Skip to main content

Arun Somani

Iowa State University, Electrical & Computer Engineering, Faculty Member

Followers

15

Following

11

Co-authors

10

Public Views

Arun K. Somani is Anson Marston Distinguished Professor, Philip, and Virginia Sproul Professor of Electrical and Computer Engineering, and is serving as Senior Associate Dean for the College of Engineering at Iowa State University. His research interests are in the design and implementation of scalable and dependable high-speed high-performance computing and networking systems, optical fiber networks, critical infrastructure protection, image-based navigation, and neural architecture search methods. He has published more than 400 technical papers, several books and conference proceedings, and 12 patents. He has supervised more than 125 graduate students’ dissertations and theses and mentored many undergraduate students.Professor Somani has served as IEEE distinguished visitor and tutorial speaker, editor of several prestigious IEEE and Elsevier Journals, and has delivered several tutorials and keynote and distinguished and invited talks all over the world. He is a Life Fellow of the Institute of Electrical and Electronics Engineers, a Fellow of the American Association for the Advancement of Science, a Distinguished Engineer of the Association for Computing Machinery, and an Eminent Engineer of Tau Beta Phi. He received Canadian Commonwealth Scholarship for his graduate work. He has been recognized as a Distinguished Alumnus of the Birla Institute of Technology and Science, Pilani, India.

less

Liverpool John Moores University

Ecole Polytechnique Federale de Lausanne

Rossano Schifanella

Università degli Studi di Torino

Delft University of Technology

University Of Bayreuth, Germany

Leandro Navarro

Universitat Politecnica de Catalunya

Panayotis Antoniadis

Swiss Federal Institute of Technology (ETH)

Colin Richardson

Colin Richardson

Cambridge Alumni

Gheorghe Silaghi

Babes-Bolyai University

Interests

Uploads

Papers by Arun Somani

CompuP2P: An Architecture for Sharing of Computing Resources In Peer-to-Peer Networks With Selfish Nodes

CompuP2P is an architecture for sharing of computing resources in peer-to-peer (P2P) networks. It... more CompuP2P is an architecture for sharing of computing resources in peer-to-peer (P2P) networks. It provide resources, such as processing power, memory storage etc., to user applications that might require them. CompuP2P creates dynamic markets for different amounts of computing resources without relying on any trusted centralized entity to monitor the activities of nodes in those markets. Moreover, the pricing of computing resources takes into account selfishness of network users and uses ideas from game theory and microeconomics.

Reliability analysis and comparison of two fail-op/fail-op/fail-safe architectures

[1989] The Nineteenth International Symposium on Fault-Tolerant Computing. Digest of Papers, 1989

ABSTRACT

Design and Protection Algorithms for Path Level Aggregation of Trac in WDM Metro Optical Networks

An Efficient Backup-Overloading for Fault-Tolerant Scheduling of Real-Time Tasks

Lecture Notes in Computer Science, 2000

Many time-critical applications require dynamic scheduling with predictable performance. Tasks co... more Many time-critical applications require dynamic scheduling with predictable performance. Tasks corresponding to these applications have deadlines to be met despite the presence of faults. In this paper, we propose a technique called dynamic grouping, to be used with backup overloading in a primary-backup based fault-tolerant dynamic scheduling algorithm in multiprocessor real-time systems. In dynamic grouping, the processors are dynamically grouped into logical groups in order to achieve e cient overloading of backups, thereby improving the schedulability. We compare the performance of dynamic grouping with that of static grouping and no-grouping schemes through extensive simulation studies and show the e ectiveness of dynamic grouping.

On Physical Considerations in Design of Wavelength Grooming Optical Networks

This paper reviews physical design issues and challenges to meet the basic premise of grooming su... more This paper reviews physical design issues and challenges to meet the basic premise of grooming sub-wavelength capacity traffic in all-optical networks. We discuss technology issues in areas such as all-optical time division Multiplexing, Optical pulse generation, the types of lasers for such pulses, modulators and types of amplifiers, as well as optical timing extraction for high speed optical waveform measurement. We also review some issues and experiments that have been performed to support terabits OTDM/WDM systems.

