No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Sustainable Intersections: Minimizing Energy Consumption and Environmental Impact Through Coordination and Communication Technologies
Abstract
Transportation is among the most prevalent, challenging, and complex sectors that significantly influence energy consumption, environmental sustainability, and economic dynamics. So, it is critical to identify effective strategies to lessen its detrimental consequences. The conventional signalized intersections, which use pre-programmed schedules to control traffic flow at junctions, are one of the most used systems and one of the biggest high Energy consumption rates creators. The study focuses on reducing fuel consumption and enhancing traffic flow by utilizing advanced technologies such as intelligent transportation systems (ITS), communication technologies, adaptive traffic systems, and coordination techniques. The study incorporates manually collected real-world data with an average time step of 15 min through various simulation scenarios. The aim is to develop adaptive coordination strategies for signalized intersections using intelligent communication technologies (ICT) and uncover the importance of coordination techniques combined with ICT. Additionally, the study investigates the effects of these technologies on traffic flow, energy consumption, and air pollution emissions. The results show that using adaptive traffic lights only reduces fuel consumption and emissions by 8%, while applying coordination techniques can increase the percentage up to 25%. In addition, by implementing ICT combined with coordination technique, fuel consumption and emissions, average queue length, and waiting time decreased by around 48%, 63%, and 41%, respectively while increase the average vehicle speed by 46% compared to the pretimed isolated intersections. The findings highlight the developed strategy capability in enhancing traffic flow, energy efficiency, environmental sustainability, leading to a cleaner environment, and transportation sector cost savings.
ResearchGate has not been able to resolve any citations for this publication.
Vehicle-to-Vehicle (V2V) communication is a groundbreaking technology that promises to reshape transportation systems globally. This paper delves into the diverse applications of V2V communication, emphasizing its potential to enhance traffic efficiency, road safety, and environmental sustainability. By facilitating real-time information exchange between vehicles, V2V communication can aid in collision prevention, traffic flow optimization, and emission reduction, thereby fostering a more secure, efficient, and eco-friendly transportation landscape. The analysis presented in this paper encompasses the key components and benefits of V2V communication, along with an exploration of its far-reaching implications for the future of transportation, including the advancement of autonomous vehicles and the establishment of greener, more sustainable transport networks.
This study proposes a two-level optimization model system for vehicle control and signal timing at isolated signal intersections under the mixed traffic flow environment composed of intelligent connected autonomous vehicles (CAVs) and connected human-driven vehicles (CHVs), to minimize the energy consumption and vehicle delay at intersections. The proposed two-layer optimization model is composed of a two-layer vehicle trajectory control model and a fuzzy control signal timing optimization model. The two-layer vehicle trajectory control model includes a signal-oriented vehicle trajectory control model and a car-following oriented vehicle trajectory control model. The former calculates expected acceleration and speed commands at each time step according to the coming signal information, to help vehicle pass the closest signal intersection without stopping during the green light interval; the latter uses the variable headway (VTH) strategy to follow the preceding vehicle by maintaining a safe distance. A microscopic simulator based on SUMO is developed to test the performance of the proposed optimization algorithm. In the simulation experiment, with the driving characteristics of CHV drivers considered, the results show that our model performs well under a CAV penetration rate of 30%–60% and under small or moderate levels of traffic flow. The average waiting time of vehicles is reduced by about 25% compared with the uncontrolled scheme. Under the condition of penetration rate of 60%, the average energy consumption of vehicles in the proposed model is 17.56% lower than that of the uncontrolled scheme. In addition, the proposed model reduces by 21.94% compared with the scheme of only controlling vehicles. When the traffic flow is at a low or medium level, the average energy consumption and waiting time of vehicles are reduced by nearly 35% with the proposed model.
In recent years, researchers have proposed smart traffic light control systems to improve traffic flow at intersections, but there is less focus on reducing vehicle and pedestrian delays simultaneously. This research proposes a cyber-physical system for smart traffic light control utilizing traffic detection cameras, machine learning algorithms, and a ladder logic program. The proposed method employs a dynamic traffic interval technique that categorizes traffic into low, medium, high, and very high volumes. It adjusts traffic light intervals based on real-time traffic data, including pedestrian and vehicle information. Machine learning algorithms, including convolutional neural network (CNN), artificial neural network (ANN), and support vector machine (SVM), are demonstrated to predict traffic conditions and traffic light timings. To validate the proposed method, the Simulation of Urban Mobility (SUMO) platform was used to simulate the real-world intersection working. The simulation result indicates the dynamic traffic interval technique is more efficient and showcases a 12% to 27% reduction in the waiting time of vehicles and a 9% to 23% reduction in the waiting time of pedestrians at an intersection when compared to the fixed time and semi-dynamic traffic light control methods.
To enhance the traffic operation efficiency at signalized intersections, a model for coupled control of traffic signals and connected autonomous vehicles at isolated signalized intersections is proposed. This model estimates the time that CAVs reach stop lines with real-time information about the speed and position of CAVs. The arrival time is leveraged to optimize traffic signal timing by rolling horizon, with the maximization of phase saturation as the optimization objective. Based on the optimized traffic signal timing, the speed profile of CAVs is optimized by a linear integer programming, with the maximization of speed at the moment of reaching the stop line as the optimization objective. Through the coupled control of travel speed and the traffic signal, CAVs can pass through the intersection safely, efficiently, and smoothly. NetLogo, a multiagent microscopic simulator, is developed to test this strategy, and an intersection in Weihai is taken for verification and analysis lastly. The simulation results demonstrate that, compared with the fixed traffic signal timing control and the model optimizing only speed profile of CAVs, the proposed model can reduce the average number of stops by 47.0% and the queuing time by 41.3%. In addition, the optimization is better during off-peak hours, about 10% higher than the peak hours.
An autonomous vehicle can sense its environment and operate without human involvement. Its adequate management in an intelligent transportation system could significantly reduce traffic congestion and overall travel time in a network. Adaptive traffic signal controller (ATSC) based on multi‐agent systems using state‐action‐reward‐state‐action (SARSA (λ)) are well‐known state‐of‐the‐art models to manage autonomous vehicles within urban areas. However, this study found inefficient weights updating mechanisms of the conventional SARSA (λ) models. Therefore, it proposes a Gaussian function to regulate the eligibility trace vector's decay mechanism effectively. On the other hand, an efficient understanding of the state of the traffic environment is crucial for an agent to take optimal actions. The conventional models feed the state values to the agents through the MinMax normalization technique, which sometimes shows less efficiency and robustness. So, this study suggests the MaxAbs scaled state values instead of MinMax to address the problem. Furthermore, the combination of the A‐star routing algorithm and proposed model demonstrated a good increase in performance relatively to the conventional SARSA (λ)‐based routing algorithms. The proposed model and the baselines were implemented in a microscopic traffic simulation environment using the SUMO package over a complex real‐world‐like 21‐intersections network to evaluate their performance. The results showed a reduction of the vehicle's average total waiting time and total stops by a mean value of 59.9% and 17.55% compared to the considered baselines. Also, the A‐star combined with the proposed controller outperformed the conventional approaches by increasing the vehicle's average trip speed by 3.4%.
