Platoon Dispersion Prediction under the Condition of Adjacent Cycle Traffic Flow Overlapping Based on Support Vector Regression

Coordinated signal control can improve the continuity of vehicular traffic flow movement and reduce delay. Cycle flow profile is the base for calculating coordinated signal control parameters. Platoon dispersion characteristic determines the cycle flow profile. So, improving platoon dispersion prediction accuracy can obtain significant benefit for signal coordination. When the velocities of the vehicles vary greatly, faster vehicles of next cycle can catch up the slower vehicles of the current cycle. Traffic flow overlapping of adjacent cycle is an important characteristic. The paper adopts support vector regression to predict platoon dispersion and compares prediction accuracy with Robertson formula. The results are encouraging, support vector regression has higher prediction accuracy.