Traffic congestion is the most frequent, wide-ranging and influential problem among all the traffic problems. The key to this problem is to identify and analyze traffic congestion. This paper reviewed the methods of traffic congestion identification from the perspectives of traditional traffic flow theory and machine learning. Traditional traffic flow theory adopts models such as indicators, MFD, cellular automata, CTM and dual-flow models, using the theory of physics and mathematics to describe the traffic behavior characteristics. The models are reasonable and simple, with clear physical meaning and also with many restrictions. The probabilistic graphical model and machine learning model are practical and not constrained by fixed structures. This paper discussed the research ideas, solutions and existing problems of different congestion identification methods by combining the specific model methods. It summarized the existing traditional traffic flow theory methods and machine learning methods, and pointed out the future development direction.