In this paper, the requirements of routing due to the multimedia applications are briefly discussed. In order to solve the QoS constrained routing effectively and efficiently, the scheme of routing based on Hopfield n...In this paper, the requirements of routing due to the multimedia applications are briefly discussed. In order to solve the QoS constrained routing effectively and efficiently, the scheme of routing based on Hopfield neural network is proposed after the analysis of related work. Then the QoS routing algorithm for unicast based on Hopfield NN is described and the result of emulation is given. At last, multicast QoS routing considerations based on Hopfield NN are proposed.展开更多
Fueled by the explosive growth of ultra-low-latency and real-time applications with specific computing and network performance requirements,the computing force network(CFN)has become a hot research subject.The primary...Fueled by the explosive growth of ultra-low-latency and real-time applications with specific computing and network performance requirements,the computing force network(CFN)has become a hot research subject.The primary CFN challenge is to leverage network resources and computing resources.Although recent advances in deep reinforcement learning(DRL)have brought significant improvement in network optimization,these methods still suffer from topology changes and fail to generalize for those topologies not seen in training.This paper proposes a graph neural network(GNN)based DRL framework to accommodate network trafic and computing resources jointly and efficiently.By taking advantage of the generalization capability in GNN,the proposed method can operate over variable topologies and obtain higher performance than the other DRL methods.展开更多
The problem of constructing minimum cost multicast trees with end to end delay and delay variation constraints to meet the quality of service requirements in high speed packet switched environments is studied in t...The problem of constructing minimum cost multicast trees with end to end delay and delay variation constraints to meet the quality of service requirements in high speed packet switched environments is studied in this paper. The routing problem of the bounded delay along the paths from the source to each destination and the bounded variation among the delays along these paths is disussed, and then a new algorithm based on Hopfield neural networks to optimize the multicast tree with delay and variation constraints is presented. The simulations show that the proposed algorithm achieves its best performance in high speed computer networks.展开更多
A novel approximation algorithm was proposed for the problem of finding the minimum total cost of all routes in Capacity Vehicle Routing Problem (CVRP). CVRP can be partitioned into three parts: the selection of vehic...A novel approximation algorithm was proposed for the problem of finding the minimum total cost of all routes in Capacity Vehicle Routing Problem (CVRP). CVRP can be partitioned into three parts: the selection of vehicles among the available vehicles, the initial routing of the selected fleet and the routing optimization. Fuzzy C-means (FCM) can group the customers with close Euclidean distance into the same vehicle according to the principle of similar feature partition. Transiently chaotic neural network (TCNN) combines local search and global search, possessing high search efficiency. It will solve the routes to near optimality. A simple tabu search (TS) procedure can improve the routes to more optimality. The computations on benchmark problems and comparisons with other results in literatures show that the proposed algorithm is a viable and effective approach for CVRP.展开更多
针对无线Mesh网络组播中包丢失严重的问题,提出了保持包的IP层不变,而改变包的目的MAC域,进而MAC层以单播形式向组成员发送包的M2U(Multicast to Unicast)优化解决方案.为了满足组成员增加时不影响用户的性能,提出在M2U中引入了机会路由...针对无线Mesh网络组播中包丢失严重的问题,提出了保持包的IP层不变,而改变包的目的MAC域,进而MAC层以单播形式向组成员发送包的M2U(Multicast to Unicast)优化解决方案.为了满足组成员增加时不影响用户的性能,提出在M2U中引入了机会路由的M2UO(Multicast to Unicast Opportunistic Routing)算法,对候选节点采用单播形式发送包,对其它节点采用组播形式发送包.在实际网络环境中的大量实验表明,优化组播减小了数据包的丢失率,提高了网络的吞吐量,具有较好的组播视频流效果.展开更多
文摘In this paper, the requirements of routing due to the multimedia applications are briefly discussed. In order to solve the QoS constrained routing effectively and efficiently, the scheme of routing based on Hopfield neural network is proposed after the analysis of related work. Then the QoS routing algorithm for unicast based on Hopfield NN is described and the result of emulation is given. At last, multicast QoS routing considerations based on Hopfield NN are proposed.
基金supported by the Beijing University of Posts and Telecommunications-China Mobile Research Institute Joint Innovation Center。
文摘Fueled by the explosive growth of ultra-low-latency and real-time applications with specific computing and network performance requirements,the computing force network(CFN)has become a hot research subject.The primary CFN challenge is to leverage network resources and computing resources.Although recent advances in deep reinforcement learning(DRL)have brought significant improvement in network optimization,these methods still suffer from topology changes and fail to generalize for those topologies not seen in training.This paper proposes a graph neural network(GNN)based DRL framework to accommodate network trafic and computing resources jointly and efficiently.By taking advantage of the generalization capability in GNN,the proposed method can operate over variable topologies and obtain higher performance than the other DRL methods.
文摘The problem of constructing minimum cost multicast trees with end to end delay and delay variation constraints to meet the quality of service requirements in high speed packet switched environments is studied in this paper. The routing problem of the bounded delay along the paths from the source to each destination and the bounded variation among the delays along these paths is disussed, and then a new algorithm based on Hopfield neural networks to optimize the multicast tree with delay and variation constraints is presented. The simulations show that the proposed algorithm achieves its best performance in high speed computer networks.
文摘A novel approximation algorithm was proposed for the problem of finding the minimum total cost of all routes in Capacity Vehicle Routing Problem (CVRP). CVRP can be partitioned into three parts: the selection of vehicles among the available vehicles, the initial routing of the selected fleet and the routing optimization. Fuzzy C-means (FCM) can group the customers with close Euclidean distance into the same vehicle according to the principle of similar feature partition. Transiently chaotic neural network (TCNN) combines local search and global search, possessing high search efficiency. It will solve the routes to near optimality. A simple tabu search (TS) procedure can improve the routes to more optimality. The computations on benchmark problems and comparisons with other results in literatures show that the proposed algorithm is a viable and effective approach for CVRP.
文摘针对无线Mesh网络组播中包丢失严重的问题,提出了保持包的IP层不变,而改变包的目的MAC域,进而MAC层以单播形式向组成员发送包的M2U(Multicast to Unicast)优化解决方案.为了满足组成员增加时不影响用户的性能,提出在M2U中引入了机会路由的M2UO(Multicast to Unicast Opportunistic Routing)算法,对候选节点采用单播形式发送包,对其它节点采用组播形式发送包.在实际网络环境中的大量实验表明,优化组播减小了数据包的丢失率,提高了网络的吞吐量,具有较好的组播视频流效果.
