The work presented in this paper is a contribution to solving a widespread problem in the field of system design, embedded the placement of a large application on an architecture (NOC). Application is represented by a set of tasks that communicate with each other by sending message via bus on a heterogeneous architecture. Our role is to place the tiles (task) on different elements (core) of architecture with the objectives of minimizing time execution and the energy consumption under the constraints of load balancing, bandwidth, available memory and size of the queue waiting processors. To solve this problem, we used in the context of our present work, a new meta-heuristic algorithm Particle Swarm. it has proved its effectiveness in many fields such as optimization of networks, image processing and even control of industrial systems but it was never applied in our domain.