Figure - available from: EURASIP Journal on Wireless Communications and Networking
This content is subject to copyright. Terms and conditions apply.
Source publication
Low earth orbit (LEO) satellite communication networks require huge load capacity and information processing speed to carry global communication traffic. Inter-satellite links and the on-board processing are the key technologies to achieve this goal, but the new network architecture leads to great challenges on satellite routing. This paper designs...
Similar publications
In order to improve the ability of power communication technology to support large-scale and massive services of smart electricity consumption, this paper designs a sensing model to collect information on new energy electricity consumption. Using the arrival rate calculation method of intelligent IoT, the information on new energy electricity users...
Citations
... Collaborative Q) [18], it selects precomputed optimal paths. On the other hand, distributed deep reinforcement learning algorithms are based on improvements to the Q-routing foundation [19], [20]. For the first method, there is usually an issue of insufficient scalability. ...
... JOURNAL OF L A T E X CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 19 1) The Architecture of Graph Neural Networks Graph Neural Networks (GNNs) extend the concepts of Deep Learning from data defined on regular grid structures (like images, audio, and texts) to irregular structures, particularly graph data. The main idea behind GNNs is to learn a function that can map the graph's input features to output features at nodes or links, or the entire graph. ...
The integration of Software-Defined Networking (SDN) and Artificial Intelligence (AI) presents promising opportunities for managing and optimizing LEO satellite network routing. However, as the scale and coverage of satellite networks continue to expand, challenges are posed to both centralized and distributed architectures in terms of managing network information and coping with routing complexity. To overcome these challenges, leveraging distributed SDN technology, a stigmergy multi-agent hierarchical deep reinforcement learning routing algorithm is proposed in multi-domain collaborative satellite networks. A pheromone-based mechanism is incorporated to facilitate collaboration during independent training, and hierarchical control is employed to decouple the complexity of cross-domain routing decisions. Simulation results demonstrate that our proposed algorithm exhibits good scalability and performance in large-scale satellite networks.
... Recently, telecommunication industrial companies including SpaceX, Telesat, and OneWeb have shown a growing interest in LEO satellite constellations due to their worldwide connectivity benefits and the scarcity of orbital resources [133]. For example, Starlink is planning to launch 12,000 with a possible extension to 42,000 satellites [134] and Oneweb is planning a network of 643 satellites with 30 satellites planned for resiliency and redundancy [135]. The satellite constellation is equipped with four ISLs, facilitating communication both within and across planes. ...
... Hence, it becomes essential for designers of satellite constellations to devise proficient routing algorithms to allocate and optimize the usage of available resources effectively. In the current literature, various studies have proposed different routing strategies in satellite constellations with ISL [134], [144]- [147]. In order to satisfy the QoS demands of various communication services, a QoS-aware routing algorithm (QoSRA) was proposed in [148]. ...
High throughput satellites (HTS), with their digital payload technology, are expected to play a key role as enablers of the upcoming 6G networks. HTS are mainly designed to provide higher data rates and capacities. Fueled by technological advancements including beamforming, advanced modulation techniques, reconfigurable phased array technologies, and electronically steerable antennas, HTS have emerged as a fundamental component for future network generation. This paper offers a comprehensive state-of-the-art of HTS systems, with a focus on standardization, patents, channel multiple access techniques, routing, load balancing, and the role of software-defined networking (SDN). In addition, we provide a vision for next-satellite systems that we named as extremely-HTS (EHTS) toward autonomous satellites supported by the main requirements and key technologies expected for these systems. The EHTS system will be designed such that it maximizes spectrum reuse and data rates, and flexibly steers the capacity to satisfy user demand. We introduce a novel architecture for future regenerative payloads while summarizing the challenges imposed by this architecture. Index Terms-High throughput satellites (HTS), load balancing , quality of service (QoS), routing, scheduling, software-defined network (SDN). ABBREVIATIONS 3GPP 3 rd generation partnership project BH Beam hopping CDMA Code division multiple access CR Cognitive radio CSI Channel state information DL Deep Learning DRA Dynamic resource allocation DRL Deep reinforcement learning DVB Digital video broadcasting ETSI European telecommunications standards institute FDMA Frequency division multiple access GEO Geostationary Earth orbit HAPS High-altitude platform stations HTS High throughput satellites ISL Inter-satellite links
... [11] seek to maximize the weighted number of completed tasks subject to constraints related to the movements of the space robots, refueling depots, and tasks. Similarly, several other studies present different algorithm for the problems [12][13] [14][15]. ...
