Taxis In Shanghai Research Articles

A traffic state prediction method based on spatial–temporal data mining of floating car data by using autoformer architecture

AbstractFloating car data (FCD), characterized by wide spatiotemporal coverage, low collection cost, and immunity to adverse weather conditions, are one of the key approaches for intelligent transportation systems to obtain real‐time urban road network traffic information. The research aims to utilize GPS data from taxis in Shanghai and vector geographic information data of the road network, with urban expressways as the research focus. Based on the different driving characteristics of expressways and the vehicles on the ramps below, a clustering analysis is employed to determine all floating vehicles traveling on the target road. Furthermore, an adaptive buffer zone consistent with the road orientation is established based on road vector geographic data. This allows for the extraction of FCD within segmented areas, and the average vehicle speed for that road segment is obtained through weighted calculations. This method fully exploits the natural characteristics of taxis in urban areas with a wide spatiotemporal distribution. The data effectiveness and coverage reach 90.2% and 85.7%, respectively, significantly surpassing the traditional grid‐based extraction method for FCD. Additionally, to capture the long‐term spatiotemporal dependencies of road network traffic states, a spatial–temporal autoformer (STAF) network based on spatial–temporal sequence autocorrelation is employed for traffic state prediction. The results indicate that the STAF method demonstrates good performance in medium‐ and long‐term prediction. We believe that the proposed FCD mining method in this paper provides a new approach for efficiently extracting large‐scale road network traffic states and conducting medium‐ to long‐term predictions.

Traffic Speed Prediction Method Based on Spatiotemporal Sampling and LSTM

Accurate prediction of traffic speed is crucial for traffic management and planning. In order to solve the problems of low prediction efficiency of previous traffic speed prediction models and easy neglect of spatiotemporal characteristics, a traffic speed prediction method based on spatiotemporal sampling and LSTM model is proposed based on the 24-hour driving dataset of 4,000 taxis in Shanghai, and draw speed heat maps in different regions at different times to visualize the spatiotemporal characteristics of traffic speed. Experimental results show that the model has high prediction accuracy and good expansion potential.

Dynamic vehicle routing problem for flexible buses considering stochastic requests

Flexible buses provide on-demand services to one or more local communities in a specific geographical area. Bus routes can be adjusted dynamically according to real-time passenger demand in a cost-effective manner. This study investigated the dynamic bus-routing problem considering stochastic future passenger demand. A two-stage stochastic programming model was formulated to minimise the total vehicle travel time cost and penalty for rejecting requests. A rolling horizon scheme was adopted to handle the dynamic changes in passenger requests and vehicle routes. A vector-similarity-based clustering and adaptive large neighbourhood searching (VSC-ALNS) algorithm was developed to solve this problem. Vehicles and passengers were matched and clustered into groups based on vector similarity, and vehicle routes were generated using an adaptive large-neighbourhood search algorithm for each cluster. The effectiveness of the proposed method was evaluated in four cases with different demand intensities using Shanghai taxi order data. The results indicate that flexible buses are more suitable for moderate demand cases, ranging from 20 to 50 requests per square kilometre per hour.

High Resolution On-Road Air Pollution Using a Large Taxi-Based Mobile Sensor Network.

Traffic-related air pollution (TRAP) was monitored using a mobile sensor network on 125 urban taxis in Shanghai (November 2019/December 2020), which provide real-time patterns of air pollution at high spatial resolution. Each device determined concentrations of carbon monoxide (CO), nitrogen dioxide (NO2), and PM2.5, which characterised spatial and temporal patterns of on-road pollutants. A total of 80% road coverage (motorways, trunk, primary, and secondary roads) required 80–100 taxis, but only 25 on trunk roads. Higher CO concentrations were observed in the urban centre, NO2 higher in motorway concentrations, and PM2.5 lower in the west away from the city centre. During the COVID-19 lockdown, concentrations of CO, NO2, and PM2.5 in Shanghai decreased by 32, 31 and 41%, compared with the previous period. Local contribution related to traffic emissions changed slightly before and after COVID-19 restrictions, while changing background contributions relate to seasonal variation. Mobile networks are a real-time tool for air quality monitoring, with high spatial resolution (~200 m) and robust against the loss of individual devices.

A Data-Driven Customer-Search Modeling With the Consideration of Traffic Environment.

