Emergent behavior is a core trait of SoSs. But the emergence cannot be predicted before its appearance. We propose a method which using Semi-autonomous Agent based simulation to detect the emergent behaviors of SoSs. Agent based Modeling and Simulation are available for the observation of emergent behaviors of SoSs. We propose the multi-agent based simulation methods to demonstrate the evolution of SoSs. Semi-autonomous Agents is applied to model the elements which are consists of SoSs. The framework of Parallel executive and feedback to real world is used to verify and validate the emergent properties which are useful to the SoSs or not. Through the comparation between real world executive results and simulation outcomes, we could regulate the parameters or adjust rules running in the SoSs and guide the emergent behavior of SoSs to the stakeholder's desire direction.