Ben Lee - Academia.edu (original) (raw)

Papers by Ben Lee

Proceedings Ninth International Conference on Computer Communications and Networks (Cat.No.00EX440), 2000

A method for testing multi-protocol implementation under test (IUT) with a single test suite has ... more A method for testing multi-protocol implementation under test (IUT) with a single test suite has been proposed in the literature. It tests a multi-protocol IUT in an integrated way compared to the conventional method, where single-layer test method and single-layer embedded test method are applied separately to the upper layer protocol and lower layer protocol, respectively. However, it did not consider how to generate the test cases automatically but proposed only an approach for the test method. This paper proposes an algorithm called Multi-protocol Test Method (MPTM) for automatic test case generation based on that approach. With the MPTM, a multi-protocol IUT consisting of two protocol layers is modeled as two Finite State Machines (FSMs), and the relationships between the transitions of them are defined as a set of transition relationships, pre-execution and carried-by. The proposed algorithm is implemented and applied to a simplified TCPnP and B-ISDN Signaling/SSCOP. The MPTM is able to test the multiprotocol IUT even though the interfaces between the protocol layers are not exposed. It also allows the same test coverage as conventional test methods with much smaller number of test cases and operations.

Proceedings Ninth International Conference on Computer Communications and Networks (Cat.No.00EX440), 2000

A method for testing multi-protocol implementation under test (IUT) with a single test suite has ... more A method for testing multi-protocol implementation under test (IUT) with a single test suite has been proposed in the literature. It tests a multi-protocol IUT in an integrated way compared to the conventional method, where single-layer test method and single-layer embedded test method are applied separately to the upper layer protocol and lower layer protocol, respectively. However, it did not consider how to generate the test cases automatically but proposed only an approach for the test method. This paper proposes an algorithm called Multi-protocol Test Method (MPTM) for automatic test case generation based on that approach. With the MPTM, a multi-protocol IUT consisting of two protocol layers is modeled as two Finite State Machines (FSMs), and the relationships between the transitions of them are defined as a set of transition relationships, pre-execution and carried-by. The proposed algorithm is implemented and applied to a simplified TCPnP and B-ISDN Signaling/SSCOP. The MPTM is able to test the multiprotocol IUT even though the interfaces between the protocol layers are not exposed. It also allows the same test coverage as conventional test methods with much smaller number of test cases and operations.

Electrical Engineering Handbook, 2002

In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance meas... more In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance measures such as delay or packet delivery ratio since it directly affects the network lifetime. In this article we introduce two different approaches for energy efficient multicast protocols developed for MANETs. The first group of energy efficient multicast protocols is based on the assumption that the transmission power is controllable. Under this assumption, the problem of finding a tree with the least consumed power becomes a conventional optimization problem on a graph where the weighted link cost corresponds to the transmission power required for transmitting a packet between two nodes of the link. The second approach focuses on maximizing sleep mode operation supported by the lower level protocol. A mobile node in tree-based protocols can safely put itself into a low power sleep mode for conserving energy if it is not a designated receiver with the employed broadcast-based mesh protocols. It is shown that mesh-based protocols are more robust to mobility but tree-based protocols may be preferable when energy is a primary concern.

Electrical Engineering Handbook, 2002

In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance meas... more In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance measures such as delay or packet delivery ratio since it directly affects the network lifetime. In this article we introduce two different approaches for energy efficient multicast protocols developed for MANETs. The first group of energy efficient multicast protocols is based on the assumption that the transmission power is controllable. Under this assumption, the problem of finding a tree with the least consumed power becomes a conventional optimization problem on a graph where the weighted link cost corresponds to the transmission power required for transmitting a packet between two nodes of the link. The second approach focuses on maximizing sleep mode operation supported by the lower level protocol. A mobile node in tree-based protocols can safely put itself into a low power sleep mode for conserving energy if it is not a designated receiver with the employed broadcast-based mesh protocols. It is shown that mesh-based protocols are more robust to mobility but tree-based protocols may be preferable when energy is a primary concern.

