Low Earth orbit (LEO) satellite constellations are emerging as a core enabler of sixth-generation (6G) wireless systems, providing global coverage and high-capacity connectivity. However, dense multi-beam LEO deployments introduce severe inter-beam and inter-satellite interferences, while rapid orbital motion results in frequent handovers and highly dynamic channels that challenge the real-time optimization. To address these issues, this paper has proposed a digital twin (DT)-driven multi-LEO network architecture that integrates ray tracing-based virtual simulations with intelligent on-orbit control. Within this framework, we develop a DT-driven Efficient handover and Multi-Agent Twin delayed deep deterministic policy gradient (DEMAT) scheme, which jointly optimizes beam training, handover, power allocation, and beamwidth adaptation to maximize energy efficiency (EE) while satisfying user throughput requirements. DEMAT leverages bidirectional DT-LEO parameter exchange and federated learning-enhanced agents for cooperative and low-latency resource management. Extensive simulations validate its convergence and scalability under diverse network configurations such as various time frame intervals and user densities. Notably, DEMAT achieves up to a 59.6% EE improvement over the Deep Deterministic Policy Gradient (DDPG) baseline and more than 40% of EE compared to the other DT-based benchmarks, demonstrating superior adaptability and coordination for the next-generation non-terrestrial networks.

A space-air-ground integrated network (SAGIN) for Internet of Things (IoT) network architecture is investigated, empowered by multi-functional reconfigurable intelligent surfaces (MF-RIS) capable of simultaneously reflecting, amplifying, and harvesting wireless energy. The MF-RIS plays a pivotal role in addressing the energy shortages of low-Earth orbit (LEO) satellites operating in the shadowed regions, while accounting for both communication and computing energy consumption across the SAGIN nodes. To maximize the long-term energy efficiency (EE) of IoT devices, we formulate a joint optimization problem over the MF-RIS parameters, including signal amplification, phase-shifts, energy harvesting ratio, and active element selection as well as the SAGIN parameters of beamforming vectors, high-altitude platform station (HAPS) deployment, IoT device association, and computing capability. The formulated problem is highly non-convex and non-linear, which contains mixed discrete-continuous parameters. To tackle this, we conceive a compressed hybrid twin-model enhanced multi-agent deep reinforcement learning (CHIMERA) framework, which integrates semantic state-action compression and parametrized sharing under hybrid reinforcement learning to efficiently explore suitable complex actions. The simulation results have demonstrated that the proposed CHIMERA scheme substantially outperforms the conventional benchmarks, including fixed-configuration or non-harvesting MF-RIS, traditional RIS, and no-RIS cases, as well as centralized and multi-agent deep reinforcement learning baselines in terms of the highest EE. Moreover, the proposed SAGIN-MF-RIS architecture in IoT network achieves superior EE performance due to its complementary coverage, offering notable advantages over either standalone satellite, aerial, or ground-only deployments.

This paper investigates a simultaneously transmitting and reflecting reconfigurable intelligent surface (STARS)-aided integrated sensing and communication (ISAC) systems in support of full-space energy-efficient data transmissions and target sensing. We formulate an energy efficiency (EE) maximization problem that jointly optimizes a dual-functional radar-communication (DFRC)-empowered base station (BS), considering its ISAC-based active beamforming, along with the passive STARS beamforming configurations of amplitudes, phase shifts, quantization levels, and element selection. Furthermore, relaxed/independent/coupled STARS are considered to examine architectural flexibility. To tackle the non-convex and mixed-integer problem, we propose a joint active-passive beamforming, quantization and element selection (AQUES) scheme based on the alternating optimization: Lagrangian dual and Dinkelbach’s transformation tackle fractional equations, whereas successive convex approximation (SCA) convexifies the non-solvable problem; Penalty dual decomposition (PDD) framework and penalty-based convex-concave programming (PCCP) procedure solve amplitude and phase-shifts with the equality constraint; Heuristic search iteratively decides the optimal quantization level; Integer relaxation deals with the discrete element selection variables. Simulation results demonstrate that STARS-ISAC with the proposed AQUES scheme significantly enhances EE while meeting communication rates and sensing quality requirements. The coupled STARS further highlights its superior EE performance over independent and relaxed STARS thanks to its reduced hardware complexity. Moreover, AQUES outperforms existing configurations and benchmark methods in the open literature across various network parameters and deployment scenarios.

Integrated sensing and communication (ISAC) systems are emerging as a key technology to optimize the use of wireless resources by simultaneously supporting communication and sensing functions. This paper introduces an innovative ISAC system that integrates Wi-Fi channel state information (CSI)-based sensing and frequency-modulated continuous-wave (FMCW) radar within the Wi-Fi frequency band to enhance energy efficiency (EE). Wi-Fi CSI-based sensing enables simultaneous communication and environmental sensing using existing infrastructure, but it often suffers from high power consumption. Conversely, FMCW radar offers lower power consumption with the capability of self-transmission and reception but is limited by bandwidth constraints when operating in Wi-Fi bands. To overcome these challenges, we formulate the resource allocation problem as an optimization task that maximizes EE while maintaining sensing accuracy, managing power consumption, and respecting bandwidth limitations. The proposed system utilizes a dueling deep Q-Network (DQN) with reward shaping to learn optimal resource allocation strategies, showing a 36% to 40% increase in EE compared to traditional DQN models, providing a viable direction for the advancement of ISAC technologies.

