Artificial intelligence(AI)-native communication is considered one of the key technologies for the development of 6G mobile communication networks.This paper investigates the architecture for developing the network da...Artificial intelligence(AI)-native communication is considered one of the key technologies for the development of 6G mobile communication networks.This paper investigates the architecture for developing the network data analytics function(NWDAF)in 6G AI-native networks.The architecture integrates two key components:data collection and management,and model training and management.It achieves real-time data collection and management,establishing a complete workflow encompassing AI model training,deployment,and intelligent decision-making.The architecture workflow is evaluated through a vertical scaling use case by constructing an AI-native network testbed on Kubernetes.Within this proposed NWDAF,several machine learning(ML)models are trained to make vertical scaling decisions for user plane function(UPF)instances based on data collected from various network functions(NFs).These decisions are executed through the Ku-bernetes API,which dynamically allocates appropriate resources to UPF instances.The experimental results show that all implemented models demonstrate satisfactory predictive capabilities.Moreover,compared with the threshold-based method in Kubernetes,all models show a significant advantage in response time.This study not only introduces a novel AI-native NWDAF architecture but also demonstrates the potential of AI models to significantly improve network management and resource scaling in 6G networks.展开更多
Conducting scientific drilling on subglacial lakes and obtaining samples of subglacial lake water holds great significance in unraveling the formation and evolution of Antarctic subglacial lakes and early Earth's ...Conducting scientific drilling on subglacial lakes and obtaining samples of subglacial lake water holds great significance in unraveling the formation and evolution of Antarctic subglacial lakes and early Earth's life forms.Despite various approaches to access and directly sample subglacial water and sediments,clean access and exploration of subglacial lakes remain challenging.To address this concern,Jilin University has developed the RECoverable Autonomous Sonde(RECAS)prototype.This technology enables sampling and in-situ detection of subglacial lake water while being isolated from the surface,thus minimizing the risk of pollution.Laboratory tests,including downward and upward drilling,long-running,remote-control,and cold-environment assessments,were conducted to validate the sonde's principle and functionality.During the 38th Chinese National Antarctic Research Expedition,CHINARE(2021–2022 season),the RECAS prototype underwent testing on the flank region of Dalk glacier,10 km from Zhongshan Station in Antarctica.Three boreholes with depths of 200.3,183.2,and 133.5 m were successfully drilled,with the refrozen meltwater sealing the boreholes during the process.Approximately 600 mL of melted water samples were collected from each hole.Throughout the drilling tests,all systems of the RECAS prototype performed within the expected ranges.展开更多
基金supported by the National Key Research and Development Program of China under Grant No.2023YFE0200700National Natural Science Foundation of China under Grant No.62171474ZTE Industry University-Institute Cooperation Funds under Grant No.IA20241014013。
文摘Artificial intelligence(AI)-native communication is considered one of the key technologies for the development of 6G mobile communication networks.This paper investigates the architecture for developing the network data analytics function(NWDAF)in 6G AI-native networks.The architecture integrates two key components:data collection and management,and model training and management.It achieves real-time data collection and management,establishing a complete workflow encompassing AI model training,deployment,and intelligent decision-making.The architecture workflow is evaluated through a vertical scaling use case by constructing an AI-native network testbed on Kubernetes.Within this proposed NWDAF,several machine learning(ML)models are trained to make vertical scaling decisions for user plane function(UPF)instances based on data collected from various network functions(NFs).These decisions are executed through the Ku-bernetes API,which dynamically allocates appropriate resources to UPF instances.The experimental results show that all implemented models demonstrate satisfactory predictive capabilities.Moreover,compared with the threshold-based method in Kubernetes,all models show a significant advantage in response time.This study not only introduces a novel AI-native NWDAF architecture but also demonstrates the potential of AI models to significantly improve network management and resource scaling in 6G networks.
基金supported by the National Key Research and Development Project of the Ministry of Science and Technology of China(Grant Nos.2016YFC1400302,2023YFC2812602)the National Natural Science Foundation of China(Grant No.41941005)。
文摘Conducting scientific drilling on subglacial lakes and obtaining samples of subglacial lake water holds great significance in unraveling the formation and evolution of Antarctic subglacial lakes and early Earth's life forms.Despite various approaches to access and directly sample subglacial water and sediments,clean access and exploration of subglacial lakes remain challenging.To address this concern,Jilin University has developed the RECoverable Autonomous Sonde(RECAS)prototype.This technology enables sampling and in-situ detection of subglacial lake water while being isolated from the surface,thus minimizing the risk of pollution.Laboratory tests,including downward and upward drilling,long-running,remote-control,and cold-environment assessments,were conducted to validate the sonde's principle and functionality.During the 38th Chinese National Antarctic Research Expedition,CHINARE(2021–2022 season),the RECAS prototype underwent testing on the flank region of Dalk glacier,10 km from Zhongshan Station in Antarctica.Three boreholes with depths of 200.3,183.2,and 133.5 m were successfully drilled,with the refrozen meltwater sealing the boreholes during the process.Approximately 600 mL of melted water samples were collected from each hole.Throughout the drilling tests,all systems of the RECAS prototype performed within the expected ranges.
