Improved algorithmic mechanism based on game theory in computational grids

Computational grids(CGs)aim to offer pervasive access to a diverse collection of geographically distributed resources owned by different self-interested agents or organizations.These agents may manipulate the resource allocation algorithm in their own benefit,and their selfish behavior may lead to severe performance degradation and poor efficiency. In this paper,game theory is introduced to solve the problem of barging for resource collection in heterogeneous distributed systems.By using the Cournot model that is an important model in static and complete information games,the algorithm is optimized in order to maximize the benefit.It can be seen that the approach is more suitable to the real situation and has practical use.Validity of the solutions is shown.