Real-world Transportation Networks Research Articles

Resilient service restoration for distribution systems with mobile resources using Floyd‐based network simplification method

The large-scale blackouts of distribution systems (DS) caused by extreme natural disasters have aroused a lot of attention. To enhance the resilience of DSs, a novel service restoration and recovery model to minimize the system-wide load loss is proposed here, where reconfiguration systems and two kinds of moveable resources, that is, mobile sources (MS) and repair crews (RC), are considered. Then, time-space network (TSN) is applied to model the movement of MSs and RCs over the real-world transportation networks (TN). However, the introduction of TSN makes solving the model become a time-consuming task as plenty of variables are involved by it. To tackle this challenge which may lead to the impracticability of the model, a Floyd-algorithm based TN simplification method is proposed to reduce the variables without sacrificing the equivalence of the TNs before and after the transformation. Finally, the applicability and effectiveness of the proposed model are verified on a 33-bus test DS and a real-world DS with complicated TNs.

Optimal Operation of Transient Gas Transport Networks

In this paper, we describe an algorithmic framework for the optimal operation of transient gas transport networks consisting of a hierarchical MILP formulation together with a sequential linear programming inspired post-processing routine. Its implementation is part of the KOMPASS decision support system, which is currently used in an industrial setting. Real-world gas transport networks are controlled by operating complex pipeline intersection areas, which comprise multiple compressor units, regulators, and valves. In the following, we introduce the concept of network stations to model them. Thereby, we represent the technical capabilities of a station by hand-tailored artificial arcs and add them to network. Furthermore, we choose from a predefined set of flow directions for each network station and time step, which determines where the gas enters and leaves the station. Additionally, we have to select a supported simple state, which consists of two subsets of artificial arcs: Arcs that must and arcs that cannot be used. The goal is to determine a stable control of the network satisfying all supplies and demands. The pipeline intersections, that are represented by the network stations, were initially built centuries ago. Subsequently, due to updates, changes, and extensions, they evolved into highly complex and involved topologies. To extract their basic properties and to model them using computer-readable and optimizable descriptions took several years of effort. To support the dispatchers in controlling the network, we need to compute a continuously updated list of recommended measures. Our motivation for the model presented here is to make fast decisions on important transient global control parameters, i.e., how to route the flow and where to compress the gas. Detailed continuous and discrete technical control measures realizing them, which take all hardware details into account, are determined in a subsequent step. In this paper, we present computational results from the KOMPASS project using detailed real-world data.

A Recursive Logit Model with Choice Aversion and Its Application to Route Choice Analysis

We propose a recursive logit model which captures the notion of choice aversion by imposing a penalty term that accounts for the dimension of the choice set at each node of the transportation network. We make three contributions. First, we show that our model overcomes the correlation problem between routes, a common pitfall of traditional logit models, and that the choice aversion model can be seen as an alternative to these models. Second, we show how our model can generate violations of regularity in the path choice probabilities. In particular, we show that removing edges in the network may decrease the probability for existing paths. Finally, we show that under the presence of choice aversion, adding edges to the network can make users worse off. In other words, a type of Braess's paradox can emerge outside of congestion and can be characterized in terms of a parameter that measures users' degree of choice aversion. We validate these contributions by estimating this parameter over GPS traffic data captured on a real-world transportation network.

Dynamic routing with ant system and memory-based decision-making process

Dynamic routing is an essential tool for today’s cities. Dynamic routing problems can be solved by modelling them as dynamic optimization problems (DOPs). DOPs can be solved using Swarm Intelligence and specially ant colony optimization (ACO) algorithms. Although different versions of ACO have already been presented for DOPs, there are still limitations in preventing stagnation and premature convergence and increasing convergence rate. To address these issues, we present an in-memory pheromone trail and an algorithm based on it (named AS-gamma) in the framework of ACO. In-memory pheromone trail is effectively increasing diversity after a change in an environment. Results of experimenting AS-gamma in three scenarios on a real-world transportation network with different simulated traffic conditions demonstrated the effectiveness of the presented in-memory pheromone trail method. The advantages of AS-gamma over three existing DOP algorithms have been illustrated in terms of solutions quality. Offline performance and accuracy measures indicate that AS-gamma faces less stagnation, premature convergence and it is suitable for crowded environments.