As the international division of labour becomes more entrenched, the distance goods travel before they reach the final consumer increases; at least this was the case before the outbreak of the COVID-19 pandemic. International trade and cross-border cargo movements generate significant carbon emissions. Despite theoretical advances, empirical studies frequently draw contradictory conclusions and the influence of international trade on a country’s decarbonization efforts is inconclusive. This study examines the carbon emissions caused by countries’ transportation services on global value chains. The input–output (IO) model and the 2015 multi-regional environmental input–output table from the UNCTAD-Eora database are employed. The input–output approach was used to determine the carbon emissions generated by the transport sector, along global value chains, in 190 countries. Environmentally extended IO analysis then reallocates emissions responsibilities of the transport sector from production to consumption. The study identifies which country’s transport sectors add more value or emit more CO2. Our findings indicated that: (1) the transportation industry of a country may have a detrimental effect on the environment while generating minimal economic benefit; and (2) a country’s transport industry may be tightly related to global value chain operations, but does not create considerable environmental impact. Given the significant differences in emissions intensity, we propose not only calculating the production-based accounting (PBA) of CO2 emissions, but also the consumption-based accounting (CBA). If CBA emissions are lower than PBA emissions, a country’s transport sector is in carbon-leakage credit. The top three countries with the highest carbon-leakage credit for the transport sector were China, Russia and USA. If carbon emissions are taken into consideration, some nations may cease to possess a comparative advantage in manufacturing and trade.
This article is concerned with the performance evaluation of connected, autonomous vehicles (CAVs) in a realistic large-scale microsimulation scenario. In particular the question is: how much could a high diffusion of CAVs possibly change (1)~the average travel speeds (2)~the trip times of all traffic participants, including pedestrians, and (3)~the energy/fuel consumption? For this purpose, admittedly favourable assumptions are made: a 100\% diffusion of platooning-capable CAVs as substitution for private cars as well as a high maximum speed of platooned vehiclesin order to enable platoon formation. The morning rush hour scenario of the metropolitan area of Bologna, Italy has been selected for assessment. This scenario, which has been created and validated in previous works, represents an activity based demand model with travel plans for individual citizens, including all relevant transport modes. The microsimulation is performed by means of the SUMO simulator. The entire demand has been generated with the SUMOPy tool. For the platooning of CAVs, SUMO's SIMPLA module has been used, which controlls the vehicles via the interactive TRACI API.
Results show an increased speed and reduced travel time for CAV vehicles, with respect to human driven cars, in particular in the periphery and less in the center with a dense road network. However, the reason for improved speeds and travel times is predominantly the higher maximum speed allowed for vehicles trying to catch up and join a platoon. Furthermore these higher speed would also be resposible for an increase in fuel consumption of approximately 5\%.
In conclusion, CAVs alone are unlikely to reduce congestion in an urban area. To make the platooning concept work, additional technology and infrastructure is required in order to merge platoons effectively at freeways and at traffic lights. The latter could be simulated with GLOSA.
In order to improve the traffic efficiency of oversaturated arterial traffic, a two-way signal coordinated control method is proposed. Taking traffic speeds, turning flow proportions and the number of lanes into consideration, a traffic flow model for oversaturated arterial is established on the basis of LWR theory, and vehicle trajectory data of arterials is used to verify this model. Then a coordinated control model for two-way oversaturated arterials is introduced, which is composed of a throughput maximization model and a delay minimization model. For the former one, the cycle length and green time at the arterial intersections are optimized to improve the arterial capacity, while the latter is built to realize the signal coordination of the consecutive intersections by optimizing offsets. A multi-objective algorithm is proposed to solve the coordinated control model. First, the throughput maximization model is solved by the standard algorithm of mixed-integer linear programming. Second, the feasible solutions of the signal orders are obtained by a phase pattern searching algorithm. Third, the delay minimization model is solved by a standard algorithm of quadratic programming model. Finally, the proposed model is used to coordinate and optimize the traffic signals on East Zhongshan Road containing 10 intersections in Nanjing, China. A trajectory-based simulation model is put forward to simulate the arterial traffic, demonstrating that the proposed coordinated control model can avoid the spillover and queue retention. After optimization, the capacity increases by 12.6% while the average vehicle delay for through vehicles drops by 23.6% compared to Synchro’s coordinated control.
While the transportation sector is one of largest economic growth drivers for many countries, the adverse impacts of transportation on air quality are also well-noted, especially in developing countries. Carbon dioxide (CO2) emissions are one of the direct results of a transportation sector powered by burning fossil-based fuels. Detailed knowledge of CO2 emissions produced by the transportation sectors in various countries is essential for these countries to revise their future energy investments and policies. In this framework, three machine learning algorithms, ordinary least squares regression (OLS), support vector machine (SVM), and gradient boosting regression (GBR), are used to forecast transportation-based CO2 emissions. Both socioeconomic factors and transportation factors are also included as features in the study. We study the top 30 CO2 emissions-producing countries, including the Tier 1 group (the top five countries, accounting for 61% of global CO2 emissions production) and the Tier 2 group (the next 25 countries, accounting for 35% of total CO2 emissions production). We evaluate our model using four-fold cross-validation and report four frequently used statistical metrics (R2, MAE, rRMSE, and MAPE). Of the three machine learning algorithms, the GBR model with features combining socioeconomic and transportation factors (GBR_ALL) has the best performance, with an R2 value of 0.9943, rRMSE of 0.1165, and MAPE of 0.1408. We also find that both transportation features and socioeconomic features are important for transportation-based CO2 emission prediction. Transportation features are more important in modeling for 30 countries, while socioeconomic features (especially GDP and population) are more important when modeling for Tier 1 and Tier 2 countries.
