The Deep Learning Vision for Heterogeneous Network Traffic Control: Proposal, Challenges, and Future Perspective

By Nei Kato, Zubair Muhammad Fadlullah, Bomin Mao, Fengxiao Tang, Osamu Akashi, Takeru Inoue, Kimihiro Mizutani. IEEE wireless communications, 2017

388 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Building and Construction, Computer Networks and Communications

View Paper: https://www.semanticscholar.org/paper/adb73d51b8473bfa403664d5417c1dea9343bba6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Nei Kato
2. Jiajia Liu
3. Fengxiao Tang
4. Bomin Mao
5. Guan Gui
6. Walid Saad
7. Yuichi Kawamoto
8. Merouane Debbah

In Building and Construction

1. Nei Kato
2. Guan Gui
3. Fengxiao Tang
4. Bomin Mao
5. Jiajia Liu
6. Yiwei Song
7. Hongji Huang
8. Ala Al-Fuqaha

In Computer Networks and Communications

1. Jiajia Liu
2. Merouane Debbah
3. Nei Kato
4. Walid Saad
5. Fengxiao Tang
6. Bomin Mao
7. Mingzhe Chen
8. Guan Gui

Citations in the corpus

• Optimizing Space-Air-Ground Integrated Networks by Artificial Intelligence (2018, methodology): “Our previous work [5] proposed a deep learning based routing strategy that utilizes the DBA as shown in Fig.”
• Secure SVM Training Over Vertically-Partitioned Datasets Using Consortium Blockchain for Vehicular Social Networks (2020, background): “Machine learning (ML) and deep learning have drawn the attention of reseachers from many domains [7]–[11].”
• 6G: Opening New Horizons for Integration of Comfort, Security, and Intelligence (2020, background): “Developed DNN models for wireless communication are also limited [15-18], and are mainly borrowed from the fields of computer vision.”
• Deep Learning for Super-Resolution Channel Estimation and DOA Estimation Based Massive MIMO System (2018, methodology): “Furthermore, deep learning has been applied in traffic control systems to optimize average delay and packet loss rate performance [28]–[30].”
• State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems (2017, methodology): “In our prior work [107], in order to train network intelligent routing, we need large amounts of training data of existing”
• Machine Learning for Wireless Networks with Artificial Intelligence: A Tutorial on Neural Networks (2017, background): “First, they are often focused on one type of machine learning techniques (often deep learning such as in [32], [51], and [54]) and, as such, they do not capture the rich spectrum of available of AI and machine learning frameworks.”
• Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “[63] Proof-of-concept deep learning for network traffic control.”
• Machine Learning for Networking: Workflow, Advances and Opportunities (2017, background): “[14] N.”
• 6G and Beyond: The Future of Wireless Communications Systems (2020, background): “network layer, machine learning (ML) algorithms can be used for traffic clustering to further adapt the network resources to various scenarios [76].”
• Edge-Computing-Enabled Smart Cities: A Comprehensive Survey (2019, neutral): “Furthermore, deep learning and game theoretic approaches can be used to enable smart devices, edge servers, and other networking devices to perform traffic flow control collaboratively [206].”
• Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks (2019, methodology): “[328] proposed a supervised DNN aided traffic routing scheme, which outperformed the classic open shortest path first (OSPF) scheme in terms of requiring a lower overhead, whilst maintaining a higher throughput and lower delay.”
• On Removing Routing Protocol from Future Wireless Networks: A Real-time Deep Learning Approach for Intelligent Traffic Control (2018, background): “Our earlier work in [6] envisioned the first proof-of-concept of using deep learning architectures for substantially improving heterogeneous network traffic control.”
• Ten Challenges in Advancing Machine Learning Technologies toward 6G (2020, methodology): “Besides the application of AI technologies, some technologies including big data analytics [2], training data management [3], high performance computing [4], and efficient energy harvesting be widely adopted to solve the difficulties in operation of the full intelligent communication system.”
• Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges (2017, background): “Kato et al. [282] proposed a supervised deep learning based routing scheme for heterogeneous network traffic control.”