Transportation Network Optimization Research Articles

Privacy-preserving coordination of power and transportation networks using spatiotemporal GAT for predicting EV charging demands

The gradual replacement of conventional-fuel vehicles by electric vehicles (EVs) in recent years provides a growing incentive for the collaborative optimization of power distribution networks (PDNs) and urban transportation networks (UTNs). However, the implementation of a centralized optimization model for PDNs and UTNs is currently unrealistic due to the requirement for establishing information privacy barriers between the two independently operated networks. The present work proposes a predict-then-optimize (PTO) framework that combines Spatiotemporal Graph Attention Network (STGAT) with enhanced queueing theory to achieve accurate prediction of EV charging demands. Building upon this, it efficiently coordinates optimization between the PDN and UTN, while preserving the information privacy of both independently operated networks. Specifically, the proposed STGAT model predicts vehicle flow by simultaneously exploiting the dynamic temporal and spatial dependencies in the historical traffic data of the target UTN. It then converts the predicted flow into spatiotemporal EV charging demands using an enhanced queuing model that considers the service capacity constraints of charging stations (CSs) and the behavior of EV users. Subsequently, the predicted EV charging demands are integrated into a multi-period PDN scheduling model. The results of numerical computations based on an IEEE 33-bus PDN and real-world traffic flow datasets demonstrate that the scheduling results provided by the proposed approach differ by only 0.5% compared to results obtained when applying actual EV charging demands.

Considering the Optimization Design of Urban Bus Network Scheduling

At present, the optimization of public transportation networks and vehicle scheduling are carried out independently in stages. However, through analysis, it has been found that scheduling information such as route schedules is an important factor related to passenger route selection. Therefore, in order to further improve the optimization effect, this article proposes an innovative idea of simultaneously optimizing the line network and scheduling. Based on the construction of a real–virtual public transportation network, this article constructs a synchronous optimization model for the line network and scheduling by considering both passenger waiting and on-board time. To achieve the consideration of passengers for different route choices, a shortest path traversal algorithm based on Yen was proposed to analyze the number and weight of the shortest paths between the same OD, and a genetic algorithm was used to solve the model. Finally, the effectiveness of the model was verified through numerical examples, and the results showed that synchronous optimization was superior to phased optimization: the passenger time cost was reduced by 21.5%, the bus operation cost was reduced by 13.7%, and the total bus system cost was reduced by 18.0%.

Has the national ocean economic pilot project promoted blue economy development in China?

This paper estimates the impact of the national ocean economic pilot project on the blue economy (BE) development using panel data for 11 coastal regions in mainland China from 2005 to 2017. The study shows that the BE is composed of three levels: traditional advantageous industrial construction, emerging industrial development, and ecological protection, where they can merge an index system using the analytic hierarchy process-improved entropy weight method. Besides, this paper adopts heterogeneous timing difference-in-differences to find that the policy increased the BE in the pilot areas by an average of 0.025. This effect passed various robustness checks including the parallel trend hypothesis and placebo test. In addition, the policy can also mediate the BE by skill and capacity aggregation, optimization of transportation networks, and incentives for innovation, and their contributions were 21.5%,10.6%, and 10.6%. Moreover, this paper finds that the current BE work shows a preference for the economy over the ecosystem. For economic growth, pilots prefer traditional rather than emerging industries. In summary, this study recommends that multi-level governments should use a project-based management model for the BE, increase international cooperation and knowledge transfer to promote the integration of the knowledge economy and the BE and facilitate administrative reform to clarify the ecological responsibilities of marine management agencies.