Proceedings of the second international workshop on Mobility management & wireless access protocols - MobiWac '04, 2004

Session Initiation Protocol (SIP) was standardized for real-time applications and extended to sup... more Session Initiation Protocol (SIP) was standardized for real-time applications and extended to support terminal mobility by Internet Expert Task Force (IETF). However, SIP terminal mobility suffers from the considerable handoff latency which is unsuitable for the real-time communications. In this paper, we propose Predictive Address Reservation with SIP (PAR-SIP) which decreases handoff delay by proactively processing the address allocation and session update using link layer information of wireless networks.

Proceedings of the second international workshop on Mobility management & wireless access protocols - MobiWac '04, 2004

Proceedings International Conference on Parallel Processing

This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete mach... more This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete machine simulator from Stanford. The motivation for Linux/SimOS is to alleviate the limitations of SimOS, which only supports proprietary operating systems. The contributions made in this paper are twofold: First, the major modifications that were necessary to run Linux on SimOS are described. Second, a detailed analysis of the UDP/IP protocol and M-VIA is performed to demonstrate the capabilities of Linux/SimOS. The simulation study shows that Linux/SimOS is capable of capturing all aspects of communication performance, including the effects of the kernel, device drivers, and network interface.

Proceedings International Conference on Parallel Processing

This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete mach... more This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete machine simulator from Stanford. The motivation for Linux/SimOS is to alleviate the limitations of SimOS, which only supports proprietary operating systems. The contributions made in this paper are twofold: First, the major modifications that were necessary to run Linux on SimOS are described. Second, a detailed analysis of the UDP/IP protocol and M-VIA is performed to demonstrate the capabilities of Linux/SimOS. The simulation study shows that Linux/SimOS is capable of capturing all aspects of communication performance, including the effects of the kernel, device drivers, and network interface.

2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.

Fourth Annual IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOMW'06)

In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered unifo... more In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered uniformly across the network area. This paper considers the clustering of peer nodes and its performance impact in MP2P networks. The model for node clustering based on a heavy-tail distribution is first introduced and then a topology generation method that produces a clustered network is presented. Experiments based on ns-2 simulation with AODV routing protocol and IEEE 802.11 MAC reveal that the clustered layout significantly degrades the network performance and the main trouble comes from the MAC layer mechanisms. Node clustering results in as much as 77.6% lower packet delivery ratio compared to random node distribution. Moreover, it results in larger variation in packet delivery service, and thus has a serious impact on QoS, which is important in MP2P networks.

2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.

This paper reevaluates the multicast protocols for MANETs in terms of energy efficiency and propo... more This paper reevaluates the multicast protocols for MANETs in terms of energy efficiency and proposes a new robust multicast protocol, called Two-Tree Multicast (TTM). Multicast protocols can be broadly categorized into two types, tree-based multicast and mesh-based multicast, based on the network structure along which multicast packets are delivered to multiple receivers. Mesh-based protocols are more robust to mobility and result in high packet delivery ratio. On the other hand, multicast trees are more energy efficient than multicast meshes. This is because mesh-based protocols depend on broadcast flooding within the mesh and therefore, mobile nodes in the mesh must receive all multicast packets during the multicast communication. The proposed TTM uses two trees, a primary and an alternative backup tree, to improve energy efficiency compared to the mesh-based protocols and to offer a better energy balance and packet delivery ratio than the tree-based protocols. Performance evaluation study shows that the proposed TTM saves energy consumption by a factor of 1.9~4.0 compared to the mesh-based multicast. In terms of combined performance metric, energy per delivered packet, TTM shows up to 80% and 40% improved performance than the mesh-based multicast and the conventional shared tree multicast, respectively. 1 Alternative path routing (APR) pursued the similar idea for routing in MANETs, where the main goal is to continually provide a path even though the current path becomes invalid due to node mobility [5].

