Defects-rich heterointerfaces integrated with adjustable crystalline phases and atom vacancies,as well as veiled dielectric-responsive character,are instrumental in electromagnetic dissipation.Conventional methods,how...Defects-rich heterointerfaces integrated with adjustable crystalline phases and atom vacancies,as well as veiled dielectric-responsive character,are instrumental in electromagnetic dissipation.Conventional methods,however,constrain their delicate constructions.Herein,an innovative alternative is proposed:carrageenan-assistant cations-regulated(CACR)strategy,which induces a series of sulfides nanoparticles rooted in situ on the surface of carbon matrix.This unique configuration originates from strategic vacancy formation energy of sulfides and strong sulfides-carbon support interaction,benefiting the delicate construction of defects-rich heterostructures in M_(x)S_(y)/carbon composites(M-CAs).Impressively,these generated sulfur vacancies are firstly found to strengthen electron accumulation/consumption ability at heterointerfaces and,simultaneously,induct local asymmetry of electronic structure to evoke large dipole moment,ultimately leading to polarization coupling,i.e.,defect-type interfacial polarization.Such“Janus effect”(Janus effect means versatility,as in the Greek two-headed Janus)of interfacial sulfur vacancies is intuitively confirmed by both theoretical and experimental investigations for the first time.Consequently,the sulfur vacancies-rich heterostructured Co/Ni-CAs displays broad absorption bandwidth of 6.76 GHz at only 1.8 mm,compared to sulfur vacancies-free CAs without any dielectric response.Harnessing defects-rich heterostructures,this one-pot CACR strategy may steer the design and development of advanced nanomaterials,boosting functionality across diverse application domains beyond electromagnetic response.展开更多
Harnessing the redox potential of biochar to activate airborne O_(2)for contaminant removal is challenging.In this study,ferrihydrite(Fh)modified the boron(B),nitrogen(N)co-doped biochars(BCs)composites(Fh/B(n)NC)were...Harnessing the redox potential of biochar to activate airborne O_(2)for contaminant removal is challenging.In this study,ferrihydrite(Fh)modified the boron(B),nitrogen(N)co-doped biochars(BCs)composites(Fh/B(n)NC)were developed for enhancing the degradation of a model pollutant,tetracycline(TC),merely by airborne O_(2).Fh/B(3)NC showed excellent O_(2)activation activity for efficient TC degradation with a apparent TC degradation rate of 5.54,6.88,and 22.15 times that of B(3)NC,Fh,and raw BCs,respectively,where 1O_(2)and H_(2)O_(2)were identified as the dominant ROS for TC degradation.The B incorporation into the carbon lattice of Fh/B(3)NC promoted the generation of electron donors,sp2 C and the reductive B species,hence boosting Fe(III)reduction and 1O_(2)generation.O_(2)adsorption was enhanced due to the positively charged adsorption sites(C-B+and N-C+).And 1O_(2)was generated via Fe(II)catalyzed low-efficient successive one-electron transfer(O_(2)→O_(2)·−→1O_(2),H_(2)O_(2)),as well as biochar catalyzed high-efficient two-electron transfer(O_(2)→H_(2)O_(2)→1O_(2))that does not involve.O_(2)−as the intermediate.Moreover,Fh/B,N co-doped biochar showed a wide pH range,remarkable anti-interference capabilities,and effective detoxification.These findings shed new light on the development of environmentally benign BCs materials capable of degradading organic pollutants.展开更多
Correction to:Nano-Micro Lett.(2025)17:24 https://doi.org/10.1007/s40820-024-01515-0 Following publication of the original article[1],the authors reported the author list needed to be updated because the last three au...Correction to:Nano-Micro Lett.(2025)17:24 https://doi.org/10.1007/s40820-024-01515-0 Following publication of the original article[1],the authors reported the author list needed to be updated because the last three author names were duplicated.The correct author list has been provided in this Correction.The original article[1]has been corrected.展开更多
Due to the depletion of conventional energy reserves,there has been a global shift towards non-conventional energy sources.Shale oil and gas have emerged as key alternatives.These resources have dense and heterogeneou...Due to the depletion of conventional energy reserves,there has been a global shift towards non-conventional energy sources.Shale oil and gas have emerged as key alternatives.These resources have dense and heterogeneous reservoirs,which require hydraulic fracturing to extract.This process depends on identifying optimal fracturing layers,also known as‘sweet spots’.However,there is currently no uniform standard for locating these sweet spots.This paper presents a new model for evaluating fracturability that aims to address the current gap in the field.The model utilizes a hierarchical analysis approach and a mutation model,and is distinct in its use of original logging data to generate a fracturability evaluation map.Using this paper’s shale fracturing sweet spot evaluation method based on a two-step mutation model,four wells in different blocks of Fuling and Nanchuan Districts in China were validated,and the results showed that the proportion of high-yielding wells on the sweet spot line could reach 97.6%,while the proportion of low-producing wells was only 78.67%.Meanwhile,the evaluation results of the model were compared with the microseismic data,and the matching results were consistent.展开更多
