In this study,a novel residential virtual power plant(RVPP)scheduling method that leverages a gate recurrent unit(GRU)-integrated deep reinforcement learning(DRL)algorithm is proposed.In the proposed scheme,the GRU-in...In this study,a novel residential virtual power plant(RVPP)scheduling method that leverages a gate recurrent unit(GRU)-integrated deep reinforcement learning(DRL)algorithm is proposed.In the proposed scheme,the GRU-integrated DRL algorithm guides the RVPP to participate effectively in both the day-ahead and real-time markets,lowering the electricity purchase costs and consumption risks for end-users.The Lagrangian relaxation technique is introduced to transform the constrained Markov decision process(CMDP)into an unconstrained optimization problem,which guarantees that the constraints are strictly satisfied without determining the penalty coefficients.Furthermore,to enhance the scalability of the constrained soft actor-critic(CSAC)-based RVPP scheduling approach,a fully distributed scheduling architecture was designed to enable plug-and-play in the residential distributed energy resources(RDER).Case studies performed on the constructed RVPP scenario validated the performance of the proposed methodology in enhancing the responsiveness of the RDER to power tariffs,balancing the supply and demand of the power grid,and ensuring customer comfort.展开更多
The fast acceptance of cloud technology to industry explains increasing energy conservation needs and adoption of energy aware scheduling methods to cloud. Power consumption is one of the top of mind issues in cloud, ...The fast acceptance of cloud technology to industry explains increasing energy conservation needs and adoption of energy aware scheduling methods to cloud. Power consumption is one of the top of mind issues in cloud, because the usage of cloud storage by the individuals or organization grows rapidly. Developing an efficient power management processor architecture has gained considerable attention. However, the conventional power management mechanism fails to consider task scheduling policies. Therefore, this work presents a novel energy aware framework for power management. The proposed system leads to the development of Inclusive Power-Cognizant Processor Controller (IPCPC) for efficient power utilization. To evaluate the performance of the proposed method, simulation experiments inputting random tasks as well as tasks collected from Google Trace Logs were conducted to validate the supremacy of IPCPC. The research based on Real world Google Trace Logs gives results that proposed framework leads to less than 9% of total power consumption per task of server which proves reduction in the overall power needed.展开更多
The virtual power plant(VPP)is a new and efficient solution to manage the integration of distributed energy resources(DERs)into the power system.Considering the unpredictable output of stochastic DERs,conventional sch...The virtual power plant(VPP)is a new and efficient solution to manage the integration of distributed energy resources(DERs)into the power system.Considering the unpredictable output of stochastic DERs,conventional scheduling strategies always set plenty of reserve aside in order to guarantee the reliability of operation,which is too conservative to gain more benefits.Thus,it is significant to research the scheduling strategies of VPPs,which can coordinate the risks and benefits of VPP operation.This paper presents a fuzzy chance-constrained scheduling model which utilizes fuzzy variables to describe uncertain features of distributed generators(DGs).Based on credibility theory,the concept of the confidence level is introduced to quantify the feasibility of the conditions,which reflects the risk tolerance of VPP operation.By transforming the fuzzy chance constraints into their equivalent forms,traditional optimization algorithms can be used to solve the optimal scheduling problem.An IEEE 6-node system is employed to prove the feasibility of the proposed scheduling model.Case studies demonstrate that the fuzzy chance strategy is superior to conservative scheduling strategies in realizing the right balance between risks and benefits.展开更多
