HDRN-19: ICNP 2019 Workshop on Harnessing the Data Revolution in Networking Chicago, IL, United States, October 7-10, 2019 |
Conference website | https://aiops.org/icnpworkshop.html |
Abstract registration deadline | June 13, 2019 |
Submission deadline | June 20, 2019 |
ICNP 2019 Workshop on Harnessing the Data Revolution in Networking
Workshop co-located with ICNP 2019 @ Chicago, Illinois, USA, October 7, 2019
Call for Papers
Artificial Intelligence (AI) and Machine Learning (ML) technologies have achieved remarkable success nowadays in many application domains, e.g., natural language processing, voice recognition, and computer vision. Meanwhile, the ever increasing complexity and scale of today’s networks keep posing new challenges for network measurement and analysis techniques and tools. Advances in the CPU/GPU performance and progress in ML methods—particularly using neural networks—have made ML/AI capable of shedding light on the enormous amount of operational and systems data. Therefore, AI/ML has been effectively used in many critical networking data analytic functions, such as fault isolation, intrusion detection, event correlation, log analysis, capacity planning, and design optimization, just to name a few.
Moreover, networking has recently undergone a huge transformation enabled by new models resulting from softwarization, virtualization, and cloud computing. This has led to a number of novel architectures supported by emerging technologies such as Software-Defined Networking (SDN), Network Function Virtualization (NFV), edge computing, IoT, and 5G. On the other hand, maturing ML techniques, such as reinforcement learning and transfer learning, can potentially serve as basis for incorporating learning into automated network control. The emergence of enhanced design coupled with the increased complexity in networking systems and protocols has fueled the need for improved network autonomy in agile infrastructures, which can be combined with AI/ML techniques to execute efficient, rapid, trustworthy management operations. For example, the coupling of the programmable control of SDN with scientific innovations in AI/ML promises unprecedented opportunities for querying high-volume and high-velocity, distributed streaming data at scale. This new technical capability can provide the necessary information to the many different network monitoring and control tasks to enable efficient automation of autonomous networks .
The above directions can be seen to collectively fall into the National Science Foundations’ (NSF) Harnessing the Data Revolution (HDR) Big Idea, a national-scale activity to enable new modes of data-driven discovery that will allow new fundamental questions to be addressed at the frontiers of science and engineering, with the focus in computer and communication networks. In this workshop, we invite submissions of high-quality original technical and survey papers, which have not been published previously, on artificial intelligence and machine learning techniques and their applications to computer and communication networks, including but not limited to following topics:
- Machine learning and data mining algorithms for networking
- Data mining and big data analytics for network management
- Reinforcement learning in network control and scheduling
- Energy-efficient/green network operations using machine learning and data mining algorithms
- Self-learning, machine learning and big data analytics for detecting network attacks and other security issues
- Big data analytics and visualization for traffic analysis
- Big data analytics/machine learning for network anomaly/outage/failure detection
- Use case applications of harnessing networking data for business intelligence such as process optimization and vendor selection
- Use case applications of harnessing networking data for enhanced service and user experience such as content recommendation, location-based service and advertising
- Machine learning algorithms for fingerprinting network device/service
- Natural language processing techniques for network log analytics
- Machine learning algorithms and tools for network diagnostics and root cause analysis
- Reinforcement learning and machine learning techniques in protocol design and optimization
- Data driven network architectural and protocol design (e.g., for vehicle networks, IoT networks)
- Learning algorithms for provisioning network resources
- Autonomous networks in DCs, WANs, IXPs, wireless networks, cloud networks, CDNs, home networks, etc.
- Machine learning, deep learning, reinforcement learning and other learning algorithms for IoT and 5G
- Reinforcement learning and other learning techniques for virtualization techniques including NFV, SDN, SFC, etc.
- Learning techniques for network slicing optimization
- Open-source AI software for networking or networked applications
- Techniques for anonymization and user privacy protection in networking data
- Federated learning from distributed network data
- Performance analysis (e.g., security, optimality, privacy) of ML algorithms as applied to networking problems