In order to explore the determinants of vacant taxi drivers' customer-search behavior, this paper intends to calibrate a time-dependent Multinomial Logit (MNL) model by mining over 1.6 billion GPS records from about 8,400 taxis in Shanghai, China. First, based on the ordering points to identify the clustering structure (OPTICS) algorithm, the downtown area of Shanghai city is divided into 47 hotspots to identify the hot areas of customer delivery and searching. Then, by investigating a typical search delivery process of a vacant taxi, five candidate factors that may affect the customer-search behavior are summarized and defined. Using the maximum likelihood method, the significant factors are finally found. The results reveal that the relative passenger demand, the regional likelihood of pick-ups as well as the expected rate of return are the most significant factors influencing customer-search behavior. Although the impact of traffic situation (i.e., the en-route delay and traffic condition of the target hotspot) is not particularly significant, service providers and policymakers should still take full advantage of it to schedule taxi service and mitigate the traffic congestion caused by the circulation of vacant taxis. Besides, this paper also shows that the customer-search behavior of a vacant taxi driver varies with the time of day. Findings in this paper are expected to provide comprehensive insights about factors that should be considered in the future operation pattern of a taxi service system where human driver taxis and self-driving taxis are mixed.

Edge Server Placement for Vehicular Ad Hoc Networks in Metropolitans

Edge computing pushes computation and storage resources to the network edge, which is close to end users, and thus, is critical for latency-sensitive applications, e.g., intelligent vehicular <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> networks (VANETs). To enable these services, a set of edge servers needs to be deployed to the roadsides. Such deployment should offer low-latency services to end users, while keeping a low deployment or maintenance cost, which is a nontrivial task. In this article, we study the edge server placement problem in a metropolitan area. This problem is composed of two parts to determine: 1) the locations of the servers and 2) the coverage of each server, with multiple optimization objectives. First, we study the Shanghai Taxi Trace to gain insights into the traffic pattern of taxis, especially how vehicles move between different locations. Second, we build multiobjective optimization models to characterize the tradeoff among three critical performance metrics, namely, the initial deployment cost, the runtime cost (i.e., number of hand-offs between different servers), and the average delay of tasks. Due to the intractability of these NP-hard problems, we propose a heuristic multiobjective optimization method to decompose the global problem into a set of local problems with tractable scale. Numerical results verify that our heuristic strategy achieves a desirable balance among the three performance metrics, e.g., a 5% compromise of the delay can reduce up to 50% of the hand-offs for small local areas, and 10%+ for the entire global area, compared with the best existing algorithms.

CEBD: Contact-Evidence-Driven Blackhole Detection Based on Machine Learning in OppNets

Blackhole detection in the opportunistic networks offers an effective means to mitigate the routing performance degradation but faces many challenges from corrupted nodes due to their collusion behaviors. Most existing effort in the literature focuses on the blackhole feature extraction from the message exchange. However, the decay effect of features and the forged features from the corrupted node, which acts as the rational node in performing message exchange, degrade the performance of the detection. In this article, we investigate the evidence construction, i.e., the direct and indirect evidence with the statistical parameters in message exchange. Specifically, we construct behavior classifiers to distinguish the blackhole behaviors from rational ones and design the collusion filtering strategy to improve the detection accuracy by separating corrupted nodes from rational ones, laying a behavior identification foundation. The contact evidence-driven blackhole detection (CEBD) based on machine learning is proposed to improve the routing performance. The soundness of the proposed scheme is verified statistically and the detection accuracy is evaluated based on random waypoint model (RWP) trace and Shanghai taxi trace. Extensive simulations show that our scheme outperforms the benchmarks, including SDBG, Li, and MDS, in terms of the delivery ratio in various scenarios.

Discovering regions of anomalous spatial co-locations

ABSTRACT Regions of anomalous spatial co-locations (ROASCs) are regions where co-locations between two different features are significantly stronger or weaker than expected. ROASC discovery can provide useful insights for studying unexpected spatial associations at regional scales. The main challenges are that the ROASCs are spatially arbitrary in geographic shape and the distributions of spatial features are unknown a priori. To avoid restrictive assumptions regarding the distribution of data, we propose a distribution-free method for discovering arbitrarily shaped ROASCs. First, we present a multidirectional optimization method to adaptively identify the candidate ROASCs, whose sizes and shapes are fully endogenized. Furthermore, the validity of the candidates is evaluated through significance tests under the null hypothesis that the expected spatial co-locations between two features occur consistently across space. To effectively model the null hypothesis, we develop a bivariate pattern reconstruction method by reconstructing the spatial auto- and cross-correlation structures observed in the data. Synthetic experiments and a case study conducted using Shanghai taxi datasets demonstrate the advantages of our method, in terms of effectiveness, over an available alternative method.