Deep reinforcement learning algorithm for dynamic pricing of express lanes with multiple access locations

This article develops a deep reinforcement learning (Deep-RL) framework for dynamic pricing on managed lanes with multiple access locations and heterogeneity in travelers’ value of time, origin, and destination. This framework relaxes assumptions in the literature by considering multiple origins and destinations, multiple access locations to the managed lane, en route diversion of travelers, partial observability of the sensor readings, and stochastic demand and observations. The problem is formulated as a partially observable Markov decision process (POMDP) and policy gradient methods are used to determine tolls as a function of real-time observations. Tolls are modeled as continuous and stochastic variables and are determined using a feedforward neural network. The method is compared against a feedback control method used for dynamic pricing. We show that Deep-RL is effective in learning toll policies for maximizing revenue, minimizing total system travel time, and other joint weighted objectives, when tested on real-world transportation networks. The Deep-RL toll policies outperform the feedback control heuristic for the revenue maximization objective by generating revenues up to 8.5% higher than the heuristic and for the objective minimizing total system travel time (TSTT) by generating TSTT up to 8.4% lower than the heuristic. We also propose reward shaping methods for the POMDP to overcome the undesired behavior of toll policies, like the jam-and-harvest behavior of revenue-maximizing policies. Additionally, we test transferability of the algorithm trained on one set of inputs for new input distributions and offer recommendations on real-time implementations of Deep-RL algorithms. The source code for our experiments is available online at https://github.com/venktesh22/ExpressLanes_Deep-RL.

Predicting disruptions and their passenger delay impacts for public transport stops

Disruptions in public transport can have major implications for passengers and service providers. Our study objective is to develop a generic approach to predict how often different disruption types occur at different stations of a public transport network, and to predict the impact related to these disruptions as measured in terms of passenger delays. We propose a supervised learning approach to perform these predictions, as this allows for predictions for individual stations for each time period, without the requirement of having sufficient empirical disruption observations available for each location and time period. This approach also enables a fast prediction of disruption impacts for a large number of disruption instances, hence addressing the computational challenges that rise when typical public transport assignment or simulation models would be used for real-world public transport networks. To improve transferability of our study results, we cluster stations based on their contribution to network vulnerability using unsupervised learning. This supports public transport agencies to apply the appropriate type of measure aimed to reduce disruptions or to mitigate disruption impacts for each station type. Applied to the Washington metro network, we predict a yearly passenger delay of 5.9 million hours for the total metro network. Based on the clustering, five different types of station are distinguished. Stations with high train frequencies and high passenger volumes located at central trunk sections of the network show to be most critical, along with start/terminal and transfer stations. Intermediate stations located at branches of a line are least critical.

Optimising Melbourne's bus routes for real-life travel patterns

This study investigates whether faster overall public transport times could be achieved if a given set of bus resources were configured in a simple but sparse network of direct and frequent services, when compared to the same level of resources currently deployed in routes that lack those characteristics. Melbourne, Australia is used as a case study. Two strands of literature are reviewed: (1) literature on public transport network design, noting that principles such as direct, simple and frequent routes are well-articulated, but that there is comparatively little quantitative academic literature applying those principles to real-world transport networks on a whole-of-city basis; and (2) studies of public transport accessibility, noting that they often focus on access to employment centres or journeys to work, rather than trips made for other purposes. Network analysis tools are used to model and compare public transport travel times under the existing Melbourne public transport network, and under a new network where bus routes are reconfigured on a basis more consistent with network design principles identified in the literature, using a set of trip patterns disclosed by a government survey of household travel activity. The results show that the reconfigured network, using existing resources, could reduce average travel times in the interpeak period across the study area by 5.30 min (12.67%), with the greatest benefits accruing to outer suburban areas.

