| Project/Area Number |
18500088
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | Nagasaki University |
|---|
Principal Investigator |
NARAZAKI Shuji Nagasaki University, Faculty of Engineering, Associate professor (80253475)
|
|---|
| Project Period (FY) |
2006 – 2007
|
| Project Status |
Completed (Fiscal Year 2007)
|
| Budget Amount *help |
¥1,870,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥270,000)
Fiscal Year 2007: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2006: ¥700,000 (Direct Cost: ¥700,000)
|
|---|
| Keywords | web system / P2P / prefetch / communication latency / web recommmndation / load balancing / P2Pシステム / インターネット / webシステム |
|---|
| Research Abstract |
Based on the new generation web system developed in last year, which consists of Chord-based P2P seb server system and a JavaScript agent on web browser which selects appropriate server based on probabilistic distributed hash table, we planned to reduce communication latency in two ways: using a popular content list which reflects loads of servers and using user profile matching with most common transition sequences in logs of web servers.
We also propose a method to prefetch new contents based on the tendency of users to access newer contents.
Experiments on our e-learning system shows that our proposed approach can prefetch 40% of contents that users select with 3 times accesses to servers.
|
