Open Journal of Transportation Technologies, Journal Year: 2023, Volume and Issue: 12(05), P. 394 - 402
Published: Jan. 1, 2023
Language: Английский
Open Journal of Transportation Technologies, Journal Year: 2023, Volume and Issue: 12(05), P. 394 - 402
Published: Jan. 1, 2023
Language: Английский
Technology in Society, Journal Year: 2024, Volume and Issue: 77, P. 102552 - 102552
Published: April 21, 2024
Language: Английский
Citations
3Vehicular Communications, Journal Year: 2023, Volume and Issue: 44, P. 100676 - 100676
Published: Sept. 15, 2023
The rapid evolution of vehicle-to-vehicle and vehicle-to-infrastructure communication opens doors to various control algorithms, one particular domain being intersection control. Several researchers have proposed communication-based algorithms omitting traditional traffic lights with the promise enhanced throughput improved safety. On other hand, majority these ignore uncertainties delays overlook new cyberattack vectors that are opened by connected traffic. present study employs a highly detailed simulation vehicular highlight sensitivity different autonomous (both centralized decentralized) communication-related imperfections. paper investigates five borrowed from literature in comparative way. This research focuses on traffic-related parameters such as average speed, occupancy, network while also analyzing (e.g., packet loss, computational demand) considering possible attack vectors. Simulation results suggest even simplest logic is sensitive failures, degrading below or compromising For presence noise, speeds drop significantly, suggesting reduced gridlock for First Come Serve algorithm. Decentralized can be heavily affected incoming message orders, which lead dangerous situations. During simulations, multiple collisions were registered Monte-Carlo Tree Search More complex rely accurate prediction vehicle trajectories more noise produce accidents simulation. In conclusion, regardless architecture, evaluated require additional fallback solutions redundancies retain
Language: Английский
Citations
5Future Internet, Journal Year: 2024, Volume and Issue: 16(5), P. 152 - 152
Published: April 28, 2024
Efficient spectrum sharing is essential for maximizing data communication performance in Vehicular Networks (VNs). In this article, we propose a novel hybrid framework that leverages Multi-Agent Reinforcement Learning (MARL), thereby combining both centralized and decentralized learning approaches. This addresses scenarios where multiple vehicle-to-vehicle (V2V) links reuse the frequency preoccupied by vehicle-to-infrastructure (V2I) links. We introduce QMIX technique with Deep Q (DQNs) algorithm to facilitate collaborative efficient management. The DQN uses neural network approximate value function high-dimensional state spaces, thus mapping input states (action, value) tables self-learning across diverse scenarios. Similarly, value-based multi-agent environments. proposed model, each V2V agent having its own observes environment, receives observation, obtains common reward. values from all agents considering individual benefits collective objectives. mechanism leads while dynamically adapt real-time conditions, improving VNs performance. Our research finding highlights potential of MARL models dynamic paves way advanced cooperative strategies vehicular Furthermore, conducted an in-depth exploration simulation environment evaluation criteria, concluding comprehensive comparative analysis cutting-edge solutions field. Simulation results show efficiently performs against benchmark architecture terms transmission probability V2I peak transfer.
Language: Английский
Citations
1Applied Optics, Journal Year: 2023, Volume and Issue: 62(6), P. 1528 - 1528
Published: Feb. 1, 2023
To address low communication quality and limited transmission rate between vehicle nodes in the vehicularad hoc network (VANET), this paper builds a heterogeneous visible light (VLC) radio frequency (RF) multi-hop model based on node clustering, then VLC/RF cluster vehicle-to-vehicle (V2V) channel allocation algorithm equivalent signal to interference plus noise ratio (SINR) (NCAABES) is presented. This clustering of nodes, which introduces concept SINR. The SINR VLC head (CH) member (CM) used as condition for allocation. When CH CM blocked or quality, neighboring two vehicles relay communicate way, with best chosen current CH-CM CM-CM method. simulation results show that NCAABES increases by 21.73%, 30.23%, 70.96% compared novel scheme weighted virtual distance detection (MCSVDD), (VLCnet), RF (RFnet), respectively. And NCAABES's bit error (BER) always lowest MCSVDD, VLCnet, RFnet, even when number power change. can improve make VANET more efficient, get higher rate.
