Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reducing Traffic Wastage in Video Streaming via Bandwidth-Efficient Bitrate Adaptation

Hairong Su, Shibo Wang, Shusen Yang, Tianchi Huang, Xuebin Ren

TL;DR

This work tackles traffic wastage in bitrate adaptation for video streaming by explicitly modeling buffered data volume (BDV) dynamics and introducing a wastage-aware ABR framework. The core method, BE-ABR, combines a Transformer-based, time-aware transmission delay predictor ($\mathrm{T^{3}P}$) with a rate-adaptation controller that jointly optimizes bitrate and inter-chunk waiting time under a QoE-wastage objective. Key contributions include the BDV-based problem formulation, a novel three-module Transformer predictor for irregular time-series network data, and a QoE-constrained, GA-assisted configuration search that achieves substantial wastage reductions (around $60.87\%$) with QoE comparable to or better than state-of-the-art baselines. Extensive experiments on real WiFi and 4G/5G traces, plus generalization tests and a user study, demonstrate BE-ABR’s robustness and practical relevance for reducing operational costs while preserving user experience.

Abstract

Bitrate adaptation (also known as ABR) is a crucial technique to improve the quality of experience (QoE) for video streaming applications. However, existing ABR algorithms suffer from severe traffic wastage, which refers to the traffic cost of downloading the video segments that users do not finally consume, for example, due to early departure or video skipping. In this paper, we carefully formulate the dynamics of buffered data volume (BDV), a strongly correlated indicator of traffic wastage, which, to the best of our knowledge, is the first time to rigorously clarify the effect of downloading plans on potential wastage. To reduce wastage while keeping a high QoE, we present a bandwidth-efficient bitrate adaptation algorithm (named BE-ABR), achieving consistently low BDV without distinct QoE losses. Specifically, we design a precise, time-aware transmission delay prediction model over the Transformer architecture, and develop a fine-grained buffer control scheme. Through extensive experiments conducted on emulated and real network environments including WiFi, 4G, and 5G, we demonstrate that BE-ABR performs well in both QoE and bandwidth savings, enabling a 60.87\% wastage reduction and a comparable, or even better, QoE, compared to the state-of-the-art methods.

Reducing Traffic Wastage in Video Streaming via Bandwidth-Efficient Bitrate Adaptation

TL;DR

This work tackles traffic wastage in bitrate adaptation for video streaming by explicitly modeling buffered data volume (BDV) dynamics and introducing a wastage-aware ABR framework. The core method, BE-ABR, combines a Transformer-based, time-aware transmission delay predictor () with a rate-adaptation controller that jointly optimizes bitrate and inter-chunk waiting time under a QoE-wastage objective. Key contributions include the BDV-based problem formulation, a novel three-module Transformer predictor for irregular time-series network data, and a QoE-constrained, GA-assisted configuration search that achieves substantial wastage reductions (around ) with QoE comparable to or better than state-of-the-art baselines. Extensive experiments on real WiFi and 4G/5G traces, plus generalization tests and a user study, demonstrate BE-ABR’s robustness and practical relevance for reducing operational costs while preserving user experience.

Abstract

Bitrate adaptation (also known as ABR) is a crucial technique to improve the quality of experience (QoE) for video streaming applications. However, existing ABR algorithms suffer from severe traffic wastage, which refers to the traffic cost of downloading the video segments that users do not finally consume, for example, due to early departure or video skipping. In this paper, we carefully formulate the dynamics of buffered data volume (BDV), a strongly correlated indicator of traffic wastage, which, to the best of our knowledge, is the first time to rigorously clarify the effect of downloading plans on potential wastage. To reduce wastage while keeping a high QoE, we present a bandwidth-efficient bitrate adaptation algorithm (named BE-ABR), achieving consistently low BDV without distinct QoE losses. Specifically, we design a precise, time-aware transmission delay prediction model over the Transformer architecture, and develop a fine-grained buffer control scheme. Through extensive experiments conducted on emulated and real network environments including WiFi, 4G, and 5G, we demonstrate that BE-ABR performs well in both QoE and bandwidth savings, enabling a 60.87\% wastage reduction and a comparable, or even better, QoE, compared to the state-of-the-art methods.

Paper Structure

This paper contains 21 sections, 39 equations, 13 figures, 5 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Adaptive Bitrate Streaming
  4. Network Condition Prediction
  5. System Model
  6. Problem Formulation
  7. BE-ABR Algorithm
  8. Problem Transformation
  9. Overview
  10. Transformer-Based, Time-Aware Transmission Delay Prediction
  11. Rate Adaptation with Fine-Grained Buffer Control
  12. Experimental results
  13. Experimental Setup
  14. Improvement over Real Wireless Network Links
  15. Component-Wise Study
  16. ...and 6 more sections

Figures (13)

  • Figure 1: An overview of DASH-based video streaming system.
  • Figure 2: Process of video chunk downloading with key time points highlighted.
  • Figure 3: The structure of Transformer-based, time-aware transmission delay prediction model $\mathrm{(T^{3}P)}$.
  • Figure 4: The unfolding structure of the Encoder-only Transformer employed in $\mathrm{T^{3}P}$.
  • Figure 5: CDF of viewing ratio under two assumed user departure behavior modes.
  • ...and 8 more figures