Learning scheduling bursty requests in Mobile Edge Computing using DeepLoad

The emergence of Mobile Edge Computing (MEC) alleviates the large transmission latency resulting from the traditional cloud computing. For the compute-intensive requests such as video analysis, mobile users prefer to obtain a desired quality of experience (QoE) with neglected latency and reduced energy consumption. The popularity of smart devices allows users to release a run of compute-intensive as well as latency-sensitive requests anywhere, which may lead to bursty requests. A single resource-constrained edge server nearby is capable of handling a small amount of requests quickly, yet it seems helpless when encountering bursty compute-intensive requests. Despite the abundance of recently proposed schemes, the majority focus on efficiently scheduling pending requests in a single edge server, and ignored the potential role of edge collaboration to schedule bursty requests. Besides, while some recent studies proposed to finish a task using multiple devices, they focused on collaboration between mobile devices rather than between edge servers. Hence, we propose DeepLoad, a S2S system that schedules the bursty requests with a collaborative method using reinforcement learning (RL). DeepLoad decouples the scheduling decision into AP selection for setting the access point and workload redistribution for collaborative servers. DeepLoad trains a neural network model that picks decisions for each request based on observations collected by mobile devices. DeepLoad learns to make scheduling decisions solely through the resulting performance of historical decisions rather than rely on pre-programmed models or specific assumptions for the environment. Naturally, DeepLoad automatically learns the scheduling algorithm for each request and obtains a gratifying QoE. We aim to maximize the fraction of requests finished before their attached deadlines. Based on the Shanghai taxi trajectory data set, we design a simulator to obtain abundant samples, and leverage two GeForce GTX TITAN Xp GPUs to train the Actor–Critic network. Compared to the state-of-the-art bandwidth-based and server resources-based methods, DeepLoad can achieve a significant improvement in average fraction.

Synergy and co-benefits of reducing CO2 and air pollutant emissions by promoting electric vehicles—A case of Shanghai

With the growing number of vehicles on the road, the transport sector has become the second largest consumer of energy, after the industrial sector, and has become the main source of air pollutants and greenhouse gas emissions. To support low-carbon development, since 2009, electric vehicles have been used to replace traditional fuel vehicles in China. In 2016, electric vehicles, including buses, taxis and private vehicles, accounted for 26.41% of the total number of new-energy vehicles in Shanghai. In this study, the synergy and co-benefits of reducing CO2 and air pollutant emissions by using electric private cars, taxis, and buses in Shanghai are analyzed. The co-control coordinate system and pollutant reduction cross-elasticity (Elsa/b) are used to identify and evaluate the generated co-benefits. Based on the total driving life cost, the unit air pollutant equivalent (Apeq) abatement costs of achieving synergy in three types of vehicles are assessed. The co-benefits generated by using the three types of electric vehicles are discussed by combining environmental benefit and cost-effectiveness analyses. The results show that electric buses provide the highest co-benefits. Thus, replacing traditional fuel vehicles with electric buses can simultaneously reduce air pollution and CO2 emissions. If we consider subsidies to electric vehicles provided by the government, there are great environmental and economic benefits of implementing electric buses in Shanghai. In addition, private electric cars and taxis also provide the co-benefits of reducing CO, NOx, NMHC, and PM10 emissions. The economic benefits of using electric taxis in Shanghai are more notable, even without considering subsidies.

Deep Reinforcement Learning for Intelligent Internet of Vehicles: An Energy-Efficient Computational Offloading Scheme

The emerging vehicular services call for updated communication and computing platforms. Fog computing, whose infrastructure is deployed in close proximity to terminals, extends the facilities of cloud computing. However, due to the limitation of vehicular fog nodes, it is challenging to satisfy the quality of experiences of users, calling for intelligent networks with updated computing abilities. This paper constructs a three-layer offloading framework in intelligent Internet of Vehicles (IoV) to minimize the overall energy consumption while satisfying the delay constraint of users. Due to its high computational complexity, the formulated problem is decomposed into two parts: 1) flow redirection and 2) offloading decision. After that, a deep reinforcement learning-based scheme is put forward to solve the optimization problem. Performance evaluations based on real-world traces of taxis in Shanghai, China, demonstrate the effectiveness of our methods, where average energy consumption can be decreased by around 60% compared with the baseline algorithm.

