This study proposes a hybrid network model based on data enhancement to address the problem of low accuracy in photovoltaic(PV)power prediction that arises due to insuffi cient data samples for new PV plants.First,a t...This study proposes a hybrid network model based on data enhancement to address the problem of low accuracy in photovoltaic(PV)power prediction that arises due to insuffi cient data samples for new PV plants.First,a time-series gener ative adversarial network(TimeGAN)is used to learn the distri bution law of the original PV data samples and the temporal correlations between their features,and these are then used to generate new samples to enhance the training set.Subsequently,a hybrid network model that fuses bi-directional long-short term memory(BiLSTM)network with attention mechanism(AM)in the framework of deep&cross network(DCN)is con structed to effectively extract deep information from the origi nal features while enhancing the impact of important informa tion on the prediction results.Finally,the hyperparameters in the hybrid network model are optimized using the whale optimi zation algorithm(WOA),which prevents the network model from falling into a local optimum and gives the best prediction results.The simulation results show that after data enhance ment by TimeGAN,the hybrid prediction model proposed in this paper can effectively improve the accuracy of short-term PV power prediction and has wide applicability.展开更多
With integration of large-scale renewable energy,new controllable devices,and required reinforcement of power grids,modern power systems have typical characteristics such as uncertainty,vulnerability and openness,whic...With integration of large-scale renewable energy,new controllable devices,and required reinforcement of power grids,modern power systems have typical characteristics such as uncertainty,vulnerability and openness,which makes operation and control of power grids face severe security challenges.Application of artificial intelligence(AI)technologies represented by machine learning in power grid regulation is limited by reliability,interpretability and generalization ability of complex modeling.Mode of hybrid-augmented intelligence(HAI)based on human-machine collaboration(HMC)is a pivotal direction for future development of AI technology in this field.Based on characteristics of applications in power grid regulation,this paper discusses system architecture and key technologies of human-machine hybrid-augmented intelligence(HHI)system for large-scale power grid dispatching and control(PGDC).First,theory and application scenarios of HHI are introduced and analyzed;then physical and functional architectures of HHI system and human-machine collaborative regulation process are proposed.Key technologies are discussed to achieve a thorough integration of human/machine intelligence.Finally,state-of-theart and future development of HHI in power grid regulation are summarized,aiming to efficiently improve the intelligent level of power grid regulation in a human-machine interactive and collaborative way.展开更多
In large-scale data centers, many servers are in- terconnected via a dedicated networking structure, so as to satisfy specific design goals, such as the low equipment cost, the high network capacity, and the increment...In large-scale data centers, many servers are in- terconnected via a dedicated networking structure, so as to satisfy specific design goals, such as the low equipment cost, the high network capacity, and the incremental expansion. The topological properties of a networking structure are criti- cal factors that dominate the performance of the entire data center. The existing networking structures are either fully random or completely structured. Although such networking structures exhibit advantages on given aspects, they suffer ob- vious shortcomings in other essential fields. In this paper, we aim to design a hybrid topology, called R3, which is the com- pound graph of structured and random topology. It employs random regular graph as a unit duster and connects many such clusters by means of a structured topology, i.e., the gen- eralized hypercube. Consequently, the hybrid topology com- bines the advantages of structured as well as random topolo- gies seamlessly. Meanwhile, a coloring-based algorithm is proposed for R3 to enable fast and accurate routing. R3 pos- sesses many attractive characteristics, such as the modularity and expansibility at the cost of only increasing the degree of any node by one. Comprehensive evaluation results show that our hybrid topology possesses excellent topology properties and network performance.展开更多
Ex-situ cultivation of biological soil crusts （biocrusts） is a promising technology to produce materials that can induce the recovery of biocrusts in the field for the purposes of preventing soil erosion and improvi...Ex-situ cultivation of biological soil crusts （biocrusts） is a promising technology to produce materials that can induce the recovery of biocrusts in the field for the purposes of preventing soil erosion and improving hydrological function in degraded ecosystems. However, the ability of artificially cultivated biocrusts to survive under adverse field conditions, including drought and heat stresses, is still relatively unknown. Mosses can bolster biocrust resistance to the stresses （e.g., drought and heat） and the resistance may be introduced prior to field cultivation. In this study, we subjected the well-developed artificial moss biocrusts （dominant species of Didjmodon vinealis （Brid.） Zand.） that we cultivated in the phytotron to a dehydration-rehydration experiment and also a heat stress experiment and measured the activities of protective enzymes （including peroxidase （POD）, superoxide dismutase （SOD）, and catalase （CAT）） and the contents of osmoregulatory substances （including soluble proteins and soluble sugars） and malondialdehyde （MDA, an indicator of oxidative stress） in the stem and leaf fragments of mosses. The results showed that, during the dehydration process, the activities of protective enzymes and the contents of osmoregulatory substances and MDA gradually increased with increasing duration of drought stress （over 13 days）. During the rehydration process, values of these parameters decreased rapidly after 1 d of rehydration. The values then showed a gradual decrease for 5 days, approaching to the control levels. Under heat stress （45℃）, the activities of protective enzymes and the content of soluble proteins increased rapidly within 2 h of heat exposure and then decreased gradually with increasing duration of heat exposure. In contrast, the contents of soluble sugars and MDA always increased gradually with increasing duration of heat exposure. This study indicates that artificial moss biocrusts possess a strong drought resistance and this resistance can be enhanced after a gradual dehydration treatment. This study also indicates that artificial moss biocrusts can only resist short-term heat stress （not long-term heat stress）. These findings suggest that short-term heat stress or prolonged drought stress could be used to elevate the resistance of artificial moss biocrusts to adverse conditions prior to field reintroduction.展开更多
基金supported by the Regional Innovation and Development Joint Fund of National Natural Science Foundation of China(No.U19A20106)the Science and Technology Major Projects of Anhui Province(No.202203f07020003)the Science and Technology Project of State Grid Corporation of China(No.52120522000F).
