More and more embedded devices, such as mobile phones, tablet PCs and laptops, are used in every field, so huge files need to be stored or backed up into cloud storage. Optimizing the performance of cloud storage is v...More and more embedded devices, such as mobile phones, tablet PCs and laptops, are used in every field, so huge files need to be stored or backed up into cloud storage. Optimizing the performance of cloud storage is very important for Internet development. This paper presents the performance evaluation of the open source distributed storage system, a highly available, distributed, eventually consistent object/blob store from Open Stack cloud computing components. This paper mainly focuses on the mechanism of cloud storage as well as the optimization methods to process different sized files. This work provides two major contributions through comprehensive performance evaluations. First, it provides different configurations for Open Stack Swift system and an analysis of how every component affects the performance. Second, it presents the detailed optimization methods to improve the performance in processing different sized files. The experimental results show that our method improves the performance and the structure. We give the methods to optimize the object-based cloud storage system to deploy the readily available storage system.展开更多
This paper proposes a content addres sable storage optimization method, VDeskCAS, for desktop virtualization storage based disaster backup storage system. The method implements a blocklevel storage optimization, by em...This paper proposes a content addres sable storage optimization method, VDeskCAS, for desktop virtualization storage based disaster backup storage system. The method implements a blocklevel storage optimization, by employing the algorithms of chunking image file into blocks, the blockffmger calculation and the block dedup li cation. A File system in Use Space （FUSE） based storage process for VDeskCAS is also introduced which optimizes current direct storage to suit our content addressable storage. An interface level modification makes our system easy to extend. Experiments on virtual desktop image files and normal files verify the effectiveness of our method and above 60% storage volume decrease is a chieved for Red Hat Enterprise Linux image files. Key words： disaster backup; desktop virtualization; storage optimization; content addressable storage展开更多
Aiming to efficiently support theLocator/Identifier Separation Protocol(LISP),in this paper,we present an enhanced pointerbased DHT mapping system:LISP-PCHORD.The system creates a pointer space to build ontop of stand...Aiming to efficiently support theLocator/Identifier Separation Protocol(LISP),in this paper,we present an enhanced pointerbased DHT mapping system:LISP-PCHORD.The system creates a pointer space to build ontop of standard DHTs.Mappings within thepointer space are(Endpoint Identifiers(EID),pointers) where the pointer is the address ofthe root node(the physical node that stores themappings) of the corresponding(EID,RoutingLocators(RLOCs)) mappings.In addition toenabling architectural qualities such as scalability and reliability,the proposed LISP-PCHORDcan copy with flat EIDs such as self-certifyingEIDs.The performance of the mapping systemplays a key role in LISP;however,DHT-basedapproaches for LISP seldom consider the mismatch problem that heavily damages the system performance in terms of lookup latency.In order to mitigate the mismatch problem andachieve optimal performance,we propose anoptimization design method that seeks an optimal matching relationship between P-nodes(nodes within the pointer space) and the physical nodes on the basis of the given lookuptraffic matrix.In order to find the optimal matching relationship,we provide two solutions:a linear programming method and a geneticalgorithm.Finally,we evaluate the performance of the proposed scheme and compare itwith that of LISP-DHT.展开更多
Building energy analyses using forecasting optimization strategies are commonly used for predicting TES （thermal energy storage） system performance. These strategies produce perfect optimized cost savings and are no...Building energy analyses using forecasting optimization strategies are commonly used for predicting TES （thermal energy storage） system performance. These strategies produce perfect optimized cost savings and are not typically realized in the real world, unless a safety factor is applied. Rather than show how to improve the industry＇s ability to accurately model and simulate a true TES system design, this paper will show advanced building information strategies and energy management simulation techniques required to truly achieve the ideal optimized cost savings, determined from the TES energy simulation analysis. This paper uses the hospitality industry as a case study, showing the application of simulation and analytical modeling for an optimized partial TES system. As a result building energy managers can make better decisions through the entire building life cycle from the earliest concept model through operation and maintenance.展开更多
基金performed by key technology of networking media broadcast based on cloud computing in"China Twelfth Five-Year"Plan for Science&Technology Project(Grant No.:2013BAH65F01-2013BAH65F04)NSFC(Grant No.:61472144)+3 种基金National science and technology support plan(Grant No.:2013BAH65F03,2013BAH65F04)GDSTP(Grant No.:2013B010202004,2014A010103012)GDUPS(2011)Research Fund for the Doctoral Program of Higher Education of China(Grant No.:20120172110023)
文摘More and more embedded devices, such as mobile phones, tablet PCs and laptops, are used in every field, so huge files need to be stored or backed up into cloud storage. Optimizing the performance of cloud storage is very important for Internet development. This paper presents the performance evaluation of the open source distributed storage system, a highly available, distributed, eventually consistent object/blob store from Open Stack cloud computing components. This paper mainly focuses on the mechanism of cloud storage as well as the optimization methods to process different sized files. This work provides two major contributions through comprehensive performance evaluations. First, it provides different configurations for Open Stack Swift system and an analysis of how every component affects the performance. Second, it presents the detailed optimization methods to improve the performance in processing different sized files. The experimental results show that our method improves the performance and the structure. We give the methods to optimize the object-based cloud storage system to deploy the readily available storage system.
