| Presentation | 2010-01-22 A Proposal of A Reinforcement Learning-Based Dynamic Session Management in Virtual Server Environments Kimihiro MIZUTANI, Izumi KOYANAGI, Takuji TACHIBANA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In a virtualized server environment, machine resources such as CPU and memory are shared by multiple services. In such a environment, as the number of sessions for each service increases, the amount of resources that are utilized by the services increases. If thrashing occurs due to the lack of resources, the performance of the server is degraded. It is effective to estimate the amount of used resources, however, it is hard to estimate the amount of resources that are used dynamically by multiple services. In this paper, we propose a dynamic session management based on a reinforcement leaning in order to utilize the resources effectively and avoid the thrashing. In the proposed method, a learning agent estimates the amount of used resources from the response time for a service request. Then, the agent decides the acceptance or reject of all arriving session request with Q-learning. Because this method can be implemented easily in a virtualized machine, it is expected that our proposed method is used in a real environment. We evaluate the performance of our proposed method with simulation. From simulation results, we show that the proposed method can allocate the resources to multiple services effectively while avoiding the thrashing and can perform the priority control for multiple services. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Virtual server environments / Session management / Rein forcement learning / Thrashing / Resource allocation |
| Paper # | ICM2009-44 |
| Date of Issue |
| Conference Information | |
| Committee | ICM |
|---|---|
| Conference Date | 2010/1/14(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Information and Communication Management(ICM) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Proposal of A Reinforcement Learning-Based Dynamic Session Management in Virtual Server Environments |
| Sub Title (in English) | |
| Keyword(1) | Virtual server environments |
| Keyword(2) | Session management |
| Keyword(3) | Rein forcement learning |
| Keyword(4) | Thrashing |
| Keyword(5) | Resource allocation |
| 1st Author's Name | Kimihiro MIZUTANI |
| 1st Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology() |
| 2nd Author's Name | Izumi KOYANAGI |
| 2nd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| 3rd Author's Name | Takuji TACHIBANA |
| 3rd Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology |
| Date | 2010-01-22 |
| Paper # | ICM2009-44 |
| Volume (vol) | vol.109 |
| Number (no) | 378 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |