The virtual network embedding/mapping problem is an important issue in network virtualization in Software-Defined Networking(SDN).It is mainly concerned with mapping virtual network requests,which could be a set of SD...The virtual network embedding/mapping problem is an important issue in network virtualization in Software-Defined Networking(SDN).It is mainly concerned with mapping virtual network requests,which could be a set of SDN flows,onto a shared substrate network automatically and efficiently.Previous researches mainly focus on developing heuristic algorithms for general topology virtual network.In practice however,the virtual network is usually generated with specific topology for specific purpose.Thus,it is a challenge to optimize the heuristic algorithms with these topology information.In order to deal with this problem,we propose a topology-cognitive algorithm framework,which is composed of a guiding principle for topology algorithm developing and a compound algorithm.The compound algorithm is composed of several subalgorithms,which are optimized for specific topologies.We develop star,tree,and ring topology algorithms as examples,other subalgorithms can be easily achieved following the same framework.The simulation results show that the topology-cognitive algorithm framework is effective in developing new topology algorithms,and the developed compound algorithm greatly enhances the performance of the Revenue/Cost(R/C) ratio and the Runtime than traditional heuristic algorithms for multi-topology virtual network embedding problem.展开更多
Satellite networks have many advantages over traditional terrestrial networks.However,it is very difficult to design a satellite network with excellent performance.The paper briefly summarizes some existing satellite ...Satellite networks have many advantages over traditional terrestrial networks.However,it is very difficult to design a satellite network with excellent performance.The paper briefly summarizes some existing satellite network routing technologies from the perspective of both single-layer and multilayer satellite constellations,and focuses on the main ideas,characteristics,and existing problems of these routing technologies.For single-layer satellite networks,two routing strategies are discussed,virtual node strategy and virtual topology strategy.Moreover,considering the deficiency of existing multilayer satellite network routing,we discuss the topic invulnerability.Finally,the challenges and problems faced by the satellite network are analyzed and the trend of future development is predicted.展开更多
针对大规模卫星高精度编队控制问题,提出了一种基于吸引法则的深度确定性策略梯度控制方法(attraction-based deep deterministic policy gradient,ADDPG)。首先阐述了超立方体拓扑编队拓扑构型特性,建立了卫星编队动力学模型,设计了超...针对大规模卫星高精度编队控制问题,提出了一种基于吸引法则的深度确定性策略梯度控制方法(attraction-based deep deterministic policy gradient,ADDPG)。首先阐述了超立方体拓扑编队拓扑构型特性,建立了卫星编队动力学模型,设计了超立方体卫星编队虚拟中心用于衡量编队整体飞行状态。为解决无模型深度强化学习的探索和扩展平衡问题,设计了ε-imitation动作选择策略方法,最终提出了基于ADDPG的卫星编队控制策略。算法不依赖于环境模型,通过充分利用已有信息,可以降低学习模型初期探索过程中的盲目试错。仿真结果表明ADDPG策略以较少的能量消耗达到更高的精度,相比知名算法在加快编队收敛速度的同时,误差减少5%以上,能量消耗减少7%以上,验证了算法的有效性。展开更多
文摘The virtual network embedding/mapping problem is an important issue in network virtualization in Software-Defined Networking(SDN).It is mainly concerned with mapping virtual network requests,which could be a set of SDN flows,onto a shared substrate network automatically and efficiently.Previous researches mainly focus on developing heuristic algorithms for general topology virtual network.In practice however,the virtual network is usually generated with specific topology for specific purpose.Thus,it is a challenge to optimize the heuristic algorithms with these topology information.In order to deal with this problem,we propose a topology-cognitive algorithm framework,which is composed of a guiding principle for topology algorithm developing and a compound algorithm.The compound algorithm is composed of several subalgorithms,which are optimized for specific topologies.We develop star,tree,and ring topology algorithms as examples,other subalgorithms can be easily achieved following the same framework.The simulation results show that the topology-cognitive algorithm framework is effective in developing new topology algorithms,and the developed compound algorithm greatly enhances the performance of the Revenue/Cost(R/C) ratio and the Runtime than traditional heuristic algorithms for multi-topology virtual network embedding problem.
基金This work is supported by the National Natural Science Foundation of China(Nos.61572435,61472305,61473222)the Natural Science Foundation of Shaanxi Province(Nos.2015JZ002,2015JM6311)+1 种基金the Natural Science Foundation of Zhejiang Province(No.LZ16F020001)Programs Supported by Ningbo Natural Science Foundation(No.2016A610035).
文摘Satellite networks have many advantages over traditional terrestrial networks.However,it is very difficult to design a satellite network with excellent performance.The paper briefly summarizes some existing satellite network routing technologies from the perspective of both single-layer and multilayer satellite constellations,and focuses on the main ideas,characteristics,and existing problems of these routing technologies.For single-layer satellite networks,two routing strategies are discussed,virtual node strategy and virtual topology strategy.Moreover,considering the deficiency of existing multilayer satellite network routing,we discuss the topic invulnerability.Finally,the challenges and problems faced by the satellite network are analyzed and the trend of future development is predicted.
文摘针对大规模卫星高精度编队控制问题,提出了一种基于吸引法则的深度确定性策略梯度控制方法(attraction-based deep deterministic policy gradient,ADDPG)。首先阐述了超立方体拓扑编队拓扑构型特性,建立了卫星编队动力学模型,设计了超立方体卫星编队虚拟中心用于衡量编队整体飞行状态。为解决无模型深度强化学习的探索和扩展平衡问题,设计了ε-imitation动作选择策略方法,最终提出了基于ADDPG的卫星编队控制策略。算法不依赖于环境模型,通过充分利用已有信息,可以降低学习模型初期探索过程中的盲目试错。仿真结果表明ADDPG策略以较少的能量消耗达到更高的精度,相比知名算法在加快编队收敛速度的同时,误差减少5%以上,能量消耗减少7%以上,验证了算法的有效性。
