Aiming at increasing the utilization of the substrate network resources

we model the VN embedding problem as an integer linear programming (ILP) with no assumption that substrate network needs to support path splitting.Then we propose a new VN embedding algorithm based on particle swarm optimization (short for VNE-PSO) for solving this problem.In VNE-PSO

the resource cost of VN embedding is considered as the fitness function and the parameters and operations of the particles in PSO are redefined according to the ILP model of the optimal VN embedding problem.The simulation results demonstrate that the proposed algorithm can increase the long-term average revenue and acceptance ratio while decreasing the runtime comparing with existing approaches.