Education is a great cause to achieve national prosperity, national rejuvenation and people’s happiness, and an important way to block the intergenerational transmission of poverty. Rural revitalization, education fi...Education is a great cause to achieve national prosperity, national rejuvenation and people’s happiness, and an important way to block the intergenerational transmission of poverty. Rural revitalization, education first. Rural children’s education is an important issue of rural revitalization. This paper takes rural children, especially left behind children and children in distress as the help objects, and uses the advantages of “Internet plus” to improve the system, strengthen family education guidance, integrate social love resources, etc., to solve the problems faced by rural children, such as no guidance in learning, lack of guidance in behavior, lack of care in life, promote the overall healthy development of rural children, and solve the problem of rural education backwardness.展开更多
The inpatient bed allocation that allows beds shared among different departments is an important and challenging problem for a healthcare system. When the objective function(s) and (some) constraints need to be estima...The inpatient bed allocation that allows beds shared among different departments is an important and challenging problem for a healthcare system. When the objective function(s) and (some) constraints need to be estimated via expensive and noisy stochastic simulation, a simulation optimization algorithm is required to solve this problem. In literature, there is a heuristic algorithm highly customized for one specific inpatient bed allocation problem, and it performs quite well on that problem. However, its lack of theoretical convergence and high specialization may not give practitioners enough confidence to apply it on real inpatient bed allocation problems. To mitigate such issues, this paper proposes to use the empirical stochastic branch-and-bound (ESB&B) algorithm, which is theoretically convergent and suitable for relatively general problems. A modest improvement for the original ESB&B algorithm is made and how to adapt the ESB&B algorithm to inpatient bed allocation problems is presented. Numerical experiments reveal the generality and fairly satisfying performance of the ESB&B algorithm, and the superiority of the improved ESB&B algorithm over the original one.展开更多
Peptide vaccines based on tumor antigens face the challenges of rapid clearance of peptides,low immunogenicity,and immune suppressive tumor microenvironment.However,the traditional solution mainly uses exogenous subst...Peptide vaccines based on tumor antigens face the challenges of rapid clearance of peptides,low immunogenicity,and immune suppressive tumor microenvironment.However,the traditional solution mainly uses exogenous substances as adjuvants or carriers to enhance innate immune responses,but excessive inflammation can damage adaptive immunity.In the current study,we propose a straightforward novel nanovaccine strategy by employing homologous human ferritin light chain for minimized innate immunity and dendritic cell(DC)targeting,the cationic KALA peptide for enhanced cellular uptake,and suppressor of cytokine signaling 1(SOCS1)siRNA for modulating DC activity.Upon fusing with the KALA peptide,this nanovaccine presents as a novel 40-mer cage structure,with highly enriched antigen peptides of proper size(25 nm)for targeted delivery to lymph nodes.The loading of SOCS1 siRNA onto the KALA peptide promoted DC maturation in tumor environment,leading to a 3-fold increase in antigen presentation compared to alum adjuvant.Moreover,it demonstrates remarkable efficacy in suppressing tumor progression and metastasis,together with prolonged survival.In addition,the nanovaccine stimulates up to 40%memory T cells,thereby achieving sustained protection against tumor re-challenge.This unprecedented nanovaccine platform can ignite fresh interdisciplinary discussions on interactive strategies for future peptide vaccine development.展开更多
The synthesis of atomically ordered Pt-based intermetallic electrocatalysts for the direct alcohol fuel cells generally requires the addition of surfactants or the high-temperature annealing.However,some residual surf...The synthesis of atomically ordered Pt-based intermetallic electrocatalysts for the direct alcohol fuel cells generally requires the addition of surfactants or the high-temperature annealing.However,some residual surfactants on the surface of the assynthesized catalysts would prevent the exposure of catalytic active sites,the high-temperature annealing process is easy to accelerate the sintering of the metal,which both lead to the decline of electrocatalytic performance.Herein,we construct the atomically ordered bimetallic PtBi intermetallics with clean surfaces and unique three-dimensional hollow acorn-shell-like structure(3D PtBi HASL)by a simple,low-temperature,surfactant-free one-pot synthetic approach.Benefiting from the special hollow structures,the obtained 3D PtBi HASL intermetallics expose abundant accessible active sites.Moreover,the introduction of oxophilic metal Bi can enhance adsorption of OHads,thereby significantly facilitating removal of poisoned intermediates.Density functional theory(DFT)simulations further indicate that formation of the PtBi intermetallic phase with the downshift of the Pt d-band center endows 3D Pt49.4Bi50.6 HASL intermetallics with significantly attenuated COads and enhanced OHads adsorption,bringing about the boosting electrocatalytic property.The mass activity of the 3D Pt49.4Bi50.6 HASL intermetallics for ethylene glycol oxidation reaction is as high as 24.67 A·mgPt^(−1),which is 12.98 times higher than that of commercial Pt/C(1.90 A·mgPt^(−1)).This work may inspire the design of Pt-based intermetallics as high-efficiency anode electrocatalysts for fuel cell applications.展开更多
