AI-driven packet forwarding with programmable data plane: A survey
The existing packet forwarding technology cannot meet the increasing requirements of
Internet development due to its rigid framework. Application of artificial intelligence (AI) for …
Internet development due to its rigid framework. Application of artificial intelligence (AI) for …
Machine learning for traffic analysis: a review
Traffic analysis has many purposes such as evaluating the performance and security of
network operations and management. Therefore, network traffic analysis is considered vital …
network operations and management. Therefore, network traffic analysis is considered vital …
A survey of machine learning techniques for video quality prediction from quality of delivery metrics
O Izima, R de Fréin, A Malik - Electronics, 2021 - mdpi.com
A growing number of video streaming networks are incorporating machine learning (ML)
applications. The growth of video streaming services places enormous pressure on network …
applications. The growth of video streaming services places enormous pressure on network …
Network for AI and AI for network: Challenges and opportunities for learning-oriented networks
The “data pipe” model used by the existing Internet protocol stack is no longer ideal for many
emerging applications, due to multimedia, multicast, mobility, machine learning, and network …
emerging applications, due to multimedia, multicast, mobility, machine learning, and network …
Incorporating intra-flow dependencies and inter-flow correlations for traffic matrix prediction
Traffic matrix (TM) prediction is essential for effective traffic engineering and network
management. Based on our analysis of real traffic traces from Wide Area Network, the traffic …
management. Based on our analysis of real traffic traces from Wide Area Network, the traffic …
A survey on deep learning for the routing layer of computer network
With recent achievements in deep learning over the past year, many computer and network
applications actively used deep learning architectures including convolution neural network …
applications actively used deep learning architectures including convolution neural network …
Predicting traffic demand matrix by considering inter-flow correlations
Accurate traffic demand matrix (TM) prediction is essential for effective traffic engineering
and network management. Based on our analysis of real traffic traces from Wide Area …
and network management. Based on our analysis of real traffic traces from Wide Area …
Dlbooster: Boosting end-to-end deep learning workflows with offloading data preprocessing pipelines
In recent years, deep learning (DL) has prospered again due to improvements in both
computing and learning theory. Emerging studies mostly focus on the acceleration of …
computing and learning theory. Emerging studies mostly focus on the acceleration of …
Joint power allocation and MCS selection for energy-efficient link adaptation: A deep reinforcement learning approach
Link adaptation is a promising tool of modern networks to combat the time-variant quality of
channels. Modulation and Coding Scheme (MCS) selection is essentially used for link …
channels. Modulation and Coding Scheme (MCS) selection is essentially used for link …
Accelerating distributed machine learning by smart parameter server
Parameter Server (PS)-based architecture is widely applied in distributed machine learning
(DML), but it is still an open issue how to improve the DML performance in this frame-work …
(DML), but it is still an open issue how to improve the DML performance in this frame-work …