Search

Millimeter-wave (mmWave) multiple-input multiple-output (MIMO) communication with the advanced beamforming technologies is a key enabler to meet the growing demands of future mobile communication. However, the dynamic nature of cellular channels in large-scale urban mmWave MIMO communication scenarios brings substantial challenges, particularly in terms of complexity and robustness. To address these issues, we propose a robust gradient-based liquid neural network (GLNN) framework that utilizes ordinary differential equation-based liquid neurons to solve the beamforming problem. Specifically, our proposed GLNN framework takes gradients of the optimization objective function as inputs to extract the high-order channel feature information, and then introduces a residual connection to mitigate the training burden. Furthermore, we use the manifold learning technique to compress the search space of the beamforming problem. These designs enable the GLNN to effectively maintain low complexity while ensuring strong robustness to noisy and highly dynamic channels. Extensive simulation results demonstrate that the GLNN can achieve 4.15% higher spectral efficiency than that of typical iterative algorithms, and reduce the time consumption to only 1.61% that of conventional methods.

Orthogonal Time Frequency Space (OTFS) is a promising modulation scheme that works in the delay-Doppler (DD) domain, offering resistance to frequency selective fading and time-varying channels. Thus, OTFS channel estimation assumes great significance for successful transmission. Typically, it requires allocating pilots in the DD domain, which often results in an increase in the peak-to-average power ratio (PAPR) and high complexity to detect the received signal. In response to these issues, we present a solution that estimates the channel in the time-frequency (TF) domain. In addition, although several works in the literature present solutions for OTFS channel estimation, few consider the presence of high-power amplifiers (HPAs) and explain the impact of nonlinear effects on channel estimation and system performance. Starting from channel estimation based on preambles and pilots in the TF domain, we present a solution capable of obtaining reliable channel estimation using a long short-term memory (LSTM) network in highly selective channel conditions, effectively compensating for nonlinearities in signal reception. Our results validate the effectiveness of the proposed solution, highlighting its potential to improve the performance and robustness of OTFS communication systems in real scenarios with nonlinear HPA effects.

The evolution of generative artificial intelligence (GenAI) constitutes a turning point in reshaping the future of technology in different aspects. Wireless networks, in particular, with the blooming of self-evolving networks, represent a rich field for exploiting GenAI and reaping several benefits that can fundamentally change the way wireless networks are designed and operated nowadays. To be specific, large GenAI models are envisioned to open up a new era of autonomous wireless networks, in which multi-modal GenAI models trained over various Telecom data, can be fine-tuned to perform several downstream tasks, eliminating the need for building and training dedicated AI models for each specific task, and paving the way for the realization of artificial general intelligence (AGI)-empowered wireless networks. In this article, we aim to unfold the opportunities that can be reaped from integrating large GenAI models into the Telecom domain. In particular, we first highlight the applications of large GenAI models in future wireless networks, defining potential use-cases and revealing insights on the associated theoretical and practical challenges. Furthermore, we unveil how 6G can open up new opportunities through connecting multiple on-device large GenAI models, and hence, pave the way to the collective intelligence paradigm. Finally, we put a forward-looking vision of how large GenAI models will be the key to realize self-evolving networks.

The emergence of 5th-generation networks and the introduction of the ultra-low latency Internet, namely, tactile Internet, by the International Telecommunication Union (ITU), has opened up a wide range of applications. Extended Reality (XR), holoportation, and remote control of machines are among the ones that would revolutionize the future of factories, smart cities, and digital healthcare. Virtual Reality (VR) technology provides users with highly realistic visual and auditory experiences, enabling a high sense of immersion and embodiment in virtual environments. In the real world, however, we use more senses than only vision and hearing to perceive our surroundings. Particularly, tactile sensation is the only bidirectional modality that enables us to perceive and interact with the objects and surfaces around us. This brief introduces a real-life testbed Unmanned Aerial Vehicle (UAV)-based system that leverages different technologies, including VR, 360° video streaming over 4G/5G, and edge computing to enable 6 Degrees of Freedom (6DoF) view with haptic feedback for a maximized immersion. The demonstration videos of the testbed are made publicly available on the following links: Link1 and Link2.

In this letter, the problem of relay selection and optimal resource allocation for two-way relaying cognitive radio networks using half duplex amplify-and-forward and decode-and-forward protocols is investigated. The primary and secondary users are assumed to access the spectrum simultaneously, in a way that the interference introduced to the primary users should be below a certain tolerated limit. Dual decomposition and subgradient methods are used to find the optimal power allocation. A suboptimal approach based on a genetic algorithm is also presented. Simulation results show that the proposed suboptimal algorithm offers a performance close to the optimal performance with a considerable complexity saving.

This paper is based on an Offset Quadrature Amplitude Modulation (OQAM) Orthogonal Frequency Division Multiplexing (OFDM) transmission scheme that is operated without a Cyclic Prefix (CP), where the multiple transmitting antennas are employed to substantially reduce the inherent intersymbol and intercarrier interference. The proposed scheme avoids the use of the CDMA technology to get rid of the interference. The nonemployment of the CP increases the spectral efficiency in comparison with classical CP-OFDM systems, as it does not employ the CP for its correct performance. On the other hand, the non-employment of the CP comes at cost of Intersymbol Interference (ISI). This paper presents a method which cancels the interference terms by employing a multiantenna precoding strategy based on spatial diversity OQAM-OFDM scheme, so that the overall system can get the advantage of the CP removal while no ISI is generated. Moreover, the proposed system benefits from the multiuser gain through an opportunistic scheduler at the transmitter side to select the user with the best channel characteristics at each instant. The resultant scheme OQAM-OFDM-MIMO data rate is obtained in a closed form expression and proved to be higher than the classical CP-OFDM systems.