A feasibility of toll road project investment that uses Public Private Partnership (PPP) scheme is determined by the accuracy of traffic forecasting as a reflection of revenue streams. This is due to some or all of the projects generally use loan funds with warranty in the form of confidence to the number of traffic forecasting that will occur, or even without using other guarantees. Therefore, accuracy and reliability in predicting the traffic volume are needed for risk and uncertainty of the toll road project to be invested. Unfortunately, the performance of toll road traffic forecasting in the first few years of operation has shown an overestimation of 20% to 30%. The problem is known as the ramp-up period phenomenon. The conventional model commonly used is aggregated (base on socio-economic and demographic) so that it has not been able to anticipate these problems. while the traffic pattern during ramp-up period is more determined by perception of traveler to route choice process. Therefore, the disaggregation model is more realistically used to predict toll road traffic during this period. Approach of traveler’s decision-making attitude to route choice process due to operating toll road will be used to describe the ramp-up phenomenon that occurs. The study has developed a simulation model approach to predict the magnitude of the volume of traffic flow during ramp-up period which can describe the decision-making attitude of the traveler in choosing the route due to the existence of a new toll road infrastructure. The analysis of the problem is proposed with an agent-based model simulation approach involving reinforcement learning to get prediction of the volume of traffic flow on the toll road from day to day.
- Principal Investigator : Prof. Ir. Ade Sjafruddin, M.Sc., Ph.D.
- Members : Dr. Eng. Ir. Russ Bona Frazila, M.T.
Dr. Eng. Febri Zukhruf
Weka Infra Dharmawan
Taufiq Suryo Nugroho
Arya Bagus Ristya