An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning

<table class="fixed-width table-group" id="tab2"><tr><td><table class="table"><colgroup><col style="width:12.28em"/><col style="width:13.47em"/></colgroup><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Control Policy</td><td class="align_center">Fuel Consumption (L/100 km)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Rule-based</td><td class="align_center">5.368</td></tr><tr><td class="align_left">Instantaneous optimization</td><td class="align_center">5.256</td></tr><tr><td class="align_left">DP</td><td class="align_center">4.952</td></tr><tr><td class="align_left">RL</td><td class="align_center">5.069</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Simulation results based on ECE_EUDC.</div>

Journal of Control Science and Engineering

tab2

Table 2

Table 2: An Energy Management Strategy for a Super-Mild Hybrid Electric Vehicle Based on a Known Model of Reinforcement Learning 