DUASVS: A Mobile Data Saving Strategy in Short-Form Video Streaming

Zhang, Guanghui; Zhang, Jie; Liu, Ke; Guo, Jing; Lee, John; Hu, Haibo; Aggarwal, Vaneet

doi:10.1109/tsc.2022.3150012

Cited by 16 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[10] on a log-rectilinear transformation for foveated 360-degree video streaming and the research by Jiménez et al [17] [34,41,42,43] in their respective studies on QoE optimization in DASH-based multiview video streaming and improving QoE for low-latency live video streaming. Additionally, Chakareski et al [32,44,45] provide insights into end-to-end optimization for viewport-driven 360° video streaming, emphasizing the importance of user navigation modeling and rate-distortion analysis.…”

Section: Literature Review Of Existing Streaming Modelsmentioning

confidence: 99%

DLLBVS: Design of a High-Efficiency Deep Learning based Low-BER Video Streaming Model for High-Noise Wireless Networks

Gowrishankar S., Ramesh Babu H. S, Prasad G. R.

2024

jes

View full text Add to dashboard Cite

Design of video streaming models for high-noise networks is a multimodal process that requires efficient channel modelling, noise analysis, error-specific stream control, intelligent data augmentation, etc. This article proposes design of a high-efficiency deep learning based low-BER (Bit Error Rate) Video streaming model for high-noise wireless networks. The proposed model initially uses a Long-Short-Term Memory (LSTM) block for estimation of frame level features, and then uses Orthogonal Frequency Division Multiple Access (OFDMA) based modulation platform for transmission and reception of processed video frames. The OFDMA model is cascaded with a chaotic communication module, which assists in improving data fidelity under different noise conditions. The chaotic communication module is optimized using Grey Wolf Optimizer (GWO), which assists in setting up its hyperparameters for better efficiency under real-time communication scenarios. Video frames were pre-processed using Dual Neural Networks that assisted in estimation of differential frame information sets. Due to estimation of this differential frame information, streaming speed is improved, which assists in increasing number of frames transmitted per second, thereby improving streaming performance for different video types. This frame information is further processed by an iterative Gated Recurrent Unit (GRU) based VARMAx Model, which assists in predicting frame removal instances, thus assisting in faster & low error communications. The GRU VARMAx Model optimizes data flow, thus reducing congestion and improving throughput. The model was tested under AWGN (Additive While Gaussian Noise), Rayleigh, & Rician channel types, and its efficiency was compared with standard streaming techniques in terms of communication delay, Bit Error Rate, Peak to Average Power Ratio (PAPR), throughput, communication jitter and computational complexity levels. Based on this comparison it was observed that the proposed model showcased 3.5% lower communication delay, 8.3% lower BER, 5.9% lower PAPR, 10.5% higher throughput, 3.9% lower jitter and 6.4% lower computational complexity, which makes it highly useful for a wide variety of real-time streaming scenarios.

show abstract

Section: Literature Review Of Existing Streaming Modelsmentioning

confidence: 99%

DLLBVS: Design of a High-Efficiency Deep Learning based Low-BER Video Streaming Model for High-Noise Wireless Networks

Gowrishankar S., Ramesh Babu H. S, Prasad G. R.

2024

jes

View full text Add to dashboard Cite

show abstract

“…Both parameters are learned based on past user behaviors and network conditions using greedy search. In [12], DUASVS is introduced as an enhanced iteration of WAS. This approach employs the Asynchronous Advantage Actor Critic (A3C) algorithm with an Actor-Critic Network to optimize wastageaware parameters.…”

Section: Related Workmentioning

confidence: 99%

“…In [7], the authors design an adaptive preloading mechanism for short-form videos which is based on the Lyapunov optimization. The method predicts the user's viewing duration of the next video and decides the number of next videos that can be downloaded and the buffer length of all videos to maximize the playback smoothness (minimize the [15] 2023 MMGC2022 [16], DUASVS [12] Imitation learning,…”

Section: Related Workmentioning

confidence: 99%

Joint Preloading and Bitrate Adaptation for Short Video Streaming

Phong,

Huong,

Nam

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Short videos have become one of the most popular content mobile users consume nowadays. However, unlike traditional videos, users watch many short videos each time and frequently skip those not of their interest. Not taking into account this factor, conventional video streaming methods result in a large amount of data wastage. Moreover, short videos are usually streamed over time-varying network conditions, which requires preloading to provide satisfactory Quality of Experience (QoE). In this paper, we formulate the QoE-Wastage trade-off optimization problem in short video streaming as a multi-objective optimization problem. We then develop a lightweight joint preloading and bitrate adaptation algorithm that utilizes cross-user behaviors to decide a suitable amount of preloaded data for each video. In addition, our method dynamically adjusts video bitrate per chunk basis to achieve high user QoE. Experimental results show that the proposed method improves QoE by approximately 12% to 45% and reduces data wastage by up to 58% compared to existing methods.

show abstract