We study a novel replication mechanism to ensure service continuity against multiple simultaneous server failures.In this mechanism,each item represents a computing task and is replicated intoξ+1 servers for some int...We study a novel replication mechanism to ensure service continuity against multiple simultaneous server failures.In this mechanism,each item represents a computing task and is replicated intoξ+1 servers for some integerξ≥1,with workloads specified by the amount of required resources.If one or more servers fail,the affected workloads can be redirected to other servers that host replicas associated with the same item,such that the service is not interrupted by the failure of up toξservers.This requires that any feasible assignment algorithm must reserve some capacity in each server to accommodate the workload redirected from potential failed servers without overloading,and determining the optimal method for reserving capacity becomes a key issue.Unlike existing algorithms that assume that no two servers share replicas of more than one item,we first formulate capacity reservation for a general arbitrary scenario.Due to the combinatorial nature of this problem,finding the optimal solution is difficult.To this end,we propose a Generalized and Simple Calculating Reserved Capacity(GSCRC)algorithm,with a time complexity only related to the number of items packed in the server.In conjunction with GSCRC,we propose a robust replica packing algorithm with capacity optimization(RobustPack),which aims to minimize the number of servers hosting replicas and tolerate multiple server failures.Through theoretical analysis and experimental evaluations,we show that the RobustPack algorithm can achieve better performance.展开更多
Data center cooling systems are substantial energy consumers,and managing the heat generated by electronic devices is becoming more complex as chip power levels continue to rise.The single-phase immersion cooling(SPIC...Data center cooling systems are substantial energy consumers,and managing the heat generated by electronic devices is becoming more complex as chip power levels continue to rise.The single-phase immersion cooling(SPIC)server with oil coolant is numerically investigated using the validated Re-Normalization Group(RNG)k-εmodel.For the investigated scenarios where coolant velocity at the tank inlet is 0.004 m/s and the total power is 740 W,the heat transfer between the heat sinks and the coolant is dominated by natural convection,although forced convection mediates the overall heat transfer inside the tank.The maximum velocity of coolant through the heat sink is 0.035 m/s and the average heat transfer coefficient is up to 75.8 W/(m2·K).The geometry of the heat sink is important for the cooling performance.Increasing both the fin thickness and number enhances the natural convection effect of the heat sink,but also increases the flow resistance.The heat sink with a fin thickness of 3 mm performs the best,reducing the average graphics processing unit(GPU)temperature from 71.3℃ to 68.6℃.A heat sink with an optimal fin number of 16 reduces the average GPU temperature to 67.7℃.As for the effect of fin height,increasing it from 15 to 30 mm results in increases in the heat transfer area and flow rate by about 72%and 32%,respectively,which reduces the average GPU temperature to 65.2℃.Therefore,the importance of fin parameters ranks in the following order:fin height,number,and thickness.This study highlights the potential application of oil coolants in SPIC systems and offers theoretical guidance for the efficient design of natural convection cooling solutions.展开更多
深入探讨了一种嵌入式云开发平台的虚拟机管理技术,通过结合Visual Studio Code插件开发框架、Spring Boot、Libvirt、QEMU等技术,实现了基于QEMU的虚拟机创建、销毁、重启等操作。详细介绍了该系统的设计与实现,包括虚拟机管理模块的...深入探讨了一种嵌入式云开发平台的虚拟机管理技术,通过结合Visual Studio Code插件开发框架、Spring Boot、Libvirt、QEMU等技术,实现了基于QEMU的虚拟机创建、销毁、重启等操作。详细介绍了该系统的设计与实现,包括虚拟机管理模块的架构设计、功能实现及技术细节。基于该研究成果,嵌入式开发人员可以在云开发平台中直接进行虚拟机管理操作,从而提高嵌入式系统开发的效率和便捷性。展开更多
Data privacy leakage has always been a critical concern in cloud-based Internet of Things(IoT)systems.Dynamic Symmetric Searchable Encryption(DSSE)with forward and backward privacy aims to address this issue by enabli...Data privacy leakage has always been a critical concern in cloud-based Internet of Things(IoT)systems.Dynamic Symmetric Searchable Encryption(DSSE)with forward and backward privacy aims to address this issue by enabling updates and retrievals of ciphertext on untrusted cloud server while ensuring data privacy.However,previous research on DSSE mostly focused on single keyword search,which limits its practical application in cloud-based IoT systems.Recently,Patranabis(NDSS 2021)[1]proposed a groundbreaking DSSE scheme for conjunctive keyword search.However,this scheme fails to effectively handle deletion operations in certain circumstances,resulting in inaccurate query results.Additionally,the scheme introduces unnecessary search overhead.To overcome these problems,we present CKSE,an efficient conjunctive keyword DSSE scheme.Our scheme improves the oblivious shared computation protocol used in the scheme of Patranabis,thus enabling a more comprehensive deletion functionality.Furthermore,we introduce a state chain structure to reduce the search overhead.Through security analysis and experimental evaluation,we demonstrate that our CKSE achieves more comprehensive deletion functionality while maintaining comparable search performance and security,compared to the oblivious dynamic cross-tags protocol of Patranabis.The combination of comprehensive functionality,high efficiency,and security makes our CKSE an ideal choice for deployment in cloud-based IoT systems.展开更多
