Aiming at the problems existing in urban ring road, this paper proposes a green wave coordination method based on multi-agents for loop intersections using multi-agent system autonomy, distribution, coordination, active learning and other excellent features. The intersections are regarded as an intelligent body. The adjacent agents can communicate and exchange information. Using the intelligent system memory storage and reasoning learning ability, the green wave coordination optimization is performed on multiple intersections on the loop, from the algorithm model and The algorithm is described and deduced from the perspective of parameter description and phase selection strategy under coordinated mode. The effectiveness of the proposed algorithm is verified by experimental simulation.