Cache Write Generate For High-Performance Processing

Much attention has been paid to read caching and several schemes have been developed to make read... more Much attention has been paid to read caching and several schemes have been developed to make read caching very e cient. As a result, the performance of write caching has become a concern. This paper investigates write caching policies and how they a ect the performance of memory systems. We show that write caching can greatly alter the hit/miss ratios, but only more subtly a ects the performance. Many factors such as write bu ers, contention, split transactions, and multilevel caches dilute the correlation of cache miss ratios to performance. A more accurate performance formula is presented taking these factors into account. This allows an incremental improvement in multiprocessor cache architectures. Cache write generate is a scheme where a cache line is validated on a write miss without fetching from memory. It avoids unnecessary reads from main memory, reduces the CPU stalling time, lowers the cache miss latency, reduces bus contention, and thus increases the available bandwidth of the memory. We compare the performance of cache write generate with the performance of write around and write allocate in single processor and shared bus multiprocessors. We use register level simulations validated by our functioning hardware prototype Proteus system. Various memory speeds and di ering numbers of processors are evaluated using detailed simulation models for high performance measurement accuracy.

Determining optimal light-trail length

2010 17th IEEE Workshop on Local & Metropolitan Area Networks (LANMAN), 2010

Light-trails based solutions have been proposed and demonstrated as a means of traffic grooming a... more Light-trails based solutions have been proposed and demonstrated as a means of traffic grooming and optical multicasting in a LAN/MAN, where multiple nodes use time division multiple access on a unidirectional optical bus. When compared to light paths or having nodes relaying traffic using optical-electronic-optical conversion there are advantages and disadvantages to light-trails in terms of bandwidth, hardware requirements and latency. Given that a light-trail of a specific length has been identified, we develop an approach to increase its capacity utilization. In particular, we show that splitting a longer light-trail in shorter segments results into more effective and efficient utilization of bandwidth. However, we do not believe that splitting a light-trail into segments of lengths one is preferable as it will increase the overall delay.

A Long-Term Investment Planning Model for Mixed Energy Infrastructure Integrated with Renewable Energy

2010 IEEE Green Technologies Conference, 2010

The current energy infrastructure heavily depends on fossil energy, which will be mostly depleted... more The current energy infrastructure heavily depends on fossil energy, which will be mostly depleted beyond 21st century. Another built-in disadvantage of fossil energy is the pollutant and green house gas emission. It is time to reform the environment-degrading energy infrastructure into a sustainable and resilient energy infrastructure such that it is more environmental friendly. Compared with fossil energy, it is

Performance Analysis of WDM Optical Networks with Wavelength Usage Constraint

IFIP Advances in Information and Communication Technology, 2003

Due to power considerations, it is possible that not all wavelengths available in a fiber can be ... more Due to power considerations, it is possible that not all wavelengths available in a fiber can be used at a given time. In this paper, an analytical model is proposed to evaluate the blocking performance of wavelength-routed optical networks with and without wavelength conversion where the usable wavelengths in a fiber is limited to a certain maximum number, referred to as wavelength usage constraint. The effect of the wavelength usage constraint is studied on ring and mesh-torus networks. It is shown that the analytical model closely approximates the simulation results. It is observed that increasing the total number of wavelengths in a fiber is an attractive alternative to wavelength conversion when the number of usable wavelengths in a fiber is maintained the same.

Revenue maximization in survivable WDM networks

Service availability is an indispensable requirement for many current and future applications ove... more Service availability is an indispensable requirement for many current and future applications over the Internet and hence has to be addressed as part of the optical QoS service model. Network service providers can offer varying classes of services based on the choice of protection employed which can vary from full protection to no protection. Based on the service classes, traffic in the network falls into one of the three classes viz., full protection, no protection and best-effort. The network typically relies on the best-effort traffic for maximizing revenue. We consider two variations on the best-effort class, (1) all connections are accepted and network tries to protect as many as possible and (2) a mix of protected and unprotected connections and the goal is to maximize revenue. In this paper, we present a mathematical formulation, that captures service differentiation based on lightpath protection, for revenue maximization in a wavelength routed backbone networks. Our approach...