A Markov decision process approach to vacant taxi routing with e-hailing

The optimal routing of a vacant taxi is formulated as a Markov Decision Process (MDP) problem to account for long-term profit over the full working period. The state is defined by the node at which a vacant taxi is located, and action is the link to take out of the node. State transition probabilities depend on passenger matching probabilities and passenger destination probabilities. The probability that a vacant taxi is matched with a passenger during the traversal of a link is calculated based on temporal Poisson arrivals of passengers and spatial Poisson distributions of competing vacant taxis. Passenger destination probabilities are calculated directly using observed fractions of passengers going to destinations from a given origin. The MDP problem is solved by value iteration resulting in an optimal routing policy, and the computational efficiency is improved by utilizing parallelized matrix operations.The proposed model and an efficient implementation of the value iteration algorithm are tested in a case study with parameters derived from GPS trajectories of over 12,000 taxis in Shanghai, China for a study period of 5:30 - 11:30 am on a typical weekday. The optimal routing policy is compared with three heuristics based on simulated trajectories. Results show that the optimal routing policy improves average unit profit by 23.0% and 8.4% over the random walk and local hotspot heuristic respectively; and improves occupancy rate by 23.8% and 8.3% respectively. The improvement is larger during higher demand periods.

A Prediction Method for Destination Based on the Semantic Transfer Model

With the widespread use of the mobile devices, destination prediction has become an important issue for location-based services (LBSs). Most existing methods are based on various Markov chain models, in which the predicted destinations are trained by historical trajectories. A problem among most of these follow-up works is that they blindly rely on the Markov process, ignoring the geographical distribution and the time property of the trajectories. In this paper, we propose a novel destination prediction algorithm, called STTL, based on the time property of the partial trajectory, along with the semantic transfer probability model trained in advance. We have conducted extensive experiments on the Shanghai Taxi dataset. The experimental results show that the STTL outperforms other state-of-the-art approaches.

Identification and interpretation of spatial–temporal mismatch between taxi demand and supply using global positioning system data

Taxis provide a type of on-demand mobility service in urban transportation. There are growing concerns regarding the level of service of taxis in satisfying residents’ mobility demand. However, the mismatch between demand and supply of taxi services has not been resolved even with the introduction of app-based vehicle services. In this study, three indicators are constructed using the Shanghai taxi global positioning system (GPS) dataset to reveal the spatial–temporal mismatch pattern. The issue is further analyzed via a case study, in which seven regions with frequent mismatch patterns are identified in the time period from 21:00 to 22:00. Then, a multinomial logistic regression model is employed to identify the demographic and built-environment factors contributing to the taxi mismatch problem. The study results show that population density, residential areas, the number of points of interest, and road density have significant relationships with the taxi undersupply. In contrast, the areas of commercial lands, as well as the other two transportation-related factors, that is, the number of bus stops and the distance to nearest subway station, are observed to be statistically significant for both “oversupply” and “undersupply” conditions. This study provides valuable insights for identifying mismatch patterns and interpreting the mismatch problem as a function of spatially explicit factors that are of great use for urban governance, especially in the improvement of taxi efficiency, taxi management, and urban planning.

Exploiting Traveling Information for Data Forwarding in Community-Characterized Vehicular Networks

In intelligent vehicular communication networks, a hybrid communication architecture is used which combines both centralized and ad hoc transmission schemes. In order to maximize the end-to-end delivery ratio while reducing the network overhead, one important problem is to efficiently design the data forwarding algorithm to guarantee the quality of data transmission. In this paper, by considering the traveling information and vehicular space-crossing community structure, two metrics, “space–time approachability” and “social approachability,” are defined to provide the absolute and relative geographical information of the forthcoming contacts, respectively. Then, a novel data-forwarding algorithm, called approachability-based algorithm, is proposed, which utilizes two metrics together for better routing quality. We evaluate the proposed approachability-based algorithm utilizing San Francisco Cabspotting and Shanghai Taxi Movement datasets. Simulation results show that the approachability-based data forwarding algorithm can achieve better performance than the popular data forwarding algorithms ZOOM and BUBBLE RAP in all the interested scenarios.

