Predictive Intelligent Transportation: Alleviating Traffic Congestion in the Internet of Vehicles
Abstract
:1. Introduction
- Compared with the isolated-dimensional TSC strategy, we formulate a PTSC model based on the feedback regulation from VRG whose decisions are considered by introducing a medium variable—predictive traffic flow (determined by the changes in vehicular path plans);
- Compared with the isolated-dimensional VRG strategy, we formulate a PVRG model based on the feedback regulation from TSC whose schemes are considered by introducing a medium variable—predictive vehicular waiting time (determined by different traffic signal schemes);
- We propose a novel “coordinated control” model—PIT for a whole traffic management system based on the two-way feedback regulation between PTSC and PVRG to acquire the coordinated schemes, and design an asymmetric information-based updating distributed algorithm to solve it.
2. Formalization for This Art
2.1. Formalization of Traffic Network
- Step 1. Based on the V2V technique, all non-head vehicles as sensor nodes send their route plans to the vehicles in front of them until all route information is gathered into the head vehicles (sub-sink nodes) on each road;
- Step 2. Based on the V2I technique, All head vehicles transmit these gathered route plans to the signal controller (sink devices) at intersection;
- Step 3. The sets of route plans and signal schemes are delivered to the cloud center from all signal controllers via the fog devices.
2.2. Formalization of Traffic Signal at Intersections
2.3. Formalization of Vehicle Driving
3. Contributions for Alleviating Traffic Congestion
3.1. Motivation
3.2. Contribution of PTSC and PVRG
3.2.1. Contribution of PTSC
Algorithm 1 Short-term flow prediction for intersections. |
Input: Set of current route directions and set of vehicular estimated arriving time Output: Set of predictive short-term flow
|
3.2.2. Contribution of PVRG
3.3. Contribution of PIT
3.3.1. Model of PIT
3.3.2. Solving Algorithm for PIT
Algorithm 2 Pseudo-code of our updating distributed algorithm for solving proposed PIT model. |
Input: Sets of current signal control schemes and current vehicular route plans Output: Sets of next signal control schemes of PTSC and next vehicle route plans of PVRG
|
3.4. Discussion
4. Simulation Experiments
Algorithm 3 Pseudo-code for vehicles driving in the experiments. |
Input: Set of initial configuration schemes of signal control and the set of initial configuration plans of vehicle route Output: Set of intersections’ delay time and the set of vehicular driving time
|
4.1. Preparation
4.2. Validity Test and Sensitivity Analysis
4.2.1. Validity Test
4.2.2. Sensitivity Analysis
- (1)
- In Figure 6a,b, for the robustness of the non-predictive dynamic TSC model, method 2 still performs better than method 1 with the increased vehicle number in Scenario 1. The average improvement efficiency is 47.85% and 65.81% in driving time and delay time, respectively. For the robustness of PVRG, all experiments in method 3 perform better than method 2 due to the working of predictive rerouting. The average improvement efficiency is 4.69% and 11.82% in driving time and delay time, respectively. For the robustness of PTSC, all experiments in method 4 achieve better results than method 3 due to the prediction of future traffic flow in TSC. The average improvement efficiency is 6.63% and 15.21% in driving time and delay time, respectively. For the robustness of PIT, the overall performance of method 5 remains better than the isolated improvements in PTSC and PVRG due to the function of our coordinated mechanism. Compared with method 4, 73.33% of the experiments obtain better results. The average improvement efficiency is 1.18% and 2.70% in driving time and delay time, respectively.
- (2)
- In Figure 6b,c, similarly, the functions of non-predictive dynamic TSC model, PVRG, PTSC and PIT are still conspicuous with the increased number of intersections in Scenario 2. Specifically, the average improvement efficiencies in driving time and delay time are 23.75% and 29.04% (comparing method 2 with 1), 8.00% and 11.97% (comparing method 3 with 2) 2.99% and 3.30% (comparing method 4 with 3), and 1.56% and 2.20% (comparing method 5 with 4), respectively. The efficiency of all methods is consistent with the conclusions in Section 4.2.1.