Modeling of Passenger Flows Analysis System of Low-carbon Transportation in a Smart City

The paper examines the impact of the increase in passenger traffic in public transport on environmental pollution, as well as the search for ways to reduce emissions of carbon-containing compounds caused by the growth of the planet’s population, the number of vehicles that transport them, and the amount of emissions that these vehicles generate. The object of research is the system of passenger transportation in a smart city. Through correlation-regression analysis of passenger flows in a regional city with a population of fewer than 1 million registered residents, the paper identifies a functional dependence between the volume of passenger transportation by public transport and the volume of carbon dioxide emissions into the atmospheric air from mobile sources of pollution, which include all types of automobile and electric transport. It was established that the optimization of the public transport network plays a decisive role in the implementation of low-carbon transportation. Conceptual provisions for the creation of an intelligent system for the organization of low-carbon passenger transportation in a smart city were proposed, which were displayed using activity, state, and deployment diagrams. The optimization of the routes of the public transport system is proposed to be implemented through the concept of adding a new passenger, supplementing the route, and adapting public transport networks to the needs of consumers and the demand for transport to achieve the goals of the concept of a smart city - reducing carbon dioxide emissions into the atmosphere. The scientific novelty of the proposed intelligent system concept consists of the use of an integrated approach to the optimization of vehicle routes in a smart city to reduce carbon dioxide emissions into the atmosphere.

Symmetry breaking in optimal transport networks

Engineering multilayer networks that efficiently connect sets of points in space is a crucial task in all practical applications that concern the transport of people or the delivery of goods. Unfortunately, our current theoretical understanding of the shape of such optimal transport networks is quite limited. Not much is known about how the topology of the optimal network changes as a function of its size, the relative efficiency of its layers, and the cost of switching between layers. Here, we show that optimal networks undergo sharp transitions from symmetric to asymmetric shapes, indicating that it is sometimes better to avoid serving a whole area to save on switching costs. Also, we analyze the real transportation networks of the cities of Atlanta, Boston, and Toronto using our theoretical framework and find that they are farther away from their optimal shapes as traffic congestion increases.

Evolution of E-Commerce Logistics: Global Trends and Implementations

E-commerce has revolutionized the way businesses operate and consumers shop, leading to a surge in online shopping and placing immense pressure on logistics providers and retailers to optimize their operations. The evolution of e-commerce logistics has become a critical factor in determining the success or failure of businesses in the digital age. The impact of e-commerce on logistics is multifaceted, encompassing various aspects such as supply chain management, transportation, warehousing, last-mile delivery, and reverse logistics. Traditional logistics models have proven inadequate in addressing the unique challenges posed by the business-to-consumer (B2C) e-commerce landscape, necessitating the development of sophisticated order fulfilment systems and the optimization of transportation networks to ensure timely and cost-effective delivery. One of the significant challenges faced by e-commerce logistics is the complexity of managing a vast number of individual orders and delivering them promptly to consumers. Unlike traditional retail, where bulk shipments are sent to stores, e-commerce requires the processing and delivery of countless parcels directly to customers’ doorsteps. This has necessitated the development of sophisticated order fulfillment systems and the optimization of transportation networks to ensure timely and cost-effective delivery. Another key aspect of e-commerce logistics is the need for seamless integration between various stakeholders, including retailers, suppliers, logistics providers, and technology platforms. Effective collaboration and data sharing among these entities are crucial for ensuring end-to-end visibility, enabling real-time tracking, and facilitating efficient decision-making throughout the supply chain. The rise of e-commerce has also led to the emergence of new business models and innovative logistics solutions, such as the proliferation of third-party logistics providers (3PLs) specializing in e-commerce fulfilment, the adoption of advanced technologies such as automation and robotics in warehousing operations, and the exploration of alternative last-mile delivery methods like drones and autonomous vehicles.

Analyzing the impact of grid structures on traffic flow optimization in autonomous transport systems

A fundamental element of a centralized autonomous vehicle control process is the representation of the transport environment. The road surface has to be partitioned to be able to ensure the main safety requirements of the transport process: a vehicle can only be in one place at a time, and only one vehicle can be in one place at a time. The occupancy grid concept is widely used for this purpose; however, previous concepts mainly utilize square grid representations, considered as a static component of the traffic models. Our research focuses on discovering and introducing the impact of different grid representations by evaluating their efficiency, computational complexity, and safety characteristics. This result provides the basis for real-time optimization of self-organizing road transport networks, as our research gives clear information on the impact of different grid structures. It has been pointed out that applying other network structures than the traditional square grid structure can achieve better results. Accordingly, some of the newly introduced structures (such as the hexagon-based, triangle-based or combined structures) are proved to have significant advantages compared to the classical grid representation.

