Abstract
Index Modulations, in the form of Spatial Modulation or Polarized Modulation, are gaining traction for both satellite and terrestrial next generation communication systems. Adaptive Spatial Modulation based links are needed to fully exploit the transmission capacity of time-variant channels. The adaptation of code and/or modulation requires a real-time evaluation of the channel achievable rates. Some existing results in the literature present a computational complexity which scales quadratically with the number of transmit antennas and the constellation order. Moreover, the accuracy of these approximations is low and it can lead to wrong Modulation and Coding Scheme selection. In this work we apply a Multilayer Feedforward Neural Network to compute the achievable rate of a generic Index Modulation link. The case of two antennas/polarizations is analyzed in depth, showing not only a one-hundred fold decrement of the Mean Square Error in the estimation of the capacity as compared with existing analytical approximations, but also a fifty times reduction of the computational complexity. Moreover, the extension to an arbitrary number of antennas is explained and supported with simulations. More generally, neural networks can be considered as promising candidates for the practical estimation of complex metrics in communication related settings.
Highlights
The evaluation of the achievable physical layer rate of a given modulation scheme is an important theoretical problem with high relevance in practice
This metric can be in the form of the average or effective Signal to Interference and Noise Ratio (SINR), or some Channel Quality Indicator (CQI) suited to the set of Modulation and Coding Scheme (MCS) available to the transmitter [4]
In this paper we present a novel method to compute the mutual information without Channel State Information at the Transmitter (CSIT) of a 2×2 Spatial Modulation (SM) system, and show how to generalize it to an arbitrary number of antennas
Summary
The evaluation of the achievable physical layer rate of a given modulation scheme is an important theoretical problem with high relevance in practice. Recent works such as [9] present experimental results with compact reconfigurable antennas for using SM in the uplink of Internet of Things (IoT) devices in 5G networks with a high number of antennas on the base station side Another interesting version of IM is that studied in [8], where the authors propose the use of PMod to increase the spectral efficiency of generation mobile satellite communications; if Multiple-Input-Multiple-Output (MIMO) signal processing techniques are applied to Dual Polarization (DP) satellite systems, the performance of single-antenna (or single polarization) links can be notably enhanced. In [27], a deep neural network is used to select the optimum codebook in adaptive SM, i.e., the particular constellation employed by each antenna This recent work is related with older SM publications which deal with adaptive SM systems, such as [28] and [29]. E [·] is the expected value operator. ◦ and denote the Hadamard (pointwise) matrix product and division. {·}, {·}, (.)∗ and | · | denote the real part, imaginary part, conjugate and absolute value of a complex number, respectively
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have