scholarly journals Towards Federated Learning in Edge Computing for Real-Time Traffic Estimation in Smart Cities

2020 ◽  
Author(s):  
Matteus Vargas Simão da Silva ◽  
Luiz Fernando Bittencourt ◽  
Adín Ramirez Rivera
Keyword(s):  
Real Time ◽  
Learning Strategy ◽  
Smart Cities ◽  
Preliminary Evaluation ◽  
Local Data ◽  
Data Set ◽  
Real Time Traffic ◽  
Learning Rates ◽  
Model Aggregation ◽  
Traffic Estimation

The wide proliferation of sensors and devices of Internet of Things(IoT), together with Artificial Intelligence (AI), has created the so-called Smart Environments. From a network perspective, these solutions suffer from high latency and increased data transmission. This paper proposes a Federated Learning (FL) architecture for Real-Time Traffic Estimation, supported by Roadside Units (RSU’s) for model aggregation. The solution envisages that learning will be done on clients with their local data, and fully distributed on the Edge, with high learning rates, low latency, and less bandwidth usage. To achieve that,this paper discusses tools and requirements for FL implementation towards a model for real-time traffic estimation, as well as how such solution could be evaluated using VANET and network simulators. As a first practical step, we show a preliminary evaluation of a learning model using a data set of cars that demonstrate a distributed learning strategy. In the future, we will use a similar distributed strategy within our proposed architecture.

Think Like A Graph: Real-Time Traffic Estimation at City-Scale

2019 ◽  
Vol 18 (10) ◽  
pp. 2446-2459 ◽  
Author(s):  
Zhidan Liu ◽  
Pengfei Zhou ◽  
Zhenjiang Li ◽  
Mo Li
Keyword(s):  
Real Time ◽  
Real Time Traffic ◽  
Traffic Estimation

scholarly journals RealTE: Real-time Trajectory Estimation Over Large-Scale Road Networks

2022 ◽  
Author(s):  
Qibin Zhou ◽  
Qingang Su ◽  
Dingyu Yang
Keyword(s):  
Travel Time ◽  
Real Time ◽  
High Speed ◽  
Road Network ◽  
Large Scale ◽  
Road Networks ◽  
Trajectory Data ◽  
Real Time Traffic ◽  
Histogram Estimation ◽  
Traffic Estimation

Real-time traffic estimation focuses on predicting the travel time of one travel path, which is capable of helping drivers selecting an appropriate or favor path. Statistical analysis or neural network approaches have been explored to predict the travel time on a massive volume of traffic data. These methods need to be updated when the traffic varies frequently, which incurs tremendous overhead. We build a system RealTER⁢e⁢a⁢l⁢T⁢E, implemented on a popular and open source streaming system StormS⁢t⁢o⁢r⁢m to quickly deal with high speed trajectory data. In RealTER⁢e⁢a⁢l⁢T⁢E, we propose a locality-sensitive partition and deployment algorithm for a large road network. A histogram estimation approach is adopted to predict the traffic. This approach is general and able to be incremental updated in parallel. Extensive experiments are conducted on six real road networks and the results illustrate RealTE achieves higher throughput and lower prediction error than existing methods. The runtime of a traffic estimation is less than 11 seconds over a large road network and it takes only 619619 microseconds for model updates.

scholarly journals Average Response Time (ART):Real-Time Traffic Management in VFC Enabled Smart Cities

2020 ◽  
Vol 981 ◽  
pp. 022054
Author(s):  
Shabana ◽  
Sallauddin Mohmmad ◽  
Mohammed Ali Shaik ◽  
K Mahender ◽  
Ranganath Kanakam ◽  
...  
Keyword(s):  
Response Time ◽  
Real Time ◽  
Traffic Management ◽  
Smart Cities ◽  
Average Response ◽  
Average Response Time ◽  
Real Time Traffic

Use of Real-Time Traffic and Signal Timing Data in Modeling Occupant Injury Severity at Signalized Intersections

2021 ◽  
pp. 036119812110478
Author(s):  
Emmanuel Kidando ◽  
Angela E. Kitali ◽  
Boniphace Kutela ◽  
Alican Karaer ◽  
Mahyar Ghorbanzadeh ◽  
...  
Keyword(s):  
Real Time ◽  
Logistic Model ◽  
Injury Severity ◽  
Random Effect ◽  
Signal Timing ◽  
Data Set ◽  
Lighting Condition ◽  
Real Time Traffic ◽  
Timing Data ◽  
Occupant Injury

This study explored the use of real-time traffic events and signal timing data to determine the factors influencing the injury severity of vehicle occupants at intersections. The analysis was based on 3 years (2017–2019) of crash and high-resolution traffic data. The best fit regression was first identified by comparing the conventional regression model and logistic models with random effect. The logistic model with a heavy-tailed distribution random effect best fitted the data set, and it was used in the variable assessment. The model results revealed that about 13.6% of the unobserved heterogeneity comes from site-specific variations, which underlines the need to use the logistic model with a random effect. Among the real-time traffic events and signal-based variables, approach delay and platoon ratio significantly influenced the injury severity of vehicle occupants at 90% Bayesian credible interval. Additionally, the manner of a collision, occupant seat position, number of vehicles involved in a crash, gender, age, lighting condition, and day of the week significantly affected the vehicle occupant injury. The study findings are anticipated to provide valuable insights to transportation agencies for developing countermeasures to mitigate the crash severity risk proactively.

Realizing a Ultra-Low Latency M-CORD Model for Real-Time Traffic Settings in Smart Cities

2021 ◽  
pp. 93-105
Author(s):  
Kathiravan Srinivasan ◽  
Aswani Kumar Cherukuri ◽  
Senthil Kumaran S. ◽  
Tapan Kumar Das
Keyword(s):  
Real Time ◽  
Mobile Devices ◽  
Mobile Networks ◽  
High Speed ◽  
Smart Cities ◽  
Low Latency ◽  
Mobile Service ◽  
Core Network ◽  
Real Time Traffic ◽  
Device User

At present, the need for an ultra-high speed and efficient communication through mobile and wireless devices is gaining significant popularity. The users are expecting their network to offer real-time streaming without much latency. In turn, this will result in a considerable rise in network bandwidth utilization. The live streaming has to reach the end users mobile devices after traveling through the base station nodes, core network, routers, switches, and other equipment. Further, this will lead to a scenario of content latency and thereby causing the rejection of the mobile devices users' request due to congestion of the network and mobile service providers' core network witnessing an extreme load. In order to overcome such problems in the contemporary 5G mobile networks, an architectural framework is essential, which offers instantaneous, ultra-low latency, high-bandwidth access to applications that are available at the network edge and also making the task processing in close proximity with the mobile device user.

Real-time traffic estimation at vehicular edge nodes

2017 ◽  
Author(s):  
Gorkem Kar ◽  
Shubham Jain ◽  
Marco Gruteser ◽  
Fan Bai ◽  
Ramesh Govindan
Keyword(s):  
Real Time ◽  
Real Time Traffic ◽  
Traffic Estimation
Sign in / Sign up

Export Citation Format

Share Document