Journal of Systems Architecture, 2005

This paper presents the implementation and performance of a hardware-VIA-based network adapter on... more This paper presents the implementation and performance of a hardware-VIA-based network adapter on Gigabit Ethernet. VIA is a user-level communication interface for high performance PC clustering. The network adapter is a 64-bit/66MHz PCI plug-in card containing an FPGA for the VIA Protocol Engine and a Gigabit Ethernet chip to construct a high performance system area network. The network adapter performs virtual-to-physical address translation, doorbell, RDMA write, and send/receive completion operations in hardware without kernel intervention. In particular, the Address Translation Table (ATT) is stored on the local memory of the network adapter, and the VIA Protocol Engine efficiently controls the address translation process by directly accessing the ATT. In addition, Address Prefetch Buffer is used to reduce the time of address translation process in the receiver. As a result, the communication overhead during send/receive transactions is greatly reduced. Our experimental results show a minimum latency of 8.2 µs, and a maximum bandwidth of 112.1 MB/s. In terms of minimum latency, the hardware-VIA-based network adapter performs 2.8 times and 3.3 times faster than M-VIA, which is a software implementation of VIA, and TCP/IP, respectively, over Gigabit Ethernet. In addition, the maximum bandwidth of the hardware-VIA-based network adapter is 24% and 55% higher than M-VIA and TCP/IP, respectively. These results show that the performance of HVIA-GE is far better than that of ServerNet II, which is a hardware version of VIA developed by Tandem/Compaq.

Fourth Annual IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOMW'06)

In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered unifo... more In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered uniformly across the network area. This paper considers the clustering of peer nodes and its performance impact in MP2P networks. The model for node clustering based on a heavy-tail distribution is first introduced and then a topology generation method that produces a clustered network is presented. Experiments based on ns-2 simulation with AODV routing protocol and IEEE 802.11 MAC reveal that the clustered layout significantly degrades the network performance and the main trouble comes from the MAC layer mechanisms. Node clustering results in as much as 77.6% lower packet delivery ratio compared to random node distribution. Moreover, it results in larger variation in packet delivery service, and thus has a serious impact on QoS, which is important in MP2P networks.

Journal of Systems Architecture, 2005

This paper presents the implementation and performance of a hardware-VIA-based network adapter on... more This paper presents the implementation and performance of a hardware-VIA-based network adapter on Gigabit Ethernet. VIA is a user-level communication interface for high performance PC clustering. The network adapter is a 64-bit/66MHz PCI plug-in card containing an FPGA for the VIA Protocol Engine and a Gigabit Ethernet chip to construct a high performance system area network. The network adapter performs virtual-to-physical address translation, doorbell, RDMA write, and send/receive completion operations in hardware without kernel intervention. In particular, the Address Translation Table (ATT) is stored on the local memory of the network adapter, and the VIA Protocol Engine efficiently controls the address translation process by directly accessing the ATT. In addition, Address Prefetch Buffer is used to reduce the time of address translation process in the receiver. As a result, the communication overhead during send/receive transactions is greatly reduced. Our experimental results show a minimum latency of 8.2 µs, and a maximum bandwidth of 112.1 MB/s. In terms of minimum latency, the hardware-VIA-based network adapter performs 2.8 times and 3.3 times faster than M-VIA, which is a software implementation of VIA, and TCP/IP, respectively, over Gigabit Ethernet. In addition, the maximum bandwidth of the hardware-VIA-based network adapter is 24% and 55% higher than M-VIA and TCP/IP, respectively. These results show that the performance of HVIA-GE is far better than that of ServerNet II, which is a hardware version of VIA developed by Tandem/Compaq.

The Journal of Supercomputing, 2012

Your article is protected by copyright and all rights are held exclusively by Springer Science+Bu... more Your article is protected by copyright and all rights are held exclusively by Springer Science+Business Media, LLC. This e-offprint is for personal use only and shall not be selfarchived in electronic repositories. If you wish to self-archive your work, please use the accepted author's version for posting to your own website or your institution's repository. You may further deposit the accepted author's version on a funder's repository at a funder's request, provided it is not made publicly available until 12 months after publication.

