J
Junjie Zhang
Researcher at Fortinet
Publications - 21
Citations - 417
Junjie Zhang is an academic researcher from Fortinet. The author has contributed to research in topics: Policy-based routing & Static routing. The author has an hindex of 9, co-authored 14 publications receiving 265 citations. Previous affiliations of Junjie Zhang include New York University.
Papers
More filters
Journal ArticleDOI
CFR-RL: Traffic Engineering with Reinforcement Learning in SDN
TL;DR: CFR-RL (Critical Flow Rerouting-Reinforcement Learning), a Reinforcement Learning-based scheme that learns a policy to select critical flows for each given traffic matrix automatically and reroutes these selected critical flows to balance link utilization of the network by formulating and solving a simple Linear Programming problem.
Journal ArticleDOI
JumpFlow: Reducing flow table usage in software-defined networks
TL;DR: This paper proposes JumpFlow, a forwarding scheme that achieves low and balanced flow table usage in an SDN by properly and reactively placing flow entries on switches by formulate and solve the reactive flow entry placement problem.
Proceedings ArticleDOI
Load balancing for multiple traffic matrices using SDN hybrid routing
TL;DR: The results show that hybrid routing achieves near-optimal load balancing compared with pure explicit routing and saves at least 84.6% TCAM resources in all practical networks used in the evaluation.
Proceedings ArticleDOI
Optimizing Network Performance Using Weighted Multipath Routing
TL;DR: This paper develops a model to obtain the split ratios such that the overall network end-to-end delay is optimized and presents a heuristic algorithm to find the near-optimal weight configurations and demonstrates the effectiveness of the algorithm using computer simulations.
Proceedings ArticleDOI
DDoS Attacks Detection with AutoEncoder
TL;DR: An AutoEncoder based DDoS attacks Detection Framework (AE-D3F), which only uses normal traffic to build the detection model and is able to update itself automatically as time goes, which is better than classical anomaly detection approaches.