Public charging station occupancy prediction plays key importance in developing a smart strategy to reduce electric vehicle (EV) operator and user inconvenience. However, existing studies are mainly based on conventional econometric or time series methodologies with limited accuracy. We propose new mixed long short-term memory neural network incorporating both historical state sequences time-related features for multistep discrete prediction. Unlike the LSTM networks, proposed model...

We propose a ridesharing strategy with integrated transit in which private on-demand mobility service operator may drop off passenger directly door-to-door, commit to dropping them at station or picking up from station, both pickup and two different stations vehicles. study the effectiveness of online solution algorithms for this proposed strategy. Queueing-theoretic vehicle dispatch idle relocation are customized problem. Several experiments conducted first synthetic instance design test...

Understanding temporal rhythms in travel and activity patterns has been recognized as an important issue for the effective management of urban congestion. Research issues related to this topic concern degree which behaviour varies from one day another, differences between weekday weekend travel, determinants variability. Thanks a seven-day diary collected 707 individuals city Ghent (Belgium) 2008, study goes further by studying variability according various time periods within week analysing...

This work contributes to develop a new methodology identify empirical-data-driven causal structure of domain knowledge. We propose an algorithm as two-stage procedure by first drawing relevant prior partial relationships between variables and using them constraints in learning task Bayesian networks (BNs). The latter is then based on model averaging approach obtain statistically sound BN. empirical study focuses modeling commuters' travel mode choice. present experimental results testing the...

Viability of electric car-sharing operations depends on rebalancing algorithms. Earlier methods in the literature suggest a trend toward non-myopic algorithms using queueing principles. We propose new policy cost function approximation. The is modeled as p-median relocation problem with minimum flow conservation and path-based charging station capacities static node-charge graph structure. NP-complete, so heuristic proposed that ensures feasible solutions can be solved an online system....

One of the determinants travel satisfaction is 'dissonance', or difference between someone's actual and their preferred ideal travel. Previous studies never questioned use as a reference point to assess satisfaction. We how what extent changes in commute dissonance, among other determinants, affect by applying prospect theory with alternative points. Results indicate that negative dissonant commuters (i.e., time > ideal) are significantly less satisfied commute, but opposite does not hold....

Existing mobility-on-demand service has a major inefficiency for its operating policy design by disregarding the opportunity in cooperation with other transportation networks. In this work, dynamic bi-/multi-modal vehicle dispatching and routing algorithm is proposed to address real-time of ride-sharing (feeder) services coordination presence existing public We propose solution based on concept shareability group bundle requests find optimal passengers-vehicles assignment least cost ensure...

Reducing car use and promoting public transport in the cross border area of Luxembourg has become a priority for sustainable development Greater region. In this study, author analyzes daily mobility mode choice behavior these workers, particular, focusing on their multimodal choices (e.g. park ride choice) trip chaining behavior. A rule-based approach based Bayesian networks is proposed to capture non-linear effects related determinants/constraints individuals’ The result shows network...

In this study, we apply a latent class choice modelling approach to the employees of European Investment Bank and Court Justice Union in Luxembourg investigate commuting mode behaviour by incorporating individual preference heterogeneity. We found two-segment differentiation determined their household locations, attitudes towards transport modes as well socio-demographic characteristics. Validity overall goodness-of-fit are compared with conditional multinomial Logit model. The empirical...

We tackle the problem of evaluating impact different operation policies on performance a microtransit service. This study is first empirical application using stable matching modelling framework to evaluate cost allocation and pricing mechanisms extend deterministic model stochastic reliability-based one consider user's heterogeneous perceptions utility service routes. The proposed applied evaluation Kussbus in Luxembourg. found that current not outcome. By reducing their route operating...

The accelerated electrification of transport systems with EVs has brought new challenges for charging scheduling, fleet management, and infrastructure location configuration planning. In this review, we have provided a systematic review the recent development in strategic, tactical, operational decisions demand responsive system planning using electric vehicles (EV-DRT). We summarized developments mathematical modeling approaches identified future research directions. A list existing...

Coordinating the charging scheduling of electric vehicles for dynamic dial-a-ride services is challenging considering queuing delays and stochastic customer demand. We propose a new two-stage solution approach to handle vehicle minimize costs daily operations fleet. The comprises two components: online vehicle–charger assignment. A battery replenishment model proposed obtain schedules by minimizing while satisfying driving needs serve customers. In second stage, an assignment developed total...

The system optimal routing problem has been widely studied for road networks, though less considered public transit systems. Traditional shortest path–based multimodal itinerary guidance systems may deteriorate the performance when assigned lines become congested. dynamic model is formulated that issue. represented by a multilevel graph to explicitly simulate passenger flow and operations. A solution algorithm based on cross entropy method proposed, its compared with of successive averages...

According to the Intergovernmental Panel on Climate Change (IPCC), in 2010 transport sector was responsible for 23% of total energy-related CO2 emissions (6.7 GtCO2) worldwide. Policy makers Luxembourg are well-aware challenges and setting ambitious objectives at country level mid long term. However, a framework assess environmental impacts from life cycle perspective scale policy scenarios, rather than individual vehicles, is lacking. We present novel linking activity-based modeling with...

Multimodal resource constrained shortest path problem consists of finding a least travel time with multiple resources and mode chain constraints on multimodal transportation network. Existing solution approaches based Lagrangian relaxation technique cannot take into account the sequence constraint used modes in path. In this study, we propose fast A*-based label setting algorithm to solve efficiently dynamic problem. A multilevel graph is proposed for modeling network provided time-dependent...