuracy and CR throughput by learning the LUs spectrum occupancy model and optimizing the spectrum sensing and access policy. MA-LESSA further extends to a distributed multi-agent setting, improving CR throughput through neighbor discovery and channel access rank allocation.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2022)
Article
Computer Science, Information Systems
Liuwen Li, Wei Xie, Xin Zhou
Summary: In this paper, a cooperative spectrum sensing model based on the parallel connection of convolutional neural network (CNN) and long-short-term memory (LSTM) is designed, making full use of the complementary feature extraction capabilities of CNN and LSTM networks. Experimental result shows that the detection performance of the proposed algorithm outperforms the conventional cooperative detection algorithm under low SNR condition.
Article
Telecommunications
Linghui Zeng, Jianzhao Zhang
Summary: This article analyzes the spectrum sharing among high-density users in future mobile communication systems and proposes a channel selection strategy based on distributed reinforcement learning, as well as a spectrum sensing skipping scheme based on Bayesian estimation, which can effectively optimize the spectrum utilization efficiency.
TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES
(2021)
Article
Engineering, Electrical & Electronic
Dawei Nie, Wenjuan Yu, Qiang Ni, Haris Pervaiz, Geyong Min
Summary: This paper proposes a cluster-based cooperative sensing-after-prediction scheme to simplify the complex physical sensing process and reduce energy consumption and the number of users, through cooperative prediction and optimization.
IEEE TRANSACTIONS ON COMMUNICATIONS
(2023)
Article
Telecommunications
Xin-Lin Huang, Yu-Xuan Li, Yu Gao, Xiao-Wei Tang
Summary: This article proposes a spectrum access scheme based on Q-learning to pursue high spectrum efficiency through intelligent access to idle spectrum. By integrating indicators such as throughput and collision probability into the reward function, the performance requirements of multimedia applications are met. Simulation results show that the proposed scheme achieves good performance in terms of throughput, power efficiency, and collision probability.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2021)
Article
Computer Science, Information Systems
Shisheng Hu, Yiyang Pei, Ying-Chang Liang
Summary: The study proposes the application of blockchain to DSA and aims to optimize the frame structure regarding sensing time and mining time to maximize achievable throughput. It proves the existence of a unique maximum point for both sub-optimization problems and proposes an alternating algorithm for optimization, illustrating the tradeoff and effectiveness through simulations.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2021)
Article
Telecommunications
Hao Fang, Tao Zhang, Linyuan Zhang, Hao Wu, Guoru Ding, Yueming Cai
Summary: This paper discusses how to detect illegal spectrum access behaviors in dynamic spectrum sharing, proposes a two-step detector and cooperative spectrum sensing scheme, and conducts performance simulations of the proposed detection schemes.
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING
(2021)
Article
Telecommunications
Omer Melih Gul, Burak Kantarci
Summary: This work focuses on the problem of data transmission in cognitive radio assisted vehicular networks. It proposes a Uniforming Random Ordered Policy (UROP) and demonstrates its near-optimal throughput. Under the assumption of block fading in generic channel evolution processes, UROP achieves close to optimal performance and outperforms the maximal power (MP) strategy in terms of throughput, especially for a limited number of available channels.
VEHICULAR COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Labsis Lyes, Teguig Djamal, Lassami Nacerredine
Summary: Spectrum sensing based on detection techniques enables cognitive radio networks to detect vacant frequency bands, increasing radio spectrum re-utilization. However, the main challenge lies in the simplicity of the detection approach and the amount of prior information needed for accurate decisions. This paper proposes a novel sensing technique based on the autocorrelation function, showing higher detection probability at low SNR compared to standard techniques. The proposed method is implemented using GNU Radio software and SDR platforms, demonstrating effectiveness in real scenarios.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Mohamed Abdelraheem, Mohammad M. Abdellatif
Summary: This article investigates the spectrum trading problem between primary users and secondary networks. Stochastic optimization techniques are used to find the optimal set of channels for each secondary network to meet user demands at the lowest cost. The results show that demanding simultaneous channels increases cost, while channel subleasing reduces demand shortages and increases throughput.
Article
Computer Science, Hardware & Architecture
Hisham M. Almasaeid
Summary: Spectrum Sensing as a Service (SSaS) is an emerging business model that enables efficient spectrum sharing. The model involves sensing infrastructure providing cognitive radio networks with information about spectrum availability. In return, the service provider imposes costs on network users. This paper addresses the problem of spectrum allocation in multi-interface dynamic spectrum access networks under the SSaS model, aiming to minimize costs and meet quality of service requirements. An Integer Linear Program (ILP) is formulated, and a sub-optimal algorithm is proposed due to the complexity of ILPs. Extensive experimentation validates the accuracy of the proposed algorithm.
Article
Computer Science, Interdisciplinary Applications
Wenyan Hu, Stephan Winter, Kourosh Khoshelham
Summary: In this paper, a method for tailored vehicle selection based on forecast fine-grained sensing coverage is proposed without trajectory data. A model is proposed to forecast fine-grained sensing coverage using coarse-grained information of candidate vehicles and a vehicle selection algorithm is developed to maximize the sensing quality. Results show that the selected vehicles based on this method achieve higher sensing quality than two other baselines. This research provides fundamental guidelines for coverage estimation and vehicle selection in urban vehicular sensing applications.
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Malgorzata Wasilewska, Hanna Bogucka, H. Vincent Poor
Summary: This article explores reliable and secure spectrum sensing in cognitive radio using federated learning. It discusses the motivation, architectures, and algorithms of federated learning in spectrum sensing. It provides an overview of security and privacy threats on these algorithms and presents possible countermeasures. The article also includes illustrative examples and offers design recommendations for future cognitive radios.
IEEE COMMUNICATIONS MAGAZINE
(2023)