With the gradually widely usage of the air conditioning(AC) loads in developing countries, the urban power grid load has swiftly increased over the past decade.Especially in China, the AC load has accounted for over30...With the gradually widely usage of the air conditioning(AC) loads in developing countries, the urban power grid load has swiftly increased over the past decade.Especially in China, the AC load has accounted for over30% of the maximum load in many cities during summer.This paper proposes a scheme of constructing a virtual peaking unit(VPU) by public buildings’ cool storage central AC(CSCAC) systems and non-CSCAC(NCSCAC)systems for the day-ahead power network dispatching(DAPND). Considering the accumulation effect of different meteorological parameters, a short term load forecasting method of public building’s central AC(CAC) baseline load is firstly discussed. Then, a second-order equivalent thermal parameters model is established for the public building’s CAC load. Moreover, the novel load reduction control strategies for the public building’s CSCAC system and the public building’s NCSCAC system are respectively presented. Furthermore, based on the multiple-rank control strategy, the model of the DAPND with the participation of a VPU is set up. The VPU is composed of large-scale regulated public building’s CAC loads. To demonstrate the effectiveness of the proposed strategy, results of a sample study on a region in Nanjing which involves 22 public buildings’ CAC loads are described in this paper. Simulated results show that, by adopting the proposed DAPND scheme, the power network peak load in the region obviously decreases with a small enough deviation between the regulated load value and the dispatching instruction of the VPU. The total electricity-saving amount accounts for7.78% of total electricity consumption of the VPU before regulation.展开更多
针对高比例分布式能源和灵活可调负荷接入下,虚拟电厂(virtual power plant,VPP)调度特性复杂、各主体隐私数据保护困难的问题,本文提出一种基于联邦强化学习的多VPP安全协同隐私数据保护方法,实现多VPP可调资源协同优化与敏感数据的可...针对高比例分布式能源和灵活可调负荷接入下,虚拟电厂(virtual power plant,VPP)调度特性复杂、各主体隐私数据保护困难的问题,本文提出一种基于联邦强化学习的多VPP安全协同隐私数据保护方法,实现多VPP可调资源协同优化与敏感数据的可用不可见.首先,通过分析VPP内部可调资源的时空耦合性和时变性,构建了多VPP协同的全网调频备用资源调度模型和VPP内部可调资源物理模型.其次,将VPP可调资源的响应行为转化为一个时序马尔可夫决策过程,建立VPP内部深度Q网络(deep Q-network,DQN)优化调度模型,以经济优化为目标响应调度需求.然后,提出了基于改进横向联邦平均算法的多个DQN模型协同训练方法,通过联邦平均优化全局模型训练参数,并设计全局模型更新间隔自适应调整机制,提升DQN模型训练效率与精度.整个训练过程各VPP无需向上层调度中心上报详细物理模型,无需在训练过程中对等交互信息.最后,结合某地区调频辅助服务市场数据与IEEE-39节点网络算例,对提出算法进行仿真验证,并讨论了不同调度策略对不确定性调节资源的适应能力.与同类算法的对比结果表明,所提算法隐私泄露方差为0.11,调度成本最大可降低22.5%,在各调节时段,能够保护VPP运行和物理模型数据并实现可调资源高效低成本参与电力市场.展开更多
随着氢燃料汽车(hydrogen vehicle,HV)的快速发展,氢燃料供给体系建设成为研究热点。利用电解水制氢消纳富余的新能源是解决此问题的一个有效手段。但氢能利用存在成本较高,难以获利的问题,考虑采用虚拟电厂(virtual power plant,VPP)...随着氢燃料汽车(hydrogen vehicle,HV)的快速发展,氢燃料供给体系建设成为研究热点。利用电解水制氢消纳富余的新能源是解决此问题的一个有效手段。但氢能利用存在成本较高,难以获利的问题,考虑采用虚拟电厂(virtual power plant,VPP)的商业模式以提高制氢收益。在虚拟电厂的技术框架下,依靠高渗透率新能源制氢,在满足氢能源汽车供氢需求的同时,使VPP同时参与能量市场、旋转备用市场、调峰市场和碳排放权交易市场以获得最大收益。以VPP期望收益最大化为目标建立了考虑氢能源综合利用及参与多级市场获利的VPP优化调度模型,对夏季和冬季典型日VPP优化调度结果的分析表明:通过对氢燃料汽车与氢储能的协调调度及作为虚拟电厂参与各级电力市场,可有效实现氢燃料的供给并获得很好的经济效益,从而实现VPP绿色、低碳、经济运行。展开更多
基金supported by the Sichuan Science and Technology Program(grant number 2022YFG0123).
文摘In this study,a novel residential virtual power plant(RVPP)scheduling method that leverages a gate recurrent unit(GRU)-integrated deep reinforcement learning(DRL)algorithm is proposed.In the proposed scheme,the GRU-integrated DRL algorithm guides the RVPP to participate effectively in both the day-ahead and real-time markets,lowering the electricity purchase costs and consumption risks for end-users.The Lagrangian relaxation technique is introduced to transform the constrained Markov decision process(CMDP)into an unconstrained optimization problem,which guarantees that the constraints are strictly satisfied without determining the penalty coefficients.Furthermore,to enhance the scalability of the constrained soft actor-critic(CSAC)-based RVPP scheduling approach,a fully distributed scheduling architecture was designed to enable plug-and-play in the residential distributed energy resources(RDER).Case studies performed on the constructed RVPP scenario validated the performance of the proposed methodology in enhancing the responsiveness of the RDER to power tariffs,balancing the supply and demand of the power grid,and ensuring customer comfort.
文摘The fast acceptance of cloud technology to industry explains increasing energy conservation needs and adoption of energy aware scheduling methods to cloud. Power consumption is one of the top of mind issues in cloud, because the usage of cloud storage by the individuals or organization grows rapidly. Developing an efficient power management processor architecture has gained considerable attention. However, the conventional power management mechanism fails to consider task scheduling policies. Therefore, this work presents a novel energy aware framework for power management. The proposed system leads to the development of Inclusive Power-Cognizant Processor Controller (IPCPC) for efficient power utilization. To evaluate the performance of the proposed method, simulation experiments inputting random tasks as well as tasks collected from Google Trace Logs were conducted to validate the supremacy of IPCPC. The research based on Real world Google Trace Logs gives results that proposed framework leads to less than 9% of total power consumption per task of server which proves reduction in the overall power needed.
