HAECN: Hierarchical Automatic ECN Tuning with Ultra-Low Overhead in Datacenter Networks

In modern datacenter networks (DCNs), mainstream congestion control (CC) mechanisms essentially rely on Explicit Congestion Notification (ECN) that is widely supported by commercial switches to reflect congestion. The traditional static ECN threshold performs poorly under dynamic scenarios, and setting a proper ECN threshold under various traffic patterns is challenging and time-consuming. The recently proposed Automatic ECN Tuning algorithm (ACC) dynamically adjusts the ECN threshold based on reinforcement learning (RL). However, the RL-based model consumes a large number of computational resources, making it difficult to deploy on switches. In this paper, we present a hierarchical automated ECN tuning algorithm called HAECN, which can fully exploit the performance benefits of deep reinforcement learning with ultra-low overhead. The simulation results show that HAECN improves performance significantly by reducing latency and increasing throughput in stable network conditions. For example, HAECN effectively improves throughput by up to 47%, 34%, 32% and 24% over DCQCN, TIMELY, HPCC and ACC, respectively.