A novel optimal power management strategy for plug-in hybrid electric vehicle with improved adaptability to traffic conditions

Adaptability to various driving conditions (TCs) is one of the essential indicators assess optimality power management strategies (PMSs) plug-in hybrid electric vehicles (PHEVs). In this study, a novel optimal PMS with improved adaptability TCs proposed for PHEVs achieve energy-efficient control in momentary scenarios by virtue advanced internet (IoVs), thus contributing remarkable promotion fuel economy PHEV. Firstly, rules PMS, corresponding diverse conditions, are optimized offline chaotic particle swarm optimization sequential quadratic programming (CPSO-SQP), which can effectively endow global knowledge into rule inspired method. Then, an online TC identification (TCI) method designed cooperatively exploiting multi-dimensional Gaussian distribution (MGD) and random forest (RF), where MGD based analysis on macrocosmic state traffic contributes valuable inputs RF classification, additionally super regression ability further improves accuracy. Finally, numerical simulation validations showcase that reasonably instantly manage flow within sources PHEV under different TCs, manifesting its anticipated preferable controlling performance. • Power conditions. Multi-dimensional utilized status analysis. Random exploited accurate condition identification. Control thresholds strategy via meta-heuristic