There is a continuous need to design and develop wireless technologies to meet the increasing demands for high-speed wireless data transfer to incorporate advanced intelligent transport systems. Different wireless technologies are continuously evolving including short-range and long-range (WiMAX, LTE, and 5G) cellular standards. These emerging technologies can considerably enhance the operational performance of communication between vehicles and road-side infrastructure. This paper analyzes the performance of cellular-based long-term evolution (LTE) and 5GTN (5G Test Network) in pilot field measurements (i.e., vehicle-to-vehicle and vehicle-to-infrastructure) when delivering road weather and traffic information in real-time environments. Measurements were conducted on a test track operated and owned by the Finnish Meteorological Institute (FMI), Finland. The results showed that 5GTN outperformed LTE when exchanging road weather and traffic data messages in V2V and V2I scenarios. This comparison was made by mainly considering bandwidth, throughput, packet loss, and latency. The safety critical messages were transmitted at a transmission frequency of 10 Hz. The performance of both compared technologies (i.e., LTE and 5GTN) fulfilled the minimum requirements of the ITS-Assisted Road weather and traffic platform to offer reliable communication for enhanced road traffic safety. The field measurement results also illustrate the advantage of cellular networks (LTE and 5GTN) with a clear potential to use it heterogeneously in future field tests with short-range protocols, e.g., IEEE 802.11p.
Traffic has a direct impact on local and regional economies, on pollution levels and is also a major source of discomfort and frustration for the public who have to deal with congestion, accidents or detours due to road works or accidents. Congestion in urban areas is a common phenomenon nowadays, as the main arteries of cities become congested during peak hours or when there are additional constraints such as traffic accidents and road works that slow down traffic on road sections. When traffic increases, it is observed that some roads are predisposed to congestion, while others are not. It is evident that both congestion and urban traffic itself are influenced by several factors represented by complex geospatial data and the spatial relationships between them. In this paper were integrated mathematical models, real time traffic data with network analysis and simulation procedures in order to analyze the public transportation in Oradea and the impact on urban traffic. A mathematical model was also adapted to simulate the travel choices of the population of the city and of the surrounding villages. Based on the network analysis, traffic analysis and on the traveling simulation, the elements generating traffic congestion in the inner city can be easily determined. The results of the case study are emphasizing that diminishing the traffic and its effects can be obtained by improving either the public transport density or its accessibility.
In this paper, we detail and evaluate a coordinated approach to determining the sequence and duration of green lights at several intersections as part of the Intelligent Transportation System. We present the architecture of a wireless network used to track variations in adjacent intersections. Our algorithm exploits the collected data to determine the sequence of the green lights based on three objectives: (i) reduce the length of queues in the intersection, (ii) prioritize sending vehicle flows to intersections with lower traffic density than the most congested, (iii) synchronize traffic signals between adjacent intersections to create green waves. Traffic simulations have been simulated by the SUMO traffic simulator, they show that our solution manages to react to traffic change and reduce waiting time compared to isolated control strategies.
A large amount of present green light optimal speed advisory (GLOSA) systems are for private vehicles. However, as one of nonnegligible transportation modes, public transportation is worth more attention. Some GLOSAs just provide several driving models with fixed speeds and accelerations which is extremely difficult for human-drivers to obey strictly and adapt dynamically. Therefore, this paper proposes a GLOSA for buses (GLOSA-B) considering the waiting time at the closest bus stop to the target intersection. By means of V2X communication based on ITS-G5 (IEEE 802.11p), this GLOSA-B could provide a range of recommended speeds and update calculation every second. To validate the proposed algorithm, 20 groups of GLOSA and non-GLOSA buses are simulated. The results indicate that this GLOSA-B could avoid unnecessary stops significantly. Compared with non-GLOSA buses, the GLOSA buses save waiting time at the target intersection by 98.95%.
Road transportation is the main factor affecting high greenhouse gas (GHG) emissions and poor air quality in the atmosphere. One cause is traffic congestion on urban streets due to plenty of travel demand over road network capacity and inefficient traffic management at signalized intersections. Moreover, typical vehicles consume much fuel affecting the problems mentioned above, and there is still little use of environmentally friendly vehicles, such as the hybrid car (HV). This research investigated how efficient traffic signal management could reduce vehicle fuel consumption approaching a signalized intersection in traffic congestion. In addition, the fuel consumption of HV was compared with that of conventional gasoline cars regarding how it could reduce fuel consumption in a condition of the adjustment of traffic signal management. Then, estimating fuel consumption at the intersection was assembled by traffic simulation to identify driving patterns/ modes of each vehicle. The results indicated that an adjustment of traffic signal management at the intersection by optimizing cycle length calculation based on Webster' s method could reduce vehicle fuel consumption by decreasing vehicle delay and stop time. If HVs replaced conventional gasoline cars by at least 5% , fuel consumption would be significantly reduced when HVs stop and run at a fluctuated speed between 1-20 km/ hr (crawling) near the intersection. Therefore, this research could well detect a reduction in fuel consumption of environmentally friendly vehicles, even for vehicles traveling at a crawl.
Recently, interest in Internet of Vehicles’ (IoV) technologies has significantly emerged due to the substantial development in the smart automobile industries. Internet of Vehicles’ technology enables vehicles to communicate with public networks and interact with the surrounding environment. It also allows vehicles to exchange and collect information about other vehicles and roads. IoV is introduced to enhance road users’ experience by reducing road congestion, improving traffic management, and ensuring the road safety. The promised applications of smart vehicles and IoV systems face many challenges, such as big data collection in IoV and distribution to attractive vehicles and humans. Another challenge is achieving fast and efficient communication between many different vehicles and smart devices called Vehicle-to-Everything (V2X). One of the vital questions that the researchers need to address is how to effectively handle the privacy of large groups of data and vehicles in IoV systems. Artificial Intelligence technology offers many smart solutions that may help IoV networks address all these questions and issues. Machine learning (ML) is one of the highest efficient AI tools that have been extensively used to resolve all mentioned problematic issues. For example, ML can be used to avoid road accidents by analyzing the driving behavior and environment by sensing data of the surrounding environment. Machine learning mechanisms are characterized by the time change and are critical to channel modeling in-vehicle network scenarios. This paper aims to provide theoretical foundations for machine learning and the leading models and algorithms to resolve IoV applications’ challenges. This paper has conducted a critical review with analytical modeling for offloading mobile edge-computing decisions based on machine learning and Deep Reinforcement Learning (DRL) approaches for the Internet of Vehicles (IoV). The paper has assumed a Secure IoV edge-computing offloading model with various data processing and traffic flow. The proposed analytical model considers the Markov decision process (MDP) and ML in offloading the decision process of different task flows of the IoV network control cycle. In the paper, we focused on buffer and energy aware in ML-enabled Quality of Experience (QoE) optimization, where many recent related research and methods were analyzed, compared, and discussed. The IoV edge computing and fog-based identity authentication and security mechanism were presented as well. Finally, future directions and potential solutions for secure ML IoV and V2X were highlighted.