In this paper, a novel network architecture that deploys the multi-functional reconfigurable intelligent surface (MFRIS) in low-Earth orbit (LEO) is proposed. Unlike traditional RIS with only signal reflection capability, the MF-RIS can reflect, refract, and amplify signals, as well as harvest energy from wireless signals. Given the high energy demands in shadow regions where solar energy is unavailable, MF-RIS is deployed on LEO to enhance signal coverage and improve energy efficiency (EE). To address this, we formulate a long-term EE optimization problem by determining the optimal parameters of MF-RIS, including amplification, phase-shifts, energy harvesting ratios, and LEO transmit beamforming. To address the complex non-convex and non-linear problem, a federated learning enhanced multi-agent deep deterministic policy gradient (FEMAD) scheme is designed. Multi-agent deep deterministic policy gradient (DDPG) of each agent can provide the optimal action policy from its interaction with environments, whereas federated learning enables the hidden information exchange among multi-agents. In numerical results, we can observe significant EE improvements compared to the other benchmarks, including centralized deep reinforcement learning as well as distributed multi-agent DDPG. Additionally, the proposed LEO-MF-RIS architecture has demonstrated its effectiveness, achieving the highest EE performance compared to the scenarios of fixed/no energy harvesting in MF-RIS, traditional reflection-only RIS, and deployment without RISs/MF-RISs.

Integrated sensing and communication (ISAC) enables the simultaneous operation of communication and sensing functionalities, leading to improved efficiency and performance. Furthermore, multi-AP coordination (MAP-Co), which provides higher transmission coverage and capacity, has attracted significant attention. Therefore, in this paper, we propose an indoor ISAC scenario assisted by the MAP-Co scheme. By jointly optimizing transmit power, bandwidth, and subchannel selection, we aim to maximize transmission throughput while guaranteeing a minimum required human presence detection accuracy. To effectively solve the complicated task, we propose a novel multi-head self-attention-assisted reinforcement learning (MH-SARL) algorithm. In our algorithm, the communication head is designed to search for the optimal resource allocation policy to maximize transmission throughput, whilst the sensing head focuses on suggesting adequate spectrum utilization to satisfy the predefined sensing quality. Simulation results demonstrate the effectiveness of our proposed MH-SARL algorithm under different scenarios and parameter settings. Compared to other benchmarks in the open literature, MH-SARL can achieve the highest transmission rate of at least 5% increase with guaranteed sensing accuracy.

Earth exploration satellite service (EESS) plays a crucial role in environmental monitoring and weather forecasting by utilizing passive sensing technologies. However, the rapid expansion of terrestrial and satellite communication networks has introduced significant interference challenges, particularly in frequency bands that overlap with or are adjacent to EESS sensors. In this work, we develop a system model that explicitly characterizes EESS interference by considering reflected signal effects and spatial interference accumulation. Based on this model, we propose a EESS-aware resource allocation (EARA) framework that jointly optimizes power allocation and user association, while ensuring that interference to EESS sensors remains within acceptable limits. A non-convex joint optimization problem is formulated and efficiently solved leveraging the Lagrangian dual transform and Dinkelbach’s method. Simulation results demonstrate that the proposed EARA scheme achieves up to 26.3% higher sum rate compared to genetic algorithm and binary whale optimization algorithm, while strictly satisfying the ITU-defined interference threshold. This work establishes a foundation for future research on the coexistence of communication networks and passive Earth observation systems, offering practical strategies for interference mitigation and spectrum sharing in next-generation networks.

In recent years, indoor human presence detection based on supervised learning (SL) and channel state information (CSI) has attracted much attention. However, existing studies that rely on spatial information of CSI are susceptible to the environmental changes, which degrade prediction accuracy. Moreover, SL-based methods require time-consuming data labeling for retraining models. Therefore, it is imperative to design a continuously monitored model using a semi-SL (SSL)-based scheme. In this article, we conceive a bifold teacher-student (BTS) learning approach for indoor human presence detection in a scenario with two adjoining rooms. The proposed SSL-based primal-dual teacher-student network intelligently learns spatial and temporal features from labeled and unlabeled CSI datasets. Additionally, the enhanced penalized loss function leverages entropy and distance measures to distinguish drifted data, i.e., features of new datasets affected by time-varying effects and altered from the original distribution. Experimental results demonstrate that the proposed BTS system accomplishes an averaged accuracy of around 98% after retraining the model with unlabeled data. BTS can sustain an accuracy of 93% under the changed layout and environments. Furthermore, BTS outperforms existing SSL-based models in terms of the highest detection accuracy of around 98% while achieving the asymptotic performance of SL-based methods.

The innovation of Wi-Fi 6, IEEE 802.11ax, was be approved as the next sixth-generation (6G) technology of wireless local area networks (WLANs) by improving the fun-damental performance of latency, throughput, and so on. The main technical feature of orthogonal frequency division multiple access (OFDMA) supports multi-users to transmit respective data concurrently via the corresponding access points (APs). However, the conventional IEEE 802.11 protocol for Wi-Fi roaming selects the target AP only depending on received signal strength indication (RSSI) which is obtained by the received Response frame from the APs. In the long term, it may lead to congestion in a single channel under the scenarios of dense users further increasing the association delay and packet drop rate, even reducing the quality of service (QoS) of the overall system. In this paper, we propose a multi-agent deep Q-Iearning for fast roaming (MADAR) algorithm to effectively minimize the latency during the station roaming for Smart Warehouse in Wi-Fi 6 system. The MADAR algorithm considers not only RSSI but also channel state information (CSI), and through online neural network learning and weighting adjustments to maximize the reward of the action selected from Epsilon-Greedy. Compared to existing benchmark methods, the MADAR algorithm has been demonstrated for improved roaming latency by analyzing the simulation result and realistic dataset.

Simultaneously transmitting and reflecting reconfig-urable intelligent surface (STAR-RIS) capable of manifesting the wireless channel provides the capability of signal reflection and refraction. However, conventional STAR-RIS has its limitation owing to signals impinging from one side of the surface, sup-porting either uplink (UL) or downlink (DL) users. Therefore, a novel concept of double-sided STAR-RIS (DS-STAR) becomes a promising solution, enabling signals impinging from both sides of the surface. In this paper, we consider multiple DS-STARs in a full-duplex (FD) enabled multi-input-multi-output (MIMO) system. We aim for maximizing joint UL/DL data rate by configuring transmit beamforming of the base station (BS) and UL users as well as configuration of DS-STARs, while ensuring quality-of-service (QoS) for both the UL/DL users. To tackle the complex problem, a genetic algorithm (GA) enhanced multi-agent Q-learning (G-MAQ) scheme is designed. MAQ considers a QoS-aware reward with each parameters as a sub-agent, whereas GA is applied to automatically optimize the hyperparameters of MAQ. In numerical results, we observe the significant im-provement of G-MAQ compared to that without hyperparameter optimization. Moreover, the proposed architecture of DS-STARs in FD networks achieves the highest rate compared to single-sided STAR-RIS, RIS and deployment without RIS/STAR-RIS. Additionally, the proposed G-MAQ scheme of DS-STAR FD sys-tems outperforms the other existing methods in open literature.

