Fig 1 - uploaded by Nariman Torkzaban
Content may be subject to copyright.
Contexts in source publication
Context 1
... integrated satellite-terrestrial networks (ISTNs) can be a cornerstone to the realization of a heterogeneous global system to enhance the end-user experience [3]. An ISTN, as depicted in Fig. 1, is composed of satellites organized in a constellation that support routing, adaptive access control, and spot-beam management [4], whereas the terrestrial optical network consists of ground stations (gateways), switches, and servers. Delay-sensitive data services are more suitable to transport in the low earth orbit (LEO) satellite ...
Context 2
... ISTN network under our study is depicted in Fig. 1.We model the terrestrial network as an undirected G = (V, E) graph where (u, v) ∈ E if there is a link between the nodes u, v ∈ V . Let J ⊆ V be the set of all potential nodes for gateway placement and I ⊆ V be the set of all demand points. We note that the sets I and J are not necessarily disjoint. A typical substrate node v ∈ V may ...
Context 3
... integrated satellite-terrestrial networks (ISTNs) can be a cornerstone to the realization of a heterogeneous global system to enhance the end-user experience [3]. An ISTN, as depicted in Fig. 1, is composed of satellites organized in a constellation that support routing, adaptive access control, and spot-beam management [4], whereas the terrestrial optical network consists of ground stations (gateways), switches, and servers. Delay-sensitive data services are more suitable to transport in the low earth orbit (LEO) satellite ...
Context 4
... ISTN network under our study is depicted in Fig. 1.We model the terrestrial network as an undirected G = (V, E) graph where (u, v) ∈ E if there is a link between the nodes u, v ∈ V . Let J ⊆ V be the set of all potential nodes for gateway placement and I ⊆ V be the set of all demand points. We note that the sets I and J are not necessarily disjoint. A typical substrate node v ∈ V may ...
Similar publications
People can learn new sensory skills that augment their perception, such as human echolocation. However, it is not clear to what extent these can become an integral part of the perceptual repertoire. Can they show automatic use, integrated with the other senses, or do they remain cognitively-demanding, cumbersome, and separate? Here, participants le...
Citations
... In addition, the challenges that arise while attempting to maintain coverage continuity while simultaneously fulfilling predetermined angular separation requirements for the beams of the same antenna have been brought to light. [62] Routing for satellite networks suggested program for mixed integer programs to deal with the issue of controller placement in conjunction with the positioning of satellite gateways while keeping in mind various design strategies such as cross-layer data transfer, load balancing, dependability, and latency optimization. ...
The potential for service continuity across uncovered and under-covered regions, service ubiquity, and service
scalability are all offered by Satellite Communication (SC) for the recent decade. However, to take advantage of these
benefits, it is necessary to address several obstacles first. This is because the management of resource, control and
security of network, the efficient utilization of spectrum, and efficient utilization of satellite-based communication
networks are more difficult to accomplish than those of Terrestrial Networks (TNs). Thereby, Artificial Intelligence (AI),
which encompasses Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL), has been
continuously expanding as an area of study and has shown good outcomes in a variety of applications, including wireless
communication. As a consequence of this, several publications put forth a variety of algorithmic solutions to the problem
involving the management of various applications for SCs. Such an algorithm will employ various DL methods to
improve the effectiveness of SCs. As a consequence of this, the aim of this paper is to provide an exhaustive overview of
the utilization of various AI methods for a broad aspect of SCs. Following this, a general overview of the most recent
details related to various AI methods and their related classifications will be presented. In addition, the study provides a
summary of the many bodies of research that apply AI-based approaches to the resolution of satellite-related problems. In
addition to this, AI may also be used to spot trends in satellite traffic and utilize bandwidth more effectively,
making better use of the resources.
