Abstract
Prior efforts have shown that network-assisted schemes can improve the quality of experience (QoE) and QoE fairness when multiple video players compete for bandwidth. However, realizing network-assisted schemes in practice is challenging, as: 1) the network has limited visibility into the client players’ internal state and actions; 2) players’ actions may nullify or negate the network’s actions; and 3) the players’ objectives might be conflicting. To address these challenges, we formulate network-assisted QoE optimization through a cascade control abstraction. This informs the design of CAscade control-based NEtwork-assisted framework (CANE), a practical network-assisted QoE framework. CANE uses machine learning (ML) techniques to approximate each player’s behavior as a black-box model and model predictive control (MPC) to achieve a near-optimal solution. We evaluate CANE through realistic simulations and show that CANE improves multiplayer QoE fairness by <inline-formula> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula>50% compared with pure client-side adaptive bitrate (ABR) algorithms and by <inline-formula> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula>20% compared with uniform traffic shaping.
Original language | English (US) |
---|---|
Pages (from-to) | 1-12 |
Number of pages | 12 |
Journal | IEEE Transactions on Control Systems Technology |
DOIs | |
State | Accepted/In press - 2023 |
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Electrical and Electronic Engineering
Keywords
- Bandwidth
- Bit rate
- Cascade control framework
- Internet
- Prediction algorithms
- Predictive control
- Quality of experience
- Video on demand
- fairness in quality of experience (QoE)
- model predictive control (MPC)
- multiplayer video streaming
- network-assisted scheme
- resource allocation