Estimating City-wide Operating Mode Distribution of Light-Duty Vehicles: A Neural Network-based Approach

TL;DR

This study tackles the challenge of accurately estimating city-wide operating mode distributions without relying on predefined driving cycles. It introduces a Modular Neural Network that links macroscopic traffic variables and link infrastructure features to MOVES operating-mode fractions, trained on ground-truth distributions derived from a calibrated Brookline microsimulation. Compared to MOVES default driving cycles, the MNN shows superior accuracy in predicting operating-mode distributions (average RMSE ~0.04 vs ~0.08) and significantly lower emission estimation errors (average ~8.6% vs ~32.9%), with CO₂ errors dropping to about 4%. The approach enables faster, real-time-like emissions estimation using readily available inputs and demonstrates robustness across urban driving regimes, though future work is needed to assess transferability to other cities and refine the architecture.

Abstract

Driving cycles are a set of driving conditions and are crucial for the existing emission estimation model to evaluate vehicle performance, fuel efficiency, and emissions, by matching them with average speed to calculate the operating modes, such as braking, idling, and cruising. While existing emission estimation models, such as the Motor Vehicle Emission Simulator (MOVES), are powerful tools, their reliance on predefined driving cycles can be limiting, as these cycles often do not accurately represent regional driving conditions, making the models less effective for city-wide analyses. To solve this problem, this paper proposes a modular neural network (NN)-based framework to estimate operating mode distributions bypassing the driving cycle development phase, utilizing macroscopic variables such as speed, flow, and link infrastructure attributes. The proposed method is validated using a well-calibrated microsimulation model of Brookline MA, the United States. The results indicate that the proposed framework outperforms the operating mode distribution calculated by MOVES based on default driving cycles, providing a closer match to the actual operating mode distribution derived from trajectory data. Specifically, the proposed model achieves an average RMSE of 0.04 in predicting operating mode distribution, compared to 0.08 for MOVES. The average error in emission estimation across pollutants is 8.57% for the proposed method, lower than the 32.86% error for MOVES. In particular, for the estimation of CO2, the proposed method has an error of just 4%, compared to 35% for MOVES. The proposed model can be utilized for real-time emissions monitoring by providing rapid and accurate emissions estimates with easily accessible inputs.

Figures (11)

• Figure 1: Calculating emissions using MOVES and the proposed model. The proposed model learns traffic dynamics from aggregated traffic and infrastructure data to directly infer accurate operating mode distributions in significantly less runtime. While MOVES uses infrastructure features not related to operating modes and bases its operating modes on drive cycles selected by speed.
• Figure 2: Methodological framework of the proposed model.
• Figure 3: Modular neural network architecture with input nodes, hidden layers, and output layer.
• Figure 4: The traffic microsimulation model of the City of Brookline, MA in Transmodeler (The red dots show the location of traffic count sensors).
• Figure 5: Traffic simulation model Origin-Destination flow calibration.