The hybrid policy is a flexible policy tool that combines features of carbon trading and carbon taxation.Its economic and environmental effects under China's background are still not studied in detail.Given the ex...The hybrid policy is a flexible policy tool that combines features of carbon trading and carbon taxation.Its economic and environmental effects under China's background are still not studied in detail.Given the exogenous carbon reduction targets,carbon prices,and carbon tax-rates,by computable general equilibrium modeling methods and factor decomposition methods,this article investigates direct and cascaded effects of the hybrid policy on economic growth,energy utilization,and carbon emission on the national level and the sector level,with China's national input-output data-set.Stepwisely,policy scenarios with irrational estimated results are selectively excluded based on comprehensive evaluation among economic,carbon reduction and other policy targets.As a result,against national economic conditions in 2007,the hybrid policy,with a carbon reduction target of -10%,a carbon tax-rate of around $10,and a ceiling carbon price of $40,is highly recommended,because of its significant lower economic loss,lower energy utilization cost,and practical robustness against fluctuation of energy market and carbon market.Furthermore,by decomposition analysis,carbon reduction-related costs are decomposed into a direct part that includes carbon allowance price and carbon tax,and an indirect part as the energy price incremental induced by direct carbon costs.Gross carbon reduction may be decomposed into three parts such as energy intensity,economic scale,and technical progress.And,carbon taxation is the main policy tool that stimulates to improve the energy efficiency.展开更多
The present study investigates an energy management strategy based on reinforcement learning for seriesparallel hybrid vehicles. Hybrid electric vehicles allow using more advanced power management policies because of ...The present study investigates an energy management strategy based on reinforcement learning for seriesparallel hybrid vehicles. Hybrid electric vehicles allow using more advanced power management policies because of their complexity of power management. Towards this feature, a Q-Learning algorithm is proposed to design an energy management strategy. Compared to previous studies, an online reward function is defined to optimize fuel consumption and battery life cycle. Moreover, in the provided method, prior knowledge of the cycle and exact modeling of the vehicle are not required. The introduced strategy is simulated for four driving cycles in MATLAB software linked with ADVISOR. The simulation results show that in the HWFET cycle, the fuel consumption decreases by 1.25 %, and battery life increases by 65% compared to the rule-based method implemented in ADVISOR. Also, the results for the other driving cycles confirm the self-improvement property. In addition, it has been depicted that in the case of change in the driving cycle, the method performance has been maintained and gained better performance than the rule-based controller.展开更多
In the paper,a novel self-learning energy management strategy(EMS)is proposed for fuel cell hybrid electric vehicles(FCHEV)to achieve the hydrogen saving and maintain the battery operation.In the EMS,it is proposed to...In the paper,a novel self-learning energy management strategy(EMS)is proposed for fuel cell hybrid electric vehicles(FCHEV)to achieve the hydrogen saving and maintain the battery operation.In the EMS,it is proposed to approximate the EMS policy function with fuzzy inference system(FIS)and learn the policy parameters through policy gradient reinforcement learning(PGRL).Thus,a so-called Fuzzy REINFORCE algorithm is first proposed and studied for EMS problem in the paper.Fuzzy REINFORCE is a model-free method that the EMS agent can learn itself through interactions with environment,which makes it independent of model accuracy,prior knowledge,and expert experience.Meanwhile,to stabilize the training process,a fuzzy baseline function is adopted to approximate the value function based on FIS without affecting the policy gradient direction.More-over,the drawbacks of traditional reinforcement learning such as high computation burden,long convergence time,can also be overcome.The effectiveness of the proposed methods were verified by Hardware-in-Loop ex-periments.The adaptability of the proposed method to the changes of driving conditions and system states is also verified.展开更多
An aero-engine maintenance policy plays a crucial role in reasonably reducing maintenance cost. An aero-engine is a type of complex equipment with long service-life. In engineering,a hybrid maintenance strategy is ado...An aero-engine maintenance policy plays a crucial role in reasonably reducing maintenance cost. An aero-engine is a type of complex equipment with long service-life. In engineering,a hybrid maintenance strategy is adopted to improve the aero-engine operational reliability. Thus,the long service-life and the hybrid maintenance strategy should be considered synchronously in aero-engine maintenance policy optimization. This paper proposes an aero-engine life-cycle maintenance policy optimization algorithm that synchronously considers the long service-life and the hybrid maintenance strategy. The reinforcement learning approach was adopted to illustrate the optimization framework, in which maintenance policy optimization was formulated as a Markov decision process. In the reinforcement learning framework, the Gauss–Seidel value iteration algorithm was adopted to optimize the maintenance policy. Compared with traditional aero-engine maintenance policy optimization methods, the long service-life and the hybrid maintenance strategy could be addressed synchronously by the proposed algorithm. Two numerical experiments and algorithm analyses were performed to illustrate the optimization algorithm in detail.展开更多
