… to better virtualnetwork embedding decisions. Specifically, we formulate adaptive online VNE as a deep reinforcementlearning (DRL) [10] problem, and design an algorithm to learn the …
Z Yan, J Ge, Y Wu, L Li, T Li - IEEE Journal on Selected Areas …, 2020 - ieeexplore.ieee.org
… deep reinforcementlearning with a novel neural network structure based on graph convolutional networks, and propose a new and efficient algorithm for automatic virtualnetwork …
R Solozabal, J Ceberio, A Sanchoyerto… - IEEE Journal on …, 2019 - ieeexplore.ieee.org
… In this work, we solve the VNF-FGE problem by means of a ReinforcementLearning approach to model a placement policy in a Network Function Virtualization infrastructure. For that …
… Then, we propose a solution based on deep reinforcementlearning (DRL). More precisely, we present a novel RL approach, called parameterized action twin (PAT) deterministic policy …
M Lu, Y Gu, D Xie - IEEE Transactions on Network and Service …, 2020 - ieeexplore.ieee.org
… multilayer VNE algorithm in SDN based on reinforcementlearning. The main contributions of this … physical network and upper VNRs to under VNRs. 2) We build a reinforcementlearning …
… -core networks. Specifically, our framework is based on a deep reinforcementlearning (DRL) … , ie it is capable of learning which slice to admit based on the availability of the physical …
P Zhang, C Wang, N Kumar… - IEEE Internet of Things …, 2021 - ieeexplore.ieee.org
… of virtualnetwork request (VNR) … reinforcementlearning (RL) and graph neural network (GNN) theory to the algorithm, especially the combination of graph convolutional neural network (…
P Zhang, C Wang, C Jiang… - … Transactions on Network …, 2020 - ieeexplore.ieee.org
… on reinforcement learning (RL). In the training phase, we use a policy network as a learning … The learning agent is trained in this environment to get the mapping probability of each …
T Miyazawa, VP Kafle, H Harai - … on Integrated Network and …, 2017 - ieeexplore.ieee.org
… reinforcementlearning for the selection of alternate resources to satisfy the QoS requirement. The reinforcementlearning [7… Therefore, we propose to utilize the reinforcementlearning to …