Online Recursive Power Management Strategy Based on the Reinforcement Learning Algorithm With Cosine Similarity and a Forgetting Factor

Lin, Xinyou; Zhou, Binhao; Xia, Yutian

doi:10.1109/tie.2020.2988189

Cited by 38 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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],…”

Section: Rl-based Energy Management Strategiesmentioning

confidence: 99%

“…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…”

Section: Algorithms References Content Descriptionmentioning

confidence: 99%

See 1 more Smart Citation

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

Tan

Tang

et al. 2021

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

Section: Rl-based Energy Management Strategiesmentioning

confidence: 99%

Section: Algorithms References Content Descriptionmentioning

confidence: 99%

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

Tan

Tang

et al. 2021

Renewable and Sustainable Energy Reviews

View full text Add to dashboard Cite

“…Moreover, advanced multi-objective optimization methods [10]- [13] have been studied to mitigate the degradation of fuel cell and battery system, save fuel consumption, and keep battery charge sustaining. Recently, machine learning algorithms, such as online learning [14], reinforcement learning [15], [16], and rule learning algorithm [17], have been investigated for power management in an FCHEV system. However, the EMS using the optimal solution shows the result using simulation, and there are few real-time optimal EMS development results.…”

Section: Introductionmentioning

confidence: 99%

A Real-Time Rule-Based Energy Management Strategy With Multi-Objective Optimization for a Fuel Cell Hybrid Electric Vehicle

et al. 2022

View full text Add to dashboard Cite

Energy management strategy (EMS) has a great impact on securing fuel cell durability, battery charge sustenance, and fuel saving in fuel cell hybrid electric vehicles (FCHEVs). This study aims to develop EMS that can be applied in real-time to satisfy above conditions. Real time power separation was performed using rule-based EMS. A genetic algorithm (GA) was implemented to calculate the optimal battery charge/discharge criterion that simultaneously satisfies the minimum hydrogen consumption rate, battery charge rate preservation, and high fuel cell efficiency. The battery charge/discharge parameter values vary according to driving patterns, and in this paper, typical suburban, urban, and highway driving conditions are considered. For the real-time application of this research method, the effectiveness was demonstrated by applying the driving conditions of unknown patterns. The effect on the initial battery SOC on EMS was analyzed, and in order to verify the superiority of this method, it was compared and analyzed with EMS results using dynamic programming and fuzzy logic under the same driving cycles. The effectiveness of this research method was verified through simulation, and it was confirmed through experiments for real-time application. Since there is a limit to the experiment using an actual fuel cell vehicle, the experiment was performed using a fuel cell and battery. This method can be applied to real fuel cell vehicles in the same way.INDEX TERMS Battery charge sustenance, energy management, fuel cell hybrid electric vehicle, hydrogen consumption, multi-objective GA.

show abstract

“…It is suitable for solving sequential decisionmaking problems. The purpose of reinforcement learning is to allow a reinforcement learning agent to learn how to behave in an environment where the only feedback consists of scalar learning signals, and the agent's goal is to maximize the reward signal from the environment in the long term [16,17]. Reinforcement learning algorithms capable of online parameter updates, fast convergence of the learning process, and suitable for different operating conditions have the potential to be applied to real-time energy management strategies [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Research on Energy Management Strategy of Electric Vehicle Hybrid System Based on Reinforcement Learning

Cheng

Chen

2022

Electronics

View full text Add to dashboard Cite

From the perspective of energy management, the demand power of a hybrid electric vehicle driving under random conditions can be considered as a random process, and the Markov chain can be used for modeling. In this article, an energy management strategy based on reinforcement learning with real-time updates is proposed to reasonably allocate the energy flow of the hybrid power system under unknown working conditions. The hybrid system is powered by a supercapacitor and a lithium battery, which uses the characteristics of each component to reduce the energy loss of the system, reduce the rate of change of the lithium battery current, and prolong the service life of the components. The strategy takes the change of the transition probability matrix under real-time working conditions as the basis. The system judges whether it is necessary to use the new transition probability to calculate and update the energy management strategy of the system by calculating the Pearson similarity between the transition probability matrix at the current time and previous time. The simulation results validate the proposed method.

show abstract

Online Recursive Power Management Strategy Based on the Reinforcement Learning Algorithm With Cosine Similarity and a Forgetting Factor

Cited by 38 publications

References 28 publications

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

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

A Real-Time Rule-Based Energy Management Strategy With Multi-Objective Optimization for a Fuel Cell Hybrid Electric Vehicle

Research on Energy Management Strategy of Electric Vehicle Hybrid System Based on Reinforcement Learning

Contact Info

Product

Resources

About