Origin-destination Demand Research Articles

Improving the variability of urban traffic microsimulation through the calibration of generative parameter models

The calibration of urban traffic microsimulation models is addressed in this paper, focusing on the multivariate distribution of traffic features. This allows to take into account day-to-day variability and possibly complex statistical dependencies, enabling robust validation and the computation of more accurate statistics. Variability in traffic models can be obtained, in principle, by suitably tuning origin-destination demand flows, but this becomes problematic for microsimulation models when complex multivariate distributions are considered, due to excessive dimensionality and nonlinearity. Thus, here we investigate how complex multivariate behavior can be achieved by suitably varying only a subset of the parameters ruling the microsimulation dynamics, without imposing any distribution on the demand flows. To this purpose, rather than looking for fixed values of the parameters, we exploit distribution models having the structure of mixtures of uniforms, through which the simulator parameter values can be randomly sampled, thus replacing the simulator inner randomization mechanism. We formalize the optimization of the mixture parameters through a maximum mean discrepancy principle involving the simulator dynamics, which leads to a large-dimensional non-differentiable problem that we solve through a method based on cross-entropy. Preliminary experiments concerning the application of the proposed methodology to the SUMO simulator show how it is possible to capture quite complex multivariate distributions of target flows varying only four parameters.

Contract-based Inter-user Usage Coordination in Free-floating Car Sharing

We propose a novel distributed user-car matching method based on a contract between users to mitigate the imbalance problem between vehicle distribution and demand in free-floating car sharing. Previous regulation methods involved an incentive system based on the predictions of origin-destination (OD) demand obtained from past usage history. However, the difficulty these methods have in obtaining accurate data limits their applicability. To overcome this drawback, we introduce contract-based coordination among drop-off and pick-up users in which an auction is conducted for drop-off users' intended drop-off locations. We theoretically analyze the proposed method regarding the upper bound of its efficiency. We also compare it with a baseline method and non-regulation scenario on a free-floating car-sharing simulator. The experimental results show that the proposed method achieves a higher social surplus than the existing method.

Integrating data-driven and simulation models to predict traffic state affected by road incidents

ABSTRACT Predicting the traffic conditions in urban networks is a priority for traffic management centres. This becomes very challenging, especially when the network is affected by traffic incidents that vary in both time and space. Although data-driven modelling can be considered an ideal tool for short-term traffic predictions, its performance is severely degraded if little historical traffic information is available under incident conditions. This paper addresses this challenge by integrating data-driven and traffic simulation modelling approaches. Instead of directly predicting the traffic states using limited historical data, we employ a traffic simulation reinforced by data-driven models. The traffic simulation uses newly reported incident information and the estimated origin-destination (OD) demand flows to capture the complex interaction between drivers and road network, and predicts traffic states under extreme conditions. We showcase the capability of the proposed data-driven enforced traffic simulation platform for incident impact analysis in a real-life sub-network in Sydney, Australia.

Assignment Matrix Free Algorithms for On-line Estimation of Dynamic Origin-Destination Matrices

Dynamic Traffic Assignment (DTA) models represent fundamental tools to forecast traffic flows on road networks, assessing the effects of traffic management and transport policies. As biased models lead to incorrect predictions, which can cause inaccurate evaluations and huge social costs, the calibration of DTA models is an established and active research field. When it comes to estimating Origin-Destination (OD) demand flows, perhaps the most important input for DTA models, one algorithm suggested to outperform all the others for real-time applications: the Kalman Filter (KF). This paper introduces a non-linear Kalman Filter framework for online dynamic OD estimation that reduces the number of variables and can easily incorporate heterogeneous data sources to better explain the non-linear relationship between traffic data and time-dependent OD-flows. Specifically, we propose a model that takes advantage of Principal Component Analysis (PCA) to capture spatial correlations between variables and better exploit the local nature of a specific KF recently proposed in literature, the Local Ensemble Transformed Kalman filter (LETKF). The main advantage of the LETKF is that the Kalman gain is not explicitly formulated which means that, differently from other approaches proposed in the literature, there is no need to compute the assignment matrix or its approximation. The paper shows that the LETKF can easily incorporate different data sources, such as traffic counts and link speeds. Additionally, thanks to the PCA, the model can identify local patterns within the data and better explain the correlation between variables and data. The effectiveness of the proposed methodology is demonstrated first through synthetic experiments where non-linear functions are used to benchmark the model in different conditions and then on the real-world network of Vitoria, Spain (2,884 nodes, 5,799 links) using the mesoscopic simulator Aimsun. Results show that the proposed method leads to better state estimation performances with respect to other Ensemble-based Kalman filters, providing improvements as high as 64% in terms of traffic data reproduction with a 17-fold problem dimensionality reduction.

