![]() Ortiz Gomez, Flor de Guadalupe ![]() in IEEE Transactions on Cognitive Communications and Networking (2022), 8(1), Very high throughput satellite (VHTS) systems are expected to have a huge increase in traffic demand in the near future. Nevertheless, this increase will not be uniform over the entire service area due to ... [more ▼] Very high throughput satellite (VHTS) systems are expected to have a huge increase in traffic demand in the near future. Nevertheless, this increase will not be uniform over the entire service area due to the non-uniform distribution of users and changes in traffic demand during the day. This problem is addressed by using flexible payload architectures, which allow the allocation of payload resources flexibly to meet the traffic demand of each beam, leading to dynamic resource management (DRM) approaches. However, DRM adds significant complexity to VHTS systems, so in this paper we discuss the use of one reinforcement learning (RL) algorithm and two deep reinforcement learning (DRL) algorithms to manage the resources available in flexible payload architectures for DRM. These algorithms are Q-Learning (QL), Deep Q-Learning (DQL) and Double Deep Q-Learning (DDQL) which are compared based on their performance, complexity and added latency. On the other hand, this work demonstrates the superiority a cooperative multiagent (CMA) decentralized distribution has over a single agent (SA). [less ▲] Detailed reference viewed: 40 (10 UL)![]() Ortiz Gomez, Flor de Guadalupe ![]() in IEEE Systems Journal (2021), 15(3), 4675-4686 Very high throughput satellite (VHTS) systems are expected to have a large increase in traffic demand in the near future. However, this increase will not be uniform throughout the service area due to the ... [more ▼] Very high throughput satellite (VHTS) systems are expected to have a large increase in traffic demand in the near future. However, this increase will not be uniform throughout the service area due to the nonuniform user distribution, and the changing traffic demand during the day. This problem is addressed using flexible payload architectures, enabling the allocation of the payload resources in a flexible manner to meet traffic demand of each beam, leading to dynamic resource management (DRM) approaches. However, DRM adds significant complexity to the VHTS systems, which is why in this article, we are analyzing the use of convolutional neural networks (CNNs) to manage the resources available in flexible payload architectures for DRM. The VHTS system model is first outlined, for introducing the DRM problem statement and the CNN-based solution. A comparison between different payload architectures is performed in terms of DRM response, and the CNN algorithm performance is compared by three other algorithms, previously suggested in the literature to demonstrate the effectiveness of the suggested approach and to examine all the challenges involved. [less ▲] Detailed reference viewed: 41 (7 UL)![]() Ortiz Gomez, Flor de Guadalupe ![]() in International Journal of Satellite Communications and Networking (2021) 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 ... [more ▼] 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. [less ▲] Detailed reference viewed: 41 (9 UL)![]() Chatzinotas, Symeon ![]() in International Journal of Satellite Communications and Networking (2016) Cognitive radio technologies have achieved in the recent years an increasing interest for the possible gain in terms of spectrum usage with respect to unshared approaches. While most of the attention has ... [more ▼] Cognitive radio technologies have achieved in the recent years an increasing interest for the possible gain in terms of spectrum usage with respect to unshared approaches. While most of the attention has been devoted to the cognitive coexistence between terrestrial systems, the coexistence between terrestrial and satellite communications is also seen as a viable option. Cognitive radio for satellite communications (CoRaSat) has been a European Commission seventh Framework Program project funded under the ICT Call 8. CoRaSat aimed at investigating, developing, and demonstrating cognitive radio techniques in satellite communication systems for flexible and dynamic spectrum access. In this paper, the CoRaSat cognitive approaches and techniques, investigated, developed, and demonstrated as most relevant to satellite communications, are described. In particular, the focus is on spectrum awareness, that is, database and spectrum sensing approaches, and on spectrum exploitation algorithms, that is, resource allocation and beamforming algorithms, to enable the use of spectrum for satellite communications using shared bands. [less ▲] Detailed reference viewed: 295 (12 UL)![]() Andrenacci, Stefano ![]() ![]() in Proceedings of 2016 8th Advanced Satellite Multimedia Systems Conference and the 14th Signal Processing for Space Communications Workshop (2016) The superframing option of the recent