1. Introduction
Intelligent Transportation Systems (ITS) and computational systems’ rapid development opened new scientific research in smart traffic safety with comfort and efficient solutions. Artificial Intelligence (AI) has been widely used to optimize traditional data-driven approaches in different research areas [1]. AI-based on the Vehicle-to-Everything (V2X) system obtains information from various sources, i.e., car, train, bus, etc., and enables to increase the realization of drivers and forecast to avoid accidents. This progression has directed to the opportunity to understand smart driving, which was built on the idea of copying real driving comportment, while avoiding human mistakes and bringing comfortable safety to drivers. Many services have been invented from crowd and light road traffic to adapting traffic, a legacy from self-based vehicle systems to the IoV [2]. IoV is addressed to change the interaction between the vehicles, roadside stations, on-board stations, and environments to communicate data and multimedia between various networks. The motivation of IoV is to be adopted and build the human-vehicle-roadside onboard IoT Connected services within the various vehicle and different networks.
Machine Learning (ML) is responsible for a wide range of AI applications. The ML techniques are unsupervised, supervised, and reinforcement learning. In the unsupervised ML scheme, training depends on untagged data. It tries to find an adequate representation of untagged data. While, in supervised learning, it learns from a group of labeled data. In supervised learning, regression and classification schemes train the discrete and continuous data for prediction and decision-making. Reinforcement learning (RL) studies from the learning agent’s activities from the consistent reward to capitalize on the notion of cumulative rewards. The Markov Decision Process (MDP) is a sample of RL [2]. This scheme is a perfect technique for taking many issues’ research problems in vehicular networks, such as in collaborative optimization of oil consumption for a specific area and optimum path forecasting of electric vehicles and minimizing traffic congestions.
Given the importance of the use of Artificial Intelligence (AI) in IoV, as it provides smart models in most of its applications, this paper contributes a brief concept on one of the AI methods known as machine learning and the possibility of its use in several specific aspects related to the IoV network. In IoV networks, edge computing and caching problems are the most considered challenges requiring an intelligent optimization method. Edge computing and caching challenges are related to many factors, i.e., channel condition, dynamic communication topology, and resource allocation management. In the IoV network architecture, artificial intelligence is in a separated layer responsible for virtual cloud infrastructure. The AI layer act as an information management brain. Deep neural networks are ML algorithms developed to make decisions according to learned IoV resource actions [3].
This paper has conducted a critical review with analytical simulation for offloading mobile edge computing decisions based on learning and Deep Reinforcement Learning (DRL) technologies for vehicular communication in (IoV). We have considered a typical IoV network architecture with one IoV Edge-Computing (IoVEC) and one mobile user. The tasks of the device arrive as a flow in time. Our analytical model performs the offloading decision process of the task flow as a Markov Decision Process (MDP). The optimization object minimizes the weighted sum of offloading latency and power consumption, which is decomposed into the reward of each time slot.
The rest of the paper is organized as follows; the study background and motivation are presented in Section 2, where systematic technical knowledge and motivation of secure ML in the IoV field were discussed. A brief concept of AI in IoV is reviewed in Section 3 by considering using AI in multimedia and IoV edge-based and Vehicle-to-Everything’s Internet communications. Section 4 provides a clear concept about the contribution of AI to enabling QoS and QoE optimization, where QoS manages and controls resources of the IoV network by setting various priorities for each data type, while QoE discusses the measurement of the overall system homogeneity and stability of service. Section 5 provides a detailed description of using machine learning algorithms with IoV in different aspects. The most common use cases of ML in IoV applications are presented in Section 6. Section 7 gives a brief review of the possible future research directions and potential ML solutions in IoV. Finally, the conclusion is presented in Section 8.
2. Background and Motivation
Due to the significant research and technology development in wireless communication, the traditional ITS has to care about the vehicular communication field. Recently, the numbers of vehicles have increased due to transporting huge numbers of people from region to region. This increment in the number of vehicles would create issues such as crowding and accidents on the roads. This issue could be considered as one of the main problems in daily life. Most of the general form of vehicular networking is known as the vehicular ad hoc network (VANET) [4]. VANET consists of Vehicle-to-Vehicle (V2V) and Vehicle-to-Roadside (V2R) communications to transfer the vehicles’ information. The VANETs’ communication depends on the Roadside Unit (RSU) to support Wireless Access in Vehicular Environments (WAVE).
The Roadside Unit (RSU) along the roadwork acts as wireless access points’ support communication to the vehicles inside its coverage area [5]. The hybrid vehicular network architecture, interacted with the cellular communication architectures, will operate the cellular communication services, i.e., voice, in collaborations. Due to the current trend to connect vehicular networks to information centers and the need to exchange data, IoV allows enabling Internet access among on-road vehicles. One of the essential IoV applications is to improve the features of VANETs to reduce various issues in urban traffic and accident environments [6]. IoV enables the vehicular road networks to interconnect with different wireless network technologies i.e., Wi-Fi and 4G/LTE for V2I, IEEE WAVE for V2V and V2R, MOST/Wi-Fi for V2S, and CarPlay NCF for V2P. It is useful to provide a comprehensive presentation to ML's concepts in IoV and explain the areas that could contribute to these networks' development [7].
In recent years, the arising need to introduce artificial intelligence technologies in IoV applications has been facing some challenges. These challenges are related to making particular decisions and forecasting different aspects of IoV, such as traffic monitoring and management, big data processing, energy and resource management, and intelligent interaction with users to provide high-quality services [6, 7]. Several studies have been conducted on using artificial intelligence techniques such as machine learning to develop solutions to most of these challenges [8]. Due to the current developments in the field of AI, especially in using machine learning techniques to make intelligent decisions in several IoV applications, it is useful to provide a comprehensive presentation to study some concepts of using ML in IoV and explain the areas that could contribute to the development of these networks.
3. Artificial Intelligence Methods in the IoV Network
AI technology is more related to the layer responsible for presentation and functionalities in the IoV-layered architecture. A term of virtual cloud infrastructure can describe this layer and be responsible for storing, processing, analyzing the information received from the IoV network, and decision-making based on the analyzed information. In IoV, the computation and analysis are provided by Big Data Analysis (BDA) and Vehicular Cloud Computing (VCC) systems which are used as an information management center [9]. According to the IoV applications, many services can be provided by the IoT cloud environment, requiring intelligent service management. The smart cloud-computing servers provide many smart services, i.e., safety, traffic administration, entertaining, and subscription, which are the foundation of elegance in IoV. The cloud servers based on AI enable the procedure and develop AI in Real-Time (RT) massive data traffic to provide a smart decision for intelligent customer services. The Vehicular Cyber-Physical System (VCPS) is considered a vehicular network model that concerns disseminating information using next-generation Internet [10]. VCPS depends on AI technology to provide smart processing in huge data traffic utilizing fog and cloud computing for civilian and safety applications.