Remarkable progress has been made in satellite-based quantum key distribution [QKD],which can effectively provide QKD service even at the intercontinental scale and construct an ultralong-distance global quantum netwo...Remarkable progress has been made in satellite-based quantum key distribution [QKD],which can effectively provide QKD service even at the intercontinental scale and construct an ultralong-distance global quantum network.But there are still some places where terrestrial fiber and ground stations cannot be constructed,like harsh mountainous areas and air space above the sea.So the airborne platform is expected to replace the ground station and provide flexible and relay links for the large-scale integrated communication network.However,the photon transmission rate would be randomly reduced,owing to the randomly distributed boundary layer that surrounds the surface of the aircraft when the flight speed is larger than0.3 Ma.Previous research of airborne QKD with boundary layer effects is mainly under the air-to-ground scenario in which the aircraft is a transmitter,while the satellite-to-aircraft scenario is rarely reported.In this article,we propose a performance evaluation scheme of satellite-to-aircraft QKD with boundary layer effects in which the aircraft is the receiver.With common experimental settings,the boundary layer would introduce a ~31 dB loss to the transmitted photons,decrease ~47% of the quantum communication time,and decrease ~51% of the secure key rate,which shows that the aero-optical effects caused by the boundary layer cannot be ignored.Our study can be performed in future airborne quantum communication designs.展开更多
A time-variable time-of-use electricity price can be used to reduce the charging costs for electric vehicle(EV)owners.Considering the uncertainty of price fluctuation and the randomness of EV owner’s commuting behavi...A time-variable time-of-use electricity price can be used to reduce the charging costs for electric vehicle(EV)owners.Considering the uncertainty of price fluctuation and the randomness of EV owner’s commuting behavior,we propose a deep reinforcement learning based method for the minimization of individual EV charging cost.The charging problem is first formulated as a Markov decision process(MDP),which has unknown transition probability.A modified long short-term memory(LSTM)neural network is used as the representation layer to extract temporal features from the electricity price signal.The deep deterministic policy gradient(DDPG)algorithm,which has continuous action spaces,is used to solve the MDP.The proposed method can automatically adjust the charging strategy according to electricity price to reduce the charging cost of the EV owner.Several other methods to solve the charging problem are also implemented and quantitatively compared with the proposed method which can reduce the charging cost up to 70.2%compared with other benchmark methods.展开更多
The multi-directional flow of energy in a multi-microgrid(MMG) system and different dispatching needs of multiple energy sources in time and location hinder the optimal operation coordination between microgrids. We pr...The multi-directional flow of energy in a multi-microgrid(MMG) system and different dispatching needs of multiple energy sources in time and location hinder the optimal operation coordination between microgrids. We propose an approach to centrally train all the agents to achieve coordinated control through an individual attention mechanism with a deep dense neural network for reinforcement learning. The attention mechanism and novel deep dense neural network allow each agent to attend to the specific information that is most relevant to its reward. When training is complete, the proposed approach can construct decisions to manage multiple energy sources within the MMG system in a fully decentralized manner. Using only local information, the proposed approach can coordinate multiple internal energy allocations within individual microgrids and external multilateral multi-energy interactions among interconnected microgrids to enhance the operational economy and voltage stability. Comparative results demonstrate that the cost achieved by the proposed approach is at most 71.1% lower than that obtained by other multi-agent deep reinforcement learning approaches.展开更多
基金financially supported by the National Natural Science Foundation of China(Grants nos.62201411,62371378,22205168,52302150 and 62304171)the China Postdoctoral Science Foundation(2022M722500)+1 种基金the Fundamental Research Funds for the Central Universities(Grants nos.ZYTS2308 and 20103237929)Startup Foundation of Xidian University(10251220001).