The Journal of Supercomputing, 2012

Your article is protected by copyright and all rights are held exclusively by Springer Science+Bu... more Your article is protected by copyright and all rights are held exclusively by Springer Science+Business Media, LLC. This e-offprint is for personal use only and shall not be selfarchived in electronic repositories. If you wish to self-archive your work, please use the accepted author's version for posting to your own website or your institution's repository. You may further deposit the accepted author's version on a funder's repository at a funder's request, provided it is not made publicly available until 12 months after publication.

International Journal of Communication Systems, 2006

This paper proposes a new mechanism, which addresses the excessive advance reservation requiremen... more This paper proposes a new mechanism, which addresses the excessive advance reservation requirements of QoS guarantee methods for mobile Internet. To save resources for excessive advance reservations, the proposed mechanism employs a movement detection scheme for a mobile host (MH) using link-layer functionalities. With the movement detection scheme, advance reservations can be established at only where a MH is likely to visit soon. Another novel feature of our mechanism is resource-aware handoff direction scheme that allows a MH to choose its next BS according to not only the link-layer signal strength, but also the available amount of resources in the reachable base stations (BSs). It considerably decreases a probability that QoS is disrupted due to the failure in advance reservation request. Also, the proposed mechanism requires fewer functional and structural changes to the current Internet components and protocols since all the enhanced features are integrated only into leaf BSs and MHs. It does not suffer from the problems of the conventional approaches based on Mobile IP and RSVP Tunnel, such as nonoptimal routing path and signalling overhead. Our experiment results show that the proposed mechanism successfully eliminates the overhead for useless advance reservations while guaranteeing seamless QoS for MHs. The performance comparison demonstrates that our mechanism slightly outperforms the conventional approaches while requiring fewer modifications and additions to the existing Internet architecture. This performance advantage of the proposed mechanism becomes noticeable when the network is congested and the mobility of a host is high.

Biosecurity and Bioterrorism: Biodefense Strategy, Practice, and Science, 2004

Objectives: Public health departments' effectiveness during catastrophic bioterrorism will requir... more Objectives: Public health departments' effectiveness during catastrophic bioterrorism will require trust on the part of diverse communities. This study describes variations in perceptions that the public health system will respond fairly to one's needs in a bioterrorist event, regardless of race/ethnicity, income, or other characteristics. Methods: Using the Los Angeles County Health Survey, a random-digit, population-based, telephone survey, we conducted multivariate logistic regression of race/ethnicity on perceived fairness, adjusting for demographic factors and perceived neighborhood safety. We performed similar analyses stratified by race/ethnicity subgroup. Results: Overall, 72.7% of respondents perceived that the public health system will respond fairly in a bioterrorist event. African Americans (AA) and Asian/Pacific Islanders (API) reported the lowest perceived fairness (AA 63.0%, API 68.2%, Latino 73.1%, White 76.6%, p ‫؍‬ 0.005 for group differences). Adjusting for demographic factors and neighborhood safety, African Americans had lower perceived fairness compared to whites (adjusted odds ratio, aOR 0.45; 95% confidence intervals, CI 0.26-0.79; p Ͻ 0.005). Other factors associated with lower perceived fairness included Asian-language compared to English-language interview (aOR 0.29; 95% CI 0.11-0.76; p Ͻ 0.05) and lower compared to higher neighborhood safety (aOR 0.48; 95% CI 0.31-0.74; p Ͻ 0.005). Among African Americans, participants aged 18-29 years were less likely to report perceived fairness (aOR 0.06; 95% CI 0.01-0.59) compared to participants older than 60 years of age. Among Asian/Pacific Islanders, Asian-language interview (aOR 0.07; 95% CI 0.01-0.48) and lower perceived neighborhood safety (aOR 0.01; 95% CI Ͻ0.01-0.13) were associated with perceived fairness. Conclusions: To strengthen bioterrorism preparedness, public health officials must continue to improve perceived fairness among African American and Asian/Pacific Islander communities.