基金supported by the National Natural Science Foundation of China(No.51577115).
文摘The virtual power plant(VPP)is a new and efficient solution to manage the integration of distributed energy resources(DERs)into the power system.Considering the unpredictable output of stochastic DERs,conventional scheduling strategies always set plenty of reserve aside in order to guarantee the reliability of operation,which is too conservative to gain more benefits.Thus,it is significant to research the scheduling strategies of VPPs,which can coordinate the risks and benefits of VPP operation.This paper presents a fuzzy chance-constrained scheduling model which utilizes fuzzy variables to describe uncertain features of distributed generators(DGs).Based on credibility theory,the concept of the confidence level is introduced to quantify the feasibility of the conditions,which reflects the risk tolerance of VPP operation.By transforming the fuzzy chance constraints into their equivalent forms,traditional optimization algorithms can be used to solve the optimal scheduling problem.An IEEE 6-node system is employed to prove the feasibility of the proposed scheduling model.Case studies demonstrate that the fuzzy chance strategy is superior to conservative scheduling strategies in realizing the right balance between risks and benefits.
基金supported by National Key Technology Support Program (No. 2013BAA01B00)National Natural Science Foundation of China (No. 51361130152, No. 51577028)
文摘With the gradually widely usage of the air conditioning(AC) loads in developing countries, the urban power grid load has swiftly increased over the past decade.Especially in China, the AC load has accounted for over30% of the maximum load in many cities during summer.This paper proposes a scheme of constructing a virtual peaking unit(VPU) by public buildings’ cool storage central AC(CSCAC) systems and non-CSCAC(NCSCAC)systems for the day-ahead power network dispatching(DAPND). Considering the accumulation effect of different meteorological parameters, a short term load forecasting method of public building’s central AC(CAC) baseline load is firstly discussed. Then, a second-order equivalent thermal parameters model is established for the public building’s CAC load. Moreover, the novel load reduction control strategies for the public building’s CSCAC system and the public building’s NCSCAC system are respectively presented. Furthermore, based on the multiple-rank control strategy, the model of the DAPND with the participation of a VPU is set up. The VPU is composed of large-scale regulated public building’s CAC loads. To demonstrate the effectiveness of the proposed strategy, results of a sample study on a region in Nanjing which involves 22 public buildings’ CAC loads are described in this paper. Simulated results show that, by adopting the proposed DAPND scheme, the power network peak load in the region obviously decreases with a small enough deviation between the regulated load value and the dispatching instruction of the VPU. The total electricity-saving amount accounts for7.78% of total electricity consumption of the VPU before regulation.
文摘针对高比例分布式能源和灵活可调负荷接入下,虚拟电厂(virtual power plant,VPP)调度特性复杂、各主体隐私数据保护困难的问题,本文提出一种基于联邦强化学习的多VPP安全协同隐私数据保护方法,实现多VPP可调资源协同优化与敏感数据的可用不可见.首先,通过分析VPP内部可调资源的时空耦合性和时变性,构建了多VPP协同的全网调频备用资源调度模型和VPP内部可调资源物理模型.其次,将VPP可调资源的响应行为转化为一个时序马尔可夫决策过程,建立VPP内部深度Q网络(deep Q-network,DQN)优化调度模型,以经济优化为目标响应调度需求.然后,提出了基于改进横向联邦平均算法的多个DQN模型协同训练方法,通过联邦平均优化全局模型训练参数,并设计全局模型更新间隔自适应调整机制,提升DQN模型训练效率与精度.整个训练过程各VPP无需向上层调度中心上报详细物理模型,无需在训练过程中对等交互信息.最后,结合某地区调频辅助服务市场数据与IEEE-39节点网络算例,对提出算法进行仿真验证,并讨论了不同调度策略对不确定性调节资源的适应能力.与同类算法的对比结果表明,所提算法隐私泄露方差为0.11,调度成本最大可降低22.5%,在各调节时段,能够保护VPP运行和物理模型数据并实现可调资源高效低成本参与电力市场.
文摘随着氢燃料汽车(hydrogen vehicle,HV)的快速发展,氢燃料供给体系建设成为研究热点。利用电解水制氢消纳富余的新能源是解决此问题的一个有效手段。但氢能利用存在成本较高,难以获利的问题,考虑采用虚拟电厂(virtual power plant,VPP)的商业模式以提高制氢收益。在虚拟电厂的技术框架下,依靠高渗透率新能源制氢,在满足氢能源汽车供氢需求的同时,使VPP同时参与能量市场、旋转备用市场、调峰市场和碳排放权交易市场以获得最大收益。以VPP期望收益最大化为目标建立了考虑氢能源综合利用及参与多级市场获利的VPP优化调度模型,对夏季和冬季典型日VPP优化调度结果的分析表明:通过对氢燃料汽车与氢储能的协调调度及作为虚拟电厂参与各级电力市场,可有效实现氢燃料的供给并获得很好的经济效益,从而实现VPP绿色、低碳、经济运行。