Optimal toll design problems under mixed traffic flow of human-driven vehicles and connected and autonomous vehicles

Compared to human-driven vehicles (HDVs), connected and autonomous vehicles (CAVs) can drive closer to each other to enhance link capacity. Thereby, they have great potential to mitigate traffic congestion. However, the presence of HDVs in mixed traffic can significantly reduce the effects of CAVs on link capacity, especially when the proportion of HDVs is high. To address this problem, this study seeks to control the HDV flow using the autonomous vehicle/toll (AVT) lanes introduced by Liu and Song (2019). The AVT lanes grant free access to CAVs while allowing HDVs to access by paying a toll. To find the optimal toll rates for the AVT lanes to improve the network performance, first, this study proposes a multiclass traffic assignment problem with elastic demand (MTA-ED problem) to estimate the impacts of link tolls on equilibrium flows. It not only enhances behavioral realism for modeling the route choices of HDV and CAV travelers by considering their knowledge level of traffic conditions but also captures the elasticity of both HDV and CAV demand in response to the changes in the level of service induced by the tolls on AVT lanes. Thereby, it better estimate the equilibrium network flows after the tolls are deployed. Then, two categories of optimal toll design problems are formulated according to whether the solution of the HDV route flows, CAV link flows and corresponding origin–destination demand of the proposed MTA-ED problem is unique or not. To solve these optimal toll design problems, this study proposes a revised method of feasible direction. It linearizes the anonymous terms in the upper-level problem by leveraging the analytical sensitivity analysis results of the lower-level MTA-ED problem. This algorithm is globally convergent on the condition that the MTA-ED problem has a unique solution. It can also be leveraged to solve optimal toll design problems when the MTA-ED problem has multiple solutions. Numerical application found that due to disruptive effects on link capacity, using HDVs may significantly reduce the network performance such as customer surplus and total travel demand. The proposed method can assist different stakeholders to find the optimal toll rates for HDVs on AVT lanes to maximize the network performance under mixed traffic environments.

Dynamic Origin-Destination Prediction in Urban Rail Systems: A Multi-Resolution Spatio-Temporal Deep Learning Approach

Short-term demand predictions, typically defined as less than an hour into the future, are essential for implementing dynamic control strategies and providing useful customer information in transit applications. Knowing the expected demand enables transit operators to deploy real-time control strategies in advance of the demand surge, and minimize the impact of abnormalities on the service quality and passenger experience. One of the most useful applications of demand prediction models in transit is in predicting the congestion on station platforms and crowding on vehicles. These require information about the origin-destination (OD) demand, providing a detailed profile of how and when passengers enter and exit the service. However, existing work in the literature is limited and overwhelmingly focuses on forecasting passenger <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">arrivals</i> at stations. This information, while useful, is incomplete for many practical applications. We address this gap by developing a scalable methodology for real-time, short-term OD demand prediction in transit systems. Our proposed model consists of three modules: multi-resolution spatial feature extraction module for capturing the local spatial dependencies with a channel-wise attention block, auxiliary information encoding module (AIE) for encoding the exogenous information, and a module for capturing the temporal evolution of demand. The OD demand at time <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$t$ </tex-math></inline-formula> , represented as a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N \times N$ </tex-math></inline-formula> matrix, is processed in two separate branches. In one branch we use the discrete wavelet transform (DWT) to decompose the demand into its different time and frequency variations, detecting patterns that are not visible in the raw data. In the other, three convolutional neural network (CNN) layers are utilized to learn the spatial dependencies from the OD demand directly. Instead of treating each channel of the resultant transformation equally, we use a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">squeeze-and-excitation</i> layer to weight feature maps based on their contribution to the final prediction. A Convolutional Long Short-term Memory network (ConvLSTM) is then used to capture the temporal evolution of demand. The approach is demonstrated through a case study using 2 months of Automated Fare Collection (AFC) data from the Hong Kong Mass Transit Railway (MTR) system. The extensive evaluation of the model shows the superiority of our proposed model compared to the other compared methods.