Utility Maximization for Multimedia Data Dissemination in Large-Scale VANETs

With the increasing demand of media-rich entertainment and location-aware services from people on the road, how to disseminate the multimedia data in large-scale Vehicular Ad-Hoc Networks (VANETs) efficiently and reliably is a pressing issue. Due to the high mobility, large scale, and limited contact time between vehicles, it is quite challenging to support the multimedia data dissemination in VANETs. In this paper, we first utilize a hybrid framework to model the VANETs to address the mobility and scalability issues. Then, we formulate a utility-based maximization problem to find the best delivery strategy and select an optimal path for the multimedia data dissemination, where the utility function has taken the delivery delay, Quality of Services (QoS), and storage cost into consideration. With rigorous analysis, we obtain the closed-form of the expected utility of a path, and then obtain the optimal solution of the problem with the convex optimization theory. Finally, we conduct trace-driven simulations to evaluate the performance of the proposed algorithm with real traces collected by taxis in Shanghai. The simulation results demonstrate the rigorousness of our theoretical analysis, and the effectiveness of the proposed solution.

Mining factors affecting taxi drivers’ incomes using GPS trajectories

Taxis provide essential transport services in urban areas. In the taxi industry, the income level remains a cause of concern for taxi drivers as well as regulators. Mining underlying factors affecting the income level will not only benefit the newcomers and low-income drivers but also assist in developing effective optimization algorithms for taxi operations. This paper intends to disclose the factors affecting incomes along with their quantitative influence by mining over 167 million GPS records from nearly 8000 taxis in Shanghai. We first identify a marked difference in drivers’ incomes and categorize drivers into three income levels accordingly. We next investigate the overall search-delivery process, thereby defining several factors that may affect the income level. We then develop a generalized multi-level ordered logit (GMOL) model to find the significant factors that influence incomes. Finally, we compute the elasticity for those significant factors and present their contributions, as well as challenge some preconceived ideas regarding how to earn high incomes.

A Simulation Study of Upgrading Urban Gasoline Taxis to Electric Taxis

Abstract Upgrading gasoline taxis to electric taxisis an important measure to achieve energy-saving and emission-reduction targets. Based on Santana taxis in Shanghai, a set ofelectric taximodels with 15-100kWh batteries are built and simulated by Advisor which is secondarily developed. Comparative analysis between electric taxis and Santana taxis is made from the viewpoint of lifecycle cost and “Well to Wheel”emissions. Besides, optimal capacity of batterieson electric taxis is discussed. Results show that electric taxiswith 60kWh batteries could satisfy power requirements and achieve optimal economy and emissions.

An Empirical Study on Evolution of the Connectivity for VANETs Based on Taxi GPS Traces

Network connectivity is a fundamental requirement for intervehicle communication and services in VANETs. The fast movement of the vehicles results in rapid changes in network topology generating dynamic variation in network connectivity, which causes dynamic variation in network connectivity. In this paper, we analyze the evolution of the VANETs connectivity based on the realistic data collected by the GPS devices installed on taxis in Shanghai. The study of the evolution characteristics shows that the number of connected components, the size of the giant component, and the connectivity length time series possess strong temporal correlation and long-range dependence. As a result, the short-range dependent processes such as the exponential, normal, or Poisson distributions cannot capture the statistical distribution characteristics. Moreover, all connectivity parameters cannot be described by unimodal distributions. We also conclude that although the whole topology of the VANETs is broken into a large number of small-sized connected components under small transmission radius, the size of the giant component keeps stable when transmission radius reaches the threshold. These results will be helpful to optimize the RSUs deployment and transmission radius to keep the giant component stable and design more efficient strategies to forward the information in VANETs.

“Internet +” Epoch Social Management Innovation: Challenge and Response - To the Case of Shanghai Taxi Operations Management

Human society has entered the Internet age, the network plays a very important function in all aspects of social management. In recent years, operational management of the taxi industry once again become the focus of the society because of various taxi network software prevalence. Take Shanghai Taxi management model for example, Compare the comparison of traditional and the present stage management mode and measures taken by the government. Summary and analysis the deficiency of the taxi industry and the government management. On this basis, developed the taxi industry how to take the role of the market in public services, how governments use the Internet to integrate the taxi market and improve management and service levels.