Research Directions

Business model

• Application Driven Pricing : A Business Model for Future Internet—–IEEE Magazine-2016
• Paris metro pricing for the internet. In Proceedings of the 1st ACM conference on Electronic commerce, pp. 140-147. ACM, 1999.
• Pricing network resources for adaptive applications. IEEE/ACM Transactions on Networking 14, no. 3 (2006): 506-519.
• The public option: a nonregulatory alternative to network neutrality. IEEE/ACM Transactions on Networking (TON) 21, no. 6 (2013): 1866-1879.
• Usage-Based Pricing and Competition in Congestible Network Service Markets.To appear in IEEE/ACM Transactions on Networking (TON)
• Neutral Net Neutrality. In Proceedings of the 2016 conference on ACM SIGCOMM 2016 Conference, pp. 483-496. ACM, 2016.

Information consumption model and application abstraction

• A Unified Framework for Information Consumption Based on Markov Chains, Arxiv 2016,
• The Learning and Prediction of Application-Level Traffic Data in Cellular Networks. Arxiv 2016.
• Max-weighted scheduling queueing networks with heavy-tailed traffic, IEEE TON, Vol. 22, Feb. 2014.
• Internet Traffic Classification Demystified: Myths, Caveats, and the Best Practices. CoNEXT’08.
• Coflow Class-of-Service Mapping for QoS: A Statistical Signature-based Approach to IP Traffic Classification. IMC’04
• Coflow: A Networking Abstraction for Cluster Applications. Hotnet’12

Network sensing

• Software Defined Traffic Measurement with OpenSketch, NSDI 13
• Planck: Millisecond-scale Monitoring and Control for Commodity Networks, SIGCOMM 14
• DREAM: Dynamic Resource Allocation for Software-defined Measurement, SIGCOMM 14
• SCREAM: Sketch Resource Allocation for Software-defined Measurement, CoNEXT 15
• FlowRadar: A Better NetFlow for Data Centers, NSDI 16
• One Sketch to Rule Them All: Rethinking Network Flow Monitoring with UnivMon, SIGCOMM 16
• Trumpet: Timely and Precise Triggers in Data Center, SIGCOMM 16
• Opprentice: Towards Practical and Automatic Anomaly Detection Through Machine Learning, IMC 15，
• A Hybrid Local and Distributed Sketching Design for Accurate and Scalable Heavy Key Detection in Network Data Streams

Control part

End based fast control

• Virtualized Congestion Control, SIGCOMM 2016
• AC/DC TCP: Virtual Congestion Control Enforcement for Datacenter Networks, SIGCOMM 2016
• Queues Don’t Matter When You Can JUMP Them!, NSDI 2015
• pFabric: Minimal Near-Optimal Datacenter Transport, SIGCOMM 2013
• Data Center TCP (DCTCP), SIGCOMM 2010
• Sharing the Data Center Network, NSDI 2011
• Improving datacenter performance and robustness with multipath tcp, SIGCOMM 2011
• Differentiated End-to-End Internet Services using a Weighted Proportional Fair Sharing TCP, SIGCOMM CCR 1998

Network based fast control

• Karuna：Scheduling Mix-flows in Commodity Datacenters with Karuna SigComm’16
• NUMFabric：Fast and Flexible Bandwidth Allocation in Datacenters SigComm’16；
• CODA: Toward Automatically Identifying and Scheduling Coflows in the Dark SigComm’16；
• PIFO: Programmable Packet Scheduling at Line Rate, SigComm’16；
• 2DFQ：Two-Dimensional Fair Queueing for Multi-Tenant Cloud Services SigComm’16
• SNAP: Stateful Network-Wide Abstractions for Packet Processing

Slow control

• A Case Study in Network Architecture Tradeoffs, ONS, 2015.
• A Theory of Dynamics, Control and Optimization in Layered Architectures, ACC, 2016.
• Optimal State-Feedback Control under Sparsity and Delay Constraints, 3rd IFAC Workshop, 2012.
• Performance of a Priority-Weighted Round Robin Mechanism for Differentiated Service Networks, ICCCN, 2007.
• Load Balancing by MPLS in Differentiated Services Networks, 2003.
• Traffic Engineering with Forward Fault Correction, SIGCOMM 2014