Integrated sensing and communication (ISAC) has become a key technology in the sixth-generation (6G) wireless networks, catering to the growing need for ubiquitous sensing and communication tasks. Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can harness both reflective and refractive signals delivered. Due to orientation limitation of STAR-RISs, the multi-dual STAR-RISs (MD-STAR) is conceived to facilitate full-plane services in ISAC systems. In this paper, we intend to solve active beamforming of dual-function radar-communication (DFRC)-enabled BSs and passive beamforming of MD-STAR in ISAC systems, aiming for maximizing the achievable sum rate constrained by the maximum position error bound (PEB) as well as hardware limitation of MD-STAR. In order to solve this complex problem, we propose a two-layered multi-agent federated Q-learning (TMFQ) scheme. The inner layer Q-learning focuses on obtaining the solution of BSs and MD-STAR, whilst the outer layer Q-learning aims for optimizing the hyperparameters, including learning rate and discount rate of the inner-layer one. Additionally, we employ federated learning to facilitate information exchange between agents in the inner Q-learning. We evaluate our proposed TMFQ in terms of different numbers of MD-STAR elements, transmit antennas, and sensing targets. Benefiting from hyperparameter optimization of the inner layer Q-learning and information exchange of federated learning, the proposed TMFQ can achieve the highest rate compared to the other benchmarks, including Q-learning without hyperparameter optimization and without federated learning, heuristic algorithm, and conventional beamforming.

Low Earth orbit (LEO) has a significant potential to provide ubiquitous global coverage with high capacity data services in sixth generation (6G) wireless networks. Due to the denser deployment of LEO satellites, it becomes mandatory to mitigate the interference induced by LEO beams. The high mobility of LEOs further stirs up a complex interference scenario different from conventional terrestrial networks. Therefore, we conceive a multi-LEO constellation that incorporates multi-beamforming and handover by using only the information of signal-to-interference-plus-noise ratio (SINR) and beam indexes. In this paper, we propose a joint LEO handover and fast beam switching (HOBS) algorithm that performs handover, beam search, and beam/power resource allocation. Our goal is to maximize energy efficiency (EE) while satisfying the SINR requirement of each user. We evaluate our proposed HOBS scheme in terms of different user densities, time frame sizes, and beam-sweeping schemes. Benefiting from a comparatively smaller beam search space, HOBS is capable of providing lower latency, as well as higher SINR and EE compared to conventional exhaustive beam search and fixed power control.

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) provides a promising way to expand coverage in wireless communications. However, limitation of single STAR-RIS inspire us to integrate the concept of multi-hop transmissions, as focused on RIS in existing research. Therefore, we propose the novel architecture of multi-hop STAR-RISs to achieve a wider range of full-plane service coverage. In this paper, we intend to solve active beamforming of the base station and passive beamforming of STAR-RISs, aiming for maximizing the energy efficiency constrained by hardware limitation of STAR-RISs. Furthermore, we investigate the impact of the on-off state of STAR-RIS elements on energy efficiency. To tackle the complex problem, a Multi-Agent Global and locAl deep Reinforcement learning (MAGAR) algorithm is designed. The global agent elevates the collaboration among local agents, which focus on individual learning. In numerical results, we observe the significant improvement of MAGAR compared to the other benchmarks, including Q-learning, multi-agent deep Q network (DQN) with golbal reward, and multi-agent DQN with local rewards. Moreover, the proposed architecture of multi-hop STAR-RISs achieves the highest energy efficiency compared to mode switching based STAR-RISs, conventional RISs and deployment without RISs or STAR-RISs.

In recent years, the demand for pervasive smart services and applications has increased rapidly. Device-free human detection through sensors or cameras has been widely adopted, but it comes with privacy issues as well as misdetection for motionless people. To address these drawbacks, channel state information (CSI) captured from commercialized Wi-Fi devices provides rich signal features for accurate detection. However, existing systems suffer from inaccurate classification under a Nonline-of-Sight (NLoS) and stationary scenario, such as when a person is standing still in a room corner. In this work, we propose a system called colorization and contrastive learning enhanced NLoS human presence detection (CRONOS), which generates dynamic recurrence plots (RPs) and color-coded CSI ratios to distinguish mobile and stationary people from vacancy in a room, respectively. We also incorporate supervised contrastive learning to retrieve substantial representations, where consultation loss is formulated to differentiate the representative distances between dynamic and stationary cases. Furthermore, we propose a self-switched static feature-enhanced classifier (S3FEC) to determine the utilization of either RPs or color-coded CSI ratios. Our comprehensive experimental results show that CRONOS outperforms existing systems that either apply machine learning or nonlearning-based methods, as well as non-CSI-based features in the open literature. CRONOS achieves the highest human presence detection accuracy in vacancy, mobility, Line-of-Sight (LoS), and NLoS scenarios.

In this paper, we consider a prospective receiving hybrid beamforming structure consisting of several radio frequency (RF) chains and abundant antenna elements in multi-input multi-output (MIMO) systems. Due to conventional costly full connections, we design an enhanced partially connected beamformer employing a low-density parity-check (LDPC)-based structure. As a benefit of the LDPC-based structure, information can be exchanged among clustered RF/antenna groups, which results in a low computational complexity order. Advanced message passing (MP) capable of inferring and transferring information among different paths is designed to support the LDPC-based hybrid beamformer. We propose a message-passing enhanced antenna and RF chain selection (MARS) scheme for minimizing the operational power of antennas and RF chains of the receiver as well as hybrid beamforming. Furthermore, sequential and parallel MP schemes for MARS are designed, namely, MARS-S and MARS-P, respectively, to address the convergence speed issue. A heuristic genetic algorithm is designed for receiving hybrid beamforming, comprising gene generation initialization, elite selection, crossover, and mutation. Simulations validate the convergence of both the MARS-P and the MARS-S algorithms. Due to the asynchronous information transfer of MARS-P, it requires higher power than MARS-S, which strikes a compelling balance among power consumption, convergence, and computational complexity. It is also demonstrated that the proposed MARS scheme outperforms the existing benchmarks using the heuristic method of fully/partially connected architectures in the open literature by requiring the lowest power and realizing the highest energy efficiency.