4.3. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
PIT | Predictive intelligent transportation |
IoVs | Internet of Vehicles |
(P)TSC | (Predictive) Traffic signal control |
(P)VRG | (Predictive) Vehicle routing guidance |
I | Set of vehicles |
J | Set of intersections |
Distance between two different intersections j and | |
Optional route node of vehicle i at the entrance of intersection j | |
Set of optional route nodes of vehicle i, | |
H | Set of optional route nodes of all vehicles, |
Path weight from route node to a different route node , | |
Estimated waiting time of vehicles at route node | |
W | Set of estimated waiting time, |
Route plan of vehicle i | |
R | Set of vehicle route plans, |
Driving time of vehicle i | |
phase of intersection j, in this paper | |
P | Set of phases, |
Estimated traffic flow at the entrances of phase | |
Q | Set of estimated traffic flow, |
Traffic signal cycle of intersection j, | |
Green traffic signal of phase , | |
Red traffic signal of phase , | |
Traffic signal scheme of intersection j | |
Z | Set of traffic signal schemes, |
Delay time of vehicle i at the green signal entrances of phase | |
Total vehicular delay time of intersection j | |
Set of virtual schemes of traffic signal | |
Set of virtual plans of vehicle route |
References
- Rocha Filho, G.P.; Meneguette, R.I.; Neto, J.R.T.; Valejo, A.; Weigang, L.; Ueyama, J.; Pessin, G.; Villas, L.A. Enhancing intelligence in traffic management systems to aid in vehicle traffic congestion problems in smart cities. Ad Hoc Netw. 2020, 107, 102265. [Google Scholar] [CrossRef]
- Zadobrischi, E.; Cosovanu, L.M.; Dimian, M. Traffic Flow Density Model and Dynamic Traffic Congestion Model Simulation Based on Practice Case with Vehicle Network and System Traffic Intelligent Communication. Symmetry 2020, 12, 1172. [Google Scholar] [CrossRef]
- Kim, D.; Jeong, O. Cooperative traffic signal control with traffic flow prediction in multi-intersection. Sensors 2020, 20, 137. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Quessada, M.S.; Pereira, R.S.; Revejes, W.; Sartori, B.; Gottsfritz, E.N.; Lieira, D.D.; da Silva, M.A.; Rocha Filho, G.P.; Meneguette, R.I. ITSMEI: An intelligent transport system for monitoring traffic and event information. Int. J. Distrib. Sens. Netw. 2020, 16, 1–13. [Google Scholar] [CrossRef]
- Brennand, C.A.; Maia, G.; Cunha, F.; Guidoni, D.L.; Villas, L.A. Towards a fog-enabled intelligent transportation system to reduce traffic jam. Sensors 2019, 19, 3916. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Hao, Z.; Boel, R.; Li, Z. Model based urban traffic control, part II: Coordinated model predictive controllers. Transp. Res. C-Emerg. Technol. 2018, 97, 23–44. [Google Scholar] [CrossRef]
- Ye, B.L.; Wu, W.; Ruan, K.; Li, L.; Chen, T.; Gao, H.; Chen, Y. A survey of model predictive control methods for traffic signal control. IEEE/CAA J. Autom. Sin. 2019, 6, 623–640. [Google Scholar] [CrossRef]
- Guo, Q.; Li, L.; Ban, X.J. Urban traffic signal control with connected and automated vehicles: A survey. Transp. Res. C-Emerg. Technol. 2019, 101, 313–334. [Google Scholar] [CrossRef]
- Tan, T.; Bao, F.; Deng, Y.; Jin, A.; Dai, Q.; Wang, J. Cooperative Deep Reinforcement Learning for Large-Scale Traffic Grid Signal Control. IEEE Trans. Cybern. 2020, 50, 2687–2700. [Google Scholar] [CrossRef]
- Lee, J.; Chung, J.; Sohn, K. Reinforcement Learning for Joint Control of Traffic Signals in a Transportation Network. IEEE Trans. Veh. Technol. 2020, 69, 1375–1387. [Google Scholar] [CrossRef]
