Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network Packet Transmission Based on Deep Learning

Mao, Bomin; Fadlullah, Zubair Md.; Tang, Fengxiao; Kato, Nei; Akashi, Osamu; Inoue, Takeru; Mizutani, Kimihiro

doi:10.1109/tc.2017.2709742

Cited by 319 publications

(125 citation statements)

References 20 publications

Supporting

Mentioning

122

Contrasting

Unclassified

Order By: Relevance

“…Note that each boxplot represents the results over 100 scenarios with different input traffic matrices of the same traffic intensity (TI). To this end, we randomly generated 100 traffic matrices (T M) for each TI (from 11 to 16) according to Equation (7). For each optimization strategy, we provide the resulting performance metrics computed by our packet-level simulator after applying the routing configuration selected in each case.…”

Section: A Delay Jitter and Loss-aware Routing Optimizationmentioning

confidence: 99%

Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN

Rusek¹,

Suárez-Varela

Mestres

et al. 2019

Proceedings of the 2019 ACM Symposium on SDN Research

171

152

View full text Add to dashboard Cite

Network modeling is a key enabler to achieve efficient network operation in future self-driving Software-Defined Networks. However, we still lack functional network models able to produce accurate predictions of Key Performance Indicators (KPI) such as delay, jitter or loss at limited cost. In this paper we propose RouteNet, a novel network model based on Graph Neural Network (GNN) that is able to understand the complex relationship between topology, routing and input traffic to produce accurate estimates of the per-source/destination perpacket delay distribution and loss. RouteNet leverages the ability of GNNs to learn and model graph-structured information and as a result, our model is able to generalize over arbitrary topologies, routing schemes and traffic intensity. In our evaluation, we show that RouteNet is able to predict accurately the delay distribution (mean delay and jitter) and loss even in topologies, routing and traffic unseen in the training (worst case R 2 = 0.878). Also, we present several use-cases where we leverage the KPI predictions of our GNN model to achieve efficient routing optimization and network planning.

show abstract

Section: A Delay Jitter and Loss-aware Routing Optimizationmentioning

confidence: 99%

Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN

Rusek¹,

Suárez-Varela

Mestres

et al. 2019

Proceedings of the 2019 ACM Symposium on SDN Research

171

152

View full text Add to dashboard Cite

show abstract

“…13: Save the knowledges (s(t), s(t + 1), r(t), r(t + 1)) in M . 14 Afterwards, noting that A as the action space, the discounted cumulative state function is formulated as…”

Section: B Learning Policymentioning

confidence: 99%

Deep Reinforcement Learning for UAV Navigation Through Massive MIMO Technique

Huang

Yang

Wang

et al. 2020

IEEE Trans. Veh. Technol.

121

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) technique has been recognized as a promising solution in future wireless connectivity from the sky, and UAV navigation is one of the most significant open research problems, which has attracted wide interest in the research community. However, the current UAV navigation schemes are unable to capture the UAV motion and select the best UAV-ground links in real-time, and these weaknesses overwhelm the UAV navigation performance. To tackle these fundamental limitations, in this paper, we merge the state-of-theart deep reinforcement learning with the UAV navigation through massive multiple input multiple output (MIMO) technique. To be specific, we carefully design a deep Q-network (DQN) for optimizing the UAV navigation by selecting the optimal policy, and then we propose a learning mechanism for processing the DQN. The DQN is trained so that the agent is capable of making decisions based on the received signal strengths for navigating the UAVs with the aid of the powerful Q-learning. Simulation results are provided to corroborate the superiority of the proposed schemes in terms of the coverage and convergence compared with that of other schemes.Index Terms-Massive multiple input multiple output (MIMO), deep reinforcement learning, UAV navigation

show abstract

“…17,18 In the traffic flow prediction, the common parameter models mainly include the moving average (MA) model, autoregressive (AR) model, autoregressive moving average (ARMA) model, maximum likelihood estimate model, Kalman filtering (KF) model, etc. 17,18 In the traffic flow prediction, the common parameter models mainly include the moving average (MA) model, autoregressive (AR) model, autoregressive moving average (ARMA) model, maximum likelihood estimate model, Kalman filtering (KF) model, etc.…”

Section: Parameter Modelsmentioning

confidence: 99%

“…Parameter models are the methods of establishing a structured expression and variables assumptions to calculate the experimental data, and the models are usually composed of the fixed assumptions and parameters. 17,18 In the traffic flow prediction, the common parameter models mainly include the moving average (MA) model, autoregressive (AR) model, autoregressive moving average (ARMA) model, maximum likelihood estimate model, Kalman filtering (KF) model, etc. The most commonly used of these parametric models is the KF model, which is a control method-based linear regression.…”

Section: Parameter Modelsmentioning

confidence: 99%

Big data‐driven machine learning‐enabled traffic flow prediction

Kong

Jiang

et al. 2018

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Real‐time effective traffic flow big data prediction network has important application significance. Over the past few years, traffic flow data have been exploding and we have entered the big data era. The key challenge of traffic flow prediction network is how to construct an adaptive model relying on historical data. Existing big data‐driven traffic flow prediction networking approaches mainly use shallow learning, and there are unsatisfying for many realistic applications, which inspire us to rethink the traffic flow big data prediction problem with deep learning. In this paper, we propose a novel prediction approach based on machine learning. In addition to the minimum prediction error as the goal, we present the long short‐term memory model, which is a typical machine learning algorithm with deep learning network. This method is applied into the real‐world traffic big data from performance measurement system. Experimental results show that the proposed machine learning algorithm has more applicability and higher performance, compared with shallow machine learning prediction network.

show abstract

Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network Packet Transmission Based on Deep Learning

Cited by 319 publications

References 20 publications

Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN

Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN

Deep Reinforcement Learning for UAV Navigation Through Massive MIMO Technique

Big data‐driven machine learning‐enabled traffic flow prediction

Contact Info

Product

Resources

About