Velocity Predictors for Predictive Energy Management in Hybrid Electric Vehicles

TLDR

Predictive energy management in hybrid electric vehicles depends critically on accurate and efficient forecasts of future vehicular velocities. This brief compares three velocity prediction strategies within a model predictive control framework. The authors evaluate exponential, stochastic Markov chain, and neural network approaches over a receding horizon without telemetry, using the predictions to optimize fuel economy in a power‑split HEV. The comparison reveals differences in tuning sensitivity, prediction precision, computational cost, and the resulting fuel economy among the three methods.

Abstract

The performance and practicality of predictive energy management in hybrid electric vehicles (HEVs) are highly dependent on the forecast of future vehicular velocities, both in terms of accuracy and computational efficiency. In this brief, we provide a comprehensive comparative analysis of three velocity prediction strategies, applied within a model predictive control framework. The prediction process is performed over each receding horizon, and the predicted velocities are utilized for fuel economy optimization of a power-split HEV. We assume that no telemetry or on-board sensor information is available for the controller, and the actual future driving profile is completely unknown. Basic principles of exponentially varying, stochastic Markov chain, and neural network-based velocity prediction approaches are described. Their sensitivity to tuning parameters is analyzed, and the prediction precision, computational cost, and resultant vehicular fuel economy are compared.