- Tang, C.; Hu, W.; Hu, S.; Stettler, M.E.J. Urban Traffic Route Guidance Method With High Adaptive Learning Ability Under Diverse Traffic Scenarios. IEEE Trans. Intell. Transp. Syst. 2020, 22, 2956–2968. [Google Scholar] [CrossRef]
- Elouni, M.; Abdelghaffar, H.M.; Rakha, H.A. Adaptive traffic signal control: Game-theoretic decentralized vs. centralized perimeter control. Sensors 2021, 21, 274. [Google Scholar] [CrossRef] [PubMed]
- Nilsson, G.; Como, G. A Micro-Simulation Study of the Generalized Proportional Allocation Traffic Signal Control. IEEE Trans. Intell. Transp. Syst. 2020, 21, 1705–1715. [Google Scholar] [CrossRef]
- Mohebifard, R.; Hajbabaie, A. Optimal network-level traffic signal control: A benders decomposition-based solution algorithm. Transp. Res. B-Meth. 2019, 121, 252–274. [Google Scholar] [CrossRef]
- Webster, F. Traffic Signal Settings; Road Res. Tech. Paper no. 39; Road Research Laboratory: London, U.K., 1958. [Google Scholar]
- Zheng, F.; van Zuylen, H.J.; Liu, X.; Le Vine, S. Reliability-based traffic signal control for urban arterial roads. IEEE Trans. Intell. Transp. Syst. 2017, 18, 643–655. [Google Scholar] [CrossRef]
- Chiou, S.W. A bi-objective bi-level signal control policy for transport of hazardous materials in urban road networks. Transp. Res. Part D-Transp. Environ. 2016, 42, 16–44. [Google Scholar] [CrossRef]
- Wang, Z.; Niu, L. A data model for using OpenStreetMap to integrate indoor and outdoor route planning. Sensors 2018, 18, 2100. [Google Scholar] [CrossRef] [Green Version]
- Chen, B.; Ding, Z.; Wu, Y.; Zhou, J.; Chen, Y. An optimal global algorithm for route guidance in advanced traveler information systems. Inf. Sci. 2021, 555, 33–45. [Google Scholar] [CrossRef]
- Dijkstra, E.W. A note on two problems in connexion with graphs. Numer. Math. 1959, 1, 269–271. [Google Scholar] [CrossRef] [Green Version]
- Yao, Y.; Peng, Z.; Xiao, B. Parallel hyper-heuristic algorithm for multi-objective route planning in a smart city. IEEE Trans. Veh. Technol. 2018, 67, 10307–10318. [Google Scholar] [CrossRef]
- De Cauwer, C.; Verbeke, W.; Van Mierlo, J.; Coosemans, T. A Model for Range Estimation and Energy-Efficient Routing of Electric Vehicles in Real-World Conditions. IEEE Trans. Intell. Transp. Syst. 2019, 21, 2787–2800. [Google Scholar] [CrossRef]
- Nallaperuma, D.; Nawaratne, R.; Bandaragoda, T.; Adikari, A.; Nguyen, S.; Kempitiya, T.; De Silva, D.; Alahakoon, D.; Pothuhera, D. Online Incremental Machine Learning Platform for Big Data-Driven Smart Traffic Management. IEEE Trans. Intell. Transp. Syst. 2019, 20, 4679–4690. [Google Scholar] [CrossRef]
- Eze, J.; Zhang, S.; Liu, E.; Eze, E. Design optimization of resource allocation in OFDMA-based cognitive radio-enabled Internet of Vehicles (IoVs). Sensors 2020, 20, 6402. [Google Scholar] [CrossRef]
- Pereira, R.; Boukerche, A.; da Silva, M.A.; Nakamura, L.H.; Freitas, H.; Rocha Filho, G.P.; Meneguette, R.I. FORESAM—FOG Paradigm-Based Resource Allocation Mechanism for Vehicular Clouds. Sensors 2021, 21, 5028. [Google Scholar] [CrossRef] [PubMed]
- Meneguette, R.I.; Filho, G.P.; Guidoni, D.L.; Pessin, G.; Villas, L.A.; Ueyama, J. Increasing intelligence in inter-vehicle communications to reduce traffic congestions: Experiments in urban and highway environments. PLoS ONE 2016, 11, e0159110. [Google Scholar] [CrossRef] [PubMed]
