Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs. (arXiv:2207.02295v1 [cs.NI])

Cloud datacenters are exponentially growing both in numbers and size. This
increase results in a network activity surge that warrants better congestion
avoidance. The resulting challenge is two-fold: (i) designing algorithms that
can be custom-tuned to the complex traffic patterns of a given datacenter; but,
at the same time (ii) run on low-level hardware with the required low latency
of effective Congestion Control (CC). In this work, we present a Reinforcement
Learning (RL) based CC solution that learns from certain …

arxiv congestion datacenter learning nvidia reinforcement reinforcement learning