In IoV networks, edge computing and caching problems are the most considered challenges requiring an intelligent optimization method. Edge computing and caching challenges are related to many factors, i.e., channel condition, dynamic communication topology, and resource allocation management. AI in IoV provides an intelligent approach to solve most of these challenges. The use of ML offers a means of interaction to the IoV environment and enables the creation of an agent that learns challenging factors to optimize the overall IoV network utilization [11]. Q-learning and deep neural networks are ML algorithms developed to make decisions according to learned IoV resource actions. In the IoV network architecture, the presentation of artificial intelligence in a separated layer is responsible for virtual cloud infrastructure. The AI layer acts as an information management brain [10, 11]. The AI layer in IoT architecture consists of big data analysis, cloud computing, and expert systems. It plays an essential task in storing, processing, and analyzing the information received from the coordination layer and takes decisions according to the network status.
3.1. Artificial Intelligence Methods for IoV Multimedia Communication
The deployment of IoV in multimedia communications requires a device that allows data exchange and communication with other surrounded devices. This can be achieved by any technology such as Personal Area Networks (PAN), the Internet of Things (IoT), and Wireless Sensor Network (WSN). Data exchange’s scalability and flexibility are quite important for IoV by integrating sensors, vehicles, humans, actuators, machines, etc. The sensor in intelligent IoV enhances vehicle and traffic systems’ safety, while harmonized traffic data transfer in the IoV system network enhances vehicular system efficiency. However, the amount of energy consumption, required capacity, green buffer-awareness, and message exchange through IoVs may compromise severe data transfer risk [12]. AI based on self-driven vehicles encourages several types of applications with many benefits of intelligence. Especially for the increase in the amount of data and complexity, which the algorithms will be processing, it is precise and effective for future directions. As growing, the high traffic information in IoVs required a smart utility, followed to efficiently monitor and manage the demand for intelligent IT technologies [13]. With the rapid evolution in digital technologies, the development of multimedia depends on the IoV system, and it needs a portable device to collect a voluminous amount of information for aiding and guiding the specific trend for analyzing the transportation industry by IoT-based platforms.
Figure 1 shows the structure of multimedia communication through sensor nodes in the IoV system. Its structure consists of three main parts for IoV data and information network techniques and models. The data and information network techniques and models are redeveloped with the central server. The inter and intravehicle network connections among various sections are executed by transferring urgent and sensitive data throughout the vehicle via adaptive and smart wireless communication. The vehicle’s client enables QoS monitoring [13, 14]. In this structure, the IoV traffic can be arranged based on the category containing sensitive/standard, prestored, real-time, or high-definition resolution, respectively. To accomplish the real-time and jitter-tolerant data and information exchange with low buffer storage and scarce power supply, it should be fortified to tolerate the raw unprocessed data and information into the regular and synchronized format with good and clean visibility.
In this paper, we propose a cellular automaton model to simulate traffic flow controlled by a series of traffic lights. The synchronized traffic light and the green wave light strategies were investigated. The spatiotemporal diagrams, energy dissipation, and CO2 emission of the system were presented. Our simulations are conducted to clarify the difference between both strategies and their effects on the traffic flow and the CO2 emission. We found that the traffic flow depends mainly on the strategy used for managing the traffic lights as well as on the parameters of the traffic lights namely; the cycle time, the number of traffic lights, and the length of the system. The fundamental diagram has barely the same characteristics for both methods and it depends on the combination of the parameters of the system. We find that the green wave is more convenient for the management of a series of traffic lights than the synchronized control strategy in terms of throughput, especially for large size systems. Unlike, in terms of CO2 emission and energy dissipation both control strategies outperform each other depending on the density regions and the parameters of the system. Finally, we investigate the effect of both cycles (i.e. red and green) for the synchronized control method on the CO2 emission. It is found that the green cycle generates often a series of acceleration events that increase CO2 emission.
This study develops a methodology for coordinated speed optimization and traffic light control in urban street networks. We assume that all vehicles are connected and automated. The signal controllers collect vehicle data through vehicle to infrastructure communications and find optimal signal timing parameters and vehicle speeds to maximize network throughput while harmonizing speeds. Connected and automated vehicles receive these dynamically assigned speeds, accept them, and implement them. The problem is formulated as a mixed-integer non-linear program and accounts for the trade-offs between maximizing the network throughput and minimizing speed variations in the network to improve the network operational performance and at the same time smoothen the traffic flow by harmonizing the speed and reducing the number of stops at signalized intersections. A distributed optimization scheme is developed to reduce the computational complexity of the proposed program, and effective coordination ensures near-optimality of the solutions. The case study results show that the proposed algorithm works in real-time and provide near-optimal solutions with a maximum optimality gap of 5.4%. The proposed algorithm is implemented in Vissim. The results show that coordinated signal timing and speed optimization improved network performance in comparison with cases that either signal timing parameters or average speed of vehicles are optimized. The coordinated approach reduced the travel time, average delay, average number of stops, and average delay at stops by 1.9%, 5.3%, 28.5%, and 5.4%, respectively compared to the case that only signal timing parameters are optimized.
Traffic lights have been used for decades to control and manage traffic flows crossing road intersections to increase traffic efficiency and road safety. However, relying on fixed time cycles may not be ideal in dealing with the increasing congestion level in cities. Therefore, we propose a new Adaptive Traffic Light Control System (ATLCS) to assist traffic management authorities in efficiently dealing with traffic congestion in cities. The main idea of our ATLCS consists in synchronizing a number of traffic lights controlling consecutive junctions by creating a delay between the times at which each of them switches to green in a given direction. Such a delay is dynamically updated based on the number of vehicles waiting at each junction, thereby allowing vehicles leaving the city centre to travel a long distance without stopping (i.e., minimizing the number of occurrences of the ‘stop and go’ phenomenon), which in turn reduces their travel time as well. The performance evaluation of our ATLCS has shown that the average travel time of vehicles traveling in the synchronized direction has been significantly reduced (by up to 39%) compared to non-synchronized fixed time Traffic Light Control Systems. Moreover, the overall achieved improvement across the simulated road network was 17%.
The transportation sector consumes 25% of world energy with 23% of the world's total carbon emission. Therefore, it is necessary to investigate the integrated effect of fossil fuel source of energy consumption, economic development, and total population on CO 2 emission based on environmental degradation transportation sector. We employed the econometric method-ologies such as a hybrid error correction model, regression coefficients, platykurtic distribution, Dickey-Fuller test, and co-integration test in order to justify empirical analysis for Pakistan transport sector. Results reveal that an increase in economic growth, urbanization, and energy consumption increased transport-based environmental degradation urbanization. Moreover, very interestingly, during this period, energy consumption has increased by 13.5%, and it shows a high dependence of economic growth on energy consumption. Further, the CO 2 emission and energy consumption per capita has a positive relationship. Finally, this study has proposed some suggestion for policy and decision-makers to mitigate environmental degradation as well as make transport sector environmentally sustainable.
