Multi-objective eco-routing for dynamic control of connected & automated vehicles

Deep Learning Based Proactive Multi-Objective Eco-Routing Strategies for Connected and Automated Vehicles

“…GHG cost5 is the most representative and suitable costing approach as it is based on the reflective ER and speed on the studied link as illustrated in Equation 5. Due to the quasi-convex relationship between the speed and GHG ER (Djavadian et al, 2020), too low or too high speed would trigger higher emission rates. Links with too high speed are associated with high GHG ERs but less travel time.…”

“…This is due to the complicated relationship between the GHG ER and the predictors, while speed has more straight forward relationships with the used predictors. For instance, speed and density have a monotonically decreasing relationship (Papacostas and Prevedouros, 1993), while the GHG ER has a quasi-convex relationship with the most important predictor (speed) (Djavadian et al, 2020). It is crucial to note that the developed LSTM predictive models are generally suitable for urban networks.…”

“…Several studies in the literature developed reactive eco-routing systems. For instance, Alfaseeh et al (2019) and Djavadian et al (2020) developed single as well as multi-objective eco-routing for CAVs and found encouraging results. A developed review paper by classified eco-routing models and illustrated the strengths and weaknesses of each category.…”

“…This work developed proactive multiobjective eco-routing strategies that can be implemented in routing systems for connected and automated vehicles. Similarly to the proposed reactive routing schemes in Djavadian et al (2020), a microscopic level of aggregation, an urban network as a case study, and a high level of spatial (link level) and temporal (1 min) resolution were employed in this study. Unlike the previous proactive approaches that were centralized solutions, this study developed the proactive routing strategies based on a dynamic distributed routing control framework, End-to-End Routing for Connected and Automated Vehicles (E2ECAV) (Farooq and Djavadian, 2019).…”

“…Although normalizing by the number of lanes resulted in underestimation for the links with a large number of lanes, reductions in the travel time and produced emissions were noticed when multi-objective routing was applied. Djavadian et al (2020) developed reactive multi-objective eco-routing strategies for CAVs, considering the cost of idling as a penalty at the downstream intersection of a link at every interval. The authors used the marginal cost for GHG in the objective function.…”