Proceedings Ninth International Conference on Computer Communications and Networks (Cat.No.00EX440), 2000

A method for testing multi-protocol implementation under test (IUT) with a single test suite has ... more A method for testing multi-protocol implementation under test (IUT) with a single test suite has been proposed in the literature. It tests a multi-protocol IUT in an integrated way compared to the conventional method, where single-layer test method and single-layer embedded test method are applied separately to the upper layer protocol and lower layer protocol, respectively. However, it did not consider how to generate the test cases automatically but proposed only an approach for the test method. This paper proposes an algorithm called Multi-protocol Test Method (MPTM) for automatic test case generation based on that approach. With the MPTM, a multi-protocol IUT consisting of two protocol layers is modeled as two Finite State Machines (FSMs), and the relationships between the transitions of them are defined as a set of transition relationships, pre-execution and carried-by. The proposed algorithm is implemented and applied to a simplified TCPnP and B-ISDN Signaling/SSCOP. The MPTM is able to test the multiprotocol IUT even though the interfaces between the protocol layers are not exposed. It also allows the same test coverage as conventional test methods with much smaller number of test cases and operations.

Proceedings Ninth International Conference on Computer Communications and Networks (Cat.No.00EX440), 2000

A method for testing multi-protocol implementation under test (IUT) with a single test suite has ... more A method for testing multi-protocol implementation under test (IUT) with a single test suite has been proposed in the literature. It tests a multi-protocol IUT in an integrated way compared to the conventional method, where single-layer test method and single-layer embedded test method are applied separately to the upper layer protocol and lower layer protocol, respectively. However, it did not consider how to generate the test cases automatically but proposed only an approach for the test method. This paper proposes an algorithm called Multi-protocol Test Method (MPTM) for automatic test case generation based on that approach. With the MPTM, a multi-protocol IUT consisting of two protocol layers is modeled as two Finite State Machines (FSMs), and the relationships between the transitions of them are defined as a set of transition relationships, pre-execution and carried-by. The proposed algorithm is implemented and applied to a simplified TCPnP and B-ISDN Signaling/SSCOP. The MPTM is able to test the multiprotocol IUT even though the interfaces between the protocol layers are not exposed. It also allows the same test coverage as conventional test methods with much smaller number of test cases and operations.

Electrical Engineering Handbook, 2002

In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance meas... more In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance measures such as delay or packet delivery ratio since it directly affects the network lifetime. In this article we introduce two different approaches for energy efficient multicast protocols developed for MANETs. The first group of energy efficient multicast protocols is based on the assumption that the transmission power is controllable. Under this assumption, the problem of finding a tree with the least consumed power becomes a conventional optimization problem on a graph where the weighted link cost corresponds to the transmission power required for transmitting a packet between two nodes of the link. The second approach focuses on maximizing sleep mode operation supported by the lower level protocol. A mobile node in tree-based protocols can safely put itself into a low power sleep mode for conserving energy if it is not a designated receiver with the employed broadcast-based mesh protocols. It is shown that mesh-based protocols are more robust to mobility but tree-based protocols may be preferable when energy is a primary concern.

Electrical Engineering Handbook, 2002

In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance meas... more In mobile ad hoc networks (MANETs), energy efficiency is as important as general performance measures such as delay or packet delivery ratio since it directly affects the network lifetime. In this article we introduce two different approaches for energy efficient multicast protocols developed for MANETs. The first group of energy efficient multicast protocols is based on the assumption that the transmission power is controllable. Under this assumption, the problem of finding a tree with the least consumed power becomes a conventional optimization problem on a graph where the weighted link cost corresponds to the transmission power required for transmitting a packet between two nodes of the link. The second approach focuses on maximizing sleep mode operation supported by the lower level protocol. A mobile node in tree-based protocols can safely put itself into a low power sleep mode for conserving energy if it is not a designated receiver with the employed broadcast-based mesh protocols. It is shown that mesh-based protocols are more robust to mobility but tree-based protocols may be preferable when energy is a primary concern.

