Non-payment Incentive Mechanism Design for Resource Allocation in A Private Cloud System

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations


Related Research Unit(s)


Original languageEnglish
Pages (from-to)44147-44160
Journal / PublicationIEEE Access
Online published31 Jul 2018
Publication statusPublished - 2018


Truthful resource request from users is the premise to achieve the maximum social welfare in an enterprise private cloud. To stimulate the truthfulness of users, most previous works mainly rely on introducing the payment, which however, might not be applicable in enterprise private clouds, where there is a lack of money transfer. To address this issue, this paper proposes non-payment but efficient mechanisms in private clouds to stimulate the truthfulness of the users and meanwhile maximize the social welfare. Moreover, different from previous works that allow only one job request from one user, this paper studies a more general model, where multiple jobs can be submitted by each user. Specifically, we consider two task models, the migration-admissible model and non-migration model. In the former model, jobs can be executed at different servers, and may undergo migration if necessary. Alternatively, in the latter model, jobs can only be executed at one server without migration. For both models, we design incentive resource allocation mechanisms to maximize the social welfare. Theoretically analysis shows that the proposed mechanisms are truthful for general monotonic profit functions and the worst-case performance on the social welfare are well-bounded within a constant factor of the optimal solution for linear profit functions. Simulation results also demonstrate that the performances of the proposed mechanisms are very close to the optimal solution, in terms of maximizing the social welfare.

Research Area(s)

  • Approximation, Cloud computing, Computer science, Incentives, Mechanism design, Non-payment, Resource allocation, Resource management, Schedules, Servers, Simulation, Task analysis