Short term traffic flow prediction research based on chaotic local model

Abstract

Short term traffic flow prediction is of great significance for easing traffic congestion and maximizing road carrying capacity. This paper proposes an effective algorithm for traffic flow prediction. Firstly, the algorithm analyzes the characteristics of daily traffic flow. According to the difference, the daily traffic flows are divided into workday type, and holiday type, and each type of data is integrated to predict the corresponding day type traffic flow. Then based on phase space reconstruction, a chaotic local prediction algorithm is proposed. The algorithm uses Euclidean distance to select phase space reference neighborhood successively, and support vector machine is used to establish the mapping relationship between neighboring points. This algorithm is used to predict the data of an intersection in Guangzhou, and satisfactory prediction accuracy has been achieved.