Proceedings of the second international workshop on Mobility management & wireless access protocols - MobiWac '04, 2004

Session Initiation Protocol (SIP) was standardized for real-time applications and extended to sup... more Session Initiation Protocol (SIP) was standardized for real-time applications and extended to support terminal mobility by Internet Expert Task Force (IETF). However, SIP terminal mobility suffers from the considerable handoff latency which is unsuitable for the real-time communications. In this paper, we propose Predictive Address Reservation with SIP (PAR-SIP) which decreases handoff delay by proactively processing the address allocation and session update using link layer information of wireless networks.

Proceedings of the second international workshop on Mobility management & wireless access protocols - MobiWac '04, 2004

Proceedings International Conference on Parallel Processing

This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete mach... more This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete machine simulator from Stanford. The motivation for Linux/SimOS is to alleviate the limitations of SimOS, which only supports proprietary operating systems. The contributions made in this paper are twofold: First, the major modifications that were necessary to run Linux on SimOS are described. Second, a detailed analysis of the UDP/IP protocol and M-VIA is performed to demonstrate the capabilities of Linux/SimOS. The simulation study shows that Linux/SimOS is capable of capturing all aspects of communication performance, including the effects of the kernel, device drivers, and network interface.

Proceedings International Conference on Parallel Processing

This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete mach... more This paper presents Linux/SimOS, a Linux operating system port to SimOS, which is a complete machine simulator from Stanford. The motivation for Linux/SimOS is to alleviate the limitations of SimOS, which only supports proprietary operating systems. The contributions made in this paper are twofold: First, the major modifications that were necessary to run Linux on SimOS are described. Second, a detailed analysis of the UDP/IP protocol and M-VIA is performed to demonstrate the capabilities of Linux/SimOS. The simulation study shows that Linux/SimOS is capable of capturing all aspects of communication performance, including the effects of the kernel, device drivers, and network interface.

2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.

Fourth Annual IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOMW'06)

In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered unifo... more In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered uniformly across the network area. This paper considers the clustering of peer nodes and its performance impact in MP2P networks. The model for node clustering based on a heavy-tail distribution is first introduced and then a topology generation method that produces a clustered network is presented. Experiments based on ns-2 simulation with AODV routing protocol and IEEE 802.11 MAC reveal that the clustered layout significantly degrades the network performance and the main trouble comes from the MAC layer mechanisms. Node clustering results in as much as 77.6% lower packet delivery ratio compared to random node distribution. Moreover, it results in larger variation in packet delivery service, and thus has a serious impact on QoS, which is important in MP2P networks.

2002 Pacific Rim International Symposium on Dependable Computing, 2002. Proceedings.

This paper reevaluates the multicast protocols for MANETs in terms of energy efficiency and propo... more This paper reevaluates the multicast protocols for MANETs in terms of energy efficiency and proposes a new robust multicast protocol, called Two-Tree Multicast (TTM). Multicast protocols can be broadly categorized into two types, tree-based multicast and mesh-based multicast, based on the network structure along which multicast packets are delivered to multiple receivers. Mesh-based protocols are more robust to mobility and result in high packet delivery ratio. On the other hand, multicast trees are more energy efficient than multicast meshes. This is because mesh-based protocols depend on broadcast flooding within the mesh and therefore, mobile nodes in the mesh must receive all multicast packets during the multicast communication. The proposed TTM uses two trees, a primary and an alternative backup tree, to improve energy efficiency compared to the mesh-based protocols and to offer a better energy balance and packet delivery ratio than the tree-based protocols. Performance evaluation study shows that the proposed TTM saves energy consumption by a factor of 1.9~4.0 compared to the mesh-based multicast. In terms of combined performance metric, energy per delivered packet, TTM shows up to 80% and 40% improved performance than the mesh-based multicast and the conventional shared tree multicast, respectively. 1 Alternative path routing (APR) pursued the similar idea for routing in MANETs, where the main goal is to continually provide a path even though the current path becomes invalid due to node mobility [5].

