In response to the complex and multidimensional nature of converged traffic on heterogeneous links in tactical communication networks,which leads to the difficulty in ensuring the quality of service(QoS)requirements f...
详细信息
In response to the complex and multidimensional nature of converged traffic on heterogeneous links in tactical communication networks,which leads to the difficulty in ensuring the quality of service(QoS)requirements for critical services,a frame generation algorithm for differentiated services(DS-FG)is ***-FG deploys an adaptive frame generation algorithm based on deep reinforcement learning(DRL-FG)for timesensitive service,while deploying a high efficient framegeneration(HEFG)algorithm for non-time-sensitive ***-FG constructs a reward function by combining the queue status information of time-sensitive service and utilizes deep deterministic policy gradients(DDPG)to train a decision model for adaptive framegeneration(AFG)algorithm ***,Gaussian noise sampling and prioritized experience replay strategies are employed to enhance model training efficiency and performance,achieving optimal matching between time-sensitive service QoS requirements and framegeneration *** results demonstrate that DS-FG outperforms traditional algorithms,achieving up to 13%improvement in throughput and over 19.7%reduction in average queueing delay for time-sensitive service.
In the framegeneration model of AOS two-layer multiplexing technology, transmission efficiency and throughput performance of the system are influenced by buffer capacity and packet extracting time. Different from pre...
详细信息
ISBN:
(纸本)9781479932795
In the framegeneration model of AOS two-layer multiplexing technology, transmission efficiency and throughput performance of the system are influenced by buffer capacity and packet extracting time. Different from previous frame generation algorithms which are studied under infinite buffer and ignore packet extracting time, high efficient framegeneration model which takes the packet extracting time into account under finite buffer is established. The buffer overflow probability is simulated under the model. The simulation results show that the model can describe the real framegeneration process accurately.
In the framegeneration model of AOS two-layer multiplexing technology,transmission efficiency and throughput performance of the system are influenced by buffer capacity and packet extracting *** from previous frame g...
详细信息
In the framegeneration model of AOS two-layer multiplexing technology,transmission efficiency and throughput performance of the system are influenced by buffer capacity and packet extracting *** from previous frame generation algorithms which are studied under infinite buffer and ignore packet extracting time,high efficient framegeneration model which takes the packet extracting time into account under finite buffer is *** buffer overflow probability is simulated under the *** simulation results show that the model can describe the real framegeneration process accurately.
暂无评论