Two-Level MPC Speed Profile Optimization of Autonomous Electric Vehicles Considering Detailed Internal and External Losses

Ata Meshginqalam,Jennifer Bauman

doi:10.1109/access.2020.3038050

Ata Meshginqalam, Jennifer Bauman

Open Access

https://doi.org/10.1109/access.2020.3038050

Copy DOI

Abstract

This paper proposes a novel two-level model predictive control (MPC) speed control algorithm for autonomous vehicles as a successive convex optimization problem focused on both energy use and arrival time. Internal losses such as detailed motor/inverter efficiency and battery loss, as well as external losses, such as wind and grade, are considered. The effect of the higher accessory energy usage of autonomous vehicles on the energy-optimal speed profile is considered in the algorithm and investigated in the paper. The proposed successive convex approach produces a highly accurate optimal speed profile while also being solvable in real-time with the vehicle on-board computing resources. An electric vehicle model is created in MATLAB/Simulink and validated to real-world logged driving data. This vehicle model is used to perform a variety of simulated test cases, which show an energy savings potential of about 1% to 20% for different driving conditions, compared to a non-energy-optimal driving profile.

Highlights

The transportation industry is currently undergoing two radical transformations: electrification, to reduce the harmful environmental effects of internal combustion engines, and autonomous driving, to reduce traffic fatalities and transform the way society moves
The main differences between the formulations used in this work compared to [22] are: the addition of the constraint for limiting to comfortable acceleration and deceleration rates, the low-level/high-level model predictive control (MPC) to allow for the successive use of the detailed motor/inverter efficiency map, the consideration of accessory power losses, and that the objective function in this paper accounts for the actual energy usage instead of an energy-like objective
The results show that 9.66%, 16.09%, and 17.83% energy savings result from the vehicle following the optimal speed trajectory compared to the logged real world drive cycle, for the 3 kW, 8 kW, and 11 kW accessory power levels, respectively

Summary

INTRODUCTION

The transportation industry is currently undergoing two radical transformations: electrification, to reduce the harmful environmental effects of internal combustion engines, and autonomous driving, to reduce traffic fatalities and transform the way society moves. A common approach to finding a globally optimal speed profile, which is critical to truly minimize energy use over a trip, is to use dynamic programming (DP) [13]–[16] This approach is computationally expensive and does not align well with the fast real-time needs of a driving vehicle. [20] and [21] use a convex formulation in a MPC platform to solve the speed optimization problem, but only simple external vehicle losses are considered, and internal losses such as the motor losses and accessories are ignored. The contribution of this paper is the development of a new convex formulation of the energy-optimal speed problem in a two-level MPC platform which considers detailed internal and external losses of an electric vehicle (EV), in order to generate a highly accurate result. The rest of the paper is organized as follows: Section II presents the convex problem formulation and the associated equations, Section III explains the vehicle modeling, Section IV presents the simulation results, and Section V presents the conclusions of this work

CONVEX PROBLEM FORMULATION

LOSSES FORMULATION

PHYSICAL LIMITATIONS

OPTIMIZATION FORMULATION

SIMULATION RESULTS

CONCLUSION