Journal of Systems Architecture, 2005

This paper presents the implementation and performance of a hardware-VIA-based network adapter on... more This paper presents the implementation and performance of a hardware-VIA-based network adapter on Gigabit Ethernet. VIA is a user-level communication interface for high performance PC clustering. The network adapter is a 64-bit/66MHz PCI plug-in card containing an FPGA for the VIA Protocol Engine and a Gigabit Ethernet chip to construct a high performance system area network. The network adapter performs virtual-to-physical address translation, doorbell, RDMA write, and send/receive completion operations in hardware without kernel intervention. In particular, the Address Translation Table (ATT) is stored on the local memory of the network adapter, and the VIA Protocol Engine efficiently controls the address translation process by directly accessing the ATT. In addition, Address Prefetch Buffer is used to reduce the time of address translation process in the receiver. As a result, the communication overhead during send/receive transactions is greatly reduced. Our experimental results show a minimum latency of 8.2 µs, and a maximum bandwidth of 112.1 MB/s. In terms of minimum latency, the hardware-VIA-based network adapter performs 2.8 times and 3.3 times faster than M-VIA, which is a software implementation of VIA, and TCP/IP, respectively, over Gigabit Ethernet. In addition, the maximum bandwidth of the hardware-VIA-based network adapter is 24% and 55% higher than M-VIA and TCP/IP, respectively. These results show that the performance of HVIA-GE is far better than that of ServerNet II, which is a hardware version of VIA developed by Tandem/Compaq.

Fourth Annual IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOMW'06)

In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered unifo... more In mobile peer-to-peer (MP2P) networks, nodes tend to gather together rather than scattered uniformly across the network area. This paper considers the clustering of peer nodes and its performance impact in MP2P networks. The model for node clustering based on a heavy-tail distribution is first introduced and then a topology generation method that produces a clustered network is presented. Experiments based on ns-2 simulation with AODV routing protocol and IEEE 802.11 MAC reveal that the clustered layout significantly degrades the network performance and the main trouble comes from the MAC layer mechanisms. Node clustering results in as much as 77.6% lower packet delivery ratio compared to random node distribution. Moreover, it results in larger variation in packet delivery service, and thus has a serious impact on QoS, which is important in MP2P networks.

Journal of Systems Architecture, 2005

This paper presents the implementation and performance of a hardware-VIA-based network adapter on... more This paper presents the implementation and performance of a hardware-VIA-based network adapter on Gigabit Ethernet. VIA is a user-level communication interface for high performance PC clustering. The network adapter is a 64-bit/66MHz PCI plug-in card containing an FPGA for the VIA Protocol Engine and a Gigabit Ethernet chip to construct a high performance system area network. The network adapter performs virtual-to-physical address translation, doorbell, RDMA write, and send/receive completion operations in hardware without kernel intervention. In particular, the Address Translation Table (ATT) is stored on the local memory of the network adapter, and the VIA Protocol Engine efficiently controls the address translation process by directly accessing the ATT. In addition, Address Prefetch Buffer is used to reduce the time of address translation process in the receiver. As a result, the communication overhead during send/receive transactions is greatly reduced. Our experimental results show a minimum latency of 8.2 µs, and a maximum bandwidth of 112.1 MB/s. In terms of minimum latency, the hardware-VIA-based network adapter performs 2.8 times and 3.3 times faster than M-VIA, which is a software implementation of VIA, and TCP/IP, respectively, over Gigabit Ethernet. In addition, the maximum bandwidth of the hardware-VIA-based network adapter is 24% and 55% higher than M-VIA and TCP/IP, respectively. These results show that the performance of HVIA-GE is far better than that of ServerNet II, which is a hardware version of VIA developed by Tandem/Compaq.

The Journal of Supercomputing, 2012

Your article is protected by copyright and all rights are held exclusively by Springer Science+Bu... more Your article is protected by copyright and all rights are held exclusively by Springer Science+Business Media, LLC. This e-offprint is for personal use only and shall not be selfarchived in electronic repositories. If you wish to self-archive your work, please use the accepted author's version for posting to your own website or your institution's repository. You may further deposit the accepted author's version on a funder's repository at a funder's request, provided it is not made publicly available until 12 months after publication.

