Control of distributed servers for quality-fair delivery of multiple video streams

Abstract

This paper proposes a quality-fair video delivery system able to transmit several encoded video streams to mobile users sharing some wireless resource. Video quality fairness, as well as similar delivery delay is targeted among streams. The proposed control system is implemented within some aggregator located near the bottleneck of the network. This is done by allocating the transmission rate among streams based on the quality of the already encoded and buffered packets in the aggregator. Encoding rate targets are evaluated by the aggregator and fed back to each remote video server, or directly evaluated by each server in a distributed way. Each encoding rate target is adjusted for each stream independently based on the corresponding buffering delay in the aggregator. The transmission and encoding rate control problems are addressed with a control-theoretic perspective. The system is described with a multi-input multi-output model and several Proportional Integral (PI) controllers are used to adjust the video quality as well as the buffering delay. The study of the system equilibrium and stability provides guidelines for choosing the parameters of the PI controllers. Experimental results show that better quality fairness is obtained compared to classical transmission rate fair streaming solutions while keeping similar buffering delays.

A linear consensus approach to quality-fair video delivery

“…In this paper we analyze the model considered in [4] where quality fairness is conjugated as ensuring the same rate-utility value for all video streams. The dynamics of the i-th video stream, i = 1, .…”

“…GoPs of 10 frames are considered, thus the GoP duration is T = 0.33 s. The considered utility is the Peak Signal-to-Noise Ratio (PSNR). To tune the controllers, the rate-utility characteristics of each GoP is estimated as described in [3], [4]. The control is assumed performed within the MANE, closely located to the BS to which the clients are connected.…”

“…Feedback control techniques have been considered in [3], [4] to reach a quality fairness among users, while controlling the level of the buffers in the network or the buffering delay. However, the tuning of the parameters is nontrivial and has been performed heuristically in these works.…”

“…Optimal control gains may then be chosen to maximize, e.g., the convergence rate. Simulation results show that the control gains are appropriately designed, providing better performance in terms of quality fairness than the reference scheme [3], [4], where a heuristic technique is used for the tuning. Moreover, the dependency in the characteristics of the video contents and in the number of users in the expression of the optimal gains is evidenced.…”

Rate Adaptation and Admission Control for Video Transmission With Subjective Quality Constraints

“…Most existing rate-adaptation algorithms such as [10]- [15], [22], [23] employ average video quality as the proxy of QoE due to its simplicity in analysis. As shown in Table I, however, average quality does not efficiently capture the impact of quality fluctuations.…”