Approaches for capacity and revenue optimization in survivable WDM networks

Journal of High Speed Networks

In this paper, we consider two important objectives of network operation: (i) capacity minimizati... more In this paper, we consider two important objectives of network operation: (i) capacity minimization and (ii) revenue maximization. For capacity minimization, we formulate three operational phases in sur- vivable WDM network operation viz., initial call set up, short/medium-term reconfiguration, and long-term reconfiguration. All three phases are derived from a single integer linear programming (ILP) formulation. This common framework incorporates service disruption. We modify the framework for revenue maximization that includes a service differentiation model based on lightpath protection. We propose a multistage solution methodology to solve individual service classes sequentially and combine them to obtain a feasible solution. We provide cost comparisons in terms of increase in revenue obtained by various service classes with the base case of accepting demands without any protection. Results are provided to demonstrate the effectiveness of our framework.

Capacity fairness of WDM networks with grooming capabilities

Storage and Retrieval for Image and Video Databases, 2001

ABSTRACT

Attack monitoring and localization in All-Optical Networks

Cluster Computing, 2006

The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or i... more The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or indistinct print, colored or poor quality illustrations and photographs, print bleed-through, substandard margins, and improper alignment can adversely affect reproduction. In the unlikely event that the author did not send a complete manuscript and there are missing pages, these will be noted. Also, if unauthorized copyright material had to be removed, a note will indicate the deletion. UMI UMI Microform 3308906

Non-arithmetic carry chains for reconfigurable fabrics

2007 25th International Conference on Computer Design, 2007

Reconfigurable fabrics cater to a wide variety of applications, but have adopted specialized comp... more Reconfigurable fabrics cater to a wide variety of applications, but have adopted specialized components to allow efficient implementation of performance-critical arithmetic operations. Carry chains have been integrated into the fabric typically as an optimized ripple-carry chain. However, in non-arithmetic operations the carry chain goes unused, when it could be a valuable adjacent-cell interconnect resource. This paper presents a cell architecture facilitating reuse, as well as an analysis of the potential benefits of reuse for an sampling of common of algorithms using commercial FPGAs. Technology map experiments indicate that a variety of applications can benefit from reuse, with utilized routing resources reduced by up to 13% and maximum clock frequency increased by up to 47%.

Reduction of green house gas emission by clean power trading

2010 IEEE Energy Conversion Congress and Exposition, 2010

It is well known that the CO2 emitted by fossil energy is one of the major reasons that result in... more It is well known that the CO2 emitted by fossil energy is one of the major reasons that result in global warming. It is still an open question about how to reducxe CO2 emission by the implementation of an investment plan for clean power systems. In this paper, we propose a clean power trading method among neighboring regions such that we can reduce CO2 emission in a large region and reduce the imbalance between the power demand and supply in a region caused by the fluctuation of clean energy. With the five states with rich wind energy in America as an example, we use the quantitative computation results of the five states (from a modeling framework designed by ourselves [3]) to show that our proposed clean power trading method can help reduce CO2 emission and realize balance.

Scalable Segment Routing—A New Paradigm for Efficient Service Provider Networking Using Carrier Ethernet Advances

