There is a growing awareness among industry players of reaping the benefits of mobile-cloud convergence by extending today's unmodified cloud to a decentralized two-level cloud-cloudlet architecture based on emerg...There is a growing awareness among industry players of reaping the benefits of mobile-cloud convergence by extending today's unmodified cloud to a decentralized two-level cloud-cloudlet architecture based on emerging mobile-edge computing(MEC) capabilities. In light of future 5G mobile networks moving toward decentralization based on cloudlets, intelligent base stations, and MEC, the inherent distributed processing and storage capabilities of radio-and-fiber(R&F) networks may be exploited for new applications, e.g., cognitive assistance, augmented reality, or cloud robotics. In this paper, we first revisit fiber-wireless(Fi Wi) networks in the context of conventional clouds and emerging cloudlets, thereby highlighting the limitations of conventional radio-overfiber(Ro F) networks such as China Mobile's centralized cloud radio access network(C-RAN) to meet the aforementioned trends. Furthermore, we pay close attention to the specific design challenges of data center networks and revisit our switchless arrayedwaveguide grating(AWG) based network with efficient support of east-west flows and enhanced scalability.展开更多
In silicon-oxide-nitride-oxide-silicon （SONOS） memory and other charge trapping memories, the charge distribution after programming operation has great impact on the devic＇s characteristics,such as reading,programm...In silicon-oxide-nitride-oxide-silicon （SONOS） memory and other charge trapping memories, the charge distribution after programming operation has great impact on the devic＇s characteristics,such as reading,programming/erasing, and reliability. The lateral distribution of injected charges can be measured precisely using the charge pumping method. To improve the precision of the actual measurement, a combination of a constant low voltage method and a constant high voltage method is introduced during the charge pumping testing of the drain side and the source side, respectively. Finally, the electron distribution after channel hot electron programming in SONOS memory is obtained,which is close to the drain side with a width of about 50nm.展开更多
To reduce the time required to complete the regeneration process of erasure codes, we propose a Tree-structured Parallel Regeneration (TPR) scheme for multiple data losses in distributed storage systems. Under the sch...To reduce the time required to complete the regeneration process of erasure codes, we propose a Tree-structured Parallel Regeneration (TPR) scheme for multiple data losses in distributed storage systems. Under the scheme, two algorithms are proposed for the construction of multiple regeneration trees, namely the edge-disjoint algorithm and edge-sharing algorithm. The edge-disjoint algorithm constructs multiple independent trees, and is simple and appropriate for environments where newcomers and their providers are distributed over a large area and have few intersections. The edge-sharing algorithm constructs multiple trees that compete to utilize the bandwidth, and make a better utilization of the bandwidth, although it needs to measure the available band-width and deal with the bandwidth changes; it is therefore difficult to implement in practical systems. The parallel regeneration for multiple data losses of TPR primarily includes two optimizations: firstly, transferring the data through the bandwidth optimized-paths in a pipe-line manner; secondly, executing data regeneration over multiple trees in parallel. To evaluate the proposal, we implement an event-based simulator and make a detailed comparison with some popular regeneration methods. The quantitative comparison results show that the use of TPR employing either the edge-disjoint algorithm or edge-sharing algorithm reduces the regeneration time significantly.展开更多
文摘There is a growing awareness among industry players of reaping the benefits of mobile-cloud convergence by extending today's unmodified cloud to a decentralized two-level cloud-cloudlet architecture based on emerging mobile-edge computing(MEC) capabilities. In light of future 5G mobile networks moving toward decentralization based on cloudlets, intelligent base stations, and MEC, the inherent distributed processing and storage capabilities of radio-and-fiber(R&F) networks may be exploited for new applications, e.g., cognitive assistance, augmented reality, or cloud robotics. In this paper, we first revisit fiber-wireless(Fi Wi) networks in the context of conventional clouds and emerging cloudlets, thereby highlighting the limitations of conventional radio-overfiber(Ro F) networks such as China Mobile's centralized cloud radio access network(C-RAN) to meet the aforementioned trends. Furthermore, we pay close attention to the specific design challenges of data center networks and revisit our switchless arrayedwaveguide grating(AWG) based network with efficient support of east-west flows and enhanced scalability.
文摘In silicon-oxide-nitride-oxide-silicon （SONOS） memory and other charge trapping memories, the charge distribution after programming operation has great impact on the devic＇s characteristics,such as reading,programming/erasing, and reliability. The lateral distribution of injected charges can be measured precisely using the charge pumping method. To improve the precision of the actual measurement, a combination of a constant low voltage method and a constant high voltage method is introduced during the charge pumping testing of the drain side and the source side, respectively. Finally, the electron distribution after channel hot electron programming in SONOS memory is obtained,which is close to the drain side with a width of about 50nm.
基金supported by the National Grand Fundamental Research of China (973 Program) under Grant No. 2011CB302601the National High Technology Research and Development of China (863 Program) under GrantNo. 2013AA01A213+2 种基金the National Natural Science Foundation of China under Grant No. 60873215the Natural Science Foundation for Distinguished Young Scholars of Hunan Province under Grant No. S2010J5050Specialized Research Fund for the Doctoral Program of Higher Education under Grant No. 20124307110015
文摘To reduce the time required to complete the regeneration process of erasure codes, we propose a Tree-structured Parallel Regeneration (TPR) scheme for multiple data losses in distributed storage systems. Under the scheme, two algorithms are proposed for the construction of multiple regeneration trees, namely the edge-disjoint algorithm and edge-sharing algorithm. The edge-disjoint algorithm constructs multiple independent trees, and is simple and appropriate for environments where newcomers and their providers are distributed over a large area and have few intersections. The edge-sharing algorithm constructs multiple trees that compete to utilize the bandwidth, and make a better utilization of the bandwidth, although it needs to measure the available band-width and deal with the bandwidth changes; it is therefore difficult to implement in practical systems. The parallel regeneration for multiple data losses of TPR primarily includes two optimizations: firstly, transferring the data through the bandwidth optimized-paths in a pipe-line manner; secondly, executing data regeneration over multiple trees in parallel. To evaluate the proposal, we implement an event-based simulator and make a detailed comparison with some popular regeneration methods. The quantitative comparison results show that the use of TPR employing either the edge-disjoint algorithm or edge-sharing algorithm reduces the regeneration time significantly.