- Wang, X.; Han, J.; Bai, C.; Shi, H.; Zhang, J.; Wang, G. Research on the Impacts of Generalized Preceding Vehicle Information on Traffic Flow in V2X Environment. Future Internet 2021, 13, 88. [Google Scholar] [CrossRef]
- Zadobrischi, E.; Dimian, M. Vehicular Communications Utility in Road Safety Applications: A Step toward Self-Aware Intelligent Traffic Systems. Symmetry 2021, 13, 438. [Google Scholar] [CrossRef]
- Goumidi, H.; Harous, S.; Aliouat, Z.; Gueroui, A.M. Lightweight Secure Authentication and Key Distribution Scheme for Vehicular Cloud Computing. Symmetry 2021, 13, 484. [Google Scholar] [CrossRef]
- Roger, S.; Martín-Sacristán, D.; Garcia-Roger, D.; Monserrat, J.F.; Kousaridas, A.; Spapis, P.; Ayaz, S. 5G V2V Communication with Antenna Selection Based on Context Awareness: Signaling and Performance Study. IEEE Trans. Intell. Transp. Syst. 2020, 1–9, in press. [Google Scholar] [CrossRef]
- Yu, Z.; Jin, D.; Zhai, C.; Ni, W.; Wang, D. Internet of Vehicles Empowered Mobile Media: Research on Mobile-Generated Content (MoGC) for Intelligent Connected Vehicles. Sustainability 2021, 13, 3538. [Google Scholar] [CrossRef]
- Rafter, C.B.; Anvari, B.; Box, S.; Cherrett, T. Augmenting traffic signal control systems for urban road networks with connected vehicles. IEEE Trans. Intell. Transp. Syst. 2020, 21, 1728–1740. [Google Scholar] [CrossRef] [Green Version]
- Chen, L.; Chang, C. Cooperative Traffic Control With Green Wave Coordination for Multiple Intersections Based on the Internet of Vehicles. IEEE Trans. Syst. Man Cybern. Syst. 2017, 47, 1321–1335. [Google Scholar] [CrossRef]
- Sun, P.; Samaan, N. A Novel VANET-Assisted Traffic Control for Supporting Vehicular Cloud Computing. IEEE Trans. Intell. Transp. Syst. 2020, in press. [Google Scholar] [CrossRef]
- Cao, Z.; Guo, H.; Zhang, J.; Fastenrath, U. Multiagent-based route guidance for increasing the chance of arrival on time. In Proceedings of the AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA, 12–17 February 2016; pp. 3813–3820. [Google Scholar]
- Rezaei, M.; Noori, H.; Mohammadkhani Razlighi, M.; Nickray, M. ReFOCUS+: Multi-Layers Real-Time Intelligent Route Guidance System with Congestion Detection and Avoidance. IEEE Trans. Intell. Transp. Syst. 2019, 22, 50–63. [Google Scholar] [CrossRef]
- Liu, X.; Liu, Y.; Chen, Y.; Hanzo, L. Enhancing the Fuel-Economy of V2I-Assisted Autonomous Driving: A Reinforcement Learning Approach. IEEE Trans. Veh. Technol. 2020, 69, 8329–8342. [Google Scholar] [CrossRef]
- Cao, Z.; Jiang, S.; Zhang, J.; Guo, H. A unified framework for vehicle rerouting and traffic light control to reduce traffic congestion. IEEE Trans. Intell. Transp. Syst. 2017, 18, 1958–1973. [Google Scholar] [CrossRef]
- Soon, K.L.; Lim, J.M.Y.; Parthiban, R. Coordinated traffic light control in cooperative green vehicle routing for pheromone-based multi-agent systems. Appl. Soft Comput. 2019, 81, 105486. [Google Scholar] [CrossRef]
- Na, X.; Cole, D.J. Modelling of a human driver’s interaction with vehicle automated steering using cooperative game theory. IEEE/CAA J. Autom. Sin. 2019, 6, 1095–1107. [Google Scholar] [CrossRef]
- Lazar, D.; Coogan, S.; Pedarsani, R. Routing for traffic networks with mixed autonomy. IEEE Trans. Autom. Control 2020, in press. [Google Scholar] [CrossRef]
- Xu, B.; Ban, X.J.; Bian, Y.; Li, W.; Wang, J.; Li, S.E.; Li, K. Cooperative method of traffic signal optimization and speed control of connected vehicles at isolated intersections. IEEE Trans. Intell. Transp. Syst. 2018, 20, 1390–1403. [Google Scholar] [CrossRef]