在两个传统补货策略IB(installation-based),EB(echelon-based)组成的混合策略1(HB1,hybrid based policy 1)基础上,提出了混合策略2(HB2,hybrid based policy 2),然后将HB1和HB2结合形成双混合策略(RH,re-hybrid policy),推导证明了HB2...在两个传统补货策略IB(installation-based),EB(echelon-based)组成的混合策略1(HB1,hybrid based policy 1)基础上,提出了混合策略2(HB2,hybrid based policy 2),然后将HB1和HB2结合形成双混合策略(RH,re-hybrid policy),推导证明了HB2和RH的总成本费用比率,给出了RH降低总成本费用比率原理.试验证明:在一个仓库和N个独立相同随机需求零售商构成的系统中,RH能有效改善IB、EB、HB1、HB2的总成本费用比率.展开更多
Green hydrogen is considered one of the key technologies of the energy transition,as it can be used to store surpluses from renewable energies in times of high solar radiation or wind speed for use in dark lulls.This ...Green hydrogen is considered one of the key technologies of the energy transition,as it can be used to store surpluses from renewable energies in times of high solar radiation or wind speed for use in dark lulls.This paper examines the decarbonization potential of hydrogen for the heating industry.Worldwide,99%of hydrogen is produced from fossil fuels,because hydrogen derived from renew-able energy sources remains prohibitively expensive compared with its conventional counterpart.However,due to the expansion of renewable energy sources and the current energy crisis of conventional energy sources,hydrogen from renewable energy sources is becoming more and more economical.To optimize the efficiency of green hydrogen production and make it more price-competitive,the author simulates a hydrogen production plant consisting of a photovoltaic plant,a power grid,hydrogen storage,an electro-lyser,a natural gas purchase option,a district heating plant and households.Using the deep deterministic policy gradient algorithm from deep reinforcement learning,the plant is designed to optimize itself by simulating different production scenarios and deriving strategies.The connected district heating plant is used to map how hydrogen can be optimally used for heat supply.A demonstrable outcome of this paper is that the utilization of deep deterministic policy gradient,over the course of a full year,can result in a com-petitive production of hydrogen derived from renewable or stored energy sources for the heating industry as a natural gas substitute.展开更多
Roughly 99% of the demand for electricity in Brazil is supplied by a national interconnected grid. The remaining 1% is spread in several “isolated systems” of the Amazon region—mini-grids that rely on expensive die...Roughly 99% of the demand for electricity in Brazil is supplied by a national interconnected grid. The remaining 1% is spread in several “isolated systems” of the Amazon region—mini-grids that rely on expensive diesel gensets due to high commodity and transportation costs. The isolated systems also have remote communities disconnected altogether from the mini-grids with inadequate health, education and leisure services. These communities are precariously supplied by small inefficient diesel gensets that run for a few hours per day. In this article, we propose a sustainable and economic alternative for the electric supply of the remote communities of isolated systems through a combination of photovoltaic solar generation and storage. The objective is to improve access to electricity with savings for the communities. The present paper outlines a public policy to meet this objective.展开更多
基金supported by the Fundamental Research Funds for the Central Universities[CDJSK10 00 68]NSFC Young Scientist Research Fund[0903080]
文摘The hybrid policy is a flexible policy tool that combines features of carbon trading and carbon taxation.Its economic and environmental effects under China's background are still not studied in detail.Given the exogenous carbon reduction targets,carbon prices,and carbon tax-rates,by computable general equilibrium modeling methods and factor decomposition methods,this article investigates direct and cascaded effects of the hybrid policy on economic growth,energy utilization,and carbon emission on the national level and the sector level,with China's national input-output data-set.Stepwisely,policy scenarios with irrational estimated results are selectively excluded based on comprehensive evaluation among economic,carbon reduction and other policy targets.As a result,against national economic conditions in 2007,the hybrid policy,with a carbon reduction target of -10%,a carbon tax-rate of around $10,and a ceiling carbon price of $40,is highly recommended,because of its significant lower economic loss,lower energy utilization cost,and practical robustness against fluctuation of energy market and carbon market.Furthermore,by decomposition analysis,carbon reduction-related costs are decomposed into a direct part that includes carbon allowance price and carbon tax,and an indirect part as the energy price incremental induced by direct carbon costs.Gross carbon reduction may be decomposed into three parts such as energy intensity,economic scale,and technical progress.And,carbon taxation is the main policy tool that stimulates to improve the energy efficiency.
文摘The present study investigates an energy management strategy based on reinforcement learning for seriesparallel hybrid vehicles. Hybrid electric vehicles allow using more advanced power management policies because of their complexity of power management. Towards this feature, a Q-Learning algorithm is proposed to design an energy management strategy. Compared to previous studies, an online reward function is defined to optimize fuel consumption and battery life cycle. Moreover, in the provided method, prior knowledge of the cycle and exact modeling of the vehicle are not required. The introduced strategy is simulated for four driving cycles in MATLAB software linked with ADVISOR. The simulation results show that in the HWFET cycle, the fuel consumption decreases by 1.25 %, and battery life increases by 65% compared to the rule-based method implemented in ADVISOR. Also, the results for the other driving cycles confirm the self-improvement property. In addition, it has been depicted that in the case of change in the driving cycle, the method performance has been maintained and gained better performance than the rule-based controller.