文摘This study proposes a hybrid network model based on data enhancement to address the problem of low accuracy in photovoltaic(PV)power prediction that arises due to insuffi cient data samples for new PV plants.First,a time-series gener ative adversarial network(TimeGAN)is used to learn the distri bution law of the original PV data samples and the temporal correlations between their features,and these are then used to generate new samples to enhance the training set.Subsequently,a hybrid network model that fuses bi-directional long-short term memory(BiLSTM)network with attention mechanism(AM)in the framework of deep&cross network(DCN)is con structed to effectively extract deep information from the origi nal features while enhancing the impact of important informa tion on the prediction results.Finally,the hyperparameters in the hybrid network model are optimized using the whale optimi zation algorithm(WOA),which prevents the network model from falling into a local optimum and gives the best prediction results.The simulation results show that after data enhance ment by TimeGAN,the hybrid prediction model proposed in this paper can effectively improve the accuracy of short-term PV power prediction and has wide applicability.
基金supported by the National Key R&D Program of China(2018AAA0101500).
文摘With integration of large-scale renewable energy,new controllable devices,and required reinforcement of power grids,modern power systems have typical characteristics such as uncertainty,vulnerability and openness,which makes operation and control of power grids face severe security challenges.Application of artificial intelligence(AI)technologies represented by machine learning in power grid regulation is limited by reliability,interpretability and generalization ability of complex modeling.Mode of hybrid-augmented intelligence(HAI)based on human-machine collaboration(HMC)is a pivotal direction for future development of AI technology in this field.Based on characteristics of applications in power grid regulation,this paper discusses system architecture and key technologies of human-machine hybrid-augmented intelligence(HHI)system for large-scale power grid dispatching and control(PGDC).First,theory and application scenarios of HHI are introduced and analyzed;then physical and functional architectures of HHI system and human-machine collaborative regulation process are proposed.Key technologies are discussed to achieve a thorough integration of human/machine intelligence.Finally,state-of-theart and future development of HHI in power grid regulation are summarized,aiming to efficiently improve the intelligent level of power grid regulation in a human-machine interactive and collaborative way.
文摘In large-scale data centers, many servers are in- terconnected via a dedicated networking structure, so as to satisfy specific design goals, such as the low equipment cost, the high network capacity, and the incremental expansion. The topological properties of a networking structure are criti- cal factors that dominate the performance of the entire data center. The existing networking structures are either fully random or completely structured. Although such networking structures exhibit advantages on given aspects, they suffer ob- vious shortcomings in other essential fields. In this paper, we aim to design a hybrid topology, called R3, which is the com- pound graph of structured and random topology. It employs random regular graph as a unit duster and connects many such clusters by means of a structured topology, i.e., the gen- eralized hypercube. Consequently, the hybrid topology com- bines the advantages of structured as well as random topolo- gies seamlessly. Meanwhile, a coloring-based algorithm is proposed for R3 to enable fast and accurate routing. R3 pos- sesses many attractive characteristics, such as the modularity and expansibility at the cost of only increasing the degree of any node by one. Comprehensive evaluation results show that our hybrid topology possesses excellent topology properties and network performance.
基金supported by the National Natural Science Foundation of China(41541008,41671276)the Chinese Universities Scientific Fund(2014YQ006)+1 种基金the West Light Foundation of the Chinese Academy of Sciences(2014-91)the Natural Science Foundation of Qinghai Province(2016-ZJ-943Q)
文摘Ex-situ cultivation of biological soil crusts （biocrusts） is a promising technology to produce materials that can induce the recovery of biocrusts in the field for the purposes of preventing soil erosion and improving hydrological function in degraded ecosystems. However, the ability of artificially cultivated biocrusts to survive under adverse field conditions, including drought and heat stresses, is still relatively unknown. Mosses can bolster biocrust resistance to the stresses （e.g., drought and heat） and the resistance may be introduced prior to field cultivation. In this study, we subjected the well-developed artificial moss biocrusts （dominant species of Didjmodon vinealis （Brid.） Zand.） that we cultivated in the phytotron to a dehydration-rehydration experiment and also a heat stress experiment and measured the activities of protective enzymes （including peroxidase （POD）, superoxide dismutase （SOD）, and catalase （CAT）） and the contents of osmoregulatory substances （including soluble proteins and soluble sugars） and malondialdehyde （MDA, an indicator of oxidative stress） in the stem and leaf fragments of mosses. The results showed that, during the dehydration process, the activities of protective enzymes and the contents of osmoregulatory substances and MDA gradually increased with increasing duration of drought stress （over 13 days）. During the rehydration process, values of these parameters decreased rapidly after 1 d of rehydration. The values then showed a gradual decrease for 5 days, approaching to the control levels. Under heat stress （45℃）, the activities of protective enzymes and the content of soluble proteins increased rapidly within 2 h of heat exposure and then decreased gradually with increasing duration of heat exposure. In contrast, the contents of soluble sugars and MDA always increased gradually with increasing duration of heat exposure. This study indicates that artificial moss biocrusts possess a strong drought resistance and this resistance can be enhanced after a gradual dehydration treatment. This study also indicates that artificial moss biocrusts can only resist short-term heat stress （not long-term heat stress）. These findings suggest that short-term heat stress or prolonged drought stress could be used to elevate the resistance of artificial moss biocrusts to adverse conditions prior to field reintroduction.