- Speranza, M.G.; Angelelli, E.; Arsik, I.; Morandi, V.; Savelsbergh, M. Proactive route guidance to avoid congestion. Transp. Res. B-Meth. 2016, 94, 1–21. [Google Scholar]
Methods | Explanation | Purpose |
---|---|---|
Method 1: Fixed TSC + Fixed VRG | Signal controllers adopt the fixed timing strategies; Vehicles calculate routes based on constant distance parameters | Control group |
Adding non-predictive dynamic TSC into Method 1 | ||
Method 2: Dynamic TSC + Fixed VRG | Signal controllers generate dynamic signal schemes based only on current traffic flow on their roads; Vehicles calculate routes based on constant distance parameters | Verifying the feasibility of non-predictive dynamic TSC |
Adding the proposed PVRG into Method 2 (for example the work in [43] adopts the predictive vehicle reroute strategy to alleviate traffic congestion) | ||
Method 3: Dynamic TSC + PVRG | Signal controllers adopt the non-predictive dynamic TSC strategies; Vehicles reroute considering predictive waiting time influenced from dynamic TSC schemes (PVRG in Section 3.2.2) | Verifying the feasibility of the proposed PVRG |
Adding the proposed PTSC into Method 3 (for example the work in [6] adopts the predictive signal control strategy to alleviate traffic congestion) | ||
Method 4: PTSC + PVRG without the coordinated mechanism of PIT | Signal controllers generate the dynamic schemes considering future traffic flow determined by dynamic VRG (PTSC in Section 3.2.1); Vehicles reroute based on the proposed PVRG | Verifying the feasibility of the proposed PTSC |
Adding the feedback regulation-based coordinated control framework of the proposed PIT model into Method 4 | ||
Method 5: PIT | PTSC and PVRG iterate together based on an asymmetric information exchange environment in Section 3.3 | Verifying the feasibility of this paper’s PIT model and the solving algorithm |
Methods | Path 1 | Path 2 | Total Driving Time | Efficiency |
---|---|---|---|---|
Method 1 | 150 | 0 | 49,315 | 0 |
Method 2 | 150 | 0 | 24,159 | 51.01% |
Method 3 | 94 | 56 | 22,626 | 54.12% |
Method 4 | 51 | 99 | 22,117 | 55.15% |
Method 5 | 71 | 79 | 21,626 | 56.15% |
Methods | Entrance | Entrance | Entrance | Entrance | Entrance | Total | Efficiency |
---|---|---|---|---|---|---|---|
Method 1 | 2431 | 441 | 0 | 33,318 | 0 | 36,190 | 0 |
Method 2 | 4767 | 1329 | 0 | 4938 | 0 | 11,034 | 69.51% |
Method 3 | 1575 | 1092 | 856 | 4938 | 897 | 9358 | 74.14% |
Method 4 | 498 | 249 | 1285 | 4944 | 1761 | 8737 | 75.86% |
Method 5 | 818 | 336 | 1028 | 4944 | 1167 | 8293 | 77.08% |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, L.; Khalgui, M.; Li, Z. Predictive Intelligent Transportation: Alleviating Traffic Congestion in the Internet of Vehicles. Sensors 2021, 21, 7330. https://doi.org/10.3390/s21217330
Zhang L, Khalgui M, Li Z. Predictive Intelligent Transportation: Alleviating Traffic Congestion in the Internet of Vehicles. Sensors. 2021; 21(21):7330. https://doi.org/10.3390/s21217330
Chicago/Turabian StyleZhang, Le, Mohamed Khalgui, and Zhiwu Li. 2021. "Predictive Intelligent Transportation: Alleviating Traffic Congestion in the Internet of Vehicles" Sensors 21, no. 21: 7330. https://doi.org/10.3390/s21217330
APA StyleZhang, L., Khalgui, M., & Li, Z. (2021). Predictive Intelligent Transportation: Alleviating Traffic Congestion in the Internet of Vehicles. Sensors, 21(21), 7330. https://doi.org/10.3390/s21217330