Abstract
In this article, we propose an orthogonal frequency-division multiplexing system supported by the compressed sensing assisted index modulation, termed as (OFDM-CSIM), applied to millimeter-wave (mmWave) communications. In the OFDM-CSIM mmWave system, information is conveyed not only by the classic constellation symbols but also by the on/off status of subcarriers, where the size of constellation symbols and the number of active subcarriers can be beneficially configured for maximizing the system’s throughput. We conceive a machine learning (ML) assisted adaptive OFDM-CSIM mmWave system, which simultaneously benefits from the OFDM with index modulation (IM), compressed sensing (CS) and the hybrid beamforming techniques. Specifically, a ML-assisted link adaptation scheme is designed based on the $k$ -nearest neighbors ( $k$ -NN) algorithm with the objective to maximize the system’s throughput. Our studies show that the proposed ML-assisted link adaptation is capable of providing higher throughput than the conventional threshold-based link adaptation when different antenna structures are considered. Furthermore, the achievable data rates of four types of antenna arrays, including uniform linear array (ULA), uniform rectangular planar array (URPA), uniform circle planar array (UCPA) and uniform cylindrical array (UCYA), are investigated and compared over mmWave channels. The simulation results show that the UCYA achieves the highest data rate among these antenna arrays.
Highlights
W ITH the development of wireless industry and the worldwide deployment of mobile networks, there has been a dramatic increase in the number of mobile devices, since powerful smart phones, laptops as well as wearable devices for entertainment have been becoming more popular and essential in our daily life
The angle spreads in both elevation and azimuth directions and at both transmitter and receiver are assumed to be the same value of 7.5◦
In this article, we first provided a survey for the various antenna structures, and compared their spectral efficiency (SE) performance in the context of mmWave communications, showing that the uniform cylindrical array (UCYA) as a three-dimensional array has some advantages over the uniform linear array (ULA), uniform rectangular planar array (URPA) and uniform circle planar array (UCPA)
Summary
W ITH the development of wireless industry and the worldwide deployment of mobile networks, there has been a dramatic increase in the number of mobile devices, since powerful smart phones, laptops as well as wearable devices for entertainment have been becoming more popular and essential in our daily life. In conventional multiple-input multiple-output (MIMO) systems, the full-digital beamforming is usually employed, which simultaneously controls the phase and amplitude of the transmit/receive signals in digital domain This kind of full-digital beamforming is infeasible for operation with mmWave systems, as each antenna element requires a radio frequency chain, leading to high cost and power consumption [4]–[6]. LIU et al.: MACHINE LEARNING ASSISTED ADAPTIVE INDEX MODULATION FOR mmWAVE COMMUNICATIONS results in significant performance loss in comparison with the full-digital beamforming. The thresholds in the conventional link adaptation are usually hard to be set to near optimum, as the result of the deficiencies introduced at the various stages of a wireless system, including time-varying channel, non-linearity of amplifier, transmission frequency instability, etc. Based on the k-nearest neighbour (k-NN) algorithm, an ML-assisted adaptive modulation scheme for operation with the OFDM-CSIM is proposed. N k is the combination of the selection of k items from a collection of n items; · F is the Frobenius norm; · express inner product operations
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