The joint uplink/downlink (JUD) design of simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) is conceived in support of both uplink (UL) and downlink (DL) users. Furthermore, the dual STAR-RISs (D-STAR) concept is conceived as a promising architecture for 360-degree full-plane service coverage, including UL/DL users located between the base station (BS) and the D-STAR as well as beyond. The corresponding regions are termed as primary (P) and secondary (S) regions. Both BS/users exist in the P-region, but only users are located in the S-region. The primary STAR-RIS (STAR-P) plays an important role in terms of tackling the P-region inter-user interference, the self-interference (SI) from the BS and from the reflective as well as refractive UL users imposed on the DL receiver. By contrast, the secondary STAR-RIS (STAR-S) aims for mitigating the S-region interferences. The non-linear and non-convex rate-maximization problem formulated is solved by alternating optimization amongst the decomposed convex sub-problems of the BS beamformer, and the D-STAR amplitude as well as phase shift configurations. We also propose a D-STAR based active beamforming and passive STAR-RIS amplitude/phase (DBAP) optimization scheme to solve the respective sub-problems by Lagrange dual with Dinkelbach’s transformation, alternating direction method of multipliers (ADMM) with successive convex approximation (SCA), and penalty convex-concave procedure (PCCP). Our simulation results reveal that the proposed D-STAR architecture outperforms the conventional single RIS, single STAR-RIS, and half-duplex networks. The proposed DBAP of D-STAR outperforms the state-of-the-art solutions found in the open literature for different numbers of quantization levels, geographic deployment, transmit power and for diverse numbers of transmit antennas, patch partitions as well as D-STAR elements.

Underwater image recognition is crucial for underwater detection applications. Fish classification has been one of the emerging research areas in recent years. Existing image classification models usually classify data collected from terrestrial environments. However, existing image classification models trained with terrestrial data are unsuitable for underwater images, as identifying underwater data is challenging due to their incomplete and noisy features. To address this, we propose a cross-modal augmentation via fusion ( CMAF ) framework for acoustic-based fish image classification. Our approach involves separating the process into two branches: visual modality and sonar signal modality, where the latter provides a complementary character feature. We augment the visual modality, design an attention-based fusion module, and adopt a masking-based training strategy with a mask-based focal loss to improve the learning of local features and address the class imbalance problem. Our proposed method outperforms the state-of-the-art methods. Our source code is available at https://github.com/WilkinsYang/CMAF .

Low-Earth orbit (LEO) satellites have been prosperously deployed for various Earth observation missions due to its capability of collecting a large amount of image or sensor data. However, traditionally, the data training process is performed in the terrestrial cloud server, which leads to a high transmission overhead. With the recent development of LEO, it is more imperative to provide ultra-dense LEO constellation with enhanced on-board computation capability. Benefited from it, we have proposed a collaborative federated learning for low Earth orbit (FELLO). We allocate the entire process on LEOs with low payload inter-satellite transmissions, whilst the low-delay terrestrial gateway server (GS) only takes care for initial signal controlling. The GS initially selects an LEO server, whereas its LEO clients are all determined by clustering mechanism and communication capability through the optical inter-satellite links (ISLs). The re-clustering of changing LEO server will be executed once with low communication quality of FELLO. In the simulations, we have numerically analyzed the proposed FELLO under practical Walker-based LEO constellation configurations along with MNIST training dataset for classification mission. The proposed FELLO outperforms the conventional centralized and distributed architectures with higher classification accuracy as well as comparably lower latency of joint communication and computing.

Channel State Information (CSI) is widely adopted as a feature for indoor localization. Taking advantage of the abundant information from the CSI, people can be accurately sensed even without equipped devices. However, the positioning error increases severely in non-line-of-sight (NLoS) regions. Reconfigurable intelligent surface (RIS) has been introduced to improve signal coverage in NLoS areas, which can redirect and enhance reflective signals with massive meta-material elements. In this paper, we have proposed a Transformer-based RIS-assisted device-free sensing for joint people counting and localization (WiRiS) system to precisely predict the number of people and their corresponding locations through configuring RIS. A series of predefined RIS beams is employed to create inputs of fingerprinting CSI features as sequence-to-sequence learning database for Transformer. We have evaluated the performance of proposed WiRiS system in both ray-tracing simulators and experiments. Both simulation and real-world experiments demonstrate that people counting accuracy exceeds 90%, and the localization error can achieve the centimeter-level, which outperforms the existing benchmarks without employment of RIS.

The open radio access network (O-RAN) architecture offers a cost-effective and scalable solution for internet service providers to optimize their networks using machine learning algorithms. The architecture’s open interfaces enable network function virtualization, with the O-RAN serving as the primary communication device for users. However, the limited frequency resources and information explosion make it difficult to achieve an optimal network experience without effective traffic control or resource allocation. To address this, we consider mobility-aware load balancing to evenly distribute loads across the network, preventing network congestion and user outages caused by excessive load concentration on open radio unit (O-RU) governed by a single open distributed unit (O-DU). We have proposed a multi-agent multi-armed bandit for load balancing and resource allocation (mmLBRA) scheme, designed to both achieve load balancing and improve the effective sum-rate performance of the O-RAN network. We also present the mmLBRA-LB and mmLBRA-RA sub-schemes that can operate independently in non-realtime RAN intelligent controller (Non-RT RIC) and near-RT RIC, respectively, providing a solution with moderate loads and high-rate in O-RUs. Simulation results show that the proposed mmLBRA scheme significantly increases the effective network sum-rate while achieving better load balancing across O-RUs compared to rule-based and other existing heuristic methods in open literature.