Recent developments by companies as Waymo, Uber, or Tesla show that autonomous driving is no science fiction anymore. Coordinated driving applications such as platooning, i.e., driving in convoys of coordinated vehicles, use the full potential of the automation. In this paper, we present a simulation framework for analyzing platooning coordination strategies which can be used by domain experts without experience in simulation as it abstract from the details of the underlying simulation. We show the applicability of the simulation framework to support the analysis of platooning coordination strategies in a case study with three coordination strategies.
Vehicle-to-vehicle (V2V)-based forward collision warning is a core connected vehicle (CV) service for preventing traffic crashes. Since the driver’s reaction affects the surrounding traffic conditions, an analysis of the effects of the CV application is required in terms of traffic stream performance. This study compared the differences in driving behaviors of CVs depending on whether V2V-based forward collision warning information was provided. The driving characteristics of CVs based on the analysis of probe vehicle data (PVD) were defined, and a methodology was proposed to simulate the driving behaviors of CVs in VISSIM environments. Additionally, the effectiveness of improving mobility and traffic safety by various market penetration rates (MPRs) of CVs in an accident situation was identified by evaluating the average travel speed and time-to-collision (TTC)-based crash risk. The simulation results for the two-lane blocking accident scenario indicated that the average speed increased by 23.18% with an MPR of 100%, and the TTC-based crash risk decreased by 18.34% compared with an MPR of 0%. It has been demonstrated that V2V-based warning information is useful for not only safety benefits but also mobility improvement. The results of this study could be employed as fundamentals to establish various policies to expedite the implementation of CV systems in practice. In addition, it is suggested that the outcome of this study will be useful for developing traffic flow management strategies technology to improve traffic safety.
Consider a bidirectional arterial road along which several junctions are controlled by fixed-time traffic signals. The driving times between the junctions are far from showing the ideal condition of integer multiples of half the cycle time. At the junctions, separate left-turn phases have to be scheduled. In particular, the two opposite directions of the arterial can but do not need to be scheduled at the same time. This paper provides an integrated mathematical optimization model that maximizes the widths and lengths of the green bands of both directions of the arterial. Within this, the model selects among three predefined signal programs with different phase sequences, and computes optimum offsets for the selected signal programs at each junction. Arranging the left-turn phases before or after the arterial’s through-traffic in a dedicated way provides much better results in the optimization model than always scheduling them at the same time. To validate the optimization result, we implemented a microscopic traffic flow simulation model (using the SUMO simulation package) inspired by certain arterials in the city of Berlin, Germany. With 11 crossings, the result was an average of less than 1.7 stops per car—already including one possible stop at the two entry points of the coordinated arterial. This compares favorably with the average number of at least 3.4 stops per car when the straight traffic in both directions is always scheduled at the same time, that is, in parallel.
An optimization model of regional green wave coordination control for the coordinated path set is proposed based on the network’s directional and asymmetric actual coordination control demands. The model in this paper selects the coordinated path set as the optimization object and takes the best regional coordination control effect as the optimization objective. By selecting signal timing parameters, such as stage time, stage center point, offset, and cycle length, as optimization variables, the relationship between signal timing parameters and the effect of green wave coordination was established. The stage time of the coordinated stage at the upstream and downstream intersections is used to calculate the evaluation index of the coordination control benefit of the whole road network. The case study demonstrates that this model can optimize coordinated path chains with left-turn traffic flows under green wave coordination management. In terms of network performance, compared with Transyt and Synchro, the signal control scheme obtained by the proposed model can reduce the average delay by about 30% and the average number of stops by about 40%. To meet the requirements of regional green wave coordination control, the proposed model can optimize different signal timing parameters to obtain a wide range of applications of green wave coordinated control in road networks.
div class="section abstract"> Eco-driving algorithms enabled by Vehicle to Everything (V2X) communications in Connected and Automated Vehicles (CAVs) can improve fuel economy by generating an energy-efficient velocity trajectory for vehicles to follow in real time. Southwest Research Institute (SwRI) demonstrated a 7% reduction in energy consumption for fully loaded class 8 trucks using SwRI’s eco-driving algorithms. However, the impact of these schemes on vehicle emissions is not well understood. This paper details the effort of using data from SwRI’s on-road vehicle tests to measure and evaluate how eco-driving could impact emissions. Two engine and aftertreatment configurations were evaluated: a production system that meets current NOX standards and a system with advanced aftertreatment and engine technologies designed to meet low NOX 2031+ emissions standards. For the production system, eco-driving on an urban cycle resulted in a CO2 reduction of 8.4% but an increase of 18% in brake specific NOX over the baseline cycle. With the low NOX system, eco-driving achieved a similar reduction in CO2. NOX emissions increased 108% over the baseline but remained below the low NOX standard. The eco-driving cycles generated lower exhaust temperatures than the baseline cycles, which inhibited SCR catalyst performance and increased tailpipe NOX. Conversely, a port drayage cycle with eco-driving showed improvements in both CO2 and NOX emissions over the baseline. The results demonstrate that eco-driving algorithms can be a technological enabler to meet current and potential future emissions targets for heavy-duty applications.
</div
Vehicle-to-infrastructure (V2I) communication connects vehicles and enables collision-free and energy-efficient driving, such as eco-approaches and departures at signalized intersections. An increased connectivity range can connect multiple signalized intersections and lead to long-term energy-efficient driving using richer information. However, no published studies to date provide insights into the energy-saving potential of increasing the connectivity range. In this paper, we present a V2I-enabled eco-driving control that can perform multiple traffic signal eco-approaches, and we systematically design a large-scale simulation study to quantify the energy impact of the increased V2I range for various scenarios. Simulation results show that the V2I-enabled eco-driving control can reduce energy use by up to 40%, on average, compared to the baseline, depending on road attributes and vehicle powertrain type. We validate these findings by evaluating the controller through a vehicle-in-the-loop testing platform.
Traffic congestion at signalized intersections often leads to serious impacts on adjacent intersections on a corridor. To enhance intersections’ throughput efficiency, traffic signals are commonly coordinated across intersections. Traditional signal coordination methods control the adjacent intersections by setting a fixed phase offset. However, these traditional coordination methods may have poor adaptability to dynamic traffic conditions, which can cause additional congestion. To reduce arterial traffic delays, this paper develops an adaptive coordination control method based on multi-agent reinforcement learning (MARL). Most existing MARL-based methods rely on impractical assumptions to improve their performance in complex and dynamic traffic scenarios. To overcome these assumptions, this paper proposes a fully scalable MARL algorithm for arterial traffic signal coordination based on the proximal policy optimization algorithm. We apply a parameter-sharing training protocol to mitigate the slow convergence due to nonstationarity and to reduce computational requirements. In addition, a new action setting is designed by using the lead-lag phase sequence to simultaneously improve the implementation and coordination flexibility of the method. Extensive simulation experiments and comparisons with existing methods demonstrate that the proposed method performed stably in both simulated and real-world arterial corridors. Hence, the proposed signal coordination method can alleviate traffic congestion more effectively than existing traditional and MARL-based methods.