Journal of Optical Communications and Networking, 2015

ABSTRACT Segment routing has recently been proposed in the IETF toward making IP/MPLS networks se... more ABSTRACT Segment routing has recently been proposed in the IETF toward making IP/MPLS networks service-oriented while simplifying network operations. Segment routing computes paths at the source node using node identifiers and adjacency identifiers conjoined together to create a source-routed path. We propose a scalable transport paradigm as an enabler toward implementing segment routing in provider networks. We propose omnipresent Ethernet, our modification of carrier Ethernet (which is based on source-routed, binary-routed labels embedded in an Ethernet frame), to implement segment routing. We identify some of the scalability issues of the segment-routing proposal in the context of source-routing overhead. To absolve scalability issues of segment routing, two routing schemes that implement multidomain source-routing techniques are proposed. The hierarchical segment-routing (H-SR) scheme is proposed, which deploys a limited number of special nodes called swap nodes that are capable of label swapping to implement routing. The swap-node placement problem is formulated as an integer linear program to minimize the total routing distance within a network. Three heuristic techniques for swap-node selection based on centrality paradigms are presented. The H-SR scheme is further improved by a proposed multisegment-routing (M-SR) scheme that assumes all nodes in the network to be capable of label swapping. The H-SR and M-SR schemes are shown to significantly enhance the scalability of segment routing. A test-bed is built using carrier Ethernet hardware to support segment routing that validates the implementation of the proposed schemes. A simulation model to evaluate the schemes from a scalability perspective and their associated trade-offs is presented.

Optimal location management algorithms for mobile networks

Proceedings of the 4th annual ACM/IEEE international conference on Mobile computing and networking - MobiCom '98, 1998

ABSTRACT

A p-cycle based survivable design for dynamic traffic in WDM networks

GLOBECOM '05. IEEE Global Telecommunications Conference, 2005., 2005

AbstractAchieving both high capacity efficiency and fast restoration speed is a primary goal of ... more

Optimal light trail design in WDM optical networks

2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577), 2004

The enabling technology for supporting IP centric traffic over optical transport networks evolves... more The enabling technology for supporting IP centric traffic over optical transport networks evolves as the amount of traffic grows. In this paper, we first review a recently proposed concept called light trails. Light trails can enable high speed provisioning, accommodate multi-granularity traffic, support high data rates and offer a good candidate for carrying IP traffic over optical networks. Next, we focus on light trail design. We propose a two-step approach for solving the light trail design problem. The first step is called traffic matrix preprocessing, it divides single long hop paths into several shorter paths that satisfy the hop-length constraint. In the second step, the light trail design problem is formulated as an integer linear programming (ILP) optimization problem. The results obtained from our experiments show that the resulting light trail network has high wavelength utilization.

Dynamic non-continuous single slot advance reservation over wavelength routed networks

2012 International Conference on Computing, Networking and Communications (ICNC), 2012

We investigate the problem of provisioning light-paths for dynamic advance reservation (AR) reque... more We investigate the problem of provisioning light-paths for dynamic advance reservation (AR) requests in all-optical wavelength division multiplexed networks. We propose a two-phase novel routing, slot, and wavelength assignment (RWSA) technique called Non-Continuous Single-Slot Advance Reservation (NC-SSAR). We propose two NC-SSAR heuristics, one with only lightpath segmentation (SEG-NC-SSAR) and the other with lightpath segmentation and lightpath switching (LPS-NC-SSAR). We briefly

CompuP2P: An Architecture for Sharing of Computing Resources In Peer-to-Peer Networks With Selfish Nodes

CompuP2P is an architecture for sharing of computing resources in peer-to-peer (P2P) networks. It... more CompuP2P is an architecture for sharing of computing resources in peer-to-peer (P2P) networks. It provide resources, such as processing power, memory storage etc., to user applications that might require them. CompuP2P creates dynamic markets for different amounts of computing resources without relying on any trusted centralized entity to monitor the activities of nodes in those markets. Moreover, the pricing of computing resources takes into account selfishness of network users and uses ideas from game theory and microeconomics.

