The proliferation of virtual reality (VR) content, particularly in resource-intensive applications, has been met by remote rendering to overcome local hardware limitations. Along with numerous advantages, remote rendering VR brings about a new traffic type that features huge throughput and burstiness generally, the understanding and modeling of which is critical for performing VR networking optimization to guarantee the Quality of Experience (QoE) of VR traffic transmission, including synthetic traffic generation and Network Slicing orchestrators. However, existing VR traffic modeling studies are limited in that they do not consider the impact of user interactions on VR traffic. In contrast, we carry out extensive traffic measurements in this paper, and discover that head movements actively affect the VR frame sizes generated. We analyze traffic features and further model the relationship between angular velocities and frame sizes quantitatively. A linear regressor is modeled to predict the frame size by considering history frame sizes and angular velocities jointly. We use Air Light VR (ALVR) to stream VR content in various scenarios, construct the datasets, and validate our model on top of them. The result shows that the our model is capable of reducing the 95% square prediction error by 18-30 compared to the state-of-the-art model. To the best of our knowledge, this is the first investigation into the intricate relationship between remote rendering VR traffic and head movement. Our dataset and results will be publicly available and reproducible.

The rapid growth of online interactive video applications reflects the increasing popularity of real-time communication (RTC). Despite advancements in network and video technologies, the worse quality of experience (QoE) such as large delay, rebuffering and low image quality, etc. remains to be complained generally. We argue that this is mainly due to the legacy network-oriented congestion control (CC), which assumes continuous stream of packets are sent. But it is not satisfied for RTC since bit-rate variation is inherent to RTC’s video encoder.

Legacy transport protocols such as TCP and QUIC suffer from high packet loss and low link utilization in Starlink. From the measurement data, we figure out the ground-satellite link (GSL) handover is mainly to blame. The periodic handovers result in link interruptions and bursty losses with a fixed interval of 15s, which impair TCP’s performance. Based on this finding, we present a handover-aware transport protocol, StarTCP, which proactively stalls transmission during handovers to avoid bursty losses and erroneous congestion signals. Preliminary results indicate that StarTCP can efficiently reduce packet loss and enhance throughput in Starlink.

Interactive video applications signal widespread interest in Real-time communication (RTC), yet issues like frame delay, rebuffering, etc. remain a common complaint. We argue that this is mainly due to legacy network-oriented congestion control (CC), which assumes a continuous stream of packets is being sent. But this assumption doesn't hold in RTC since the video encoder exhibits inherent bit-rate variation: (1) Bursty spiking bit-rate leads to packets waiting in the sending buffer, which increases frame delay. (2) Low bit-rate causes insufficient packets available for sending, making current CCs hard to detect available bandwidth. In response, we propose BurstRTC, a novel paradigm for RTC transport protocol. Each frame is emitted as a whole, and the video bit-rate is directly controlled by network congestion feedback. BurstRTC uses frame-bursting to estimate available bandwidth efficiently regardless of bit-rate variation. Considering the impact of bit-rate variation on network congestion, BurstRTC models frame size as a Gaussian distribution instead of a fixed size and further derives its frame delay, preventing suboptimal performance of purely network-oriented designs. An analytic method for determining the target bit-rate replaces the trial-and-error updates of gradient-based methods, ensuring fast convergence to the available bandwidth. We evaluated the performance of BurstRTC and found that, compared with GCC, BurstRTC achieves up to$59.8 \%$higher bit-rate and up to$\mathbf{4 8. 9 \%}$lower frame delay. Further, compared with SQP and Pudica, BurstRTC can also reduce tail frame delay by up to$89.2 \%$, and improve average bit-rate by up to$15.6 \%$.

The advancement of next-generation networks such as 5G/6G and satellite systems has significantly increased available network bandwidth, while also exacerbating network burstiness. This surge presents a formidable challenge for congestion control (CC), a pivotal mechanism for achieving high bandwidth utilization and low latency by adjusting congestion windows or modifying sending rates. Traditional end-to-end CC algorithms fall short of optimality due to their reliance on congestion signals in acknowledgment packets, which introduce a delay of one round-trip time (RTT). In this paper, to mitigate end-to-end delayed feedback, we introduce a novel Real-Time Congestion Control (RTCC) algorithm that integrates machine learning with conventional model-based CC. RTCC employs a Multi-Layer Perceptron (MLP) to model network conditions and predict current congestion signals accurately. A tailored network model then utilizes these predictions to manage packet accumulation in the network bottleneck. Moreover, an online model-updating mechanism is proposed to adapt to diverse network environments. We integrate RTCC into QUIC and conduct comprehensive experiments in both emulated test-beds and real-world settings, including WiFi/4G/5G and cross-continent networks. The results demonstrate RTCC's efficacy, with up to a 32% increase in average throughput, a reduction in RTT by up to 21% compared to BBR V2, and the maintenance of fair bandwidth allocation.

Real-time video streaming is getting indispensable in people’s daily life, and poses heavy loads and stringent performance requirements on the network. For Internet Service Providers (ISPs), ensuring high-quality real-time video communication is a widely concerned issue. However, inferring the quality of real-time video streaming based on passively-collected network traffic is a great challenge due to limited information in the User Datagram Protocol (UDP) header and the encryption of the application-level protocol. In this paper, we propose IReaV-T to Infer Real-time Video streaming quality with a generalized Transformer, which understands the intrinsic state of the network and predicts the future real-time video quality. By applying novel embedding methods, IReaV-T could make full use of observed traffic features and distinguish different real-time video applications. Extensive comparative experiments demonstrate the effectiveness of IReaV-T, showing that IReaV-T could predict future real-time video quality with mean squared Video Multimethod Assessment Fusion (VMAF) score error less than 6.

Low Earth orbit (LEO) satellite networks have attracted extensive research due to their potential to provide high-quality Internet access services. However, the existing TCP variants, which are designed for terrestrial networks, can hardly work in LEO satellite networks with characteristics such as error-prone, bandwidth variations, and link switching. To address these challenges, in this paper we present a new information-centric transport layer protocol LEOTP to guarantee reliable, high-throughput, and low-latency data transmission in LEO satellite networks. It leverages the idea of Information-Centric Networking (ICN) with a Request-Response transmission model and in-network caching. The connectionless transmission paradigm in LEOTP makes it resilient to dynamic topology changes. The caches equipped in intermediate nodes help to recover packet loss while the hop-by-hop congestion control mechanism provides a fast reaction to time-varying network conditions. We evaluate the performance of LEOTP in emulated Starlink constellation, which shows that it increases the throughput by 8%-12% with 40%-60% delay reduction compared with the state-of-the-art TCP variants in the transcontinental data transmission.

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 find that RTT variation is linearly related to the difference between sending rate and receiving rate, 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 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 over transport layer and application layer respectively. The testing environment includes emulated network, real-world Internet and commercial cellular networks. Compared against Transmission Control Protocol (TCP) flavors and state-of-the-art protocols, Iris is able to achieve high bandwidth utilization, low latency and good fairness concurrently. Especially for HyperText Transfer Protocol (HTTP) video streaming service, Iris is able to increase the video bitrate up to 25% and Peak Signal to Noise Ratio (PSNR) up to 1 dB.