... In addition, the challenges that arise while attempting to maintain coverage continuity while simultaneously fulfilling predetermined angular separation requirements for the beams of the same antenna have been brought to light. [62] Routing for satellite networks suggested program for mixed integer programs to deal with the issue of controller placement in conjunction with the positioning of satellite gateways while keeping in mind various design strategies such as cross-layer data transfer, load balancing, dependability, and latency optimization. ...
... These algorithms aim to minimise the network's size while ensuring the target link availabilities due to cloud blockage. A joint strategy for GSD and routing network is proposed in [418] for satellite-terrestrial integration. CARAMUEL project [419] presents the GSD considering ground network with Quantum Key Distribution in GEO satellites. ...
This paper surveys the application and development of Artificial Intelligence (AI) in Satellite Communication (SatCom) and Non-Terrestrial Networks (NTN). We first present a comprehensive list of use cases, the relative challenges and the main AI tools capable of addressing those challenges. For each use case, we present the main motivation, a system description, the available non-AI solutions and the potential benefits and available works using AI. We also discuss the pros and cons of an on-board and on-ground AI-based architecture, and we revise the current commercial and research activities relevant to this topic. Next, we describe the state-of-the-art hardware solutions for developing ML in real satellite systems. Finally, we discuss the long-term developments of AI in the SatCom and NTN sectors and potential research directions. This paper provides a comprehensive and up-to-date overview of the opportunities and challenges offered by AI to improve the performance and efficiency of NTNs.
... In Ref. [5], a software defined network (SDN) based framework which leveraged multi-layered satellites was proposed for integrated satellite-terrestrial networks (ISTN). The authors in Ref. [6] proposed an SDN/NFV based framework for ISTN. Based on that, they proposed an algorithm to achieve flexible routing and to fulfill QoS requirements simultaneously. ...
... To further show the reserch status of NEP, we have summarized related works in Table 1. Although many researches have already studied SAGIN architectures and NEP [1][2][3][4][5][6][7][8][9][10][11] , there still lacks a comprehensive tutorial focusing on explaining NEP in SAGIN. In this regard, we study NEP in SAGIN from three aspects, i.e., RAN, CN and end-to-end BN, where specific NF characteristics are also analyzed. ...
With the demand for Internet connectivity in remote areas, the space‐air‐ground integrated network (SAGIN) was proposed to achieve ubiquitous coverage and enhance service capabilities of extant terrestrial networks. The paradigm of virtual network element placement (NEP) is applied into SAGIN. It can save energy and operating costs by placing specific network elements (NEs) as software instances. In addition, it helps to provide services in end‐to‐end networks with its ability to allocate and manage resources flexibly. However, NEP faces some challenges in SAGIN. The network topologies can be dynamic, and links such as the satellite‐to‐ground and air‐to‐ground ones are prone to fail. These will make NEP management more complicated. Moreover, the static NEP schemes are hard to accommodate the time‐varying traffic. In this context, this work explains the NEP problem in SAGIN from three aspects, i.e., the SAGIN radio access network (RAN), the SAGIN core network (CN), and the SAGIN barrier network (BN). First, the physical and networking architectures of SAGIN are introduced. Then the status of the network element placement and corresponding challenges are described from these two aspects. Finally, this paper discusses future research directions and key technical challenges.
... The research topic has attracted increasing attentions. Torkzaban et al. [12] pointed out that the inclusion of plug-andplay SatCom solutions are investigated, primarily in the context of 5G. Technologies such as SDN is exploited to support a more agile integration of terrestrial and satellite domains. ...
Traditional satellite networks have problems with their service provision method which makes it difficult to keep pace with emerging technologies in the terrestrial networks, such as 5G. Service Function Chain (SFC) is a good choice to enable flexible service provision for different applications. SFC can be used in satellite networks. However, the challenge is how to select Service Function Path (SFP) considering the characteristics of multi-layer satellite networks. In this paper, we model the problem of SFP selection in Multi-layer satellite networks (SFPM) and propose a path selection algorithm, Objective Weight-based Path Selection (OWPS). OWPS is designed based on objective weights considering dynamic topology and link parameters. Then, we propose OWPS-based algorithms under different networking rules to select SFP in multi-layer satellite networks and compare them with the benchmark algorithms. Simulation results show the performance of our proposed algorithms in terms of hops, connection time, handover times, packet loss rate, delay, request acceptance ratio, and resource utilization. Finally, we summarize the applicable conditions for the algorithms.
