摘要：Due to the security threat to task scheduling problems in the grid environment, by considering both the inherent security and behavior safety of grid resource nodes, security benefit functions and credibility assessment strategies of grid resource nodes are constructed respectively. At the same time, the corresponding membership function is established in order to establish the membership between task security requirements and resource security attributes. Based on these, a new grid dependent tasks security scheduling model is set up. In order to solve this model, the particle evolution equation is re-designed by combining the specific characteristics of the dependent task scheduling problem. Meanwhile, in order to prevent the algorithm falling into local optimum, a uniform speed of disturbance is adopted and a new discrete Particle Swarm Optimization algorithm is proposed. Simulation results show that this algorithm has better scheduling length and higher safety performance than the genetic algorithm.