A dual toll policy for maintaining risk equity in hazardous materials transportation with fuzzy incident rate

A dual-toll policy, considering a multi-degree fuzzy incident rate, is proposed to mitigate the risk caused by hazardous material (hazmat) transportation in a road network. To address several carriers transporting multiple hazmat types, we use a bi-level programming formulation. The upper and lower levels, respectively, exemplify decision problems faced by the regulators (regional and local governments) and travelers (hazmat and non-hazmat).The contributions of this paper are threefold. •In addition to the total network risk, our model includes risk equity (minimization of the maximum link risk). This makes the spatial distribution of risk closer to homogeneous.•We propose a new definition of risk measurement, based on the integration of a fuzzy incident rate and population exposure, together with the transportation time. This new definition better reflects the uncertain nature of actual transportation situations.•We construct a new real-world transportation network based on data from the City of Nanchang, China. Empirical distances, travel times, population densities, and applicable regulations are incorporated in this network of 32 nodes and 102 arcs. Our model is solved, based upon the preceding figures and toll values that are consistent with Chinese national standards.To solve the model effectively, a genetic-algorithm-based methodology is employed, along with a piecewise linearization method and a Frank-Wolfe approach. Employing both the well-known Sioux-Falls network and the new, larger network, case studies are presented. If distinct hazmat tolls are imposed on differing hazmat types, those case studies enable managerial insights, derived from the dual toll policy, when incident possibilities vary.

The Bi-Objective Shortest Path Network Interdiction Problem: Subgraph Algorithm and Saturation Property

Critical network defense and attack problems, usually modeled as network interdiction, is of great significance. It is of great interest from the interdictor's view to study saturation property of resource allocations. This paper presents a bi-objective shortest path network interdiction model with node interdiction, in which the interdictor seeks to interdict a set of nodes in the network that is Pareto-optimal with respect to two objectives, i.e., maximization of shortest path length and minimization of resources cost. A novel subgraph sequence algorithm is developed to identify the efficient frontier through a sequence of single-objective problems. Novel subgraph decomposition algorithms are proposed to solve single-objective problems. Features and time complexity of those problems and algorithms are analyzed. Moreover, to make a trade-off between the resource investment and the interdiction performance, the definition and the computing method of saturation point are introduced in this paper. Both simulated grid network and real-world transportation network data are used to evaluate the performance of algorithms in numerical experiments. The results show that the subgraph sequence algorithm can achieve the optimal Pareto-frontier of this bi-objective problem effectively.

An activity chain optimization method with comparison of test cases for different transportation modes

ABSTRACTIn order to provide optimal choice of activity locations and travel time reduction, a daily activity chain optimization method has been elaborated, which includes temporal and spatial flexibility of the activities. In the course of the optimization process, possible alternatives are searched using a modified version of the Traveling Salesman Problem with Time Window. The method is extended with a genetic algorithm to provide an optimal order of activities as the minimum of the predefined cost function (i.e. travel time). The multiobjective optimization can efficiently mitigate the travel time of the users. In order to provide some insight regarding the performance of the optimization algorithm, application-oriented simulations were performed on a real-world transportation network using real travel time information. Three transportation modes were considered: car, public transport, and combined (public transport with car-sharing). The simulation results demonstrate that the optimization is able to reduce travel time by 20–30%.

Coordinated Charging Scheduling of Electric Vehicles: A Mixed-Variable Differential Evolution Approach

The increasing popularity of battery-limited electric vehicles puts forward an important issue of how to charge the vehicles effectively. This problem, commonly referred to as Electric Vehicle Charging Scheduling (EVCS), has been proven to be NP-hard. Most of the existing works formulate the EVCS problem simply as a constrained shortest path finding problem and treat it by discrete optimization. However, other variables such as the charging amount of energy and the charging option at a station need to be considered in practical use. This paper hence formulates the EVCS problem as a hierarchical mixed-variable optimization problem, considering the dependency among the station selection, the charging option at each station and the charging amount settings. To adapt to the new problem model, we specifically design a Mixed-Variable Differentiate Evolution (MVDE) as the scheduling algorithm for our proposed EVCS system. The MVDE contains several specific operators, including a charging station route construction, a hierarchical mixed-variable mutation operator and a constraint-aware evaluation operator. Experimental results validate the effectiveness of our proposed MVDE-based system on both synthetic and real-world transportation networks.

