A Performance Evaluation Platform for Mega Satellite Constellation Network

With the rapid development of satellite technology, mega satellite constellations have become a research hotspot. A large number of related techniques have been developed on orbit topology, network routing, energy balance and resource control. However, it is difficult to accurately compare the performance of similar studies due to differences in the means of validation. Especially for invulnerability studies in many military applications, a unified evaluation system is essential. This paper proposes a network evaluation system for mega satellite constellations. Evaluation parameters include orbit topology, communication network, energy balance and invulnerability. Different application algorithms and traffic models were used to validate the specific system. .

Reinforcement learning based dynamic distributed routing scheme for mega LEO satellite networks

Recently,mega Low Earth Orbit(LEO)Satellite Network(LSN)systems have gained more and more attention due to low latency,broadband communications and global coverage for ground users.One of the primary challenges for LSN systems with inter-satellite links is the routing strategy calculation and maintenance,due to LSN constellation scale and dynamic network topology feature.In order to seek an efficient routing strategy,a Q-learning-based dynamic distributed Routing scheme for LSNs(QRLSN)is proposed in this paper.To achieve low end-toend delay and low network traffic overhead load in LSNs,QRLSN adopts a multi-objective optimization method to find the optimal next hop for forwarding data packets.Experimental results demonstrate that the proposed scheme can effectively discover the initial routing strategy and provide long-term Quality of Service(QoS)optimization during the routing maintenance process.In addition,comparison results demonstrate that QRLSN is superior to the virtual-topology-based shortest path routing algorithm.

Sequential dynamic resource allocation in multi-beam satellite systems:A learning-based optimization method

Multi-beam antenna and beam hopping technologies are an effective solution for scarce satellite frequency resources.One of the primary challenges accompanying with Multi-Beam Satellites(MBS)is an efficient Dynamic Resource Allocation(DRA)strategy.This paper presents a learning-based Hybrid-Action Deep Q-Network(HADQN)algorithm to address the sequential decision-making optimization problem in DRA.By using a parameterized hybrid action space,HADQN makes it possible to schedule the beam pattern and allocate transmitter power more flexibly.To pursue multiple long-term QoS requirements,HADQN adopts a multi-objective optimization method to decrease system transmission delay,loss ratio of data packets and power consumption load simultaneously.Experimental results demonstrate that the proposed HADQN algorithm is feasible and greatly reduces in-orbit energy consumption without compromising QoS performance.

A compass time-space model-based virtual IP routing scheme for NTSN satellite constellations

Recently,Non-Terrestrial Satellite Networks(NTSTs)have gained more and more attentions due to global coverage,low latency,and high-speed communications.The routing scheme is one of the primary challenges for NTSNs,due to the mega scale of an NTSN constellation and the dynamic topology feature.To solve many pressing problems,a Compass time-space Model-based Virtual IP(CMVIP)routing scheme is proposed in this paper.In order to compensate for discontinuities in existing topology models,a compass-shaped time-space model is proposed.It can be adapted with Inter-Satellite-Link(ISL)and Ground-Satellite-Link(GSL)transmissions.A distributed algorithm with multiple optimization objectives and multiple constraints is applied for routing path discovery.To more realistically verify the specific scheme,a traffic model that supports two different services is proposed.Access and bearer services are the two main applications of an NTSN.Experimental results demonstrate that the proposed scheme achieves superior Qualityof-Service(QoS)performance.In addition,comparison results demonstrate that the CMVIP routing scheme is superior to the Virtual-Topology-based Shortest Path(VT-SP)routing algorithm.

Attitude Guidance Algorithms for Agile Satellite Dynamic Imaging

Dynamic imaging modes are increasingly crucial for agile satellites to perform complicated Earth observation tasks.In this study,a direct guidance algorithm is developed to calculate the reference attitude and velocity for dynamic imaging mode from target geolocation information while considering the constraints on both the satellite camera boresight axis and the image motion vector.The two slew angles are determined directly,and no rotation around the boresight or reference vector is required.The proposed approach employs a direct solution instead of the iterative process to obtain the reference attitude,which releases the onboard control system from the intensive computational load.To illustrate the performance of the proposed guidance algorithms,numerical simulation results are presented.