Modeling External and Empty Freight Truck Trips using Agent-Based Simulation

Modeling external and empty freight trips helps in better planning and scheduling of transportation operations. This can lead to more effective route planning, load consolidation, and overall optimization of transportation networks. In this study external and empty truck trips modeled using Freight Analysis Framework (FAF) and Highway Performance Measurement System (HPMS) data with generating trip outputs from POLARIS agent-based simulation framework. The model then applied to the Austin metropolitan area, Texas, USA. The model estimated single and multi-unit AADT values with 91% and 93.4% accuracy compared with the HPMS volume, respectively. The estimated error – 9% and 6.6% - is due to the shortest path routing that may prefer faster routes on certain highways. Truck trips on large volume links tend to be overestimated while short links underestimate truck trips to some extent.

Multi-Objective Optimization of Urban Air Transportation Networks Under Social Considerations

Multi-Objective Optimization of Urban Air Transportation Networks Under Social Considerations

Simultaneous multi-objective framework of natural gas pipeline network operations

The optimization of gas transportation networks is essential as natural gas demand increases. Conflicting objectives, such as maximizing delivery flow rate, minimizing power consumption, and maximizing line pack, pose challenges in this context. To address these complexities, a novel multi-objective optimization method based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) is proposed. The method generates a diverse set of Pareto optimal solutions, empowering decision-makers to select the most suitable solution for gas transportation networks. Three case studies validate the approach's effectiveness, showcasing its advantages in yielding more economical networks and enhancing the cost-effectiveness of natural gas transmission networks. The proposed method's versatility allows application to various gas transportation network scenarios. Decision-makers benefit from a range of Pareto optimal solutions, providing valuable insights. Moreover, the seamless integration of the proposed method into existing gas transportation network optimization frameworks further enhances performance. In conclusion, the study presents a robust multi-objective optimization method based on TOPSIS for gas transportation network optimization. It offers cost-effective solutions and improves the efficiency of natural gas transmission networks. The provision of diverse Pareto optimal solutions enables well-informed decision-making, contributing to sustainable energy solutions in the face of increasing natural gas demand.

Bilevel Optimization for Traffic Mitigation in Optimal Transport Networks.

Global infrastructure robustness and local transport efficiency are critical requirements for transportation networks. However, since passengers often travel greedily to maximize their own benefit and trigger traffic jams, overall transportation performance can be heavily disrupted. We develop adaptation rules that leverage optimal transport theory to effectively route passengers along their shortest paths while also strategically tuning edge weights to optimize traffic. As a result, we enforce both global and local optimality of transport. We prove the efficacy of our approach on synthetic networks and on real data. Our findings on the international European highways suggest that thoughtfully devised routing schemes might help to lower car-produced carbon emissions.

From patch, sample to domain: Capture geometric structures for few-shot learning

Few-shot learning aims to recognize novel concepts with only few samples by using prior knowledge learned from the seen concepts. In this paper, we address the problem of few-shot learning under domain shifts. Traditional few-shot learning methods are not directly applicable to cross-domain scenarios due to the large discrepancy of feature distributions across domains. To this end, we propose a novel Hierarchical Optimal Transport network with Attention (HOTA) for cross-domain few-shot learning. The underlying idea is to learn the transferable and discriminative embeddings by taking advantage of the hierarchical geometric structures among image data, ranging from patch, sample to domain. The HOTA framework utilizes a hierarchical optimal transport network to smooth the domain shifts by domain alignment while enhancing the discrimination and the transferability of the embeddings by aligning the patches of images. To further enhance the transferability, HOTA conducts a mix-up data augmentation based on cross-domain attention to capture the relationships of samples in different domains. The extensive experiments on a variety of few-shot benchmark scenarios demonstrate that HOTA outperforms the state-of-the-art methods under both supervised and unsupervised conditions.

