The Experts below are selected from a list of 83157 Experts worldwide ranked by ideXlab platform
Jeffrey H. Reed - One of the best experts on this subject based on the ideXlab platform.
-
beyond overlay reaping mutual benefits for primary and secondary networks through Node Level cooperation
IEEE Transactions on Mobile Computing, 2017Co-Authors: Xu Yuan, Wenjing Lou, Sastry Kompella, Yi Shi, Xiaoqi Qin, Thomas Y Hou, Scott F Midkiff, Jeffrey H. ReedAbstract:Existing spectrum sharing paradigms have set clear boundaries between the primary and secondary networks. There is either no or very limited Node-Level cooperation between the primary and secondary networks. In this paper, we develop a new and bold spectrum-sharing paradigm beyond the state of the art for future wireless networks. We explore network cooperation as a new dimension for spectrum sharing between the primary and secondary users. Such network cooperation can be defined as a set of policies under which different degrees of cooperation are to be achieved. The benefits of this paradigm are numerous, as they allow integrating resources from two networks. There are many possible Node-Level cooperation policies that one can employ under this paradigm. For the purpose of performance study, we consider a specific policy called U nited cooperation of P rimary and S econdary (UPS) networks. UPS allows a complete cooperation between the primary and secondary networks at the Node Level to relay each other's traffic. As a case study, we consider a problem with the goal of supporting the rate requirement of the primary network traffic while maximizing the throughput of the secondary sessions. For this problem, we develop an optimization model and formulate a combinatorial optimization problem. We also develop an approximation solution based on a piece-wise linearization technique. Simulation results show that UPS offers significantly better throughput performance than that under the interweave paradigm.
-
On Throughput Region for Primary and Secondary Networks With Node-Level Cooperation
IEEE Journal on Selected Areas in Communications, 2016Co-Authors: Xu Yuan, Feng Tian, Y. Thomas Hou, Wenjing Lou, Hanif D. Sherali, Sastry Kompella, Jeffrey H. ReedAbstract:Cooperation has become an essential element in spectrum sharing between the primary and secondary networks. A new trend in cooperation is to allow the primary and secondary networks to cooperate on the Node Level for data forwarding. This new paradigm allows to pool network resources from both the primary and secondary networks and allows users in each network to access a much richer network infrastructure in a combined network. This paper offers an in-depth study of such Node-Level cooperation by explaining its optimal throughput curve—the maximum achievable throughput for both the primary and secondary users. We formulate the problem as a multicriteria optimization problem with the goal of maximizing the throughput of both the primary and secondary users. Through a novel approach based on weighted Chebyshev norm, we transform the multicriteria optimization problem into a single criteria optimization problem and find a sequence of Pareto-optimal points iteratively. Based on the Pareto-optimal points, we construct the throughput curve and show that it provides an $\varepsilon $ -approximation to the optimal curve. We prove some important properties of the optimal throughput curve. Through a case study, we show that the throughput region (the area under the throughput curve) under Node-Level cooperation is substantially larger than that when there is no Node-Level cooperation.
-
DySPAN - Optimal throughput curve for primary and secondary users with Node-Level cooperation
2015 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2015Co-Authors: Xu Yuan, Feng Tian, Y. Thomas Hou, Wenjing Lou, Hanif D. Sherali, Sastry Kompella, Jeffrey H. ReedAbstract:A new trend in cooperation is to allow the primary and secondary networks to cooperate on the Node Level for data forwarding, which we call the UPS paradigm. This paper offers an in-depth study of the UPS paradigm in terms of its optimal throughput curve — the maximum achievable throughput for both primary and secondary users. We formulate the problem into a multicriteria optimization problem with the goal of maximizing the throughput of both primary and secondary users. Through a novel approach based on weighted Chebyshev norm, we transform the multicriteria optimization problem into a single criteria optimization problem and find a sequence of Pareto-optimal points iteratively. Based on the Pareto-optimal points, we find the throughput curve and show that it is e-approximation to the optimal. Through a case study, we show that the throughput region (the area under the throughput curve) under a UPS paradigm is substantially larger than that under the interweave paradigm.
Richard Han - One of the best experts on this subject based on the ideXlab platform.
