Optimized rule-based energy management for a polymer electrolyte membrane fuel cell/battery hybrid power system using a genetic algorithm

Abstract

The polymer electrolyte membrane fuel cell (PEMFC) coupled with the battery is a promising hybrid power system for future energy supply application. Fuel cell durability, battery charge sustenance, and fuel consumption strongly rely on the energy management strategy (EMS). This paper puts forward an optimized rule-based EMS using genetic algorithm (GA) to optimally allocate the power between the fuel cell and the battery system. Control variables in real-time rule-based EMS are optimally adjusted with single objective of battery charge sustenance considering the fuel cell durability and efficiency. The proposed optimized rule-based EMS is simulated and experimentally verified via MATLAB/Simulink and LabVIEW-based experimental rig, respectively. The conventional rule-based EMS, fuzzy logic EMS, and dynamic programming (DP) EMS are also examined for comparison. The comparison results elucidate that the optimized rule-based EMS realizes a large performance improvement over the conventional rule-based and fuzzy logic EMSs. Near optimal performance is verified compared with DP EMS in terms of fuel economy, battery charge sustenance, fuel cell efficiency, and system durability. The combination of rule-based EMS and GA optimization algorithm has the advantage of having expert experience and global optimization properties, realizing optimal power allocation in real-time application with lower computation burden, which could be applied easily to other EMS system without loss of validity.