Reliability analysis and comparison of two fail-op/fail-op/fail-safe architectures

[1989] The Nineteenth International Symposium on Fault-Tolerant Computing. Digest of Papers, 1989

ABSTRACT

Design and Protection Algorithms for Path Level Aggregation of Trac in WDM Metro Optical Networks

An Efficient Backup-Overloading for Fault-Tolerant Scheduling of Real-Time Tasks

Lecture Notes in Computer Science, 2000

Many time-critical applications require dynamic scheduling with predictable performance. Tasks co... more Many time-critical applications require dynamic scheduling with predictable performance. Tasks corresponding to these applications have deadlines to be met despite the presence of faults. In this paper, we propose a technique called dynamic grouping, to be used with backup overloading in a primary-backup based fault-tolerant dynamic scheduling algorithm in multiprocessor real-time systems. In dynamic grouping, the processors are dynamically grouped into logical groups in order to achieve e cient overloading of backups, thereby improving the schedulability. We compare the performance of dynamic grouping with that of static grouping and no-grouping schemes through extensive simulation studies and show the e ectiveness of dynamic grouping.

On Physical Considerations in Design of Wavelength Grooming Optical Networks

This paper reviews physical design issues and challenges to meet the basic premise of grooming su... more This paper reviews physical design issues and challenges to meet the basic premise of grooming sub-wavelength capacity traffic in all-optical networks. We discuss technology issues in areas such as all-optical time division Multiplexing, Optical pulse generation, the types of lasers for such pulses, modulators and types of amplifiers, as well as optical timing extraction for high speed optical waveform measurement. We also review some issues and experiments that have been performed to support terabits OTDM/WDM systems.

Cache Write Generate For High-Performance Processing

Much attention has been paid to read caching and several schemes have been developed to make read... more Much attention has been paid to read caching and several schemes have been developed to make read caching very e cient. As a result, the performance of write caching has become a concern. This paper investigates write caching policies and how they a ect the performance of memory systems. We show that write caching can greatly alter the hit/miss ratios, but only more subtly a ects the performance. Many factors such as write bu ers, contention, split transactions, and multilevel caches dilute the correlation of cache miss ratios to performance. A more accurate performance formula is presented taking these factors into account. This allows an incremental improvement in multiprocessor cache architectures. Cache write generate is a scheme where a cache line is validated on a write miss without fetching from memory. It avoids unnecessary reads from main memory, reduces the CPU stalling time, lowers the cache miss latency, reduces bus contention, and thus increases the available bandwidth of the memory. We compare the performance of cache write generate with the performance of write around and write allocate in single processor and shared bus multiprocessors. We use register level simulations validated by our functioning hardware prototype Proteus system. Various memory speeds and di ering numbers of processors are evaluated using detailed simulation models for high performance measurement accuracy.

Determining optimal light-trail length

2010 17th IEEE Workshop on Local & Metropolitan Area Networks (LANMAN), 2010

Light-trails based solutions have been proposed and demonstrated as a means of traffic grooming a... more Light-trails based solutions have been proposed and demonstrated as a means of traffic grooming and optical multicasting in a LAN/MAN, where multiple nodes use time division multiple access on a unidirectional optical bus. When compared to light paths or having nodes relaying traffic using optical-electronic-optical conversion there are advantages and disadvantages to light-trails in terms of bandwidth, hardware requirements and latency. Given that a light-trail of a specific length has been identified, we develop an approach to increase its capacity utilization. In particular, we show that splitting a longer light-trail in shorter segments results into more effective and efficient utilization of bandwidth. However, we do not believe that splitting a light-trail into segments of lengths one is preferable as it will increase the overall delay.

A Long-Term Investment Planning Model for Mixed Energy Infrastructure Integrated with Renewable Energy

2010 IEEE Green Technologies Conference, 2010

The current energy infrastructure heavily depends on fossil energy, which will be mostly depleted... more The current energy infrastructure heavily depends on fossil energy, which will be mostly depleted beyond 21st century. Another built-in disadvantage of fossil energy is the pollutant and green house gas emission. It is time to reform the environment-degrading energy infrastructure into a sustainable and resilient energy infrastructure such that it is more environmental friendly. Compared with fossil energy, it is

Performance Analysis of WDM Optical Networks with Wavelength Usage Constraint

IFIP Advances in Information and Communication Technology, 2003

Due to power considerations, it is possible that not all wavelengths available in a fiber can be ... more Due to power considerations, it is possible that not all wavelengths available in a fiber can be used at a given time. In this paper, an analytical model is proposed to evaluate the blocking performance of wavelength-routed optical networks with and without wavelength conversion where the usable wavelengths in a fiber is limited to a certain maximum number, referred to as wavelength usage constraint. The effect of the wavelength usage constraint is studied on ring and mesh-torus networks. It is shown that the analytical model closely approximates the simulation results. It is observed that increasing the total number of wavelengths in a fiber is an attractive alternative to wavelength conversion when the number of usable wavelengths in a fiber is maintained the same.

