Deep Learning aided Spectrum Prediction for Satellite Communication Systems

Author(s):  
Xiaojin Ding ◽  
Lijie Feng ◽  
Yulong Zou ◽  
Gengxin Zhang
Author(s):  
Teodor Narytnik ◽  
Vladimir Saiko

The technical aspects of the main promising projects in the segments of medium and low-orbit satellite communication systems are considered, as well as the project of the domestic low-orbit information and telecommunications system using the terahertz range, which is based on the use of satellite platforms of the micro- and nanosatellite class and the distribution of functional blocks of complex satellite payloads more high-end on multiple functionally related satellites. The proposed system of low-orbit satellite communications represents the groupings of low-orbit spacecraft (LEO-system) with the architecture of a "distributed satellite", which include the groupings of the root (leading) satellites and satellite repeaters (slaves). Root satellites are interconnected in a ring network by high-speed links between the satellites. The geometric size of the “distributed satellite” is the area around the root satellite with a radius of about 1 km. The combination of beams, which are formed by the repeater satellites, make up the service area of the LEO system. The requirements for the integrated service area of the LEO system (geographical service area) determine the requirements for the number of distributed satellites in the system as a whole. In the proposed system to reduce mutual interference between the grouping of the root (leading) satellites and repeater satellites (slaves) and, accordingly, minimizing distortions of the information signal when implementing inter-satellite communication, this line (radio channel) was created in an unlicensed frequency (e.g., in the terahertz 140 GHz) range. In addition, it additionally allows you to minimize the size of the antennas of such a broadband channel and simplify the operation of these satellite systems.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Youngbin Na ◽  
Do-Kyeong Ko

AbstractStructured light with spatial degrees of freedom (DoF) is considered a potential solution to address the unprecedented demand for data traffic, but there is a limit to effectively improving the communication capacity by its integer quantization. We propose a data transmission system using fractional mode encoding and deep-learning decoding. Spatial modes of Bessel-Gaussian beams separated by fractional intervals are employed to represent 8-bit symbols. Data encoded by switching phase holograms is efficiently decoded by a deep-learning classifier that only requires the intensity profile of transmitted modes. Our results show that the trained model can simultaneously recognize two independent DoF without any mode sorter and precisely detect small differences between fractional modes. Moreover, the proposed scheme successfully achieves image transmission despite its densely packed mode space. This research will present a new approach to realizing higher data rates for advanced optical communication systems.


Sign in / Sign up

Export Citation Format

Share Document