In this part, similar to Part I of this paper, a new two-level method for nonlinear optimal control of large scale systems is introduced. This approach is based on Interaction Balance Principle for coordination of large-scale systems. In the first level, the optimization problems are solved for nonlinear dynamics using a gradient method, and in the second level, the coordination is done using the gradient of errors to improve the convergence rate in compare to the classical Goal Coordination method and obtain the overall optimal solution. The efficacy and advantages of the new approach is shown in an application example.