The demand for device-free indoor localization using commercial Wi-Fi devices has rapidly increased in various fields due to its convenience and versatile applications. However, random frequency offset (RFO) in wireless channels poses challenges to the accuracy of indoor localization when using fluctuating channel state information (CSI). To mitigate the RFO problem, an error vector spectrum (EVS) is conceived thanks to its higher resolution of signal and robustness to RFO. To address these challenges, this paper proposed a novel error vector assisted learning (EVAL) for device-free indoor localization. The proposed EVAL scheme employs deep neural networks to classify the location of a person in the indoor environment by extracting ample channel features from the physical layer signals. We conducted realistic experiments based on OpenWiFi project to extract both EVS and CSI to examine the performance of different device-free localization techniques. Experimental results show that our proposed EVAL scheme outperforms conventional machine learning methods and benchmarks utilizing either CSI amplitude or phase information. Compared to most existing CSI-based localization schemes, a new paradigm with higher positioning accuracy by adopting EVS is revealed by our proposed EVAL system.

Wi-Fi channel state information (CSI) has become a promising solution for non-invasive breathing and body motion monitoring during sleep. Sleep disorders of apnea and periodic limb movement disorder (PLMD) are often unconscious and fatal. The existing researches detect abnormal sleep disorders in impractically controlled environments. Moreover, it leads to compelling challenges to classify complex macro- and micro-scales of sleep movements as well as entangled similar waveforms of cases of apnea and PLMD. In this paper, we propose the attention-based learning for sleep apnea and limb movement detection (ALESAL) system that can jointly detect sleep apnea and PLMD under different sleep postures across a variety of patients. ALE-SAL contains antenna-pair and time attention mechanisms for mitigating the impact of modest antenna pairs and emphasizing the duration of interest, respectively. Performance results show that our proposed ALESAL system can achieve a weighted F1-score of 84.33, outperforming the other existing non-attention based methods of support vector machine and deep multilayer perceptron.

Low Earth orbit (LEO) satellite constellation is capable of providing global coverage area with high-rate services in the next sixth-generation (6G) non-terrestrial network (NTN). Due to limited onboard resources of operating power, beams, and channels, resilient and efficient resource management has become compellingly imperative under complex interference cases. However, different from conventional terrestrial base stations, LEO is deployed at considerable height and under high mobility, inducing substantially long delay and interference during transmission. As a result, acquiring the accurate channel state information between LEOs and ground users is challenging. Therefore, we construct a framework with a two-way transmission under unknown channel information and no data collected at long-delay ground gateway. In this paper, we propose hierarchical multi-agent multi-armed bandit resource allocation for LEO constellation (mmRAL) by appropriately assigning available radio resources. LEOs are considered as collaborative multiple macro-agents attempting unknown trials of various actions of micro-agents of respective resources, asymptotically achieving suitable allocation with only throughput information. In simulations, we evaluate mmRAL in various cases of LEO deployment, serving numbers of users and LEOs, hardware cost and outage probability. Benefited by efficient and resilient allocation, the proposed mmRAL system is capable of operating in homogeneous or heterogeneous orbital planes or constellations, achieving the highest throughput performance compared to the existing benchmarks in open literature.

IEEE 802.11ax system has been adopted to provide enhanced throughput performance for next-generation wireless local area networks. Its orthogonal frequency division multiple access (OFDMA) allows massive users to concurrently utilize different subbands for data transmission from their corresponding access points (APs). However, severe adjacent channel interference (ACI) incurs overlapping channels under the scenarios of dense users with multiple APs, which should be properly alleviated to provide adequate system throughput. In this paper, we propose a long-/short-term reinforcement learning channel allocation (LSRCA) scheme to effectively mitigate ACI for multi-AP scenarios in IEEE 802.11ax systems. With the considerations of signal features from both long and short time durations, the LSRCA algorithm can maximize effective sum rate through online adaptation and learning via the updates of two Q-tables for weighting adjustments and action execution. Experimental results in realistic fields have demonstrated the effectiveness of LSRCA scheme by providing higher system throughput compared to existing benchmark methods.

With explosively escalating service demands, beyond fifth generation (B5G) aims to realize various requirements for multi-service networks, i.e., higher performance of mixed enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (URLLC) services than 5G. To flexibly serve diverse traffic, various functional split options (FSOs) are specified by 5G protocols enabling different network functions. In order to improve signal qualities for edge users, we consider flexible FSO (FFS) based coordinated multi-point (CoMP) transmission as a prominent technique capable of supporting high traffic demands. However, due to conventional confined hardware processing capability, a processor sharing (PS) model is introduced to deal with high latency for multi-service FSO-based networks. Therefore, it becomes essential to assign CoMP-enhanced functional split modes under PS model. A more tractable FSO-based network in terms of ergodic rate and reliability is derived by stochastic geometry approach. Moreover, we have proposed CoMP-enhanced functional split mode allocation (CFSMA) scheme to adaptively assign FSOs to provide enhanced mixed throughput and latency-aware services. The simulation results have validated analytical derivation and demonstrated that the proposed CFSMA scheme optimizes system spectrum efficiency while guaranteeing stringent latency requirement. The proposed CFSMA scheme with the designed PS FFS-CoMP system outperforms the benchmarks of conventional FCFS scheduling, non-FSO network, fixed FSOs, and limited available FSO selections in open literature.

