Power Management Strategy of Hybrid Vehicles Using Sarsa Method

Cooperative energy management and eco-driving of plug-in hybrid electric vehicle via multi-agent reinforcement learning

“…Simulation results show that the fuel economy of the proposed EMS is improved by 11.93% compared with the binary mode control strategy. In [19], a HEV EMS based on SARSA algorithm was studied. Unlike Q-learning, SARSA is onpolicy.…”

How to Implement Automotive Fault Diagnosis Using Artificial Intelligence Scheme

“…In addition, because the detection range was becoming longer and longer, two methods were also proposed to improve the performance of sequence anomaly detection. First, inspired by the success of generative adversarial networks (GANs) in image generation [52,53] and sequence generation tasks [54,55], and, second, to adequately capture normal patterns in time series, the authors of [51] adopted the model built based on information from the time and frequency domains, and a new network architecture was designed in order to combine the discriminator with the sequence predictor. The discriminator tries to distinguish between real and predicted sequences.…”

Driving conditions-driven energy management strategies for hybrid electric vehicles: A review

“…Aim to prolong the service time of power sources and reduce hydrogen consumption. In [92], the SARSA algorithm was applied to address the issue of EMS for a FCHEV, the reward function was modeled as Gaussian distribution and the degree of hybridization was chosen as the action variable. A recursive algorithm was used to online update the TPM of demand power in [93],…”

“…Q-learning [87][88][89][90][91], [93] Derive the optimal EMS for FCHEV, aim to improve the FCHEVs' performance SARSA [92] Compare the performance of Q-learning and SARSA in EMS for a FCHEV Q-learning [94,95] Propose an improve Q-learning, embed the recursive algorithm to update the TMP online Q-learning [96,97], [100] Combine the merits of Q-learning, PMP and DP Q-learning [98] Analyzes the impact of algorithm hyperparameters on EMS Policy iteration [99] Calculate the TPM of power demand, apply the EMS in real-time DP [101] Employ the DP in off-line training and ECMS in the on-line application Q-learning [102] Discuss the influence of the number of state variables in the Q-learning algorithm Dyna-H [103] Analyzes the difference between the Dyna-H and Q-learning…”