Impact of Execution Time on Adaptive Wireless Video Scheduling
Impact of Execution Time on Adaptive Wireless Video Scheduling
复制标题
DOI：
10.1109/jsac.2014.140408
复制
发表时间：
2014-03
影响因子：
16.4
通讯作者：
Liang Zhou;Zhen Yang;Haohong Wang;M. Guizani
中科院分区：
文献类型：
--
作者：
Liang Zhou;Zhen Yang;Haohong Wang;M. Guizani
为了提高网络性能，自适应无线视频调度技术得到了广泛的研究。然而，现有的调度算法大多假设它们能够瞬间收敛以适应动态的网络状态，即调度的执行时间可以忽略不计。然而，由于无线节点的计算能力有限，这种假设在实践中很难满足，有时甚至不可能满足。这促使我们在本文中解决以下具有挑战性的问题：执行时间对调度性能的影响是什么？为此，我们首先将调度描述为一个随机优化问题，使我们能够以一种易于处理的方式开辟一个新的性能程度。其次，我们建立了执行时间与视频质量之间的联系，并严格证明了执行时间不利于稳定区域，而有利于流量平衡。因此，这些结果有助于揭示设计高效视频传输系统的基本调度准则。
Adaptive wireless video scheduling has been widely studied to improve network performance. However, the majority of existing scheduling algorithms assume that they are able to converge instantaneously to adapt to a dynamic network state, that is, the execution time of the scheduling can be ignored. Nevertheless, due to the limited computation capacity of wireless nodes, this assumption is very difficult, sometimes even impossible, to satisfy in practice. This motivates us to address in this paper the following challenging question: what is the effect of the execution time on the scheduling performance? To this end, we first characterize the scheduling as a stochastic optimization problem that enables us to open up a new degree of performance to exploit in a tractable manner. Next, we build a connection between the execution time and video quality, and rigorously prove that the execution time is disadvantageous to the stability region, but advantageous to the flow balance. Therefore, these results are helpful to shed insights on fundamental scheduling guidelines on designing an efficient video transmission system.