A Collaborative Cache Strategy Based on Utility Optimization  

作　　者：Pingshan Liu Shaoxing Liu Guimin Huang 

机构地区：[1]Business School,Guilin University of Electronic Technology,Guilin,China [2]Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin,China

出　　处：《国际计算机前沿大会会议论文集》2021年第1期140-153,共14页International Conference of Pioneering Computer Scientists, Engineers and Educators（ICPCSEE）

基　　金：This research was supported by the national key research and development program of China(No.2020YFF0305301);the National Natural Science Foundation(61762029,U1811264).References。

摘　　要：With the continuous development of network technology, the numberof streaming media videos is growing rapidly. More and more users are watchingvideos through the Internet, which leads to the increasing huge server load andthe increasing transmission cost across ISP domains. A feasible scheme to reducetransmission cost across ISP domains and alleviate the server load is to cachesome popular videos in a large number of terminal users. Therefore, in this paper,in order to utilize the idle resources of the terminal peers, some peers with goodperformance were selected from the fixed peers as the super peers, which wereaggregated into a super peer set (SPS). In addition, with the supply and demandrelation of streaming videos among ISP domains, a mathematical model was formulatedto optimize the service utility of ISP. Then, a collaborative cache strategywas proposed based on the utility optimization. The simulation results show thatthe strategy proposed can effectively improve the user playback fluency and hitrate while ensuring the optimal service utility.

关 键 词：PEER-TO-PEER Super Peer Set Collaborative cache management ISP Utility optimization 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]