Enhancing intelligence in traffic management systems to aid in vehicle traffic congestion problems in smart cities

Filho, Geraldo P. Rocha; Meneguette, Rodolfo I.; Valladares‐Neto, José; Valejo, Alan; Weigang, Li; Ueyama, Jó; Pessin, Gustavo; Villas, Leandro A.

doi:10.1016/j.adhoc.2020.102265

Cited by 43 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The time for an EV stopped waiting for a traffic light to turn from red to green at the entrance to each road segment was randomly set within the interval of 15 seconds. The upper limit of the traffic density permitted on each of the three expressways was set to 50 vehicles per kilometer [45].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Distributed Urban Traffic Congestion Prevention Mechanism for Mixed Flow of Human-Driven and Autonomous Electric Vehicles

Huang¹,

Hu²,

Ho³

et al. 2021

IJCIS

View full text Add to dashboard Cite

Traffic congestion in urban areas has become a critical problem that municipal governments cannot overlook. Meanwhile, mixed traffic systems containing both autonomous and human-driven electric vehicles ramp up the challenge for traffic management in urban areas. Although numerous researchers have proposed traffic control heuristics to alleviate traffic congestion problems in the recent literature, scant research has addressed the joint problems of route and charging strategies for electric vehicles along with urban traffic congestion prevention. Accordingly, this work tackles the complex task of traffic management in urban areas during peak periods by using practical congestion prevention strategies that consider the characteristics of mixed traffic flows and the charging demands of electric vehicle users. Notably, we apply support vector regressions to compute the charging time at each charging point and the traverse time of an electric vehicle at each road segment/intersection, based on historical traffic data. The simulation results reveal that the proposed algorithms are feasible because they can avoid possible occurrences of traffic congestion during rush hours and provide the routes and charging options that are chosen by electric vehicle users.

show abstract

Section: Methodsmentioning

confidence: 99%

“…This work first goes through α and selects the qualified candidate routes in accordance with the list of constraints given in Eqs. (44)(45)(46)(47)(48)(49)(50)(51)(52)(53)(54)(55). Next, we derive the value inside the Min (⋅) operator in Eq.…”

Section: Amod Matching Servicementioning

confidence: 99%

A Distributed Urban Traffic Congestion Prevention Mechanism for Mixed Flow of Human-Driven and Autonomous Electric Vehicles

Huang¹,

Hu²,

Ho³

et al. 2021

IJCIS

View full text Add to dashboard Cite

show abstract

“…Raza et al [12] proposed the framework of vehicle edge computing (VEC). Using artificial intelligence technology, the author of [13] proposed a method of V2V communication to maximize the vehicle traffic flow in the transport system. Si et al [14] proposed a solution to utilize the potential resources of vehicles in the Internet to solve the congestion problem in other data networks.…”

Section: Related Workmentioning

confidence: 99%

Research on a Task Offloading Strategy for the Internet of Vehicles Based on Reinforcement Learning

Xiao

Wang

Zhuang

et al. 2021

Sensors

View full text Add to dashboard Cite

Today, vehicles are increasingly being connected to the Internet of Things, which enables them to obtain high-quality services. However, the numerous vehicular applications and time-varying network status make it challenging for onboard terminals to achieve efficient computing. Therefore, based on a three-stage model of local-edge clouds and reinforcement learning, we propose a task offloading algorithm for the Internet of Vehicles (IoV). First, we establish communication methods between vehicles and their cost functions. In addition, according to the real-time state of vehicles, we analyze their computing requirements and the price function. Finally, we propose an experience-driven offloading strategy based on multi-agent reinforcement learning. The simulation results show that the algorithm increases the probability of success for the task and achieves a balance between the task vehicle delay, expenditure, task vehicle utility and service vehicle utility under various constraints.

show abstract

“…However, it makes use of historical data and in the case of a large enough deviation from historical patterns, uses an Extended Kalman Filter for estimation and prediction. [9] uses an ensemble of classifiers (Fuzzy logic, KNN, ANN-MLP). Weights are Additionally, authors in [9] describe a Pub/Sub message dissemination architecture.…”

Section: Related Workmentioning

confidence: 99%

“…[9] uses an ensemble of classifiers (Fuzzy logic, KNN, ANN-MLP). Weights are Additionally, authors in [9] describe a Pub/Sub message dissemination architecture. A broker (or server) is present in each road segment where services are registered through a subscription in the Pub/Sub bar event.…”

Section: Related Workmentioning

confidence: 99%

Deep and Shallow Neural Networks for Blockchain in Edge Computing Environment

Mulani

Dua

Tanwar

et al. 2021

Preprint

View full text Add to dashboard Cite

With the rise in traffic congestion and associated costs, it becomes crucial to readily make available accurate traffic reports to the general public and also to predict the traffic levels to mitigate further congestion. Various tools and technologies have emerged to solve the aforementioned problem, which comprises of secure and accurate data collection, storage, utilisation of this data for the purpose of prediction, and making required data available to the public. Motivated from the aforementioned discussion, in this paper, various approaches to solve this larger puzzle have been discussed and analysed, and a holistic solution combining the power of blockchain, InterPlanetary File System (IPFS), and neural networks has been suggested. Simulation results show that an LSTM model with 50 time steps and 200 units in the hidden layer, followed by a dense layer leads to minimum Root Mean Square Error (RMSE) value, with a randomly generated but complete dataset. Security analysis of the proposed solutions shows its efficacy compared to state-of-the-art approaches.

show abstract

Enhancing intelligence in traffic management systems to aid in vehicle traffic congestion problems in smart cities

Cited by 43 publications

References 23 publications

A Distributed Urban Traffic Congestion Prevention Mechanism for Mixed Flow of Human-Driven and Autonomous Electric Vehicles

A Distributed Urban Traffic Congestion Prevention Mechanism for Mixed Flow of Human-Driven and Autonomous Electric Vehicles

Research on a Task Offloading Strategy for the Internet of Vehicles Based on Reinforcement Learning

Deep and Shallow Neural Networks for Blockchain in Edge Computing Environment

Contact Info

Product

Resources

About