DwaRa: A Deep Learning-Based Dynamic Toll Pricing Scheme for Intelligent Transportation Systems

Authors:
Publisher website
Google Scholar
Abstract
In smart cities, intelligent toll gates (ITGs) connect nearby metropolitan cities through smart highways. The toll payments at ITGs between vehicle owners (VOs) and governing authorities (GA) are automated by low-powered sensor tag units and transactional payments are processed through third party payment gateways (TPPG) using an open channel. Hence, transactional payments and privacy of VOs data are vulnerable to network and security attacks. Moreover, toll prices at all lanes are fixed based on vehicle types. However, the congestion varies due to variable waiting queues at different toll lanes, but VOs pay a fixed price for all toll lanes. This sacrifices the overall quality-of- experience (QoE) of VOs at ITGs. To address the aforementioned issues, we propose a framework DwaRa to secure, automate, and estimate a dynamic price for different toll lanes based on defined quality-of-service (QoS) offered to VOs. DwaRa operates in three phases. In the first phase, future traffic is predicted based on Markov queues to balance the congestion at different lanes at ITG efficiently. Then, we propose a novel spatially induced LSTM (SI-LSTM) model to predict current traffic and weather based on historical repositories. Second, based on inputs by the Markov model, SI-LSTM, lane type, and vehicle type, a dynamic pricing algorithm is presented to improve the QoE of the VOs. Finally, based on dynamic price fixation between the VO and the GA, smart contracts (SCs) are executed and transactional data is secured through the blockchain (BC). The obtained results are compared against parameters like average MSE, predicted traffic, scalability, IPFS storage, communication, and computation cost against conventional approaches to indicate the efficacy of the proposed framework.

This publication has 13 references indexed in Scilit: