.png){kind=icon}
.png){kind=icon}
Return
Concurrent Request Multiplexing for Cloud Composite Service Reservation
.png){kind=icon}
PRE
AI
DOI：10.1109/TSC.2020.2967379.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Combining a series of atomic services into a composite value-added service offers promise in meeting the increasingly diverse needs of users in the cloud market. However, without considering concurrency of composite service requests among multiple users, existing studies seldom focus on the competition relationship among users and thus lack an incentive mechanism to efficiently provide the request strategy of users. In this article, taking into consideration the multi-user competition and interaction with the cloud provider, we design a composite service reservation framework in which users' requests can be rationally and efficiently multiplexed. Due to selfishness, each user tends to expect to maximize its own utility in terms of revenue, payoff, and performance of composite service. The optimization problem is modeled from the perspective of game theory and defined as a non-cooperative game. The existence of Nash equilibrium solution of the formulated game is proved by an equivalent variational inequality problem. An iterative proximate algorithm (IPA) is proposed to find a utility-balanced request strategy, which theoretically leads to a Nash equilibrium solution. A series of simulation experiments are conducted to verify our theoretical analysis. The experimental results show that IPA converges to a Nash equilibrium in an acceptable number of iterations. The stable request strategies can improve the utilities of users and the resource utilization of the cloud provider, as the proposed framework empowers users to transfer requests from peak periods into non-peak ones.
Keywords:
Cloud computing
Nash equilibrium
Games
Multiplexing
Quality of service
Optimization
Cloud computing
composite service
non-cooperative game
nash equilibrium
variational inequality theory
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.8
Papers:
2.1K
Citations:
6.5K