... The scarce literature on beam and gateway routing mainly focuses on how to route users to gateways in order to minimize delay. While most studies suggest non-AI load balancing solutions (Torkzaban et al. 2020;Yang et al. 2016), some authors have proposed GA (Rao and Wang 2011) and Q-Learning (Gong et al. 2020) frameworks in the context of highly-varying environments. ...
The next generation of satellite constellations is designed to better address the future needs of our connected society: highly-variable data demand, mobile connectivity, and reaching more under-served regions. Artificial Intelligence (AI) and learning-based methods are expected to become key players in the industry, given the poor scalability and slow reaction time of current resource allocation mechanisms. While AI frameworks have been validated for isolated communication tasks or subproblems, there is still not a clear path to achieve fully-autonomous satellite systems. Part of this issue results from the focus on subproblems when designing models, instead of the necessary system-level perspective. In this paper we try to bridge this gap by characterizing the system-level needs that must be met to increase satellite autonomy, and introduce three AI-based components (Demand Estimator, Offline Planner, and Real Time Engine) that jointly address them. We first do a broad literature review on the different subproblems and identify the missing links to the system-level goals. In response to these gaps, we outline the three necessary components and highlight their interactions. We also discuss how current models can be incorporated into the framework and possible directions of future work.
... Zhang et al. [33] used edge computing techniques to improve the QoS of STINs. In order to reduce the cost of gateway deployment and data routing in STINs, the authors in [34] proposed a joint satellite gateway deployment and routing scheme. Xu et al. [35] proposed a hybrid routing algorithm to realize the seamless integration of STINs. ...
Satellite-terrestrial integrated network (STIN) is an indispensable component of the Next Generation Internet (NGI) due to its wide coverage, high flexibility, and seamless communication services. It uses the part of satellite network to provide communication services to the users who cannot communicate directly in terrestrial network. However, existing satellite routing algorithms ignore the users’ request resources and the states of the satellite network. Therefore, these algorithms cannot effectively manage network resources in routing, leading to the congestion of satellite network in advance. To solve this problem, we model the routing problem in satellite network as a finite-state Markov decision process and formulate it as a combinatorial optimization problem. Then, we put forth a Q-learning-based routing algorithm (QLRA). By maximizing users’ utility, our proposed QLRA algorithm is able to select the optimal paths according to the dynamic characteristics of satellite network. Considering that the convergence speed of QLRA is slow due to the routing loop or ping-pong effect in the process of routing, we propose a split-based speed-up convergence strategy and also design a speed-up Q-learning-based routing algorithm, termed SQLRA. In addition, we update the Q value of each node from back to front in the learning process, which further accelerate the convergence speed of SQLRA. Experimental results show that our improved routing algorithm SQLRA greatly enhances the performance of satellite network in terms of throughput, delay, and bit error rate compared with other routing algorithms.
... Torkzaban et al (2020) [21] also suggested a joint satellite gateway placement and routing approach for the terrestrial network to reduce the overall cost of gateway deployment and traffic routing, while meeting the average delay requirement for traffic needs. [22] proposed the integration of satellite and LTE network framework for both infrastructure-based and infrastructure-less scenarios. ...