This paper designs the vehicle tracking and resource allocation in the terahertz (THz) vehicle-to-infrastructure communications (V2I) networks, where roadside units (RSUs) equipped with leaky-wave antennas help to estimate the driving states of multiple vehicles and optimize the transmit power and bandwidth per vehicle after receiving the vehicles' feedback. Different from the conventional phased arrays, the leaky-wave antenna has the potential of improving the sensing accuracy with lower system overhead thanks to its unique spatial-spectral coupling feature. The generalized mobile scenario is studied in which vehicles drive at time-varying speeds. A novel unscented Kalman filter (UKF) based solution is proposed to track the vehicles without requirement of addressing the Doppler effect. Based on the estimated states of multiple vehicles, a low-complexity resource allocation method is developed to maximize the sum rate under user fairness concern. Simulation results confirm that the proposed tracking solution can evaluate the propagation angle, vehicle's states and inter-vehicle distance accurately, and the tailored resource allocation method strikes a delicate balance between the sum rate and user fairness in the multi-vehicle V2I scenario.
As one of the innovative technologies of intelligent transportation systems (ITS), Connected and Autonomous Vehicles (CAVs) have been deployed gradually. Given that there will be a long transition period before reaching a fully CAVs environment, it is crucial to assess the potential impacts of CAVs on mixed traffic flow. Considering platoon formation process, this study develops a platoon cooperation strategy based on “catch-up” mechanism, and then analyzes the impact on fundamental diagram, traffic oscillation, and traffic safety within mixed traffic. Simulation results show that with an increasing market penetration rate (MPR) of CAVs, road capacity shows an increasing trend. Compared with base scenario, a clear increase in road capacity is also observed under platoon scenario. With an increasing MPR, traffic oscillation is shown to reduce largely. Furthermore, the proposed platoon strategy could dampen frequent shockwaves and shorten the propagation range of waves. Regarding traffic safety, multiple surrogate safety measures (SSMs) are used to evaluate the traffic risk: including Criticality Index Function (CIF), Potential Index for Collision with Urgent Deceleration (PICUD), and Deceleration Rate to Avoid a Crash (DRAC). With increasing MPR, collision risk identified by CIF and DRAC shows an increase tendency, while that identified by PICUD has no apparent trend. Furthermore, the platoon strategy is shown to increase the severity of traffic conflicts significantly. Overall, this study provides novel insights into CAVs deployment through the analysis of platoon strategy.
Unreliable transit services can negatively impact transit ridership and discourage passengers from regularly choosing public transport. As the most important content of bus service reliability, accurate bus arrival prediction can improve travel efficiency for enabling a reliable and convenient transportation system. Accordingly, this paper proposes a novel deep learning method, i.e. variational mode decomposition long short-term memory (VMD-LSTM), for bus travel speed prediction in urban traffic networks using a forecast of bus arrival information on variable time horizons. The method uses the temporal and spatial patterns of the average bus speed series. The results show that the VMD-LSTM model outperforms other models on forecasting bus link speed series in future time intervals, whereas the artificial neural network model achieves the worst prediction. In conclusion, the VMD-LSTM method can detect irregular peaks of transit samples from a series of temporal or spatial variations and performs better on major and auxiliary corridors.
From the point of view of environmental protection, the development of vehicles and their drives is determined in the future by the constant tightening of exhaust gas requirements. In addition, measures to reduce fuel consumption and CO2 emissions are increasingly influencing the concept of vehicle and drive optimization. Since most of the world's energy consumption is taken by transport, mainly cars, manufacturers are often faced with the need to develop and implement new, increasingly energy efficient and environmentally friendly energy methods - for example, the use of unconventional fuels, including: alcohol fuels (ethanol and methanol), biodiesel, Fischer's fluid -Tropsch, hydrogen fuel. So, the long-term guaranteed supply of transport energy, together with sound fuel management, ensures the medium and long-term diversification of energy for its production, especially, including alternative and renewable energy. Much has happened over the past decade, although policy goals remain unchanged for many countries improving energy security and limiting greenhouse gas emissions may be more important than ever. And, unprecedentedly, energy use in transportation is at the heart of these issues. New methods are needed to free transport from its persistent dependence on oil and take a new path. But technology has made interesting progress, and this progress will continue in the coming years, creating new opportunities to achieve these goals. Unsurprisingly, interest in biofuels and their production has skyrocketed over the past decade. Global production of total ethanol doubled between 1990 and 2021. In some regions, especially in Europe, the use of biofuels for diesel engines has also increased significantly in recent years. Perhaps most importantly, countries around the world are now seriously considering increasing the production and use of biofuels, and many countries have formulated policies to ensure this growth.
Vehicular networks have become among the most interesting topics in Internet of Things era as they are key factor in limiting road crashes and introducing a smart transportation system with high level of safety. The communication between vehicles and other devices is known as a Vehicle-to-Everything (V2X) and it is categorized into two main types: Vehicles-to-Infrastructure (V2I) and Vehicles-to-Vehicles (V2V). This paper considers vehicular networks based on 5G cellular network with a Device-to-Device (D2D) technology support. The main challenges here are to guarantee all V2V links reliability while maximizing both of ergodic capacity for those V2I ones and the overall network utilization. Furthermore, each channel should be shared between a V2I link and multiple V2V links. The paper proposes a sequence of procedures to solve the mentioned problem. First, an efficient power optimization mechanism is modeled to guarantee all V2V links reliability. Then, an analytical model is proposed to maximize V2Is ergodic capacity. Lastly, the paper investigates various resources assignment algorithms for V2I and V2V links, where demanding V2V links could share multiple V2I channels to enhance the network utilization. The proposed algorithms analysis results are presented and compared with others showing the performance metrics enhancement including V2I capacity, network bandwidth efficiency, number of dropped V2V links, and run time for assigning channels.
The uptake of electric vehicles supports decarbonization and increasingly interconnects the electricity and transport system. While the integration of electric vehicles could challenge electricity grids, bidirectional power flows between vehicles and grids could support grid operations. Despite the globally increasing number of Vehicle-to-X trials, including Vehicle-to-Grid and Vehicle-to-Customer, an in-depth understanding of trial implementations and expert experiences has largely been overlooked although they are both crucial for technological development and deployment. Based on our analysis of a global Vehicle-to-X trial database and 47 interviews with experts from industry and academia, we (i) provide an overview of the implementation status of Vehicle-to-X and analyze predominate trial configurations, i.e. combinations of characteristics, (ii) identify important technical, social and regulatory challenges for the implementation of Vehicle-to-X and assess and discuss expert evaluations of these challenges and (iii) derive implications for different actors.