Language: Английский
Citations
1Physica A Statistical Mechanics and its Applications, Journal Year: 2023, Volume and Issue: 621, P. 128826 - 128826
Published: May 5, 2023
Language: Английский
Citations
1Journal of Communications and Networks, Journal Year: 2024, Volume and Issue: 26(2), P. 239 - 251
Published: April 1, 2024
Vehicle-to-everything (V2X) communication is an essential component for fully autonomous vehicles in future intelligent transportation systems, and cellular-V2X (C-V2X) a standard that allows to communicate with its surroundings using cellular technology. Among the resource allocation modes of C-V2X, Mode 4 distributed scheme which each vehicle independently selects radio sensing-based semi-persistent scheduling (SB-SPS) algorithm. However, it susceptible conflicts especially increased density or mobility, cannot be detected, leading poor performance due collisions interference. To address this problem, paper proposes delivery rate estimation based probabilistic re-scheduling (EB-PRS) scheme. The ratio estimated opportunistic bloom filter-based feedback on vehicle's messages are received successfully. Based rate, EB-PRS carefully reselects resources probabilistically maximize performance. evaluated highway urban scenarios WiLabV2Xsim simulator show significantly improves upon SB-SPS by reducing packet collisions.
Language: Английский
Citations
0IEEE Transactions on Intelligent Transportation Systems, Journal Year: 2024, Volume and Issue: 25(11), P. 15291 - 15313
Published: July 3, 2024
Language: Английский
Citations
0Észak-magyarországi Stratégiai Füzetek, Journal Year: 2024, Volume and Issue: 21(03), P. 35 - 55
Published: Sept. 16, 2024
Egyre több tudományos és gyakorlati forgatókönyv lát napvilágot arról, hogy miképpen hat majd az önvezető járművek (Autonomous Vehicles, AV) tömeges megjelenése a városi közlekedésre ezen keresztül városlakók egyéni életére. többen fogadják el azt logikát, saját autó tulajdonlással szembeni önvezetőflotta-használat jelentősen csökkentheti utakon levő számát is, amelynek fontos területhasználati városképi következményei lehetnek. többet tudunk már ezekről lehetőségekről, ugyanakkor jóval kevesebbet még mindezt fogadnák városlakók. Ráadásul lakosság preferenciáit vizsgáló kutatások többsége teljes alapsokaságra fogalmaz meg állításokat, nem pedig annak egyes részeire, így kevés információval rendelkezünk önvezetőjármű-vezérelt jövőbeni mobilitásnak kimagaslóan kitett fiatalok preferenciáiról. Tanulmányunk célja megismerése, magyar fiatal különböző szegmentumai mennyire hatására potenciálisan bekövetkező konkrét változásokat. Kutatásunk során vizuálisan könnyen áttekinthető, felhasználók számára leginkább vonzó attribútumszint kombinációinak meghatározására alkalmas módszertant alkalmazzuk. Teljes profilú conjoint elemzésünk 1015 személyes adatfelvétel 18 db nyomtatott kártya lépésben történő értékelésével fejezte ki preferenciáit, melynek eredményeképpen 5 perszóna típusát azonosítottuk: AV fanatikusok, Visszafogott szimpatizánsok, Fontolva haladók, Tech ambivalensek szkeptikus zöldek.
Citations
0Published: Oct. 1, 2024
Language: Английский
Citations
0Journal of Urban Design, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 19
Published: Nov. 11, 2024
The study aims to investigate how much young Hungarian city dwellers would accept potential urban environment changes triggered by AVs. In the full-profile conjoint analysis, 1011 people expressed their preferences through evaluation of 18 printed cards in multiple steps during in-person data collection. As a result, 'city future' most preferred youngsters can be described with help partial utility attribute levels and constant value. Their ideal envisions roads exclusively for AVs new lane allocations, no drones, pedestrian-only sidewalks equipped sensors, frequent 5G system boost connectivity.
Language: Английский
Citations
0