Short-term origin-destination demand prediction in urban rail transit systems: A channel-wise attentive split-convolutional neural network method

Short-term origin–destination (OD) flow prediction in urban rail transit (URT) plays a crucial role in smart and real-time URT operation and management. Different from other short-term traffic forecasting methods, the short-term OD flow prediction possesses three unique characteristics: (1) data availability: real-time OD flow is not available during the prediction; (2) data dimensionality: the dimension of the OD flow is much higher than the cardinality of transportation networks; (3) data sparsity: URT OD flow is spatiotemporally sparse. There is a great need to develop novel OD flow forecasting method that explicitly considers the unique characteristics of the URT system. To this end, a channel-wise attentive split–convolutional neural network (CAS-CNN) is proposed. The proposed model consists of many novel components such as the channel-wise attention mechanism and split CNN. In particular, an inflow/outflow-gated mechanism is innovatively introduced to address the data availability issue. We further originally propose a masked loss function to solve the data dimensionality and data sparsity issues. The model interpretability is also discussed in detail. The CAS–CNN model is tested on two large-scale real-world datasets from Beijing Subway, and it outperforms the rest of benchmarking methods. The proposed model contributes to the development of short-term OD flow prediction, and it also lays the foundations of real-time URT operation and management.

Graph Neural Network for Robust Public Transit Demand Prediction

Understanding and forecasting mobility patterns and travel demand are fundamental and critical to efficient transport infrastructure planning and service operation. However, most existing studies focused on deterministic demand estimation/prediction/analytics. Differently, this study provides confidence interval based demand forecasting, which can help transport planning and operation authorities to better accommodate demand uncertainty/variability. The proposed Origin-Destination (OD) demand prediction approach well captures and utilizes the correlations among spatial and temporal information. In particular, the proposed Probabilistic Graph Convolution Model (PGCM) consists of two components: (i) a prediction module based on Graph Convolution Network and combined with the gated mechanism to predict OD demand by utilizing spatio-temporal relations; (ii) a Bayesian-based approximation module to measure the confidence interval of demand prediction by evaluating the graph-based model uncertainty. We use a large-scale real-world public transit dataset from the Greater Sydney area to test and evaluate the proposed approach. The experimental results demonstrate that the proposed method is capable of capturing the spatial-temporal correlations for more robust demand prediction against several established tools in the literature.

Bi-objective traffic count location model for mean and covariance of origin–destination estimation

This paper describes a bi-objective optimization model for the traffic count location problem in stochastic origin–destination (OD) traffic demand estimation. Two measures are defined to capture the maximum possible absolute error of the mean and the covariance of the estimated OD demand. The bounds of these two measures are mathematically deduced, and then the bi-objective optimization model is formulated to minimize the two upper bounds simultaneously. A surrogate-assisted genetic algorithm is proposed to solve this model, and a series of numerical examples are presented to demonstrate the applicability of the proposed model and the efficiency of the proposed algorithm.