Cellular networks are anticipated to handle a significant increase in data traffic, as well as a huge number of devices and new use cases in the very near future; therefore, future 5G networks are being built with heterogeneity in mind. The user's device will be able to connect to the network using 5G and other technologies such as LTE, WiMAX, WiFi, Satellite, etc. Satellite Communication (SatCOM), on the other hand, has been proposed as a network of choice to supplement the 5G use cases. In most of 5G's use cases, satellite communication would provide a complimentary service for global coverage, critical communication, broadcast/multicast provision, and multimedia traffic growth. Hence, for these connections to operate effectively, a smooth transmission between 5G and satellite is needed. However, in a heterogeneous wireless network, a major issue is determining how to assign a user to the best Radio Access Technology (RAT). An intelligent hybrid RAT selection algorithm based on machine learning is proposed in this paper. The User Terminal is trained to select the necessary RAT to admit its call using the Actor-Critic Reinforcement Learning Algorithm. Based on the simulation results, the proposed algorithm has the ability to learn in a competent way to successfully manage resource management autonomously and therefore increases the user's quality of service (QoS). The algorithm also showed better expected total reward, lower call blocking probability and higher throughput when compared with a Markov Reward-Based Greedy Algorithm.
... Our approach to solve this problem is sequential. In [1], we formulated the satellite gateway placement problem while also optimizing the traffic routing. In this paper, we model and solve the SDN controller placement problem in 5G-satellite hybrid networks. ...
... Table II lists the range of failure probabilities in different cases for each network component. The placement of gateways is already given according to [1]. To solve the MILP models we use CPLEX commercial solver, and conduct all the experiments on an Intel Xeon processor at 3.5 GHz and 16 GB of main memory. ...
SDN-enabled Integrated satellite-terrestrial networks (ISTNs), can provide several advantages including global seamless coverage, high reliability, low latency, etc. and can be a key enabler towards next generation networks. To deal with the complexity of the control and management of the integrated network, leveraging the concept of software-defined networking (SDN) will be helpful. In this regard, the SDN controller placement problem in SDN-enabled ISTNs becomes of paramount importance. In this paper, we formulate an optimization problem for the SDN controller placement with the objective of minimizing the average failure probability of SDN control paths to ensure the SDN switches receive the instructions in the most reliable fashion. Simultaneously, we aim at deploying the SDN controllers close to the satellite gateways to ensure the connection between the two layers occurs with the lowest latency. We first model the problem as a mixed integer linear program (MILP). To reduce the time complexity of the MILP model, we use submodular optimization techniques to generate near-optimal solutions in a time-efficient manner. Finally, we verify the effectiveness of our approach by means of simulation, showing that the approximation method results in a reasonable optimality gap with respect to the exact MILP solution.
... In [9], this issue is mitigated to some extent as the authors take into account the capacity constraints of satellite links and formulate a problem towards maximizing the average reliability which they solve using a greedy algorithm. In [11], a joint gateway placement and traffic routing is formulated as an instance of the capacitated facility location-routing problem which does not make any assumption on the optimal number of gateways, and also provides a routing solution that does not contradict the capacity constraints and is not limited to the shortest paths using multi-commodity flow allocation. ...
... The propagation latency of a path in the network is the sum of the propagation delays over its constituting links. A GEO satellite is considered in the particular system model similar to [8], [9], [10], and [11]. Let d uv represent the contribution of the terrestrial link (u, v) to the propagation delay of a path which contains that link. ...
... Similar to [11], for our simulations, we utilize multiple real network topologies publicly available at the Internet Topology Zoo [30]. In addition to the previous topologies used in [11] we use 4 new networks to be able to compare the performance of our algorithms to that of the literature. ...
Several challenging optimization problems arise while considering the deployment of the space-air-ground integrated networks (SAGINs), among which the optimal satellite gateway deployment problem is of significant importance. Moreover, with the increasing interest in the software-defined integration of 5G networks and satellites, the existence of an effective scheme for optimal placement of SDN controllers is essential. In this paper, we discuss the interrelation between the two problems above and propose suitable methods to solve them under various network design criteria. We first provide a MILP model for solving the joint problem, and then motivate the decomposition of the model into two disjoint MILPs. We then show that the resulting problems can be modeled as the optimization of submodular set functions and can be solved efficiently with provable optimality gaps.