Relation between learning process and morphology of transport tube network in plasmodium of Physarum polycephalum.

The question of whether a single-celled organism without a brain could have functions such as learning and memory has been the subject of much debate in recent years. The plasmodium of the true slime mold, Physarum polycephalum, is an ideal model organism for such a question. The plasmodium exhibits behaviors that resemble intelligence, including solving mazes, mimicking optimal rail transportation networks, predicting the weather, and solving traveling salesman problems. In addition, the plasmodium has recently been shown to have the simplest form of learning: habituation. In the experiments in which plasmodia were repeatedly allowed to cross bridges containing aversive chemicals, the habituation behavior has been confirmed. It has been shown that the habituation process involves chemicals that are stored internally. However, it is not clear how these chemicals result in change in the behavior of plasmodium during habituation learning. This study focused on the transport tube network formed in plasmodium during the above experiments. Then, the role of the network morphology in the habituation learning process was investigated. The results showed that the network morphology changes from tree to mesh type during habituation learning, and disrupting the learned network reduces habituation behavior. In addition, it was shown that the thickness oscillation frequency depends on the network morphology. The study found that in the plasmodium of P. polycephalum, a primitive organism without a brain, transport tube networks, instead of neuronal networks, play an important role in habituation learning and the resulting decision making.

Obtaining the optimal origin-destination multimodal freight transportation network for the City of Bogotá

Bogotá’s logistics performance as the principal hub for shipping cargo to other destinations in Colombia has not been optimal. Excessive truck traffic, low density of railways in service, and no accessible river routes seem to be major determinant factors. This article proposes a balanced linear transshipment (BLT) model to estimate the optimal origin-destination (OD) multimodal freight transportation network for the mentioned city to seven main destinations in the country. This research also provides an appropriate framework for assessing several hypothetical transportation scenarios. Thus, based on national transport statistics, this study evaluates three main criteria: freight transportation cost, number of nodes, and number of routes. The results of analysis suggest that if alternative modes of transportation are implemented in Bogotá, the three mentioned criteria will improve substantially. The analysis is limited by the size of the OD transportation network considered, the assumptions associated with the research methodology, and the scope and diversity of data sources used as reference. To the authors' knowledge, this study is the first of its kind to examine the optimal OD transportation network in Bogotá by using a BLT model.

Cascading failures and maintenance optimization of urban transportation networks

A convenient urban transportation network facilitates a high-quality life and a high-growth economy. Due to cascading failures being a ticklish question triggering continuous road congestion, the maintenance plan is momentous to restore the urban transportation network. Considering fault edges are removed and cars slowly drive out of these edges to ease traffic congestion, a traffic distribution model is proposed to analyze the cascading failures process. To resume the transportation network, this paper proposes a maintenance optimization with minimizing maintenance time. It recovers the cascading failures from two perspectives: the intra-area maintenance model and the inter-area maintenance model. At last, a transportation network of a city in China is regarded as a case study to illuminate the feasibility of the proposed models. The results show that on the premise of dividing traffic areas, it is reasonable to adopt the intra-area maintenance plan for cascading failures. Compared with the intra-area maintenance plan, the inter-area maintenance plan saves more time.

Unseen-Material Few-Shot Defect Segmentation With Optimal Bilateral Feature Transport Network