Estimating the market potential for long-haul narrowbody aircraft using origin-destination demand and flight schedules data

Air transport has constantly evolved over the past decades. Main drivers affecting the shape of supply were new, e.g. low cost, business models, and new aircraft technologies, like the emergence of jet airliners in the 1950s/1960s. One of the most recent and potentially highly disrupting developments was the announcement by Airbus in 2015 and 2018 to launch new long-range (LR) and extra long-range (XLR) versions of its largest narrowbody aircraft, A321neo. With this step, Airbus is tapping into a market which is covered insufficiently by existing aircraft types. The new Airbus A321 versions will be used to replace the aging fleet of Boeing 757 aircraft, but will also offer airlines the opportunity to serve thin long-haul routes. Airlines may offer a higher number of frequencies than with today’s widebody aircraft or introduce completely new non-stop services, where existing types are either limited in range or have too many seats. We estimate the market potential for long-haul narrowbody aircraft with a model using Sabre’s Market Intelligence origin-destination demand and Innovata’s flight schedules data. Furthermore, the implications of the new long-range narrowbody aircraft for airline business models will be discussed.

Long-term Origin-Destination Demand Prediction with Graph Deep Learning

Accurate long-term origin-destination demand (OD) prediction can help understand traffic flow dynamics, which plays an essential role in urban transportation planning. However, the main challenge originates from the complex and dynamic spatial-temporal correlation of the time-varying traffic information. In response, a graph deep learning model for long-term OD prediction (ST-GDL) is proposed in this paper, which is among the pioneering work that obtains both short-term and long-term OD predictions simultaneously. ST-GDL avoids the conventional multi-step forecasting and thus prevents learning from prediction errors, rendering better long-term forecasts. The proposed method captures time attributes from multiple time scales, namely closeness, periodicity, and trend, to study the features with temporal dynamics. Besides, two gate mechanisms are introduced over the vanilla convolution operation to alleviates the error accumulation issue of typical recurrent forecast in long-term OD prediction. A method based on graph convolution is proposed to capture the dynamic spatial relationship, which projects the transportation network into a graphical time-series. Finally, the long-term OD prediction results are obtained by combining the extracted spatio-temporal features with external features from the meteorological information. Case studies on a practical dataset show that the proposed model is superior to existing methods in long-term OD prediction problems.

Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network

With the rapid development of mobile-internet technologies, on-demand ride-sourcing services have become increasingly popular and largely reshaped the way people travel. Demand prediction is one of the most fundamental components in supply-demand management systems of ride-sourcing platforms. With an accurate short-term prediction for origin-destination (OD) demand, the platforms make precise and timely decisions on real-time matching, idle vehicle reallocations, and ride-sharing vehicle routing, etc. Compared to the zone-based demand prediction that has been examined in many previous studies, OD-based demand prediction is more challenging. This is mainly due to the complicated spatial and temporal dependencies among the demand of different OD pairs. To overcome this challenge, we propose the Spatio-Temporal Encoder-Decoder Residual Multi-Graph Convolutional network (ST-ED-RMGC), a novel deep learning model for predicting ride-sourcing demand of various OD pairs. Firstly, the model constructs OD graphs, which utilize adjacent matrices to characterize the non-Euclidean pair-wise geographical and semantic correlations among different OD pairs. Secondly, based on the constructed graphs, a residual multi-graph convolutional (RMGC) network is designed to encode the contextual-aware spatial dependencies, and a long-short term memory (LSTM) network is used to encode the temporal dependencies, into a dense vector space. Finally, we reuse the RMGC networks to decode the compressed vector back to OD graphs and predict the future OD demand. Through extensive experiments on the for-hire-vehicles datasets in Manhattan, New York City, we show that our proposed deep learning framework outperforms the state-of-arts by a significant margin.

DNEAT: A novel dynamic node-edge attention network for origin-destination demand prediction

The ride-hailing service platforms have grown tremendously around the world and attracted a wide range of research interests. A key to ride-hailing service platforms is how to realize accurate and reliable demand prediction. However, most of the existing studies focus on the region-level demand prediction while only a few attempts to address the problem of origin–destination (OD) demand prediction. In this paper, from the graph aspects, we construct the dynamic OD graphs to describe the ride-hailing demand data. We propose a novel neural architecture named the Dynamic Node-Edge Attention Network (DNEAT) to address the unique challenges of OD demand prediction from the demand generation and attraction perspectives. Different from previous studies, in DNEAT, we develop a new neural layer, named k-hop temporal node-edge attention layer (k-TNEAT), to capture the temporal evolution of node topologies in dynamic OD graphs instead of the pre-defined relationships among regions. We evaluate our model on two real-world ride-hailing demand datasets (from Chengdu, China, and New York City). The experiment results show that the proposed model outperforms six baseline models and is more robust to demand data with high sparsity.

