Real-time communication (RTC) platforms have seen a considerable surge in popularity in recent years, largely due to the COVID-19 pandemic which facilitated remote work. To ensure adequate Quality of Experience (QoE) for users, a good congestion control algorithm is needed. RTC applications use UDP, so congestion control is done on the application layer, leaving way for advanced algorithms. In this paper, we propose ReCoCo, a solution for congestion control in RTC applications based on Reinforcement learning (RL). ReCoCo gains information about the network conditions at the receiver-side, such as receiving rate, one-way delay and loss ratio and predicts the available bandwidth in the next time bin. We train ReCoCo on 9 bandwidth trace files that cover a vast array of network types. We try different algorithms, states and parameters, training both specific and general models. We find that ReCoCo outperforms the de-facto standard heuristic algorithm GCC in both specialized and general models. We also make observations on the difficulty of generalization when using RL.
ReCoCo: Reinforcement learning-based Congestion control for Real-time applications
2023-01-01
Conference paper
Electronic Resource
English
DDC: | 629 |
Partially Oblivious Congestion Control for the Internet via Reinforcement Learning
BASE | 2023
|Owl: Congestion Control with Partially Invisible Networks via Reinforcement Learning
BASE | 2021
|Transportation Research Record | 2023
|