文摘Defects-rich heterointerfaces integrated with adjustable crystalline phases and atom vacancies,as well as veiled dielectric-responsive character,are instrumental in electromagnetic dissipation.Conventional methods,however,constrain their delicate constructions.Herein,an innovative alternative is proposed:carrageenan-assistant cations-regulated(CACR)strategy,which induces a series of sulfides nanoparticles rooted in situ on the surface of carbon matrix.This unique configuration originates from strategic vacancy formation energy of sulfides and strong sulfides-carbon support interaction,benefiting the delicate construction of defects-rich heterostructures in M_(x)S_(y)/carbon composites(M-CAs).Impressively,these generated sulfur vacancies are firstly found to strengthen electron accumulation/consumption ability at heterointerfaces and,simultaneously,induct local asymmetry of electronic structure to evoke large dipole moment,ultimately leading to polarization coupling,i.e.,defect-type interfacial polarization.Such“Janus effect”(Janus effect means versatility,as in the Greek two-headed Janus)of interfacial sulfur vacancies is intuitively confirmed by both theoretical and experimental investigations for the first time.Consequently,the sulfur vacancies-rich heterostructured Co/Ni-CAs displays broad absorption bandwidth of 6.76 GHz at only 1.8 mm,compared to sulfur vacancies-free CAs without any dielectric response.Harnessing defects-rich heterostructures,this one-pot CACR strategy may steer the design and development of advanced nanomaterials,boosting functionality across diverse application domains beyond electromagnetic response.
基金supported by the National Natural Science Foundation of China(No.U21A20293).
文摘Harnessing the redox potential of biochar to activate airborne O_(2)for contaminant removal is challenging.In this study,ferrihydrite(Fh)modified the boron(B),nitrogen(N)co-doped biochars(BCs)composites(Fh/B(n)NC)were developed for enhancing the degradation of a model pollutant,tetracycline(TC),merely by airborne O_(2).Fh/B(3)NC showed excellent O_(2)activation activity for efficient TC degradation with a apparent TC degradation rate of 5.54,6.88,and 22.15 times that of B(3)NC,Fh,and raw BCs,respectively,where 1O_(2)and H_(2)O_(2)were identified as the dominant ROS for TC degradation.The B incorporation into the carbon lattice of Fh/B(3)NC promoted the generation of electron donors,sp2 C and the reductive B species,hence boosting Fe(III)reduction and 1O_(2)generation.O_(2)adsorption was enhanced due to the positively charged adsorption sites(C-B+and N-C+).And 1O_(2)was generated via Fe(II)catalyzed low-efficient successive one-electron transfer(O_(2)→O_(2)·−→1O_(2),H_(2)O_(2)),as well as biochar catalyzed high-efficient two-electron transfer(O_(2)→H_(2)O_(2)→1O_(2))that does not involve.O_(2)−as the intermediate.Moreover,Fh/B,N co-doped biochar showed a wide pH range,remarkable anti-interference capabilities,and effective detoxification.These findings shed new light on the development of environmentally benign BCs materials capable of degradading organic pollutants.
文摘Correction to:Nano-Micro Lett.(2025)17:24 https://doi.org/10.1007/s40820-024-01515-0 Following publication of the original article[1],the authors reported the author list needed to be updated because the last three author names were duplicated.The correct author list has been provided in this Correction.The original article[1]has been corrected.
基金This work was supported by the National Science and Technology Major Project during the 13th Five-Year Plan under Grant Number 2016ZX05060004.
文摘Due to the depletion of conventional energy reserves,there has been a global shift towards non-conventional energy sources.Shale oil and gas have emerged as key alternatives.These resources have dense and heterogeneous reservoirs,which require hydraulic fracturing to extract.This process depends on identifying optimal fracturing layers,also known as‘sweet spots’.However,there is currently no uniform standard for locating these sweet spots.This paper presents a new model for evaluating fracturability that aims to address the current gap in the field.The model utilizes a hierarchical analysis approach and a mutation model,and is distinct in its use of original logging data to generate a fracturability evaluation map.Using this paper’s shale fracturing sweet spot evaluation method based on a two-step mutation model,four wells in different blocks of Fuling and Nanchuan Districts in China were validated,and the results showed that the proportion of high-yielding wells on the sweet spot line could reach 97.6%,while the proportion of low-producing wells was only 78.67%.Meanwhile,the evaluation results of the model were compared with the microseismic data,and the matching results were consistent.
