To integrate different renewable energy resources effectively in a microgrid, a configuration optimization model of a multi-energy distributed generation（DG） system and its auxiliary equipment is proposed. The model...To integrate different renewable energy resources effectively in a microgrid, a configuration optimization model of a multi-energy distributed generation（DG） system and its auxiliary equipment is proposed. The model mainly consists of two parts, the determination of initial configuration schemes according to user preference and the selection of the optimal scheme. The comprehensive evaluation index（CEI）, which is acquired through the analytic hierarchy process（AHP） weight calculation method, is adopted as the evaluation criterion to rank the initial schemes. The optimal scheme is obtained according to the ranking results. The proposed model takes the diversity of different equipment parameters and investment cost into consideration and can give relatively suitable and economical suggestions for system configuration.Additionally, unlike Homer Pro, the proposed model considers the complementation of different renewable energy resources, and thus the rationality of the multi-energy DG system is improved compared with the single evaluation criterion method which only considers the total cost.展开更多
This paper studied a supervisory control system for a hybrid off-highway electric vehicle under the chargesustaining(CS)condition.A new predictive double Q-learning with backup models(PDQL)scheme is proposed to optimi...This paper studied a supervisory control system for a hybrid off-highway electric vehicle under the chargesustaining(CS)condition.A new predictive double Q-learning with backup models(PDQL)scheme is proposed to optimize the engine fuel in real-world driving and improve energy efficiency with a faster and more robust learning process.Unlike the existing“model-free”methods,which solely follow on-policy and off-policy to update knowledge bases(Q-tables),the PDQL is developed with the capability to merge both on-policy and off-policy learning by introducing a backup model(Q-table).Experimental evaluations are conducted based on software-in-the-loop(SiL)and hardware-in-the-loop(HiL)test platforms based on real-time modelling of the studied vehicle.Compared to the standard double Q-learning(SDQL),the PDQL only needs half of the learning iterations to achieve better energy efficiency than the SDQL at the end learning process.In the SiL under 35 rounds of learning,the results show that the PDQL can improve the vehicle energy efficiency by 1.75%higher than SDQL.By implementing the PDQL in HiL under four predefined real-world conditions,the PDQL can robustly save more than 5.03%energy than the SDQL scheme.展开更多
The energy management may perform well under normal conditions, but may lead to poor behavior under abnormal situations. To tackle this problem, an optimal control strategy called rule-based equivalent fuel consumptio...The energy management may perform well under normal conditions, but may lead to poor behavior under abnormal situations. To tackle this problem, an optimal control strategy called rule-based equivalent fuel consumption minimization strategy （RECMS） is developed for a new complex hybrid electric vehicle （CHEV）. It optimizes the energy efficiency and drive performance to cater for normal and power-loss operations of the tractive motor. Firstly, the strategy formulates a novel objective function based on the equivalent fuel concept. By accounting for the actual fuel cost, the equivalent fuel cost for the electric machines and virtual fuel cost for the drivability, the cost function is obtained. Furthermore, some penalty factors are presented to optimize the performance target. Finally, experiments for a practical CHEV are performed to validate a simulation model. Then simulations are carried out for both rule-based and RECMS. The results show that the optimal energy management is working well.展开更多
基金The National Natural Science Foundation of China(No.51377021)the Science and Technology Project of State Grid Corporation of China(No.SGTJDK00DWJS1600014)
文摘To integrate different renewable energy resources effectively in a microgrid, a configuration optimization model of a multi-energy distributed generation（DG） system and its auxiliary equipment is proposed. The model mainly consists of two parts, the determination of initial configuration schemes according to user preference and the selection of the optimal scheme. The comprehensive evaluation index（CEI）, which is acquired through the analytic hierarchy process（AHP） weight calculation method, is adopted as the evaluation criterion to rank the initial schemes. The optimal scheme is obtained according to the ranking results. The proposed model takes the diversity of different equipment parameters and investment cost into consideration and can give relatively suitable and economical suggestions for system configuration.Additionally, unlike Homer Pro, the proposed model considers the complementation of different renewable energy resources, and thus the rationality of the multi-energy DG system is improved compared with the single evaluation criterion method which only considers the total cost.
基金Project(KF2029)supported by the State Key Laboratory of Automotive Safety and Energy(Tsinghua University),ChinaProject(102253)supported partially by the Innovate UK。
文摘This paper studied a supervisory control system for a hybrid off-highway electric vehicle under the chargesustaining(CS)condition.A new predictive double Q-learning with backup models(PDQL)scheme is proposed to optimize the engine fuel in real-world driving and improve energy efficiency with a faster and more robust learning process.Unlike the existing“model-free”methods,which solely follow on-policy and off-policy to update knowledge bases(Q-tables),the PDQL is developed with the capability to merge both on-policy and off-policy learning by introducing a backup model(Q-table).Experimental evaluations are conducted based on software-in-the-loop(SiL)and hardware-in-the-loop(HiL)test platforms based on real-time modelling of the studied vehicle.Compared to the standard double Q-learning(SDQL),the PDQL only needs half of the learning iterations to achieve better energy efficiency than the SDQL at the end learning process.In the SiL under 35 rounds of learning,the results show that the PDQL can improve the vehicle energy efficiency by 1.75%higher than SDQL.By implementing the PDQL in HiL under four predefined real-world conditions,the PDQL can robustly save more than 5.03%energy than the SDQL scheme.
基金the National High Technology Research and Development Program (863) of China(No. 2006AA11A127)
文摘The energy management may perform well under normal conditions, but may lead to poor behavior under abnormal situations. To tackle this problem, an optimal control strategy called rule-based equivalent fuel consumption minimization strategy （RECMS） is developed for a new complex hybrid electric vehicle （CHEV）. It optimizes the energy efficiency and drive performance to cater for normal and power-loss operations of the tractive motor. Firstly, the strategy formulates a novel objective function based on the equivalent fuel concept. By accounting for the actual fuel cost, the equivalent fuel cost for the electric machines and virtual fuel cost for the drivability, the cost function is obtained. Furthermore, some penalty factors are presented to optimize the performance target. Finally, experiments for a practical CHEV are performed to validate a simulation model. Then simulations are carried out for both rule-based and RECMS. The results show that the optimal energy management is working well.