Real-Time Traffic Speed Estimation With Graph Convolutional Generative Autoencoder

Real-time traffic speed estimation is an essential component of intelligent transportation system (ITS) technologies. It is the foundation of modern transportation control and management applications. However, the existing traffic speed acquisition systems can only provide real-time speed measurements of a small number of roads with stationary speed sensors and crowdsourcing vehicles. How to utilize this information to provide traffic speed maps for transportation networks is becoming a key problem in ITSs. In this paper, we present a novel deep-learning model called graph convolutional generative autoencoder to fully address the real-time traffic speed estimation problem. The proposed model incorporates the recent development in deep-learning techniques to extract the spatial correlation of the transportation network from the input incomplete historical data. To evaluate the proposed speed estimation technique, we conduct comprehensive case studies on a real-world transportation network and vehicular traces. The simulation results demonstrate that the proposed technique can notably outperform existing traffic speed estimation and deep-learning techniques. In addition, the impact of dataset properties and control parameters is investigated.

Online Vehicle Routing With Neural Combinatorial Optimization and Deep Reinforcement Learning

Online vehicle routing is an important task of the modern transportation service provider. Contributed by the ever-increasing real-time demand on the transportation system, especially small-parcel last-mile delivery requests, vehicle route generation is becoming more computationally complex than before. The existing routing algorithms are mostly based on mathematical programming, which requires huge computation time in city-size transportation networks. To develop routes with minimal time, in this paper, we propose a novel deep reinforcement learning-based neural combinatorial optimization strategy. Specifically, we transform the online routing problem to a vehicle tour generation problem, and propose a structural graph embedded pointer network to develop these tours iteratively. Furthermore, since constructing supervised training data for the neural network is impractical due to the high computation complexity, we propose a deep reinforcement learning mechanism with an unsupervised auxiliary network to train the model parameters. A multisampling scheme is also devised to further improve the system performance. Since the parameter training process is offline, the proposed strategy can achieve a superior online route generation speed. To assess the proposed strategy, we conduct comprehensive case studies with a real-world transportation network. The simulation results show that the proposed strategy can significantly outperform conventional strategies with limited computation time in both static and dynamic logistic systems. In addition, the influence of control parameters on the system performance is investigated.

Two‐fold calibration approach for microscopic traffic simulation models

Calibrating the microsimulation traffic models can be defined as a black-box optimisation problem with some non-concave objective functions. In this regard, the stochastic optimisation algorithms are suitable choices to explore the search space and prevent getting stuck in local optimums. However, considering only the traffic attributes-related objectives may fail to calibrate the model in terms of safety. Therefore, by defining two different objectives, a two-fold calibration approach is proposed such that the simulation model reproduces the real-world transportation network more accurately, both in terms of safety and operation. Moreover, the performance of two different approaches to solve this multi-objective optimisation problem are evaluated. It is shown that by aggregating the objectives in one single formula (i.e. a priori methods), the information exchange among solutions is not captured, which may lead to non-optimal solutions. While this limitation is overcome by a posteriori methods since different objectives can be optimised separately and simultaneously. In this regard, the performance of posteriori-based multi-objective particle swarm optimisation (MOPSO) algorithm in calibrating VISSIM is compared with some priori-based optimisation algorithms (e.g. PSO, genetic algorithm, and whale optimisation algorithm). The results show that posteriori-based MOPSO leads to a more accurate solution set in terms of both objectives.

A data-parallel many-source shortest-path algorithm to accelerate macroscopic transport network assignment

The performance and scalability of macroscopic assignment and simulation software limits the quantity, scale and complexity of simulations of transport networks that are used to aid the planning, design and operation of transport systems. Through the application of many-core processing architectures (such as Graphics Processing Units (GPUs)) and data-parallel algorithms, the performance of such software can be dramatically increased. In this paper, a work-efficient, Multiple Source Shortest Path (MSSP) implementation of the Bellman-Ford algorithm is proposed to dramatically increase the performance of shortest path calculations for low-density high-diameter graphs, which are characteristic of transportation networks. This is achieved through the use of an Origin-Vertex Frontier to increase the level of parallelism within the shortest path algorithm for multiple source vertices in low-density graphs, when executed on GPUs. The algorithm is implemented within the SATURN transport simulation software and benchmarked on a range of real-world transportation networks. Our algorithm improves hardware utilisation of massively-parallel GPUs; demonstrating performance improvements of up to 7.8x over a multi-core CPU (Central Processing Unit) implementation.