文摘Education is a great cause to achieve national prosperity, national rejuvenation and people’s happiness, and an important way to block the intergenerational transmission of poverty. Rural revitalization, education first. Rural children’s education is an important issue of rural revitalization. This paper takes rural children, especially left behind children and children in distress as the help objects, and uses the advantages of “Internet plus” to improve the system, strengthen family education guidance, integrate social love resources, etc., to solve the problems faced by rural children, such as no guidance in learning, lack of guidance in behavior, lack of care in life, promote the overall healthy development of rural children, and solve the problem of rural education backwardness.
基金supported in part by the National Natural Science Foundation of China under Grant Nos.72031006,72031007,and 72394375.
文摘The inpatient bed allocation that allows beds shared among different departments is an important and challenging problem for a healthcare system. When the objective function(s) and (some) constraints need to be estimated via expensive and noisy stochastic simulation, a simulation optimization algorithm is required to solve this problem. In literature, there is a heuristic algorithm highly customized for one specific inpatient bed allocation problem, and it performs quite well on that problem. However, its lack of theoretical convergence and high specialization may not give practitioners enough confidence to apply it on real inpatient bed allocation problems. To mitigate such issues, this paper proposes to use the empirical stochastic branch-and-bound (ESB&B) algorithm, which is theoretically convergent and suitable for relatively general problems. A modest improvement for the original ESB&B algorithm is made and how to adapt the ESB&B algorithm to inpatient bed allocation problems is presented. Numerical experiments reveal the generality and fairly satisfying performance of the ESB&B algorithm, and the superiority of the improved ESB&B algorithm over the original one.
基金supported by National Key R&D Program of China(2021YFC2103100)National Natural Science Foundation of China(22008090)+1 种基金Natural Science Foundation of Jiangsu Province(BK20180625)Postgraduate Research&Practice Innovation Program of Jiangsu Province[KYCX22_2329].
文摘Peptide vaccines based on tumor antigens face the challenges of rapid clearance of peptides,low immunogenicity,and immune suppressive tumor microenvironment.However,the traditional solution mainly uses exogenous substances as adjuvants or carriers to enhance innate immune responses,but excessive inflammation can damage adaptive immunity.In the current study,we propose a straightforward novel nanovaccine strategy by employing homologous human ferritin light chain for minimized innate immunity and dendritic cell(DC)targeting,the cationic KALA peptide for enhanced cellular uptake,and suppressor of cytokine signaling 1(SOCS1)siRNA for modulating DC activity.Upon fusing with the KALA peptide,this nanovaccine presents as a novel 40-mer cage structure,with highly enriched antigen peptides of proper size(25 nm)for targeted delivery to lymph nodes.The loading of SOCS1 siRNA onto the KALA peptide promoted DC maturation in tumor environment,leading to a 3-fold increase in antigen presentation compared to alum adjuvant.Moreover,it demonstrates remarkable efficacy in suppressing tumor progression and metastasis,together with prolonged survival.In addition,the nanovaccine stimulates up to 40%memory T cells,thereby achieving sustained protection against tumor re-challenge.This unprecedented nanovaccine platform can ignite fresh interdisciplinary discussions on interactive strategies for future peptide vaccine development.
基金the Natural Science Foundation of Anhui Province(Nos.2108085MB55 and 2208085MB24)the National Natural Science Foundation of China(Nos.21571001,21706048,and 21701001)the Natural Science Research Project of Anhui Province(Nos.KJ2021A0004 and KJ2020ZD04).
