Signal Phasing and Timing Prediction Using Connected Vehicle Data

Signal phasing and timing can be adaptive and actuated in practice. This makes it challenging to understand what the cycle length and phase duration of the next few cycles will be. Many innovative applications can be designed based on the knowledge of future signal timing states such as dilemma zone warning, efficient route planning, and so forth. This work proposes a long short-term memory model capable of predicting both cycle length and phase duration prediction up to six cycles in the future. GPS information of several vehicles are merged with signal timing information of eight intersections. Several key features such as waiting time, approach speed and acceleration, departing speed and acceleration, are calculated based on the geolocation of individual journeys. The results show that cycle length prediction can reach mean absolute error (MAE) of about 7 s while phase prediction MAE is about 9 s.

Automated summary

Signal phasing and timing can be adaptive and actuated, making it difficult to predict future cycle length and phase duration. This study proposes a long short-term memory model to predict cycle length and phase duration up to six cycles ahead. By merging GPS information and signal timing information, key features such as waiting time, approach speed, and acceleration are calculated. The results show a mean absolute error of about 7 seconds for cycle length prediction and 9 seconds for phase prediction.