Multi-numerology (MN) providing a flexible transmission frame structure has attracted a considerable attention for supporting abundant services for beyond fifth-generation (B5G) networks. However, mobility induces severe performance degradation under different numerologies including temporal and spectral fluctuation, which is not well-investigated in existing literature. We have conceived an MN-enabled energy efficiency (EE) problem aiming for alleviating mobility- and MN-induced interferences through moderate power and sub-carrier assignment, while considering quality-of-service (QoS) and latency requirements for different services. We propose a multi-numerology based power and resource block allocation (MNPRA) scheme considering time-/frequency-division (TD/MD) based MN leveraging temporal and spectral features among numerologies. The original non-solvable problem is theoretically transformed into a convex one by employing Dinkelbach process, Taylor approximation and difference of two concave functions (D.C.). Convergence of proposed MNPRA scheme is analyzed and verified by simulations. In simulation results, we have evaluated MNPRA under different service demands, user velocities and MN types. Our proposed scheme outperforms the conventional single-numerology framing and existing methods in open literature, which results in performances of higher EE as well as of lower throughput/delay outage probability.

Substantially increasing wireless traffic and extending serving coverage is required with the advent of sixth-generation (6G) wireless communication networks. Reconfigurable intelligent surface (RIS) is widely considered as a promising technique which is capable of improving the system sum rate and energy efficiency. Moreover, full-duplex (FD) multi-input-multi-output (MIMO) transmission provides simultaneous transmit and received signals, which theoretically provides twice of spectrum efficiency. However, the self-interference (SI) in FD system is a challenging task requiring high-overhead cancellation, which can be resolved by configuring appropriate phase shifts of RIS. This paper has proposed an RIS-empowered full-duplex interference cancellation (RFIC) scheme in order to alleviate the severe interference in an RIS-FD system. We consider the interference minimization of RIS-FD MIMO while guaranteeing quality-of-service (QoS) of whole system. The closed-form solution of RIS phase shifts is theoretically derived with the discussion of different numbers of RIS elements and receiving antennas. Simulation results reveal that the proposed RFIC scheme outperforms existing benchmarks with more than 50% of performance gain of sum rate.

Terahertz (THz) communication with ultra-wide available spectrum is a promising technique that can achieve the stringent requirement of high data rate in the next-generation wireless networks, yet its severe propagation attenuation significantly hinders its implementation in practice. Finding beam directions for a large-scale antenna array to effectively overcome severe propagation attenuation of THz signals is a pressing need. This paper proposes a novel approach of federated deep reinforcement learning (FDRL) to swiftly perform THz-beam search for multiple base stations (BSs) coordinated by an edge server in a cellular network. All the BSs conduct deep deterministic policy gradient (DDPG)-based DRL to obtain THz beamforming policy with limited channel state information (CSI). They update their DDPG models with hidden information in order to mitigate inter-cell interference. We demonstrate that the cell network can achieve higher throughput as more THz CSI and hidden neurons of DDPG are adopted. We also show that FDRL with partial model update is able to nearly achieve the same performance of FDRL with full model update, which indicates an effective means to reduce communication load between the edge server and the BSs by partial model uploading. Moreover, the proposed FDRL outperforms conventional non-learning-based and existing non-FDRL benchmark optimization methods.

IEEE 802.11ax supports orthogonal frequency division multiple access (OFDMA) separating the channel into multiple resource units (RUs), which achieves higher flexibility and diversity in terms of spectrum utilization compared to conventional 802.11 mechanisms. Benefited by multi-band resources, enormous stations (STAs) are allowed to access different bands for data transmission from the serving access points (APs). Conventional uplink (UL) OFDMA non-random access (UONRA) specified in 802.11ax confronts with the bottleneck of buffer state report phase which lacks appropriate scheduling and queueing information. Furthermore, dense scenario with multi-AP deployment for downlink (DL) data transfer is challenging to assign limited radio resources due to adjacent channel interference (ACI) problem. Based on the aforementioned issues, we propose an enhanced queue-aware arbitration-based contention and resource allocation (QCRA) scheme for joint UL arbitration-based contention and DL resource assignment to mitigate collision occurrence and severe interference. The proposed objective aims at maximizing the effective sum rate by jointly considering UL overhead and DL rate which is theoretically resolved via difference of concave (D.C.) method and Taylor approximation. Simulation results reveal that the proposed QCRA scheme outperforms the other existing benchmarks in open literatures in terms of both higher UL contention successful probability and effective DL sum rate.

In the fifth-generation (5G) communication system, millimeter-wave (mmWave) technology brings superior capabilities, such as higher capacity, lower latency, and a flexible beamforming structure. The interference management strategies play an important role in mmWave beamforming networks to support the multibeam operation and maximize the overall data rates for user equipments (UEs). Currently, most of the existing research do not jointly consider designs, including the mainlobe interference (MI) avoidance and resource blocks (RBs) fairness allocation. In this article, a novel fairness allocation strategy is proposed to achieve the minimum MI and a fair RB assignment for mmWave networks. To achieve the minimum MI, an MI mitigation (MIM) algorithm is designed to maximize the data rate for each UE. With the adaptive mini-timeslot design, the MIM algorithm can achieve MI cancelation for all UEs at each identical timeslot and beam. To combine MIM and fairness for RB allocation among all UEs, the MIM-fairness allocation (MIM-FA) algorithm is also presented. Based on a novel mini-timeslot with designed multiple frames, the MIM-FA algorithm can simultaneously guarantee the fairness among all UEs and mitigate MI at each mini-timeslot for each beam. Additionally, the MIM-FA algorithm can be verified that it achieves the maximum user data rate with the identical number of RBs under the lowest number of frames. Simulation results validate that the proposed MIM and MIM-FA algorithms can provide a higher data rate and better fairness for different scenarios compared to current state-of-the-art competitive approaches.

In this paper, we study a delay-aware admission control (AC) and beam allocation (BA) problem with the consideration of quality of experience (QoE) and dynamic variation of channel condition for centralized unit (CU) and distributed unit (DU) based functional split options (FSOs) in millimeter wave (mmWave) fronthaul downlink networks. The original optimization problem aims to maximize time-average QoE subject to delay and queue stability constraints. The intractability of the considered problem comes from the necessity to allocate resources across periods of time slots. After applying virtual queue transformation and Lyapunov optimization method, the targeting problem can be converted into two independent AC and BA sub-problems in each time slot. The converted problem involves actual and virtual queues, which causes conflicting tendency. With the design of a flexible Lyapunov function, the influences of actual and virtual queues are theoretically to be proved balanced. Moreover, the AC sub-problem can be solved by Karush-Kuhn-Tucker condition, whereas mmWave BA sub-problem is tackled by genetic algorithm and matching game for the CU-based and DU-based FSOs, respectively. Simulation results demonstrate the applicability of the proposed CU-/DU-based algorithms in terms of average data rate, admission control rate, queue length, and corresponding system delay under either uniform or dense deployment of DUs. Moreover, the proposed scheme achieves the lowest delay and highest QoE performances while sustaining the system stability compared with the state-of-the-art mechanisms in open literatures.

