Green Energy and Intelligent Transportation · 2022 · 44 citations · 24 references
EngineeringAutomotive EngineeringElectrical EngineeringElectric Vehicle EngineeringMachine LearningPowertrain EngineeringElectric Motor Drive SystemsElectric PowertrainsPower Electronics For Hybrid VehiclesPowertrain Control SystemsReinforcement LearningVehicle Control SystemsBattery AgingDeep Reinforcement LearningEnergy Cost OptimizationHybrid Electric VehiclesLow-speed OperationPlug-in Hybrid Electric VehiclesReward Function DesignVector Quantization
This paper proposes a novel power management strategy for plug-in hybrid electric vehicles based on deep reinforcement learning algorithm. Three parallel soft actor-critic (SAC) networks are trained for high speed, medium speed, and low-speed conditions respectively; the reward function is designed as minimizing the cost of energy cost and battery aging. During operation, the driving condition is recognized at each moment for the algorithm invoking based on the learning vector quantization (LVQ) neural network. On top of that, a driving cycle reconstruction algorithm is proposed. The historical speed segments that were recorded during the operation are reconstructed into the three categories of high speed, medium speed, and low speed, based on which the algorithms are online updated. The SAC-based control strategy is evaluated based on the standard driving cycles and Shenyang practical data. The results indicate the presented method can obtain the effect close to dynamic programming and can be further improved by up to 6.38% after the online update for uncertain driving conditions.
24
Yuankai Wu, Huachun Tan, Jiankun Peng et al. · Applied Energy · 2019 · 322 citations
Engineering, Electrical Engineering, Electric Vehicle Engineering +16