•  3
    Datacenter Traffic Optimization with Deep Reinforcement Learning
    with Li Chen, Justinas Lingys, and Xudong Liao
    In Ahmad Alnafessah, Gabriele Russo Russo, Valeria Cardellini, Giuliano Casale & Francesco Lo Presti (eds.), Communication Networks and Service Management in the Era of Artificial Intelligence and Machine Learning, Wiley. 2021.
    Traffic optimizations (TOs, e.g. flow scheduling, load balancing) in datacenters are difficult online decision-making problems. Previously, they are done with heuristics relying on operators’ understanding of the workload and environment. Designing and implementing proper TO algorithms thus take at least weeks. Encouraged by recent successes in applying deep reinforcement learning (DRL) techniques to solve complex online control problems and leveraging the long-tail distribution of datacenter tr…Read more