Clustered Energy Management Strategy of Plug-In Hybrid Electric Logistics Vehicle Based on Gaussian Mixture Model and Stochastic Dynamic Programming
Rong Guo, Xiang Xue, Ziyi Sun, Ze Hong
Abstract
Energy management strategy (EMS) is one of the most important technologies for hybrid electric vehicles (HEVs). An EMS based on the Gaussian mixture model (GMM) and stochastic dynamic programming (SDP) is proposed. The driving conditions are grouped into five clusters according to the velocity and power demand by GMM. Five corresponding transition probability matrices (TPMs) can be obtained by the nearest neighbor method. Then, strategies generated by SDP are linearly combined using posterior probabilities of GMM as weights. The simulation results show that, compared with the conventional strategies, the proposed strategy can conserve the equivalent fuel consumption and is more adaptive when driving cycle changes. The minimum equivalent fuel consumption of the proposed method can reach 101.07%, using the strategy based on dynamic programming (DP) as a baseline. As a result of the Jensen–Shannon (JS) divergence analysis, the proposed strategy improves performance by increasing the representativeness of the TPM for test driving cycles. Experimental test results indicate that the proposed strategy can be implemented on automotive standard microcontrollers. Compared with benchmark strategies, engine operating efficiency of the proposed strategy has been improved by up to 3.56% and engine operating time is reduced by up to 2.96%.