基金the Hi-tech Research and Development Program of China，the National Natural Science Foundation of China，the Beijing Natural Science Foundation，the Fundamental Research Funds for the Central Universities，the Fund of the State Key Laboratory of Software Development Environment
文摘This paper proposes a content addres sable storage optimization method, VDeskCAS, for desktop virtualization storage based disaster backup storage system. The method implements a blocklevel storage optimization, by employing the algorithms of chunking image file into blocks, the blockffmger calculation and the block dedup li cation. A File system in Use Space （FUSE） based storage process for VDeskCAS is also introduced which optimizes current direct storage to suit our content addressable storage. An interface level modification makes our system easy to extend. Experiments on virtual desktop image files and normal files verify the effectiveness of our method and above 60% storage volume decrease is a chieved for Red Hat Enterprise Linux image files. Key words： disaster backup; desktop virtualization; storage optimization; content addressable storage
基金supported by the National Key Basic Research Program of China(973Program) under Grant No.2007CB307100the National Natural Science Foundation of China under Grant No.61001084
文摘Aiming to efficiently support theLocator/Identifier Separation Protocol(LISP),in this paper,we present an enhanced pointerbased DHT mapping system:LISP-PCHORD.The system creates a pointer space to build ontop of standard DHTs.Mappings within thepointer space are(Endpoint Identifiers(EID),pointers) where the pointer is the address ofthe root node(the physical node that stores themappings) of the corresponding(EID,RoutingLocators(RLOCs)) mappings.In addition toenabling architectural qualities such as scalability and reliability,the proposed LISP-PCHORDcan copy with flat EIDs such as self-certifyingEIDs.The performance of the mapping systemplays a key role in LISP;however,DHT-basedapproaches for LISP seldom consider the mismatch problem that heavily damages the system performance in terms of lookup latency.In order to mitigate the mismatch problem andachieve optimal performance,we propose anoptimization design method that seeks an optimal matching relationship between P-nodes(nodes within the pointer space) and the physical nodes on the basis of the given lookuptraffic matrix.In order to find the optimal matching relationship,we provide two solutions:a linear programming method and a geneticalgorithm.Finally,we evaluate the performance of the proposed scheme and compare itwith that of LISP-DHT.
文摘Building energy analyses using forecasting optimization strategies are commonly used for predicting TES （thermal energy storage） system performance. These strategies produce perfect optimized cost savings and are not typically realized in the real world, unless a safety factor is applied. Rather than show how to improve the industry＇s ability to accurately model and simulate a true TES system design, this paper will show advanced building information strategies and energy management simulation techniques required to truly achieve the ideal optimized cost savings, determined from the TES energy simulation analysis. This paper uses the hospitality industry as a case study, showing the application of simulation and analytical modeling for an optimized partial TES system. As a result building energy managers can make better decisions through the entire building life cycle from the earliest concept model through operation and maintenance.