基金supported in part by the National Key R&D Program of China under No.2023YFB2703800the National Science Foundation of China under Grants U22B2027,62172297,62102262,61902276 and 62272311+3 种基金Tianjin Intelligent Manufacturing Special Fund Project under Grants 20211097the China Guangxi Science and Technology Plan Project(Guangxi Science and Technology Base and Talent Special Project)under Grant AD23026096(Application Number 2022AC20001)Henan Provincial Natural Science Foundation of China under Grant 622RC616CCF-Nsfocus Kunpeng Fund Project under Grants CCF-NSFOCUS202207。
文摘We study a novel replication mechanism to ensure service continuity against multiple simultaneous server failures.In this mechanism,each item represents a computing task and is replicated intoξ+1 servers for some integerξ≥1,with workloads specified by the amount of required resources.If one or more servers fail,the affected workloads can be redirected to other servers that host replicas associated with the same item,such that the service is not interrupted by the failure of up toξservers.This requires that any feasible assignment algorithm must reserve some capacity in each server to accommodate the workload redirected from potential failed servers without overloading,and determining the optimal method for reserving capacity becomes a key issue.Unlike existing algorithms that assume that no two servers share replicas of more than one item,we first formulate capacity reservation for a general arbitrary scenario.Due to the combinatorial nature of this problem,finding the optimal solution is difficult.To this end,we propose a Generalized and Simple Calculating Reserved Capacity(GSCRC)algorithm,with a time complexity only related to the number of items packed in the server.In conjunction with GSCRC,we propose a robust replica packing algorithm with capacity optimization(RobustPack),which aims to minimize the number of servers hosting replicas and tolerate multiple server failures.Through theoretical analysis and experimental evaluations,we show that the RobustPack algorithm can achieve better performance.
基金supported by the Basic Research Funds for the Central Government“Innovative Team of Zhejiang University”under contract number(2022FZZX01-09).
文摘Data center cooling systems are substantial energy consumers,and managing the heat generated by electronic devices is becoming more complex as chip power levels continue to rise.The single-phase immersion cooling(SPIC)server with oil coolant is numerically investigated using the validated Re-Normalization Group(RNG)k-εmodel.For the investigated scenarios where coolant velocity at the tank inlet is 0.004 m/s and the total power is 740 W,the heat transfer between the heat sinks and the coolant is dominated by natural convection,although forced convection mediates the overall heat transfer inside the tank.The maximum velocity of coolant through the heat sink is 0.035 m/s and the average heat transfer coefficient is up to 75.8 W/(m2·K).The geometry of the heat sink is important for the cooling performance.Increasing both the fin thickness and number enhances the natural convection effect of the heat sink,but also increases the flow resistance.The heat sink with a fin thickness of 3 mm performs the best,reducing the average graphics processing unit(GPU)temperature from 71.3℃ to 68.6℃.A heat sink with an optimal fin number of 16 reduces the average GPU temperature to 67.7℃.As for the effect of fin height,increasing it from 15 to 30 mm results in increases in the heat transfer area and flow rate by about 72%and 32%,respectively,which reduces the average GPU temperature to 65.2℃.Therefore,the importance of fin parameters ranks in the following order:fin height,number,and thickness.This study highlights the potential application of oil coolants in SPIC systems and offers theoretical guidance for the efficient design of natural convection cooling solutions.
文摘深入探讨了一种嵌入式云开发平台的虚拟机管理技术,通过结合Visual Studio Code插件开发框架、Spring Boot、Libvirt、QEMU等技术,实现了基于QEMU的虚拟机创建、销毁、重启等操作。详细介绍了该系统的设计与实现,包括虚拟机管理模块的架构设计、功能实现及技术细节。基于该研究成果,嵌入式开发人员可以在云开发平台中直接进行虚拟机管理操作,从而提高嵌入式系统开发的效率和便捷性。
基金supported in part by the Major Science and Technology Projects in Yunnan Province(202202AD080013)King Khalid University for funding this work through Large Group Project under grant number RGP.2/373/45.
文摘Data privacy leakage has always been a critical concern in cloud-based Internet of Things(IoT)systems.Dynamic Symmetric Searchable Encryption(DSSE)with forward and backward privacy aims to address this issue by enabling updates and retrievals of ciphertext on untrusted cloud server while ensuring data privacy.However,previous research on DSSE mostly focused on single keyword search,which limits its practical application in cloud-based IoT systems.Recently,Patranabis(NDSS 2021)[1]proposed a groundbreaking DSSE scheme for conjunctive keyword search.However,this scheme fails to effectively handle deletion operations in certain circumstances,resulting in inaccurate query results.Additionally,the scheme introduces unnecessary search overhead.To overcome these problems,we present CKSE,an efficient conjunctive keyword DSSE scheme.Our scheme improves the oblivious shared computation protocol used in the scheme of Patranabis,thus enabling a more comprehensive deletion functionality.Furthermore,we introduce a state chain structure to reduce the search overhead.Through security analysis and experimental evaluation,we demonstrate that our CKSE achieves more comprehensive deletion functionality while maintaining comparable search performance and security,compared to the oblivious dynamic cross-tags protocol of Patranabis.The combination of comprehensive functionality,high efficiency,and security makes our CKSE an ideal choice for deployment in cloud-based IoT systems.
