Dynamic programming-based approximate real-time control policies for plug in hybrid electric vehicles

This paper examines the application of dynamic programming (DP) to the development of parametric real-time power management policies for the plug-in hybrid electric vehicles (PHEVs). First, a representative power-split PHEV powertrain model is introduced, followed by a DP formulation for obtaining the cost-optimal powertrain trajectories. The obtained optimal trajectories are then used to train a set of control policies for the powertrain control inputs through a least-squares linear regression process. The proposed controller receives the demanded propulsion force and the powertrain variables as inputs, and generates the torque commands for the engine and the electric drivetrain system. Numerical simulations indicate that the proposed control policy is able to approximate the optimal trajectories closely, using the real-time powertrain system information for the training drive cycle data. To maintain the battery state-of-charge (SOC) above a certain lower bound for arbitrary test data, a switching logic is implemented to transition to a conservative control policy when the battery SOC drops below a certain threshold. Simulation results indicate the effectiveness of the proposed approach in achieving near-optimal performance while maintaining the SOC within the desired range.