The mobile wireless communication system with high-speed massive transmissions attracts immense attention in the fifth-generation (5G) new radio (NR) networks. However, it provokes difficulties to provide high-performance services for massive connections due to inter-carrier interference (ICI) caused by mobility factors. Furthermore, under the limited number of hardware antennas, it becomes essential to develop an effective testbed that is capable of emulating and evaluating an excessive number of users. In this paper, we propose virtual user equipment (VUE) emulation system with a VUE generator emulating massive VUE transmissions under a limited number of antennas. The precoding scheme is designed to transform the virtual channels of mobile VUEs to the realistic channels of antennas of the VUE generator. With the consideration of channel transformation estimation error and ICI, we propose the antenna selection and power/sub-carrier allocation (APSA) scheme aiming to maximize the achievable system sum rate. Simulation results demonstrate that the performance is influenced by VUE positions and channel errors in the designed VUE emulation system. Moreover, the proposed APSA scheme outperforms other methods in terms of quality-of-service (QoS) outage and sum rate.

In recent years, indoor positioning system employing Bluetooth has attracted tremendous attention. However, it is investigated that its received channel information is significantly affected by hardware configuration and wireless environments, especially the received dataset of angle of arrival (AOA), which leads to inaccurate channel estimation and positioning. Further-more, AOA estimation at larger angle direction is severely influenced by the variant wireless environment and signal distortion, which has not been resolve in existing literature. In this paper, we propose an advanced I/Q density-based AOA estimation (IQDAE) to deal with the above-mentioned problem, which consists of two sub-schemes. We firstly employ the designed phase difference (PD) filter to convert I/Q signals to phase information and then select the candidate sets by eliminating outliers. Afterward, we conceive a PD density-based classification algorithm to estimate AOA. The experimental results show that the mean absolute error of proposed IQDAE algorithm is comparably smaller than that from the other schemes, including commercial solutions, especially at larger angles. The results indicate that we can effectively increase the service range for the Bluetooth positioning system by adopting the proposed algorithm.

Internet of Things (IoT) is a promising technology attracting huge attentions in recent years, allowing an excessive number of connections between sensors and devices. Different from conventional human-oriented applications, long range (LoRa) developed in IoT facilitates massive simultaneous sensor data transmissions for the low-power wide-area network (LPWAN), where massive LoRa devices perform packet contention and backoff mechanisms to access opportunity for uplink data transfer. Therefore, it is compellingly imperative to take into account the fluctuation of different channel qualities and various traffic-buffer types for the optimum contention policy, which are not considered in open literatures. In this article, we propose a traffic-aware channel and backoff window size allocation (TCBA) scheme to improve network capacity and latency. Moreover, a statistical latency-aware network model is designed to derive the closed forms of the optimum packet transmission probability and maximum number of LoRa devices supported. The performance results validate that the theoretical analysis approaches the simulated one. Moreover, in both simulated and experimental results, our proposed TCBA scheme is capable of supporting massive LoRa connections achieving the highest throughput and the lowest end-to-end latency compared to other schemes in existing literatures.

In this paper, we conceive the first work of optimal functional split mode (FSM) selection for striking a balance between enhanced mobile broadband (eMBB) and ultra-reliable low-latency communication (uRLLC) in a cloudradio access network (C-RAN) for 5G new radio (NR). As a benefit of processing sharing (PS) and of coordinated multipoint transmission (CoMP) techniques, the user equipment (UE) can be served with more flexible transmission and sustaining eMBB/uRLLC service quality. Therefore, we aim at minimizing delay-outage probability (DOP) for uRLLC services by guaranteeing the quality of eMBB traffic. By employing Newton's method and convexity property, we propose an optimal FSM decision (OFD) scheme to achieve the optimal centralized/distributed control mode (CM/DM) assignment. Simulation results demonstrate the convergence and optimality of the proposed OFD algorithm compared to different parameters and schemes.

This paper is the first work to investigate power allocation design for multi-numerology based 5G new radio (NR) networks. With consideration of inter-numerology interference (INI) caused by the non-orthogonality between different numerologies, the objective function of considered optimization problem is to maximize total effective capacity (EC) under transmission power constraint. A geometry programming based power allocation (GPA) algorithm is proposed, which firstly tackles the non-convexity induced by INI in the multi-numerology systems via lower bound estimation and variable transformation techniques. Power allocation solution is then obtained by Lagrangian dual method. Simulation results reveal the influence of INI on power allocation result and demonstrate the superiority of proposed GPA algorithm based on its performance on total EC.

Millimeter wave (mmWave) is capable of supporting ultra-high system performance due to its spatial diversity from directional transmission techniques in fifth generation (5G) wireless networks. Improved by the beamforming, mmWave could be applied to potentially achieve more accurate indoor positioning. Due to impermeability and high path loss of mmWave, most of transmission is operated under line-of-sight (LoS) conditions. In this paper, we propose beam-based midline intersection positioning (BMIP) and advanced beam scaling positioning (ABSP) for indoor positioning. Two mmWave access points (APs) are employed for performing positioning under LoS conditions. The user equipment (UE) will receive downlink information of angle-of-departure (AoD) and corresponding signal-to-noise-ratio (SNR) values from two APs, respectively. We have evaluated our proposed BMIP and ABSP indoor positioning algorithms via both mmWave ray-tracing based simulation and experimental implementation using commercialized 60 GHz transceivers. The results demonstrate that our proposed positioning algorithms could achieve the centimeter-level estimation errors.