Revenue maximization in survivable WDM networks

Service availability is an indispensable requirement for many current and future applications ove... more Service availability is an indispensable requirement for many current and future applications over the Internet and hence has to be addressed as part of the optical QoS service model. Network service providers can offer varying classes of services based on the choice of protection employed which can vary from full protection to no protection. Based on the service classes, traffic in the network falls into one of the three classes viz., full protection, no protection and best-effort. The network typically relies on the best-effort traffic for maximizing revenue. We consider two variations on the best-effort class, (1) all connections are accepted and network tries to protect as many as possible and (2) a mix of protected and unprotected connections and the goal is to maximize revenue. In this paper, we present a mathematical formulation, that captures service differentiation based on lightpath protection, for revenue maximization in a wavelength routed backbone networks. Our approach...

Approaches for capacity and revenue optimization in survivable WDM networks

Journal of High Speed Networks

In this paper, we consider two important objectives of network operation: (i) capacity minimizati... more In this paper, we consider two important objectives of network operation: (i) capacity minimization and (ii) revenue maximization. For capacity minimization, we formulate three operational phases in sur- vivable WDM network operation viz., initial call set up, short/medium-term reconfiguration, and long-term reconfiguration. All three phases are derived from a single integer linear programming (ILP) formulation. This common framework incorporates service disruption. We modify the framework for revenue maximization that includes a service differentiation model based on lightpath protection. We propose a multistage solution methodology to solve individual service classes sequentially and combine them to obtain a feasible solution. We provide cost comparisons in terms of increase in revenue obtained by various service classes with the base case of accepting demands without any protection. Results are provided to demonstrate the effectiveness of our framework.

Capacity fairness of WDM networks with grooming capabilities

Storage and Retrieval for Image and Video Databases, 2001

ABSTRACT

Attack monitoring and localization in All-Optical Networks

Cluster Computing, 2006

The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or i... more The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or indistinct print, colored or poor quality illustrations and photographs, print bleed-through, substandard margins, and improper alignment can adversely affect reproduction. In the unlikely event that the author did not send a complete manuscript and there are missing pages, these will be noted. Also, if unauthorized copyright material had to be removed, a note will indicate the deletion. UMI UMI Microform 3308906

Non-arithmetic carry chains for reconfigurable fabrics

2007 25th International Conference on Computer Design, 2007

Reconfigurable fabrics cater to a wide variety of applications, but have adopted specialized comp... more Reconfigurable fabrics cater to a wide variety of applications, but have adopted specialized components to allow efficient implementation of performance-critical arithmetic operations. Carry chains have been integrated into the fabric typically as an optimized ripple-carry chain. However, in non-arithmetic operations the carry chain goes unused, when it could be a valuable adjacent-cell interconnect resource. This paper presents a cell architecture facilitating reuse, as well as an analysis of the potential benefits of reuse for an sampling of common of algorithms using commercial FPGAs. Technology map experiments indicate that a variety of applications can benefit from reuse, with utilized routing resources reduced by up to 13% and maximum clock frequency increased by up to 47%.

Reduction of green house gas emission by clean power trading

2010 IEEE Energy Conversion Congress and Exposition, 2010

It is well known that the CO2 emitted by fossil energy is one of the major reasons that result in... more It is well known that the CO2 emitted by fossil energy is one of the major reasons that result in global warming. It is still an open question about how to reducxe CO2 emission by the implementation of an investment plan for clean power systems. In this paper, we propose a clean power trading method among neighboring regions such that we can reduce CO2 emission in a large region and reduce the imbalance between the power demand and supply in a region caused by the fluctuation of clean energy. With the five states with rich wind energy in America as an example, we use the quantitative computation results of the five states (from a modeling framework designed by ourselves [3]) to show that our proposed clean power trading method can help reduce CO2 emission and realize balance.