A Big Data Demand Estimation Model for Urban Congested Networks

Abstract The origin-destination (OD) demand estimation problem is a classical problem in transport planning and management. Traditionally, this problem has been solved using traffic counts, speeds or travel times extracted from location-based sensor data. With the advent of new sensing technologies located on vehicles (GPS) and nomadic devices (mobile and smartphones), new opportunities have emerged to improve the estimation accuracy and reliability, and more importantly to better capture the dynamics of the daily mobility patterns. In this paper we frame this new data in a comprehensive framework which estimates origin-destination flows in two steps: the first step estimates the total generated demand for each traffic zone, while the second step adjusts the spatial and temporal distribution on the different OD pairs. We show how mobile data can be used to obtain OD matrices that reflect the aggregated movements of individuals in complex and large-scale instances, while speed information from floating car data can be used in the second step. We showcase the added value of big data on a realistic network comprising Luxembourg’s capital city and its surrounding. We simulate traffic by means of a commercial simulation software, PTV-Visum, and leverage real mobile phone data from the largest telco operator in the country and real speed data from a floating car data service provider. Results show how OD estimation improves both in solution reliability and in convergence speed.

The capacitated directed cycle hub location and routing problem under congestion

This paper deals with hub-and-spoke network design in the liner shipping sector. It introduces a capacitated directed cycle hub location and cargo routing problem under congestion. The problem involves four decisions: location of hub ports; allocation of non-hub ports to hub ports; construction of a directed cyclic route at the hub port network level; and the routing of cargo between all origin-destination demand pairs in the network. The objective is to minimize the cost which includes fixed hub opening, feeder collection and distribution, inter-hub transportation, cargo handling, and non-linear hub port congestion costs. We present a mixed integer linear programming model in which the non-linear congestion costs at the hub ports are approximated through a (semi-continuous) piecewise linear function and use this model to calculate lower bounds on the objective function. We also develop a Tabu Search algorithm, which employs a hierarchical approach for the different decisions in the hub-and-spoke network design problem, with customized procedures for the generation of the initial solution and the selection of the search moves. The neighborhood search is diversified by randomly changing the locations of hubs based on their location frequency history in previous solutions. Computational experiments, using instances from the literature and problems based on real-world data, demonstrate that the algorithm finds high quality solutions in a reasonable time. The experiments show that the network design can be highly influenced by scale economies in mainline vs. feeder transportation costs, the port locations and hinterland flows, and congestion at the hub ports.

Investigating impact of the heterogeneity of trajectory data distribution on origin‐destination estimation: a spatial statistics approach

Many studies have been conducted to estimate origin-destination (OD) demand based on vehicle trajectory data. However, the estimation accuracy heavily relies on the temporal-spatial distribution of trajectories, and its effect on OD estimation remains unrevealed and under-estimated. This study proposes a novel method for investigating the impact of the heterogeneity of trajectory data distribution on OD estimation at urban road networks. Synthetic scenarios are designed based on automatic license plate recognition data collected from a real-world traffic network in Kunshan, China. Four factors: test area, sampling rate, time period, and the sampling method are selected for scenario settings. Next, a particle filter-based method is implemented to reconstruct vehicle trajectories using the sampled trajectory data, and then the path flows and OD demands are extracted. Finally, a spatial statistics approach is introduced to reveal the spatial autocorrelation of trip generation/attraction variations, and the high-high clusters whose OD values are significantly affected are identified. Test results show that the heterogeneity effects of trajectory distribution on OD estimation can be effectively studied by the proposed method. Further investigation shows that the findings of spatial statistics can be applied for improving OD estimation accuracy.