DVB-S2X standard specifies, for the so-called SF-Pilot fields, the use of the orthogonal set of Walsh-Hadamard (WH) sequences. In order to exploit this orthogonality ... [more ▼] The superframing option of the recent DVB-S2X standard specifies, for the so-called SF-Pilot fields, the use of the orthogonal set of Walsh-Hadamard (WH) sequences. In order to exploit this orthogonality, waveforms coming from different beams to the k-th User Terminal (UT) should be quasi perfectly aligned in time. While in the downlink part of a terrestrial system this is quite straightforward, in satellite system, having a satellite as a relay, this is not the case, especially when large baudrates are considered in the transmission. A procedure to compensate for timing misalignment amongst waveforms is here presented and the advantages are quantified through numerical simulations.In particular, Channel State Information (CSI) estimation errors, which are fundamental for precoding techniques, are evaluated. While the focus of the work is on systems which enable precoding techniques, the procedure can be applied in each scenario which uses the superframing structure of DVB-S2X in an interference limited scenario. [less ▲] Detailed reference viewed: 175 (39 UL)![]() Maleki, Sina ![]() ![]() in IEEE Communications Magazine (2015), 53(3), 24-29 Multibeam satellite networks in Ka band have been designed to accommodate the increasing traffic demands of the coming years. However, these systems are spectrum limited due to the current spectrum ... [more ▼] Multibeam satellite networks in Ka band have been designed to accommodate the increasing traffic demands of the coming years. However, these systems are spectrum limited due to the current spectrum allocation policies. This paper investigates the potentials of applying cognitive radio techniques in satellite communications in order to increase the spectrum opportunities for future generation of satellite networks without interfering operation of incumbent services. These extra spectrum opportunities can potentially amount to 2.4 GHz of bandwidth in downlink, and to 2 GHz of bandwidth in uplink for high density fixed satellite services (HDFSS). [less ▲] Detailed reference viewed: 370 (19 UL)![]() ; ; et al in European Conference on Networks and Communications (EuCNC), Paris, France, Jun 2015. (2015) Detailed reference viewed: 103 (3 UL)![]() Maleki, Sina ![]() ![]() ![]() in 32nd AIAA International Communications Satellite Systems Conference, August 2014 (2014, August) The satellite communication data traffic is increasing dramatically over the coming years. High throughput multibeam satellite networks in Ka band are potentially able to accommodate the upcoming high ... [more ▼] The satellite communication data traffic is increasing dramatically over the coming years. High throughput multibeam satellite networks in Ka band are potentially able to accommodate the upcoming high data rate demands. However, there is only 500 MHz of exclusive band for download and the same amount for upload. This spectrum shortage impose a barrier in order to satisfy the increasing demands. Cognitive satellite communication in Ka band is considered in this paper in order to potentially provide an additional 4.4 GHz bandwidth for downlink and uplink fixed-satellite-services. In this way, it is expected that the problem of spectrum scarcity for future generation of satellite networks is alleviated to a great extent. The underlying scenarios and enabling techniques are discussed in detail, and finally we investigate the implementation issues related to the considered techniques. [less ▲] Detailed reference viewed: 267 (19 UL)![]() ; ; et al in Proc. European Conference on Networks and Communications (EuCNC) (2014, June) Detailed reference viewed: 375 (8 UL)![]() ; ; et al in 9th International Conference on Cognitive Radio Oriented Wireless Networks and Communications (CROWNCOM), 2014 (2014, June) During the last years, spectrum scarcity has become one of the major issues for the development of new communication systems. Cognitive Radio (CR) approaches have gained an ever increasing attention from ... [more ▼] During the last years, spectrum scarcity has become one of the major issues for the development of new communication systems. Cognitive Radio (CR) approaches have gained an ever increasing attention from system designers and operators, as they promise a more efficient utilization of the available spectral resources. In this context, while the application of CRs in terrestrial scenarios has been widely considered from both theoretical and practical viewpoints, their exploitation in satellite communications is still a rather unexplored area. In this paper, we address the definition of several satellite communications scenarios, where cognitive radio techniques promise to introduce significant benefits, and we discuss the major enablers and the associated challenges [less ▲] Detailed reference viewed: 208 (7 UL) |
||