A Data-Driven Framework for Driving Cycle Generation and Analysis

Abstract

This paper presents a methodology for generating realistic driving cycles using Markov chain modelling, Monte Carlo simulation and dynamic time warping. The study focuses on the construction of a representative driving cycle for the city of Igdir, taking into account its unique traffic characteristics. The methodology involves segmenting the original driving datasets based on traffic conditions and road types, creating a detailed representation of driving behaviour. Dynamic time warping is used to identify reference segments for each group of segments, ensuring accurate matching with the generated driving cycles. The integration of Markov chain-Monte Carlo simulation introduces variability and randomness. The proposed methodology provides an advanced algorithm for generating highly accurate representative driving cycles, which can contribute to energy consumption analysis, vehicle performance and emission evaluation. The comprehensive approach provided by the methodology enables an accurate understanding of driving patterns, promoting the development of sustainable mobility solutions and advancing transport research.