BRIGHT—Drift-Aware Demand Predictions for Taxi Networks

Massive data broadcast by GPS-equipped vehicles provide unprecedented opportunities. One of the main tasks in order to optimize our transportation networks is to build data-driven real-time decision support systems. However, the dynamic environments where the networks operate disallow the traditional assumptions required to put in practice many off-the-shelf supervised learning algorithms, such as finite training sets or stationary distributions. In this paper, we propose BRIGHT: a drift-aware supervised learning framework to predict demand quantities. BRIGHT aims to provide accurate predictions for short-term horizons through a creative ensemble of time series analysis methods that handles distinct types of concept drift. By selecting neighborhoods dynamically, BRIGHT reduces the likelihood of overfitting. By ensuring diversity among the base learners, BRIGHT ensures a high reduction of variance while keeping bias stable. Experiments were conducted using three large-scale heterogeneous real-world transportation networks in Porto (Portugal), Shanghai (China), and Stockholm (Sweden), as well as with controlled experiments using synthetic data where multiple distinct drifts were artificially induced. The obtained results illustrate the advantages of BRIGHT in relation to state-of-the-art methods for this task.

Studying the Topology of Transportation Systems through Complex Networks: Handle with Care

The introduction of complex network concepts in the study of transportation systems has supposed a paradigm shift and has allowed understanding different transport phenomena as the emergent result of the interactions between the elements composing them. In spite of several notable achievements, lurking pitfalls are undermining our understanding of the topological characteristics of transportation systems. In this study, we analyse four of the most common ones, specifically related to the assessment of the scale-freeness of networks, the interpretation and comparison of topological metrics, the definition of a node ranking, and the analysis of the resilience against random failures and targeted attacks. For each topic we present the problem from both a theoretical and operational perspective, for then reviewing how it has been tackled in the literature and finally proposing a set of solutions. We further use six real-world transportation networks as case studies and discuss the implications of these four pitfalls in their analysis. We present some future lines of work that are stemming from these pitfalls and that will allow a deeper understanding of transportation systems from a complex network perspective.

Transitions from Trees to Cycles in Adaptive Flow Networks

Transport networks are crucial to the functioning of natural and technological systems. Nature features transport networks that are adaptive over a vast range of parameters, thus providing an impressive level of robustness in supply. Theoretical and experimental studies have found that real-world transport networks exhibit both tree-like motifs and cycles. When the network is subject to load fluctuations, the presence of cyclic motifs may help to reduce flow fluctuations and, thus, render supply in the network more robust. While previous studies considered network topology via optimization principles, here, we take a dynamical systems approach and study a simple model of a flow network with dynamically adapting weights (conductances). We assume a spatially non-uniform distribution of rapidly fluctuating loads in the sinks and investigate what network configurations are dynamically stable. The network converges to a spatially non-uniform stable configuration composed of both cyclic and tree-like structures. Cyclic structures emerge locally in a transcritical bifurcation as the amplitude of the load fluctuations is increased. The resulting adaptive dynamics thus partitions the network into two distinct regions with cyclic and tree-like structures. The location of the boundary between these two regions is determined by the amplitude of the fluctuations. These findings may explain why natural transport networks display cyclic structures in the micro-vascular regions near terminal nodes, but tree-like features in the regions with larger veins.

Robustness of complex networks with both unidirectional and bidirectional links against cascading failures

The robustness of complex networks against cascading failures has been of great interest, while most of the researchers have considered undirected networks. However, to be more realistic, a part of links of many real systems should be described as unidirectional. In this paper, by applying three link direction-determining (DD) strategies, the tolerance of cascading failures is investigated in various networks with both unidirectional and bidirectional links. By extending the utilization of a classical global betweenness method, we propose a new cascading model, taking into account the weights of nodes and the directions of links. Then, the effects of unidirectional links on the network robustness against cascaded attacks are examined under the global load-based distribution mechanism. The simulation results show that the link-directed methods could not always lead to the decrease of the network robustness as indicated in the previous studies. For small-world networks, these methods certainly make the network weaker. However, for scale-free networks, the network robustness can be significantly improved by the link-directed method, especially for the method with non-random DD strategies. These results are independent of the weight parameter of the nodes. Due to the strongly improved robustness and easy realization with low cost on networks, the method for enforcing proper links to the unidirectional ones may be useful for leading to insights into the control of cascading failures in real-world networks, like communication and transportation networks.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.