T Subramanya, R Riggio - 2019 IEEE Conference on Network …, 2019 - ieeexplore.ieee.org
… a neural-network model (ie, a subset of machinelearning) that … function of the network traffic they should process. Based on the traffic traces collected over a commercial mobile network, …
… In this work, we first propose machinelearning models, … networkfunction instances based on the traffic demand, using the traffic traces collected over a real-operator commercial network…
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 NetworkFunction Virtualization infrastructure. For that …
OA Wahab, N Kara, C Edstrom, Y Lemieux - Journal of Network and …, 2019 - Elsevier
… network into a … machinelearning-based VNF placement and readjustment algorithms to efficiently deploy and migrate VNFs across physical servers. Note that many machine-learning-…
… By increasing the capacity, we allow one or more requests to share the same network function image. Reducing the capacity, we aim at a more concise and efficient use of the server …
S Schneider, NP Satheeschandran… - … on Network …, 2020 - ieeexplore.ieee.org
… We then use these machinelearning models inside existing VNF placement algorithms for improved dynamic resource allocation. These algorithms – irrespective of which model for …
S Park, HG Kim, J Hong, S Lange… - … Asia-Pacific Network …, 2020 - ieeexplore.ieee.org
… hardware-based middleboxes at the suitable location inside the network and controlled traffic flows to provide the various networkfunctions. NetworkFunction Virtualization (NFV) [1] …
… , a reinforcementlearning (RL) approach to efficiently find device placements for distributed neural network training. Unlike prior approaches that only find a device placement for a …
IP Bolodurina, DI Parfenov - IOP Conference Series: Materials …, 2018 - iopscience.iop.org
… networkfunctions allows optimizing their placement in the virtual data center. We will optimize the placement of the networkfunctions … by using Kokhonen's network by the following …