Recently, many researches are focusing on millimeter wave (mmWave) due to its large bandwidth resources. In the next 5G generation, wireless multi-gigabit (WiGig) is developed based on IEEE 802.11ad/ay standards at unlicensed mmWave bands for providing extremely high throughput. However, mmWave has high propagation loss due to high frequency transmission properties. Beamforming (BF) technique is adopted to solve this problem, and therefore, we have to perform beam training before data transmission. In the standard, the conventional method for beam training is exhaustive beam search (EBS) which takes too much time so that the data transmission time will decrease. On the other hand, blocked environments may severely degrade WiGig beam training performance, and most of existing algorithms do not consider this issue. Recently, machine and deep learning have been widely used in the wireless communication field. We propose a learning-based beam training (LBT) to simultaneously learn about wireless environments and beam training candidates. We select simplified neural network (NN) model to achieve lower computation overhead. To further refine learning information, we propose two enhanced algorithm, expanded LBT (LBT-E) and history-aided expanded LBT(LBT-HE). LBT-E aims to tackle unexpected slight deviation and LBT-HE make use of historical information to improve beam matching accuracy with acceptable latency. In our simulation, our proposed learning-based schemes achieve much higher throughput compared to EBS and algorithms in existing literatures.

Millimeter wave (mmWave) offers Gbps-level wireless services thanks to its huge spectrum and spatial utilization in the next fifth-generation (5G) wireless networks. Due to attenuations of signal loss, beam-based directional transmission is thus significant to overcome physical disadvantages. For multiuser service demands, the base station is capable of transmitting multiple high-gained beams via the massive antenna deployment. To simultaneously support a large number of users in a hotspot with finite beams, clustering is needed which several user groups are scheduled for each beam. To mitigate inter-beam interferences, we partition the original non-convex and nonlinear problem into two parts and propose the orthogonal beam clustering (OBC) and iterative power allocation (IPA) schemes through gradient descent method. Simulation results demonstrate that the groups with larger beam gains tend to be assigned with more power in order to provide higher rate. It also achieves better performance with increments of the orthogonal beam resources. Our proposed scheme can supports Gbps-level per user throughput which is twice higher compared to existing literatures.

Transmission policy of the hybrid energy model allows maximizing energy utilization of small cells in the wireless system. One of the key challenges in maximization of energy utilization is to minimize the grid power and energy wastage of green harvested energy (GHE) sources simultaneously. In this paper, unlike existing transmission policy solution which focuses only on one highlighted objective, we proposed multi-objective model checking for Markov decision process (MOMC-MDP) with linear temporal logic (LTL) to find the best feasible solution for packet transmissions in each time slot. Based on the MOMC-MDP for different battery status, the optimal transmission policy of small cells is obtained in order to deliver the highest harvest energy sources and guarantee the quality of service (QoS) demands. Numerical results show that the MOMC- MDP scheme can ensure to efficiently use the limited energy of battery while maximizing green energy utilization in real-time transmission.

MmWave in the unlicensed 60GHz band is highly discussed due to the rapid growth of wireless communication services. The utilization of microwave spectrum below 10 GHz is almost reaching its limit. Beamforming (BF) has become an essential technique to compensate the high path loss phenomenon of mmWave. IEEE 802.11ad and 802.11ay standardization task group institute directional multi-gigabit (DMG) wireless local area networks (WLANs) supporting mmWave techniques. With wireless devices explosively increasing, the limited number of BF slots in conventional DMG protocols leads to high packet collision probability, which potentially degrades the system performance. Most of the existing research does not take the multi-user BF contention problem into consideration. In this paper, we design a non-slotted association beamforming training (A-BFT) frame structure for multi-users without separating A-BFT slots in order to alleviate packet collisions due to the shortage of contention and training frames. This new proposed structure allows collisions with useful information left in remaining non-collided slots or frames in order to leverage the insufficiency of BF training for multiple devices. Furthermore, in order to further reduce BF collision probability, we propose two multiuser beamforming training mechanisms, including the time-based distributed coordination function (TDCF) and time-based beam-collision avoidance (TBCA) schemes. Simulation results demonstrate that our new proposed frame structure along with proposed TDCF and TBCA mechanisms outperforms 802.11ad protocol.

Millimeter wave (mmWave) technology provides multi-Gbps services thanks to huge spectrum usage. IEEE 802.11ad/ay standardizes the next generation wireless local area networks (WLANs) for high data rate transmissions at 60 GHz band. Directional beamforming (BF) transmissions overcome the difficulty of high signal attenuation. In addition, a beam sector based scheme for BF training is taken by 802.11ad/ay to tackle sophisticated indoor environments. However, conventional exhaustive beam search (EBS) takes much time and some literatures try to design to reduce training latency. Also, most of papers do not consider about the mobility effect of moving devices, which deteriorates the beam matching outcomes. With the consideration of beam matching accuracy and mobility effects corresponding to historically observed transmitted beams, we propose the mobility-aware fast beam training (MFBT) algorithm. Simulation results show how mobility affects the system in terms of latency and throughput. There are trade-offs when operating with different beamwidth and matching accuracy requirements. Moreover, our proposed algorithm achieves lower latency and higher throughput than other existing beam training schemes.

To satisfy future explosive demands of mobile traffic, millimeter wave (mmWave) technology has been widely considered in the next generation wireless networks thanks to its large spectrum and spatial resources. MmWave Hybrid beamforming (HBF) with multi-input multi-output (MIMO) system is a critical technique to support multi-beam operation and reduce the cost and complexity. In this paper, we define inter-user interference in the mainlobe and the sidelobe. With the consideration of quality of service (QoS) requirements, we design a mainlobe interference avoidance (MIA) scheduling algorithm to maximize data throughput under the existence of inter-user interferences. Our proposed scheme allocates system resources by jointly considering not only the subband resources but also the antenna beamwidth and beam direction. Simulation results demonstrate that the proposed scheme outperforms existing heuristic algorithms both in the uniform and hotspot scenarios.