A time series clustering based approach for construction of real-world drive cycles

Abstract

• A comprehensive, flexible approach and a generic framework for the construction of drive cycles. • A new definition of micro-trip to capture the stop-and-go driving behavior related emissions. • Time series shape based distances in the clustering process to retain real world transients. • The idea of a set of representative drive cycles for any region instead of one. Building representative real world drive cycles is an important component in the modelling of emissions, battery health of electric vehicles and autonomous vehicles. All these applications are sensitive to the transients and diversity present in real world driving patterns, which are not adequately captured by current approaches. To address this lacuna, we use clustering techniques involving time-series (shape) based distances on the raw data directly to obtain representative sets of real world drive cycles. We demonstrate the efficacy of our approach using experimental data from a fleet of eight motorcycles run across five locations in India. Dynamic Time Warping (DTW) distance based clustering gives optimal results. We give theoretical and experimental justification for our constructions. We believe that the constructed drive cycles using the proposed approach would help in assessing the impact of various policies aimed at building eco-friendly transportation systems.