Estimating multi-class dynamic origin-destination demand through a forward-backward algorithm on computational graphs

Transportation networks are unprecedentedly complex with heterogeneous vehicular flow. Conventionally, vehicles are classified by size, the number of axles or engine types, e.g., standard passenger cars versus trucks. However, vehicle flow heterogeneity stems from many other aspects in general, e.g., ride-sourcing vehicles versus personal vehicles, human driven vehicles versus connected and automated vehicles. Provided with some observations of vehicular flow for each class in a large-scale transportation network, how to estimate the multi-class spatio-temporal vehicular flow, in terms of time-varying Origin-Destination (OD) demand and path/link flow, remains a big challenge. This paper presents a solution framework for multi-class dynamic OD demand estimation (MCDODE) in large-scale networks that work for any vehicular data in general. The proposed framework cast the standard OD estimation methods into a computational graph with tensor representations of spatio-temporal flow and all intermediate features involved in the MCDODE formulation. A forward-backward algorithm is proposed to efficiently solve the MCDODE formulation on computational graphs. In addition, we propose a novel concept of tree-based cumulative curves to compute the exact multi-class Dynamic Assignment Ratio (DAR) matrix. A Growing Tree algorithm is developed to construct tree-based cumulative curves. The proposed framework is examined on a small network, a mid-size network as well as a real-world large-scale network. The experiment results indicate that the proposed framework is compelling, satisfactory and computationally plausible.

Integration of Departure Time Choice Modeling and Dynamic Origin–Destination Demand Estimation in a Large-Scale Network

Time-dependent origin–destination (OD) demand estimation using link traffic data in a large-scale network is a highly underdetermined problem. As a result, providing an accurate initial solution is crucial for obtaining a more reliable estimated demand. In this paper, we discuss the necessity of having a comprehensive demand profiling model that considers the spatial differences of OD pairs and we demonstrate its application in the calibration of large-scale traffic assignment models. First, we apply a departure choice model that adds a time dimension to the OD demand flows concerning their spatial differences. The time-profiled demand is then fed into the time-dependent OD demand estimation problem for further adjustment. Results show that in addition to reducing the error between simulation outputs and the observed link counts, the estimated demand profile more accurately reflects the spatial correlation of the OD pairs in the large-scale network being studied. Results provide practical insights into deployment and calibration of simulation-based dynamic traffic assignment models.

A Unified Demand-Diversion Prediction Approach to Real-Time Group Route Guidance

Dynamic origin-destination (OD) demand estimation and prediction (DODE) and drivers' route diversion behavior (DRDB) are two fundamental determinants in the development of effective group route guidance (GRG) strategies for balancing traffic loads and enhancing system performance. This work presents a unified approach to incorporate DRDB into a DODE model. This model accounts for the influence of route diversion on DODE and predicts the OD demand in information provision environment. This study also develops a dynamic aggregate DRDB model based on the traffic data obtained through online detection and integrates this model with the DODE model. The test results of the case study show that the maximum deviation between the real OD volumes and the proposed DODE model under information provision, mean absolute percentage error, and normalized root mean square error is approximately 11.46%, 4.53%, and 5.29%, respectively. The integrated demand-diversion prediction model can accurately estimate and predict possible DRDB and the effect of traffic information on OD demand prediction using real-time traffic detected data. The model can also enhance the accuracy of OD demand and traffic state prediction under information provision, consequently increasing the effectiveness of the proposed GRG strategies.

Active group route guidance based on DODE: A novel modeling framework integrating dynamic driver behavior

This work aims to provide effective and reliable traffic guidance strategies for improving the system performance and travel reliability, wherein the drivers’ route diversion behavior is the key determinant in these strategies. This study presents a novel modeling framework that can incorporate the dynamic driver behavior into a real-time group route guidance model based on dynamic origin–destination demand estimation and prediction (DODE) for information-based active traffic management. Experiments are conducted to test the effectiveness of the proposed model on the basis of the traffic dataset of the Route Guidance Pilot Project. Experimental results show that the effect of route diversion on DODE under information provision, which can improve the accuracy of DODE, must be considered. Compared with the traditional guidance model, the proposed model considers the system objective and the actual route diversion behavior and can provide better performance and ensure system sustainability.