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.

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.

Peridynamic Meso-scale Modeling for Degradation in Transverse Mechanical Properties of Composites with Micro-void Defects

The effect of micro-void on transverse stiffness and strength for fiber-reinforced composites subjected to load perpendicular to fiber is studied using the state-based peridynamic(PD)theory.The heterogeneous microstructure with micro-voids are discretized with irregular and non-uniform grids on mesoscale.The PD representative volume element with randomly distributed and sized micro-voids has been established with periodic boundary conditions.A parametric study was performed to evaluate the effects of void fraction and void size on transverse properties.It was found that the transverse modulus decreases with the void fraction in the range of 0.5–2%.A smaller void has a greater impact on the transverse modulus than a larger void under the same void content.The crack growth path for the multi-fiber model subjected to transverse tension was analyzed.The PD predictions show that cracks initiate at the interface between fiber and matrix,then deflect to the micro-voids nearby.The PD predictions match well with the analytical and experimental observations available in the literature.

Meso-Scale Modeling for Effective Properties in Continuous Fiber-Reinforced Composites by State-Based Peridynamics

This study demonstrates a homogenization approach via a modified state-based peridynamic(PD)method to predict the effective elastic properties of composite materials with periodic microstructure.The procedure of modeling the PD unit cell(UC)of continuous fiber-reinforced composite is presented.Periodic boundary conditions are derived and implemented through the Lagrange multiplier method.A matrix-dominated approach for modeling the interphase properties between dissimilar materials is proposed.The periodicity and continuity assumptions are employed to determine the stress and strain fields,as well as the effective elastic properties.The PD-UCs of square and hexagonal packs as well as the 0/90 laminate microstructure are modeled and compared with the analytical,numerical and experimental results from the literature.Good agreement of predicted effective properties can be observed.Unlike other PD homogenization approaches,the effective material properties can be directly and individually obtained from simple loading conditions.