Adaptive Video Streaming for Wireless Networks with Multiple Users and Helpers

Abstract

We consider the design of a scheduling policy for video streaming in a wireless network formed by several users and helpers (e.g., base stations). In such networks, any user is typically in the range of multiple helpers. Hence, an efficient policy should allow the users to dynamically select the helper nodes to download from and determine adaptively the quality level of the requested video segment. In order to obtain a tractable formulation, we follow a "divide and conquer" approach: i) We formulate a Network Utility Maximization (NUM) problem where the network utility function is a concave and componentwise nondecreasing function of the time-averaged users' requested video quality index and maximization is subject to the stability of all queues in the system. ii) We solve the NUM problem by using a Lyapunov Drift Plus Penalty approach, obtaining a dynamic adaptive scheme that decomposes into two building blocks: 1) adaptive video quality and helper selection (run at the user nodes); 2) dynamic allocation of the helper-to-user transmission rates (run at the help nodes). Our solution provably achieves NUM optimality in a strong per-sample path sense (i.e., without assumptions of stationarity and ergodicity). iii) We observe that, since all queues in the system are stable, all requested video chunks shall be eventually delivered. iv) In order to translate the requested video quality into the effective video quality at the user playback, it is necessary that the chunks are delivered within their playback deadline. This requires that the largest delay among all queues at the helpers serving any given user is less than the pre-buffering time of that user at its streaming session startup phase. In order to achieve this condition with high probability, we propose an effective and decentralized (albeit heuristic) scheme to adaptively calculate the pre-buffering and re-buffering time at each user. In this way, the system is forced to work in the "smooth streaming regime," i.e., in the regime of very small playback buffer underrun rate. Through simulations, we evaluate the performance of the proposed algorithm under realistic assumptions of a network with densely deployed helper and user nodes, including user mobility, variable bit-rate video coding, and users joining or leaving the system at arbitrary times. Contributions:In order to obtain a tractable formulation, we follow a "divide and conquer" approach, conceptually organized in the following steps: i) We formulate a Network Utility Maximization (NUM) problem [19]-[21] where the network utility function is a concave and componentwise non-decreasing function of the time-averaged users' requested video quality index and the maximization is subject to the stability of all queues in the system. The shape of the network utility function can be chosen in order to enforce some desired notion of fairness across the users [22].ii) We solve the NUM problem in the framework of Lyapunov Optimization [23], using the drift plus penalty (DPP) approach [23]. The obtained solution is...

Dynamic Resource Allocation and Layer Selection for Scalable Video Streaming in Femtocell Networks: A Twin-Time-Scale Approach

“…However, they mainly focus their attention on scheduling the access to both the Macrocell Base Station(MBS) and to the FBS. In [29] and [30], the authors jointly consider the wireless transmission scheduling and video quality adaptation in dense wireless networks. In [31], time-domain resource partitioning between the macrocell and small cells is invoked for optimizing the delivery of Dynamic Adaptive Streaming over HTTP (DASH).…”

Optimal Dynamic Multicast Scheduling for Cache-Enabled Content-Centric Wireless Networks

“…By exploiting the structural properties of the optimal policy in Theorems 1 and 2, we modify (22) in Step 3 (policy update) of Algorithm 3 to reduce its computational complexity. The modified step is given by Algorithm 4 (structured policy update).…”

“…The modified step is given by Algorithm 4 (structured policy update). Replacing (22) in Step 3 of Algorithm 3 with Algorithm 4, we obtain a low complexity PIA, which is referred to as the structured policy iteration algorithm (SPIA). From [24, Chapter 8.11.2], we can see that SPIA also converges in a finite number of iterations to the optimal policy µ * in (11) and hence is an optimal algorithm.…”

A Novel Clustering Tree-based Video lookup Strategy for Supporting VCR-like Operations in MANETs

“…By making use of the cooperation between peers, Peer-to-Peer (P2P) technologies can provide the feasible solution for the large-scale deployment of media streaming service. With the development of Mobile Internet, mobile Peerto-Peer (MP2P) technologies have emerged as a state-of-the-art technology for video resource sharing in MANETs [5][6][7][8].…”