Industrial defect segmentation is important to ensure product quality and production safety. The main challenges in industrial applications are insufficient defect samples, large intra-class variation, and the interference of background information. However, most current texture defect segmentation methods rely on large-scale datasets and can only deal with one specific type of texture defect, which reduces the application efficiency and application scope of defect segmentation algorithms. To this end, we propose an optimal bilateral feature transport network (OBFTNet) for few-shot texture defect segmentation, which can accurately segment texture defects in multiple unseen materials (domains), such as steel, wood, leather, etc. OBFTNet can perform bilateral prediction for background and defect regions of unseen material by dynamically predicting task-specific semantic correspondences conditioned on a small guidance set. Specifically, we introduce background images (defect-free images) as supplementary learning information for reverse prediction and model the semantic correspondence between the guidance (support and background images) and the query images in few-shot segmentation as an optimal bilateral feature transport problem and generate a set of optimal bilateral correlation tensors. Using 4D and 2D convolutions the model gradually reduces optimal bilateral correlation tensors to precise segmentation masks. Experimental results show that our proposed method outperforms several state-of-the-art techniques with very few labeled samples and the method generalizes well to industrial defects on unseen materials.

Hub seaport multimodal freight transport network design: Perspective of regional integration development

To design the multimodal freight transport network of regional hub seaports, and promote the high-quality development of regional economic integration. Combined with the principal component analysis method, the comprehensive evaluation value of the inland cities is determined. Meanwhile, the gravity model is used to obtain the correlation degree between non-core cities and core cities, and the hinterlands of these core cities are divided. The entropy weight TOPSIS model is applied to select the inland hinterland transshipment cities. Taking the minimum total transport costs as the objective function, the regional hub seaport multimodal freight transport network optimization model with space-time constraints is established, and solved by MATLAB software. Taking the freight transport from Chengdu-Chongqing Economic Zone to Yangtze River Delta as an example, a multimodal freight transport network is constructed. It is calculated that Chengdu and Chongqing can be set as freight consolidation centers, and Changsha, Wuhan, Nanchang, Nanjing, Hangzhou, Hefei, Zhengzhou and Xi'an can be set as transshipment nodes. These non-core cities in the Chengdu-Chongqing Economic Zone can be divided into five groups to achieve effective improvement in transport efficiency through group combined transport. This study gives managerial implications for multimodal transport structure optimization and provides reference for the regional integration development between seaports and hinterlands.

Fleeting Route Design with Uncertainty

During COVID-19, the air industry has shrunk due to drastically reduced demand and flight bans. Air transport network optimization is significant in fleet routing design, which helps the air company to make a decision to open the new routes while maximizing the profit. We want to study when an area is subjected to stability shocks that prevent air trac from entering, how air planners comprehensively consider the factors to design new fleeting routes while optimizing the profit. In this research, we start by developing a baseline model and then a networked model, both theoretical, to simulate the situation for an air company and provide optimization results. We find a simple situation to determine: if a route has a positive maximized expected profit, we will decide to open the route. The optimal results obtained from the model are proved to be optimal by mathematics analysis in the study. Several potential future study directions relevant to the research are discussed, including stochastic demand and network connection, which could be better explain the situation of air transport network design and thus be more applicable in reality.

Immiscible color flows in optimal transport networks for image classification

In classification tasks, it is crucial to meaningfully exploit the information contained in the data. While much of the work in addressing these tasks is focused on building complex algorithmic infrastructures to process inputs in a black-box fashion, little is known about how to exploit the various facets of the data before inputting this into an algorithm. Here, we focus on this latter perspective by proposing a physics-inspired dynamical system that adapts optimal transport principles to effectively leverage color distributions of images. Our dynamics regulates immiscible fluxes of colors traveling on a network built from images. Instead of aggregating colors together, it treats them as different commodities that interact with a shared capacity on the edges. The resulting optimal flows can then be fed into standard classifiers to distinguish images in different classes. We show how our method can outperform competing approaches on image classification tasks in datasets where color information matters.

Optimization of transport network using mathematical methods

The aim of this paper is to outline the possibilities of implementing mathematical methods in optimization of the costs in the transport network. Transport accounts for between 50% and 60% of distribution costs and is an element of the supply chain that is most often the subject of outsourcing. Transport problems, like most logistics problems, can be reduced to optimization problems that are efficiently solved using mathematical methods. This paper presents mathematical methods of linear programming that are used to reduce transport costs on the real case study in the Adria region.