The Journal of Supercomputing, 2012

Your article is protected by copyright and all rights are held exclusively by Springer Science+Bu... more Your article is protected by copyright and all rights are held exclusively by Springer Science+Business Media, LLC. This e-offprint is for personal use only and shall not be selfarchived in electronic repositories. If you wish to self-archive your work, please use the accepted author's version for posting to your own website or your institution's repository. You may further deposit the accepted author's version on a funder's repository at a funder's request, provided it is not made publicly available until 12 months after publication.

International Journal of Communication Systems, 2006

This paper proposes a new mechanism, which addresses the excessive advance reservation requiremen... more This paper proposes a new mechanism, which addresses the excessive advance reservation requirements of QoS guarantee methods for mobile Internet. To save resources for excessive advance reservations, the proposed mechanism employs a movement detection scheme for a mobile host (MH) using link-layer functionalities. With the movement detection scheme, advance reservations can be established at only where a MH is likely to visit soon. Another novel feature of our mechanism is resource-aware handoff direction scheme that allows a MH to choose its next BS according to not only the link-layer signal strength, but also the available amount of resources in the reachable base stations (BSs). It considerably decreases a probability that QoS is disrupted due to the failure in advance reservation request. Also, the proposed mechanism requires fewer functional and structural changes to the current Internet components and protocols since all the enhanced features are integrated only into leaf BSs and MHs. It does not suffer from the problems of the conventional approaches based on Mobile IP and RSVP Tunnel, such as nonoptimal routing path and signalling overhead. Our experiment results show that the proposed mechanism successfully eliminates the overhead for useless advance reservations while guaranteeing seamless QoS for MHs. The performance comparison demonstrates that our mechanism slightly outperforms the conventional approaches while requiring fewer modifications and additions to the existing Internet architecture. This performance advantage of the proposed mechanism becomes noticeable when the network is congested and the mobility of a host is high.

Biosecurity and Bioterrorism: Biodefense Strategy, Practice, and Science, 2004

Objectives: Public health departments' effectiveness during catastrophic bioterrorism will requir... more Objectives: Public health departments' effectiveness during catastrophic bioterrorism will require trust on the part of diverse communities. This study describes variations in perceptions that the public health system will respond fairly to one's needs in a bioterrorist event, regardless of race/ethnicity, income, or other characteristics. Methods: Using the Los Angeles County Health Survey, a random-digit, population-based, telephone survey, we conducted multivariate logistic regression of race/ethnicity on perceived fairness, adjusting for demographic factors and perceived neighborhood safety. We performed similar analyses stratified by race/ethnicity subgroup. Results: Overall, 72.7% of respondents perceived that the public health system will respond fairly in a bioterrorist event. African Americans (AA) and Asian/Pacific Islanders (API) reported the lowest perceived fairness (AA 63.0%, API 68.2%, Latino 73.1%, White 76.6%, p ‫؍‬ 0.005 for group differences). Adjusting for demographic factors and neighborhood safety, African Americans had lower perceived fairness compared to whites (adjusted odds ratio, aOR 0.45; 95% confidence intervals, CI 0.26-0.79; p Ͻ 0.005). Other factors associated with lower perceived fairness included Asian-language compared to English-language interview (aOR 0.29; 95% CI 0.11-0.76; p Ͻ 0.05) and lower compared to higher neighborhood safety (aOR 0.48; 95% CI 0.31-0.74; p Ͻ 0.005). Among African Americans, participants aged 18-29 years were less likely to report perceived fairness (aOR 0.06; 95% CI 0.01-0.59) compared to participants older than 60 years of age. Among Asian/Pacific Islanders, Asian-language interview (aOR 0.07; 95% CI 0.01-0.48) and lower perceived neighborhood safety (aOR 0.01; 95% CI Ͻ0.01-0.13) were associated with perceived fairness. Conclusions: To strengthen bioterrorism preparedness, public health officials must continue to improve perceived fairness among African American and Asian/Pacific Islander communities.