文摘The synthesis of atomically ordered Pt-based intermetallic electrocatalysts for the direct alcohol fuel cells generally requires the addition of surfactants or the high-temperature annealing.However,some residual surfactants on the surface of the assynthesized catalysts would prevent the exposure of catalytic active sites,the high-temperature annealing process is easy to accelerate the sintering of the metal,which both lead to the decline of electrocatalytic performance.Herein,we construct the atomically ordered bimetallic PtBi intermetallics with clean surfaces and unique three-dimensional hollow acorn-shell-like structure(3D PtBi HASL)by a simple,low-temperature,surfactant-free one-pot synthetic approach.Benefiting from the special hollow structures,the obtained 3D PtBi HASL intermetallics expose abundant accessible active sites.Moreover,the introduction of oxophilic metal Bi can enhance adsorption of OHads,thereby significantly facilitating removal of poisoned intermediates.Density functional theory(DFT)simulations further indicate that formation of the PtBi intermetallic phase with the downshift of the Pt d-band center endows 3D Pt49.4Bi50.6 HASL intermetallics with significantly attenuated COads and enhanced OHads adsorption,bringing about the boosting electrocatalytic property.The mass activity of the 3D Pt49.4Bi50.6 HASL intermetallics for ethylene glycol oxidation reaction is as high as 24.67 A·mgPt^(−1),which is 12.98 times higher than that of commercial Pt/C(1.90 A·mgPt^(−1)).This work may inspire the design of Pt-based intermetallics as high-efficiency anode electrocatalysts for fuel cell applications.
基金supported by the National Natural Science Foundation of China(Nos.61971436,61972410,and 61803382)the Natural Science Basic Research Plan in Shaanxi Province of China(No.2018020JQ6020)+1 种基金the Research Plan of National University of Defense Technology(Nos.ZK19-13 and 19-QNCXJ-107)the Postgraduate Scientific Research Innovation Project of Hunan Province(No.CX20200003)。
文摘Remarkable progress has been made in satellite-based quantum key distribution [QKD],which can effectively provide QKD service even at the intercontinental scale and construct an ultralong-distance global quantum network.But there are still some places where terrestrial fiber and ground stations cannot be constructed,like harsh mountainous areas and air space above the sea.So the airborne platform is expected to replace the ground station and provide flexible and relay links for the large-scale integrated communication network.However,the photon transmission rate would be randomly reduced,owing to the randomly distributed boundary layer that surrounds the surface of the aircraft when the flight speed is larger than0.3 Ma.Previous research of airborne QKD with boundary layer effects is mainly under the air-to-ground scenario in which the aircraft is a transmitter,while the satellite-to-aircraft scenario is rarely reported.In this article,we propose a performance evaluation scheme of satellite-to-aircraft QKD with boundary layer effects in which the aircraft is the receiver.With common experimental settings,the boundary layer would introduce a ~31 dB loss to the transmitted photons,decrease ~47% of the quantum communication time,and decrease ~51% of the secure key rate,which shows that the aero-optical effects caused by the boundary layer cannot be ignored.Our study can be performed in future airborne quantum communication designs.
基金supported by the Sichuan Science and Technology Program(No.2020JDJQ0037)。
文摘A time-variable time-of-use electricity price can be used to reduce the charging costs for electric vehicle(EV)owners.Considering the uncertainty of price fluctuation and the randomness of EV owner’s commuting behavior,we propose a deep reinforcement learning based method for the minimization of individual EV charging cost.The charging problem is first formulated as a Markov decision process(MDP),which has unknown transition probability.A modified long short-term memory(LSTM)neural network is used as the representation layer to extract temporal features from the electricity price signal.The deep deterministic policy gradient(DDPG)algorithm,which has continuous action spaces,is used to solve the MDP.The proposed method can automatically adjust the charging strategy according to electricity price to reduce the charging cost of the EV owner.Several other methods to solve the charging problem are also implemented and quantitatively compared with the proposed method which can reduce the charging cost up to 70.2%compared with other benchmark methods.
基金supported by Sichuan Province Innovative Talent Funding Project for Postdoctoral Fellows (No. BX202210)。
文摘The multi-directional flow of energy in a multi-microgrid(MMG) system and different dispatching needs of multiple energy sources in time and location hinder the optimal operation coordination between microgrids. We propose an approach to centrally train all the agents to achieve coordinated control through an individual attention mechanism with a deep dense neural network for reinforcement learning. The attention mechanism and novel deep dense neural network allow each agent to attend to the specific information that is most relevant to its reward. When training is complete, the proposed approach can construct decisions to manage multiple energy sources within the MMG system in a fully decentralized manner. Using only local information, the proposed approach can coordinate multiple internal energy allocations within individual microgrids and external multilateral multi-energy interactions among interconnected microgrids to enhance the operational economy and voltage stability. Comparative results demonstrate that the cost achieved by the proposed approach is at most 71.1% lower than that obtained by other multi-agent deep reinforcement learning approaches.
