DCVS A Dynamic Control for Video Traffic in SPICE

DCVS A Dynamic Control for Video Traffic in SPICE

Yu Chen (Wuhan Textile University, Wuhan, China), Aiwu Shi (Wuhan Textile University, Wuhan, China), Kai He (Wuhan Textile University, Wuhan, China), Zhiqiang Hu (Wuhan Textile University, Wuhan, China) and Nan Su (Wuhan Textile University, Wuhan, China)
Copyright: © 2018 |Pages: 14
DOI: 10.4018/JITR.2018070102
OnDemand PDF Download:
List Price: $37.50
10% Discount:-$3.75


This article describes how with the development of cloud computing and virtualization technology, the desktop virtualization solution is becoming more and more mature. As a virtual desktop transport protocol, SPICE is used for deploying virtual desktops on servers and remote clients with high performance. However, it will take up a lot of network bandwidth and cause network congestion in a relatively poor network environment on video transmission. To solve this problem, a dynamic adjustment for video traffic (DCVS) in SPICE is proposed. It can dynamically adjust the bit rate of the video encoding according to the state of the virtual buffer and the feedback from client. The experiment results prove that DCVS can effectively reduce the video traffic and the probability of congestion.
Article Preview

SPICE protocol is an open source virtual desktop transport protocol, providing users with interactive experience similar to the local hosts. SPICE has the advantages of good image display experience, high transmission security. But it also has some shortcomings, such as large consumption of the switching image compression algorithm, lack of video processing capacity, lack of controllability (Wang, Yu, Li, Zhu, & Sheng, 2015) and so on. In order to solve these problems, some improvement approaches have been proposed. In order to achieve the progressive image transmission, Xu and Lan (2013) propose using JPEG2000 (Wang, Zhu, Liu, & Qi, 2016) compression algorithm to replace the original image compression algorithm, in which the image and video compression algorithms can be switched smoothly. Qiao (2013) proposes using discrete wavelet transform (Chen, Wang, & Cheng, 2011) to replace the original discrete cosine transform video compression in Spice to construct a new video compression method, which enhances the ability of SPICE video processing. Wang, et al (2015) adds a user controlled transparent file transfer mechanism in SPICE. Most of improvement schemes about SPICE are optimized graphics, video compression mechanism, and user controllable. However, in the video transmission, due to lack of network adaptability, SPICE consumes a lot of network bandwidth, and might causes network congestion (Kong, Zhao, & Wan, 2005) in a relatively poor network environment, especially in WAN. The service availability of cloud computing also can be reduced (Lv, Lin, Wang, Feng, & Zhou, 2015). In this article, we propose a method to improve SPICE.

Figure 1.

Virtual desktop infrastructure


This paper indicates the shortcomings of SPICE on control of video traffic (Nieh, Yang, & Novik, 2003), and proposes DCVS that control video traffic output by using the virtual buffer and adjust encoder bit rate through the client feedback mechanism. DCVS enables the SPICE to dynamically adjust the image bit rate in the process of video transmission. In the end, the experiment results prove that the optimization method can effectively reduce the video bandwidth consumption and the probability of congestion by comparing the change of network traffic and the lost frame of the video before and after optimization. Figure 1 shows the virtual desktop infrastructure.

Complete Article List

Search this Journal:
Volume 16: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 15: 6 Issues (2022): 1 Released, 5 Forthcoming
Volume 14: 4 Issues (2021)
Volume 13: 4 Issues (2020)
Volume 12: 4 Issues (2019)
Volume 11: 4 Issues (2018)
Volume 10: 4 Issues (2017)
Volume 9: 4 Issues (2016)
Volume 8: 4 Issues (2015)
Volume 7: 4 Issues (2014)
Volume 6: 4 Issues (2013)
Volume 5: 4 Issues (2012)
Volume 4: 4 Issues (2011)
Volume 3: 4 Issues (2010)
Volume 2: 4 Issues (2009)
Volume 1: 4 Issues (2008)
View Complete Journal Contents Listing