“Social Benchmarking of QoS & QoE in Cellular Data Networks“
Hirochika Asai, The University of Tokyo, Japan; Kensuke Fukuda, National Institute of Informatics, Japan; Hiroshi Esaki, The University of Tokyo, Japan
Abstract – We developed a benchmarking tool called NetBench to measure the quality of service (QoS) and quality of experience (QoE) in cellular data networks and to share them among users of the tool. This tool has a user interface that displays the summarized QoS and QoE on a map to motivate users to share their QoS and QoE. We have been continuously collecting QoS related metrics and a QoE related metric from this tool. We characterize the QoS and QoE of three cellular data network carriers (one is a CDMA2000 operator and the others are UMTS/WCDMA operators supporting HSDPA/HSUPA) in Japan from the collected data for eight months. We demonstrate that round trip time (RTT) among other QoS related metrics such as signal strength and packet loss rate is one of the metrics that explains the performance of TCP throughput. We also demonstrate that the packet loss rate and RTT of the QoS related metrics affects the QoE. These overall results of QoS and QoE indicate that the characteristics of QoE is explained by QoS, especially by RTT.
“Query Guidance with Transmission Records for Efficient Content Searching in Unstructured Peer-to-Peer Networks“
Takuya Tomimatsu, Shinji Sugawara and Yutaka Ishibashi, Nagoya Institute of Technology, Japan
Abstract – Recently, a lot of content searching methods applied to Peer-to-Peer (P2P) networks have been researched, in which the peers accomplish their duties evenly and autonomously. However, especially in unstructured P2P networks, the amount of traffic grows when a flooding-based content searching method is adopted because of no contents indexing capability. Accordingly, in this paper, for unstructured P2P networks, we propose an efficient content searching method in which content searching queries are guided properly only to the proven peers by using query transmission records kept in each peer. Consequently, the number of wasted queries can be reduced. In addition, we discuss the availability of the proposal by using computer simulations.