Application of the support vector machine and heuristic k-shortest path algorithm to determine the most eco-friendly path with a travel time constraint

This study aims to determine an eco-friendly path that results in minimum CO2 emissions while satisfying a specified budget for travel time. First, an aggregated CO2 emission model for light-duty cars is developed in a link-based level using a support vector machine. Second, a heuristic k-shortest path algorithm is proposed to solve the constrained shortest path problem. Finally, the CO2 emission model and the proposed eco-routing model are validated in a real-world network. Specifically, the benefit of the trade-off between CO2 emission reduction and the travel time budget is discussed by carrying out sensitivity analysis on a network-wide scale. A greater spare time budget may enable the eco-routing to search for the most eco-friendly path with higher probability. Compared to the original routes selected by travelers, the eco-friendly routes can save an average of 11% of CO2 emissions for the trip OD pairs with a straight distance between 6 km and 9 km when the travel time budget is set to 10% above the least travel time. The CO2 emission can also be reduced to some degree for other OD pairs by using eco-routing. Furthermore, the impact of market penetration of eco-routing users is quantified on the potential benefit for the environment and travel-time saving.