The most predominate trial configurations are Vehicle-to-Customer and transmission-level services provided by commercial fleets that charge at work due to current practical advantages of centralized approaches. From a technical standpoint, we find that although Vehicle-to-X can defer or even mitigate grid reinforcement at the distribution level, this potential is highly dependent on local conditions. Regarding social aspects, incentives and Vehicle-to-X operations need to be tailored to different vehicle users. Concerning regulation, it is imperative to avoid double taxation of electricity, simplify market participation for small providers, and further develop Vehicle-to-X standards. Implications for actors include the evaluation and enablement of portfolios with different flexibility assets, and stacking of services to increase revenue streams and reduce risk resulting from variations in driving patterns and charging behavior.
Recent research reveals that reinforcement learning can potentially perform optimal decision-making compared to traditional methods like Adaptive Traffic Signal Control (ATSC). With the development of knowledge through trial and error, the Deep Reinforcement Learning (DRL) technique shows its feasibility for the intelligent traffic lights control. However, the general DRL algorithms cannot meet the demands of agents for coordination within large complex road networks. In this article, we introduce a new Cooperative Group-Based Multi-Agent reinforcement learning-ATSC (CGB-MATSC) framework. It is based on Cooperative Vehicle Infrastructure System (CVIS) to realize effective control in the large-scale road network. We propose a CGB-MAQL algorithm that applies k-nearest-neighbor-based state representation, pheromone-based regional green-wave control mode, and spatial discounted reward to stabilize the learning convergence. Extensive experiments and ablation studies of the CGB-MAQL algorithm show its effectiveness and scalability in the synthetic road network, Monaco city and Harbin city scenarios. Results demonstrate that compared with a set of general control methods, our algorithm can better control multiple intersection cases on congestion alleviation and environmental protection.
Vehicle platooning is an automated driving technology that enables a group of vehicles to travel very closely together as a single unit to improve fuel efficiency and driving safety. These advantages of platooning attract huge interests from academia and industry, especially logistics companies that can utilize the platooning technology for their heavy-duty trucks due to the huge cost savings. In this paper, we demonstrate that existing platooning solutions, however, fail to support formation of a ‘long’ platoon consisting of many vehicles especially long-body heavy-duty trucks due to the limited range of vehicle-to-vehicle communication such as DSRC and device-to-device communication for C-V2X. To address this problem, we propose
L-Platooning
, the first platooning protocol that enables seamless, reliable, and rapid formation of a long platoon. We introduce a novel concept called
Virtual Leader
that refers to a vehicle that acts as a platoon leader to extend the coverage of the original platoon leader. A virtual leader election algorithm is developed to effectively designate a virtual leader based on the novel metric called the
Virtual Leader Quality Index (VLQI)
which quantifies the effectiveness of a vehicle serving as a platoon leader. We also develop mechanisms for
L-Platooning
to support the vehicle join and leave maneuvers specifically for a long platoon. Through extensive simulations, we demonstrate that
L-Platooning
enables vehicles to form a long platoon effectively by allowing them to maintain the desired inter-vehicle distance accurately. We also show that
L-Platooning
handles seamlessly the vehicle join and leave maneuvers for a long platoon.
Vehicular emissions make significant contribution to the total ambient airborne pollutants. Global warming and human health concerns are motivating researchers to come out with newer ways of controlling air pollution effectively. On the other hand, there are significant challenges in complying with current and upcoming vehicle emission regulations, which are quite stringent. It is therefore quite important to monitor vehicular emissions closely, which can facilitate adopting effective control measures when necessary, and also in predicting the impact of vehicular emissions on ambient air quality. Traditionally, dynamometers (both engine and chassis) testing has been used extensively to measure and monitor vehicular emissions, and the database generated has been used as input in modeling the traffic-related air quality impact. Even though standard driving cycles are followed in dynamometer tests attempting to closely replicate real-world driving conditions, they may not necessarily represent actual real-world driving conditions and emissions thereof. Therefore, in recent years, significant scientific efforts have been directed to measure and analyze real-world driving emissions (RDE) from vehicles. In this paper, the state-of-the-art techniques and methods for vehicular emissions monitoring under real-world driving conditions are reviewed and discussed in detail. Different vehicle emissions monitoring methods are presented in comparison to dynamometer-based measurements. Several influencing factors which affect on-road and in laboratory measurements are identified and discussed. Potential applications of different emission control strategies are reviewed. Finally, guidelines are formulated for effective vehicular emissions monitoring, and to minimize discrepancies between on-road and laboratory based measurements, in order to have a sustainable road transport system in future.
Smart and decentralized control systems have recently been proposed to handle the growing traffic congestion in urban cities. Proposed smart traffic light solutions based on Wireless Sensor Network and Vehicular Ad-hoc NETwork are either unreliable and inflexible or complex and costly. Furthermore, the handling of special vehicles such as emergency is still not viable, especially during busy hours. Inspired by the emergence of distributed smart cameras, we present a novel fuzzy logic approach to traffic control at intersections . Our approach uses smart cameras at intersections along with image understanding for real-time traffic monitoring and assessment. Besides understanding the traffic flow, the cameras can detect and track special vehicles and help prioritize emergency cases. Traffic violations can be identified as well and traffic statistics collected. In this paper, we introduce a flexible, adaptive and phase-free distributed traffic-control algorithm that uses the information provided by distributed smart cameras to efficiently control traffic signals. Experimental results show that our collision-free approach outperforms the state-of-the-art of the average user's waiting time in the queue and improves the routing of emergency vehicles in a cross congestion area.
Greenhouse gas emission in transport sector is a major problem with its harmful effects on environment and population. This paper proposes to devise green routing solution for Mobile Advertisement Vehicle (MAV). The objective of the problem is to minimize route cost and carbon emission under time dependent speed constraint. The problem is modelled with hierarchical optimization and is solved in stages. This paper also highlights the idling emission estimation and its impact on the total emission. The problem is solved using Hybrid Particle Swarm Optimization (HPSO) and the minimum cost routes obtained are improved using local exchange operator to minimize emission. The model is tested on a case study of mobile advertisement vehicle which produces minimum emission routes.
Microscopic traffic simulation is an invaluable tool for traffic research. In recent years, both the scope of research and the capabilities of the tools have been extended considerably. This article presents the latest developments concerning intermodal traffic solutions, simulator coupling and model development and validation on the example of the open source traffic simulator SUMO.