Scalable Segment Routing—A New Paradigm for Efficient Service Provider Networking Using Carrier Ethernet Advances

Journal of Optical Communications and Networking, 2015

ABSTRACT Segment routing has recently been proposed in the IETF toward making IP/MPLS networks se... more ABSTRACT Segment routing has recently been proposed in the IETF toward making IP/MPLS networks service-oriented while simplifying network operations. Segment routing computes paths at the source node using node identifiers and adjacency identifiers conjoined together to create a source-routed path. We propose a scalable transport paradigm as an enabler toward implementing segment routing in provider networks. We propose omnipresent Ethernet, our modification of carrier Ethernet (which is based on source-routed, binary-routed labels embedded in an Ethernet frame), to implement segment routing. We identify some of the scalability issues of the segment-routing proposal in the context of source-routing overhead. To absolve scalability issues of segment routing, two routing schemes that implement multidomain source-routing techniques are proposed. The hierarchical segment-routing (H-SR) scheme is proposed, which deploys a limited number of special nodes called swap nodes that are capable of label swapping to implement routing. The swap-node placement problem is formulated as an integer linear program to minimize the total routing distance within a network. Three heuristic techniques for swap-node selection based on centrality paradigms are presented. The H-SR scheme is further improved by a proposed multisegment-routing (M-SR) scheme that assumes all nodes in the network to be capable of label swapping. The H-SR and M-SR schemes are shown to significantly enhance the scalability of segment routing. A test-bed is built using carrier Ethernet hardware to support segment routing that validates the implementation of the proposed schemes. A simulation model to evaluate the schemes from a scalability perspective and their associated trade-offs is presented.

Optimal location management algorithms for mobile networks

Proceedings of the 4th annual ACM/IEEE international conference on Mobile computing and networking - MobiCom '98, 1998

ABSTRACT

A p-cycle based survivable design for dynamic traffic in WDM networks

GLOBECOM '05. IEEE Global Telecommunications Conference, 2005., 2005

AbstractAchieving both high capacity efficiency and fast restoration speed is a primary goal of ... more

Optimal light trail design in WDM optical networks

2004 IEEE International Conference on Communications (IEEE Cat. No.04CH37577), 2004

The enabling technology for supporting IP centric traffic over optical transport networks evolves... more The enabling technology for supporting IP centric traffic over optical transport networks evolves as the amount of traffic grows. In this paper, we first review a recently proposed concept called light trails. Light trails can enable high speed provisioning, accommodate multi-granularity traffic, support high data rates and offer a good candidate for carrying IP traffic over optical networks. Next, we focus on light trail design. We propose a two-step approach for solving the light trail design problem. The first step is called traffic matrix preprocessing, it divides single long hop paths into several shorter paths that satisfy the hop-length constraint. In the second step, the light trail design problem is formulated as an integer linear programming (ILP) optimization problem. The results obtained from our experiments show that the resulting light trail network has high wavelength utilization.

Dynamic non-continuous single slot advance reservation over wavelength routed networks

2012 International Conference on Computing, Networking and Communications (ICNC), 2012

We investigate the problem of provisioning light-paths for dynamic advance reservation (AR) reque... more We investigate the problem of provisioning light-paths for dynamic advance reservation (AR) requests in all-optical wavelength division multiplexed networks. We propose a two-phase novel routing, slot, and wavelength assignment (RWSA) technique called Non-Continuous Single-Slot Advance Reservation (NC-SSAR). We propose two NC-SSAR heuristics, one with only lightpath segmentation (SEG-NC-SSAR) and the other with lightpath segmentation and lightpath switching (LPS-NC-SSAR). We briefly