Statistical Learning Based Congestion Control for Real-Time Video Communication

Abstract

With the increasing demands on interactive video applications, how to adapt video bit rate to avoid network congestion has become critical, since congestion results in selfinflicted delay and packet loss which deteriorate the quality of real-time video service. The existing congestion control is hard to simultaneously achieve low latency, high throughput, good adaptability and fair bandwidth allocation, mainly because of the hardwired control strategy and egocentric convergence objective.To address these issues, we propose an end-to-end statistical learning based congestion control, named Iris. By exploring the underlying principles of self-inflicted delay, we reveal that congestion delay is determined by sending rate, receiving rate and network status, which inspires us to control video bit rate using a statistical-learning congestion control model. The key idea of Iris is to force all flows to converge to the same queue load, and adjust the bit rate by the model. All flows keep a small and fixed number of packets queuing in the network, thus the fair bandwidth allocation and low latency are both achieved. Besides, the adjustment step size of sending rate is updated by online learning, to better adapt to dynamically changing networks.We carried out extensive experiments to evaluate the performance of Iris, with the implementations of transport layer (UDP) and application layer (QUIC) respectively. The testing environment includes emulated network, real-world Internet and commercial LTE networks. Compared against TCP flavors and state-of-the-art protocols, Iris is able to achieve high bandwidth utilization, low latency and good fairness concurrently. Especially over QUIC, Iris is able to increase the video bitrate up to 25%, and PSNR up to 1dB.Index Terms-Congestion control, real-time video streaming, low latency, statistical learning, adaptive adjustment.• Non-coexistence of high throughput and low latency.Considering only packet loss will lead to high queuing delay, but the algorithms overly concerned about delay also lead to low throughput [25]. • Hardwired control strategy. Most methods adjust sending rate with fixed step size or multiplier [26]. This manual mapping cannot always be optimal in changing networks, resulting in performance degradation. • Egocentric convergence objective. Some algorithms based on objective function are self-centered and lack communication between concurrent data streams, thus thye can not keep the same convergence goal for different clients, which leads to unfair bandwidth allocation.Motivated by these issues, to obtain higher video transmission quality, we probe into the essence of congestion control and consider whether it is possible to design an algorithm that achieves the goals of low latency, high channel utilization, good adaptability to changing networks and fair bandwidth allocation. Some recently proposed algorithms [27, 28] have enlightened us: a congestion control with low-latency fairness arXiv:1905.05998v2 [cs.MM]

An efficient congestion control in multimedia streaming using adaptive BRR and fuzzy butterfly optimization

“…Dai et al 2 developed a congestion control model named Iris using statistical learning for video communication in real‐time. They conducted thorough tests to evaluate the performance of Iris using implementations at the application and transport layers respectively.…”

“…The speed of the network has achieved a great peak in recent years and is still developing. To continue this success these platforms must provide great‐quality videos to the users 2 . Due to some challenges such as variation of transmission conditions, various client request patterns, and changing conditions of media, the quality of experience (QoE) may be reduced 3,4 .…”

“…To continue this success these platforms must provide great-quality videos to the users. 2 Due to some challenges such as variation of transmission conditions, various client request patterns, and changing conditions of media, the quality of experience (QoE) may be reduced. 3,4 To achieve better performance of QoE, several optimization techniques are designed that use available bandwidth and minimize operation cost efficiently.…”

When Machine Learning Meets Congestion Control: A Survey and Comparison

“…Moreover, there has been various research measuring RTT based on other parameters in the network. In [61], linear regression was used to establish the relationship between RTT and the sending rate. In [62], a Bayesian technique was used to simulate the distribution between delay and the sending rate and then to predict delay based on the sending rate.…”

A Minmax Utilization Algorithm for Network Traffic Scheduling of Industrial Robots

“…The authors in [11] propose a scheme called XMAS to improve the accuracy of bandwidth estimation and determine the transmission bitrate. In [12], a linear-regression learning model is used for sending data rate adjusting. Moreover, two adaptive bitrate algorithms, which are based on deep reinforcement learning model, are provided in [13] and [14] for unmanned aerial vehicle transmission and multimedia broadcast scenarios respectively.…”