Paper: IEEE Access - DNN partitioning for inference throughput acceleration at the edge
Intro I am very excited to present this work, published in the IEEE Access journal, which presents an alternative to standard AI workload acceleration mechanisms at the edge (hardware acceleration, model compression, cloud off-loading). This work, in collaboration with Cisco,...Read moreRead More »
Paper: CIKM'22 - Multi-Agent Reinforcement Learning for Network Load Balancing in Data Center
Intro Glad to announce that, together with my friend at Princeton University, I have pushed a paper on multi-agent reinforcement learning algorithms for load balancing problems to CIKM. Extending based on the paper “Reinforced Workload Distribution Fairness” which we have...Read moreRead More »
Paper: Aquarius - Enable Fast, Scalable, Data-Driven Service Management in the Cloud
Intro Extending based on the paper Efficient Data-Driven Network Functions which I will physically present in the 30th International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems in Nice, France, we have developed a platform...Read moreRead More »
Paper: HLB - Towards Load-Aware Load Balancing
Intro I have been working for a couple of years on the subject of making load balancers in data center networks more “intelligent”–in the sense of making appropriate task allocation according to both the dynamic server load states and the...Read moreRead More »
Paper: Learning Distributed and Fair Policies for Network Load Balancing as Markov Potentia Game
Throughout the whole summer vacation, I have been waiting for this moment. Finally! My collaboration with my friend Zihan, who is pursuing his PhD at Princeton University, is acknowledged and accepted in the main conference of the 36th Conference on...Read moreRead More »