DeepAI AI Chat
Log In Sign Up

Internet Congestion Control via Deep Reinforcement Learning

by   Nathan Jay, et al.

We present and investigate a novel and timely application domain for deep reinforcement learning (RL): Internet congestion control. Congestion control is the core networking task of modulating traffic sources' data-transmission rates so as to efficiently and fairly allocate network resources. Congestion control is fundamental to computer networking research and practice, and has recently been the subject of extensive attention in light of the advent of challenging Internet applications such as live video, augmented and virtual reality, Internet-of-Things, and more. We build on the recently introduced Performance-oriented Congestion Control (PCC) framework to formulate congestion control protocol design as an RL task. Our RL framework opens up opportunities for network practitioners, and even application developers, to train congestion control models that fit their local performance objectives based on small, bootstrapped models, or complex, custom models, as their resources and requirements merit. We present and discuss the challenges that must be overcome so as to realize our long-term vision for Internet congestion control.


page 1

page 2

page 3

page 4


MACC: Cross-Layer Multi-Agent Congestion Control with Deep Reinforcement Learning

Congestion Control (CC), as the core networking task to efficiently util...

Smart City Intelligent System Traffic Congestion Optimization using Internet Of Things

The raising level of traffic imposes a great demand in the growth of int...

Performance Evaluation of Advanced Congestion Control Mechanisms for COAP

In Internet of Things (IoT), the simple IPv6 capable electronic devices ...

MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions

Effective network congestion control strategies are key to keeping the I...

Micro Congestion Control: Every Flow Deserves a Second Chance

Today, a considerable Internet traffic is sent from the datacenter and h...

RACE: A Reinforcement Learning Framework for Improved Adaptive Control of NoC Channel Buffers

Network-on-chip (NoC) architectures rely on buffers to store flits to co...

Pied Piper: Rethinking Internet Data Delivery

We contend that, analogously to the transition from resource-limited on-...