arXiv subjects

Levente Alekszejenkó

Publications and source records attributed to Levente Alekszejenkó.

2 recordsLinked to original sources

arXiv2026

On the Transition to an Auction-based Intelligent Parking Assignment System

Finding a free parking space in a city has become a challenging task over the past decades. A recently proposed auction-based parking assignment can alleviate cruising for parking and also set a market-driven, demand-responsive parking price. However, the wide acceptance of such a system is far from certain. To evaluate the merits of auction-based parking assignment, we assume that drivers have access to a smartphone-based reservation system prior to its mandatory introduction and thus have the opportunity to test and experience its merits voluntarily. We set our experiment as Eclipse SUMO simulations with different rates of participants and non-participants to check how different market penetration levels affect the traffic flow, the performance of the auction-based assignment system, and the financial outcomes. The results show that the auction-based system improves traffic flow with increasing penetration rates, allowing participants to park gradually closer to their preferred parking lots. However, it comes with a price; the system also increases parking expenditures for participants. Interestingly, non-participating drivers will face even higher parking prices. Consequently, they will be motivated to use the new system.

cs.MA↗

arXiv2024

A V2X-based Privacy Preserving Federated Measuring and Learning System

Future autonomous vehicles (AVs) will use a variety of sensors that generate a vast amount of data. Naturally, this data not only serves self-driving algorithms; but can also assist other vehicles or the infrastructure in real-time decision-making. Consequently, vehicles shall exchange their measurement data over Vehicle-to-Everything (V2X) technologies. Moreover, predicting the state of the road network might be beneficial too. With such a prediction, we might mitigate road congestion, balance parking lot usage, or optimize the traffic flow. That would decrease transportation costs as well as reduce its environmental impact. In this paper, we propose a federated measurement and learning system that provides real-time data to fellow vehicles over Vehicle-to-Vehicle (V2V) communication while also operating a federated learning (FL) scheme over the Vehicle-to-Network (V2N) link to create a predictive model of the transportation network. As we are yet to have real-world AV data, we model it with a non-IID (independent and identically distributed) dataset to evaluate the capabilities of the proposed system in terms of performance and privacy. Results indicate that the proposed FL scheme improves learning performance and prevents eavesdropping at the aggregator server side.

cs.LG↗