Optimizing satellite routes for multiple space debris collection and multiple on-orbit servicing can be a very complex problem due to the large number of variables and constraints that need to be taken into account. Factors such as the location and movement of the debris and servicing targets in the orbit, the capabilities of the satellite, and the constraints on the satellite's fuel and power usage all need to be considered. Additionally, the problem may be further complicated by the need to consider multiple objectives, such as minimizing fuel usage while maximizing debris collection or servicing coverage. Classical approach to solve this problem includes heuristics and metaheuristics methods like Genetic Algorithm, Particle Swarm Optimization, Ant Colony Optimization and mixed-integer programming. In the current paper, we plan to implement Quantum annealing based algorithm for optimizing satellite routes. It is a quantum computing method that can be used to optimize satellite routes. The principle behind quantum annealing is to use quantum-mechanical effects to find the global minimum of a function. In the context of satellite routing, this function would represent the cost or energy required for a satellite to travel a certain route. The satellite's routes would be represented by variables in the function, and the quantum annealer would use quantum-mechanical effects to search for the lowest-energy route, which would correspond to the optimal path for the satellite to take. We plan to use Ising model to implement quantum annealing for satellite routing. It can used to represent the cost function as a set of binary variables interacting with each other through pairwise interactions. The interactions between the variables would represent the different constraints and objectives of the routing problem, such as fuel usage and debris collection. The goal would be to find the configuration of variables that minimizes the cost function, which corresponds to the optimal satellite route. A complete mathematical model will be generated, and numerical analysis will be performed based on the presented technique.
... Two papers on communication and routing strategies are listed as follows: (1) "Asynchronous dissipative control for networked time-delay Markov jump systems with the event-triggered scheme and packet dropouts, " by Chen et al. [17]; (2) "LEO laser microwave hybrid inter-satellite routing strategy based on modified Q-routing algorithm, " by Zheng et al. [18]. Detailed information of each article could be found in [17,18]. ...
... Two papers on communication and routing strategies are listed as follows: (1) "Asynchronous dissipative control for networked time-delay Markov jump systems with the event-triggered scheme and packet dropouts, " by Chen et al. [17]; (2) "LEO laser microwave hybrid inter-satellite routing strategy based on modified Q-routing algorithm, " by Zheng et al. [18]. Detailed information of each article could be found in [17,18]. ...
... In recent years, with the continuous development of demand for new cloud computing services such as AI and big data, especially the extensive application of deep learning, higher requirements have been put forward for the computing ability of servers deployed in the cloud [1][2][3]. Affected by the physical design limit and energy consumption control, the traditional single computing unit with CPU can no longer meet the growing demand for diverse cloud requirements [4][5]. As the demand for computing power in various fields continues to increase, various hardware chip products have been launched for different computing scenario applications, such as GPUs for image processing [6][7], FPGAs for highperformance computing [8], NPUs for neural network based training [9], and DPUs for data processing [10]. ...
With the development of intelligent applications, simply relying on traditional single type of computing unit cannot efficiently satisfy diverse cloud requirements. The emergence of heterogeneous computing can efficiently achieve the adaptation of these intelligent applications by using different types of processing units such as Graphics Processing Unit (GPU) and Field Programmable Gate Array (FPGA). However, the trade-off between profit and costs in the process of scheduling heterogeneous computing resources is also an issue worthy of attention. To address this challenge, this work establishes a heterogeneous computing resource scheduling model based on Stackelberg differential game, which includes three roles Computing Power Trading Platforms (CPTPs), Heterogeneous Computing Service Providers (HCSPs), and Heterogeneous Computing Application Providers (HCAPs). The objective is to maximize utility function of CPTPs and HCSPs subject to rental ratio, pricing strategy and energy consumption of resource scheduling, which has proved that there exists a Stackelberg Nash Equilibrium (NE) solution. The Support Vector Machine based on Artificial Fish (SVM-AF) is proposed to predict the access times of heterogeneous computing applications. In addition, the distributed iteration method and Cauchy distribution is adopted to optimize the computing price strategy and improve its convergence performance. The simulation results show that compared with other strategies, the proposed strategy can effectively improve computing revenue of user experience and while reducing energy consumption in the process of resource scheduling.