基金This work has been supported by the ANR DEAL(contract ANR-20-CE05-0016-01)This work has also been partially funded by Region Sud Provence-Alpes-Cote d’Azur via project AMULTI(2021_02918).
文摘In the paper,a novel self-learning energy management strategy(EMS)is proposed for fuel cell hybrid electric vehicles(FCHEV)to achieve the hydrogen saving and maintain the battery operation.In the EMS,it is proposed to approximate the EMS policy function with fuzzy inference system(FIS)and learn the policy parameters through policy gradient reinforcement learning(PGRL).Thus,a so-called Fuzzy REINFORCE algorithm is first proposed and studied for EMS problem in the paper.Fuzzy REINFORCE is a model-free method that the EMS agent can learn itself through interactions with environment,which makes it independent of model accuracy,prior knowledge,and expert experience.Meanwhile,to stabilize the training process,a fuzzy baseline function is adopted to approximate the value function based on FIS without affecting the policy gradient direction.More-over,the drawbacks of traditional reinforcement learning such as high computation burden,long convergence time,can also be overcome.The effectiveness of the proposed methods were verified by Hardware-in-Loop ex-periments.The adaptability of the proposed method to the changes of driving conditions and system states is also verified.
基金co-supported by the Key National Natural Science Foundation of China (No. U1533202)the Civil Aviation Administration of China (No. MHRD20150104)the Shandong Independent Innovation and Achievements Transformation Fund, China (No. 2014CGZH1101)
文摘An aero-engine maintenance policy plays a crucial role in reasonably reducing maintenance cost. An aero-engine is a type of complex equipment with long service-life. In engineering,a hybrid maintenance strategy is adopted to improve the aero-engine operational reliability. Thus,the long service-life and the hybrid maintenance strategy should be considered synchronously in aero-engine maintenance policy optimization. This paper proposes an aero-engine life-cycle maintenance policy optimization algorithm that synchronously considers the long service-life and the hybrid maintenance strategy. The reinforcement learning approach was adopted to illustrate the optimization framework, in which maintenance policy optimization was formulated as a Markov decision process. In the reinforcement learning framework, the Gauss–Seidel value iteration algorithm was adopted to optimize the maintenance policy. Compared with traditional aero-engine maintenance policy optimization methods, the long service-life and the hybrid maintenance strategy could be addressed synchronously by the proposed algorithm. Two numerical experiments and algorithm analyses were performed to illustrate the optimization algorithm in detail.
文摘在两个传统补货策略IB(installation-based),EB(echelon-based)组成的混合策略1(HB1,hybrid based policy 1)基础上,提出了混合策略2(HB2,hybrid based policy 2),然后将HB1和HB2结合形成双混合策略(RH,re-hybrid policy),推导证明了HB2和RH的总成本费用比率,给出了RH降低总成本费用比率原理.试验证明:在一个仓库和N个独立相同随机需求零售商构成的系统中,RH能有效改善IB、EB、HB1、HB2的总成本费用比率.
文摘Green hydrogen is considered one of the key technologies of the energy transition,as it can be used to store surpluses from renewable energies in times of high solar radiation or wind speed for use in dark lulls.This paper examines the decarbonization potential of hydrogen for the heating industry.Worldwide,99%of hydrogen is produced from fossil fuels,because hydrogen derived from renew-able energy sources remains prohibitively expensive compared with its conventional counterpart.However,due to the expansion of renewable energy sources and the current energy crisis of conventional energy sources,hydrogen from renewable energy sources is becoming more and more economical.To optimize the efficiency of green hydrogen production and make it more price-competitive,the author simulates a hydrogen production plant consisting of a photovoltaic plant,a power grid,hydrogen storage,an electro-lyser,a natural gas purchase option,a district heating plant and households.Using the deep deterministic policy gradient algorithm from deep reinforcement learning,the plant is designed to optimize itself by simulating different production scenarios and deriving strategies.The connected district heating plant is used to map how hydrogen can be optimally used for heat supply.A demonstrable outcome of this paper is that the utilization of deep deterministic policy gradient,over the course of a full year,can result in a com-petitive production of hydrogen derived from renewable or stored energy sources for the heating industry as a natural gas substitute.
文摘Roughly 99% of the demand for electricity in Brazil is supplied by a national interconnected grid. The remaining 1% is spread in several “isolated systems” of the Amazon region—mini-grids that rely on expensive diesel gensets due to high commodity and transportation costs. The isolated systems also have remote communities disconnected altogether from the mini-grids with inadequate health, education and leisure services. These communities are precariously supplied by small inefficient diesel gensets that run for a few hours per day. In this article, we propose a sustainable and economic alternative for the electric supply of the remote communities of isolated systems through a combination of photovoltaic solar generation and storage. The objective is to improve access to electricity with savings for the communities. The present paper outlines a public policy to meet this objective.
