DocumentCode :
3443967
Title :
A Transmission Model Based on Wireless Protocol for Network Auto-Tuning and Pressure Forcasting
Author :
Wang, Jianrong ; Chang, Xinglong ; Zhao Zheng
Author_Institution :
Sch. of Comput. Sci. & Technol., Tianjin Univ., Tianjin
fYear :
2008
fDate :
12-14 Oct. 2008
Firstpage :
1
Lastpage :
5
Abstract :
Today with limited wireless network bandwidth, network application performance often depends on the performance of network transmission. Then, optimizing the transmission model of wireless protocol and perfecting protocol on the wireless network transmission forecast capacity come to be the key point. This paper proposes a transmission model called wireless transmission protocol stack (WTPS), which not only could transfer almost any type of data conveniently using simple operations such as "push" and "pop", but also could make improvement itself by designed machine learning algorithm and give out network pressure prediction based on the real application situation. This paper also proposed related algorithms and a detailed exposition. Further, it\´s a unified transmission model in wireless protocol which could used between server and terminals, terminals and terminals in the protocol of Bluetooth, UWB, ZigBee, and Wi-Fi without any changes.
Keywords :
forecasting theory; learning (artificial intelligence); prediction theory; protocols; radio networks; Bluetooth; UWB; Wi-Fi; ZigBee; machine learning algorithm; network auto-tuning; network pressure prediction; network transmission; pop operation; push operation; transmission model; wireless network; wireless protocol; wireless transmission protocol stack; Access protocols; Algorithm design and analysis; Bandwidth; Bluetooth; Machine learning algorithms; Predictive models; Wireless application protocol; Wireless communication; Wireless networks; ZigBee;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Wireless Communications, Networking and Mobile Computing, 2008. WiCOM '08. 4th International Conference on
Conference_Location :
Dalian
Print_ISBN :
978-1-4244-2107-7
Electronic_ISBN :
978-1-4244-2108-4
Type :
conf
DOI :
10.1109/WiCom.2008.1051
Filename :
4678959
Link To Document :
بازگشت