This paper introduces the application of machine learning (ML)-based procedures in real-world satellite communication operations. While the application of ML in image processing has led to unprecedented advantages in new services and products, the application of ML in wireless systems is still on its infancy. In particular, this paper focuses on the introduction ML-based mechanisms in satellite network operation centers such as interference detection, flexible payload configuration and congestion prediction. Three different use cases are described and the proposed ML models are introduced. All the models have been constructed using real data and considering current operations. As reported in the numerical results, the ML-based proposed techniques can improve a certain key performance indicator of each use case at least a 10%. In light of the results, the proposed techniques are useful in the process of automating satellite communication systems.

No abstract

Abstract-This paper presents the novel application of polarized modulation (PMod) for increasing the throughput in mobile satellite transmissions. One of the major drawbacks in mobile satellite communications is the fact that the power budget is often restrictive, making it unaffordable to improve the spectral efficiency without an increment of transmitted power. By using dual polarized antennas in the transmitter and receiver, the PMod technique achieves an improvement in throughput of up to 100% with respect to existing deployments, with an increase of less than 1 dB at low E b /N 0 regime. Additionally, the proposed scheme implies minimum hardware modifications with respect to the existing dual polarized systems and does not require additional channel state information at the transmitter; thus it can be used in current deployments. Demodulation (i.e., detection and decoding) alternatives, with different processing complexity and performance, are studied. The results are validated in a typical mobile interactive scenario, the newest version of TS 102 744 standard [Broadband Global Area Network (BGAN)], which aims to provide interactive mobile satellite communications.Index Terms-Satellite communications, polarized modulation, dual polarized antennas, interactive services.

In this paper we present a novel modulation technique for dual polarization communication systems, which reduces the error rate compared with the existent schemes. This modulation places the symbols in a 3D constellation, rather than the classic approach of 2D. Adjusting the phase of these symbols depending on the information bits, we are able to increase the bit rate. Hence, the proposed scheme conveys information by selecting both polarization state and the phase of radiated electromagnetic wave. We also analyse the performance of 3D Polarized Modulation (PMod) for different constellation sizes and we obtain a curve of rate adaptation. Finally, we compare the proposed 3D PMod with other existing schemes such as single polarization Phase Shift Keying (PSK) and double polarization Vertical Bell Laboratories Layer Space-Time (V-BLAST), both carrying the same number of information bits. The results show that 3D PMod always outperforms all other schemes, except for low order modulation. Therefore, we can conclude that 3D PMod is an excellent candidate for medium and high modulation order transmissions.

Abstract-Determining the capacity of a modulation scheme is a fundamental topic of interest. Index Modulations (IM), such as Spatial Modulation (SMod), Polarized Modulation (PMod) or Frequency Index Modulation (FMod), are widely studied in the literature. However, finding a closed-form analytical expression for their capacity still remains an open topic. In this paper, we formulate closed-form expressions for the instantaneous capacity of IM, together with its 2nd and 4th order approximations. We show that, in average, the 2nd approximation error tends to zero for low Signal to Noise Ratio (SNR) and is o (SNR). Also, a detailed analysis of the ergodic capacity over Rayleigh, Rice and Nakagami-m channel distributions is provided. As application of the capacity analysis, we leverage the proposed expressions to compute the ergodic capacities of SMod for different antenna configuration and correlations, PMod for different channel components and conditions, and FMod for different frequency separations. Although V-BLAST offers higher capacity, it requires high power budget. On the contrary, OSTBC exploits the full channel diversity at the expense of sacrificing multiplexing gain. Note also that OSTBC can only provide full diversity with 2 transmitting antennas. SMod strikes a balance between V-BLAST and OSTBC by increasing the channel capacity that OSTBC offers with less power requirements and is a trade-off between V-BLAST and OSTBC. In addition, it also provides more flexibility than OSTBC in the achievable rate that is obtained by increasing the number of transmitting antennas.SMod can be classified in to the general modulation strategy of Index Modulations (IM), term employed by [23], [30].