Supervised machine learning for power and bandwidth management in very high throughput satellite systems

In the near future, very high throughput satellite (VHTS) systems are expected to have a high increase in traffic demand. However, this increase will not be uniform over the service area and will be also dynamic. A solution to this problem is given by flexible payload architectures; however, they require that resource management is performed autonomously and with low latency. In this paper, we propose the use of supervised machine learning, in particular a classification algorithm using a neural network, to manage the resources available in flexible payload architectures. Use cases are presented to demonstrate the effectiveness of the proposed approach, and a discussion is made on all the challenges that are presented.

[1]  Daniele Tarchi,et al.  Convolutional Neural Networks for Flexible Payload Management in VHTS Systems , 2021, IEEE Systems Journal.

[2]  Daniele Tarchi,et al.  Supervised Machine Learning for Power and Bandwidth Management in VHTS Systems , 2020, 2020 10th Advanced Satellite Multimedia Systems Conference and the 16th Signal Processing for Space Communications Workshop (ASMS/SPSC).

[3]  2020 10th Advanced Satellite Multimedia Systems Conference and the 16th Signal Processing for Space Communications Workshop (ASMS/SPSC) , 2020 .

[4]  Flor G. Ortiz-Gomez,et al.  Correction: Ortiz-Gomez, F.G. et al. Forward Link Optimization for the Design of VHTS Satellite Networks. Electronics 2020, 9, 473 , 2020 .

[5]  Juan Jose Garau Luis,et al.  Artificial Intelligence Algorithms for Power Allocation in High Throughput Satellites: A Comparison , 2020, 2020 IEEE Aerospace Conference.

[6]  M. Salas-Natera,et al.  Forward Link Optimization for the Design of VHTS Satellite Networks , 2020, Electronics.

[7]  Marina Ruggieri,et al.  Smart Gateway Diversity Optimization for EHF Satellite Networks , 2020, IEEE Transactions on Aerospace and Electronic Systems.

[8]  Lixiang Liu,et al.  AG‐DPA: Assignment game–based dynamic power allocation in multibeam satellite systems , 2019, Int. J. Satell. Commun. Netw..

[9]  Juan Jose Garau Luis,et al.  Deep Reinforcement Learning for Continuous Power Allocation in Flexible High Throughput Satellites , 2019, 2019 IEEE Cognitive Communications for Aerospace Applications Workshop (CCAAW).

[10]  Aleix Paris,et al.  A Genetic Algorithm for Joint Power and Bandwidth Allocation in Multibeam Satellite Systems , 2019, 2019 IEEE Aerospace Conference.

[11]  Flor G. Ortiz-Gomez,et al.  Adaptive Resources Allocation for Flexible Payload enabling VHTS systems: Methodology and Architecture , 2019, Advances in Communications Satellite Systems Proceedings of The 36th International Communications Satellite Systems Conference (ICSSC-2018).

[12]  Charilaos I. Kourogiorgas,et al.  Optimal Capacity Allocation Strategies in Smart Gateway Satellite Systems , 2019, IEEE Communications Letters.

[13]  Weiming Xiang,et al.  Verification for Machine Learning, Autonomy, and Neural Networks Survey , 2018, ArXiv.

[14]  Giuseppe Cocco,et al.  Radio Resource Management Optimization of Flexible Satellite Payloads for DVB-S2 Systems , 2018, IEEE Transactions on Broadcasting.

[15]  A. Pablo Honold,et al.  Flexible Payload Operations of Satellite Communication Systems , 2018 .

[16]  Randy Paffenroth,et al.  Multiobjective Reinforcement Learning for Cognitive Satellite Communications Using Deep Neural Network Ensembles , 2018, IEEE Journal on Selected Areas in Communications.

[17]  Weidong Wang,et al.  Deep Reinforcement Learning Based Dynamic Channel Allocation Algorithm in Multibeam Satellite Systems , 2018, IEEE Access.

[18]  Pariwat Ongsulee,et al.  Artificial intelligence, machine learning and deep learning , 2017, 2017 15th International Conference on ICT and Knowledge Engineering (ICT&KE).

[19]  Randy Paffenroth,et al.  Multi-objective reinforcement learning-based deep neural networks for cognitive space communications , 2017, 2017 Cognitive Communications for Aerospace Applications Workshop (CCAA).

[20]  Srikanth Kandula,et al.  Resource Management with Deep Reinforcement Learning , 2016, HotNets.

[21]  Marina Ruggieri,et al.  Satellite communication and propagation experiments through the alphasat Q/V band Aldo Paraboni technology demonstration payload , 2016, IEEE Aerospace and Electronic Systems Magazine.

[22]  Y. Fujino,et al.  Development of Resource Allocation Re-construction Technology (Digital Beam Former and Digital Channelizer) , 2016 .

[23]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[24]  Sotiris B. Kotsiantis,et al.  Machine learning: a review of classification and combining techniques , 2006, Artificial Intelligence Review.

[25]  Rich Caruana,et al.  An empirical comparison of supervised learning algorithms , 2006, ICML.

[26]  Matti Tommiska,et al.  Efficient digital implementation of the sigmoid function for reprogrammable logic , 2003 .