-
Nodemd diagnosing Node Level faults in remote wireless sensor systems
International Conference on Mobile Systems Applications and Services, 2007Co-Authors: Veljko Krunic, Eric Trumpler, Richard HanAbstract:Software failures in wireless sensor systems are notoriously difficult to debug. Resource constraints in wireless deployments substantially restrict visibility into the root causes of Node-Level system and application faults. At the same time, the high cost of deployment ofwireless sensor systems often far exceeds the cumulative cost of allother sensor hardware, so that software failures that completely disable a Node are prohibitively expensive to repair in real worldapplications, e.g. by on-site visits to replace or reset Nodes. We describe NodeMD, a deployment management system that successfully implements lightweight run-time detection, logging, and notificationof software faults on wireless mote-class devices. NodeMD introduces a debug mode that catches a failure before it completely disables a Node and drops the Node into a stable state that enables further diagnosis and correction, thus avoiding on-site redeployment. We analyze the performance of NodeMD on a real world application ofwireless sensor systems.
Xu Yuan - One of the best experts on this subject based on the ideXlab platform.
-
beyond overlay reaping mutual benefits for primary and secondary networks through Node Level cooperation
IEEE Transactions on Mobile Computing, 2017Co-Authors: Xu Yuan, Wenjing Lou, Sastry Kompella, Yi Shi, Xiaoqi Qin, Thomas Y Hou, Scott F Midkiff, Jeffrey H. ReedAbstract:Existing spectrum sharing paradigms have set clear boundaries between the primary and secondary networks. There is either no or very limited Node-Level cooperation between the primary and secondary networks. In this paper, we develop a new and bold spectrum-sharing paradigm beyond the state of the art for future wireless networks. We explore network cooperation as a new dimension for spectrum sharing between the primary and secondary users. Such network cooperation can be defined as a set of policies under which different degrees of cooperation are to be achieved. The benefits of this paradigm are numerous, as they allow integrating resources from two networks. There are many possible Node-Level cooperation policies that one can employ under this paradigm. For the purpose of performance study, we consider a specific policy called U nited cooperation of P rimary and S econdary (UPS) networks. UPS allows a complete cooperation between the primary and secondary networks at the Node Level to relay each other's traffic. As a case study, we consider a problem with the goal of supporting the rate requirement of the primary network traffic while maximizing the throughput of the secondary sessions. For this problem, we develop an optimization model and formulate a combinatorial optimization problem. We also develop an approximation solution based on a piece-wise linearization technique. Simulation results show that UPS offers significantly better throughput performance than that under the interweave paradigm.
-
On Throughput Region for Primary and Secondary Networks With Node-Level Cooperation
IEEE Journal on Selected Areas in Communications, 2016Co-Authors: Xu Yuan, Feng Tian, Y. Thomas Hou, Wenjing Lou, Hanif D. Sherali, Sastry Kompella, Jeffrey H. ReedAbstract:Cooperation has become an essential element in spectrum sharing between the primary and secondary networks. A new trend in cooperation is to allow the primary and secondary networks to cooperate on the Node Level for data forwarding. This new paradigm allows to pool network resources from both the primary and secondary networks and allows users in each network to access a much richer network infrastructure in a combined network. This paper offers an in-depth study of such Node-Level cooperation by explaining its optimal throughput curve—the maximum achievable throughput for both the primary and secondary users. We formulate the problem as a multicriteria optimization problem with the goal of maximizing the throughput of both the primary and secondary users. Through a novel approach based on weighted Chebyshev norm, we transform the multicriteria optimization problem into a single criteria optimization problem and find a sequence of Pareto-optimal points iteratively. Based on the Pareto-optimal points, we construct the throughput curve and show that it provides an $\varepsilon $ -approximation to the optimal curve. We prove some important properties of the optimal throughput curve. Through a case study, we show that the throughput region (the area under the throughput curve) under Node-Level cooperation is substantially larger than that when there is no Node-Level cooperation.
-
DySPAN - Optimal throughput curve for primary and secondary users with Node-Level cooperation
2015 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2015Co-Authors: Xu Yuan, Feng Tian, Y. Thomas Hou, Wenjing Lou, Hanif D. Sherali, Sastry Kompella, Jeffrey H. ReedAbstract:A new trend in cooperation is to allow the primary and secondary networks to cooperate on the Node Level for data forwarding, which we call the UPS paradigm. This paper offers an in-depth study of the UPS paradigm in terms of its optimal throughput curve — the maximum achievable throughput for both primary and secondary users. We formulate the problem into a multicriteria optimization problem with the goal of maximizing the throughput of both primary and secondary users. Through a novel approach based on weighted Chebyshev norm, we transform the multicriteria optimization problem into a single criteria optimization problem and find a sequence of Pareto-optimal points iteratively. Based on the Pareto-optimal points, we find the throughput curve and show that it is e-approximation to the optimal. Through a case study, we show that the throughput region (the area under the throughput curve) under a UPS paradigm is substantially larger than that under the interweave paradigm.
Dhabaleswar K. Panda - One of the best experts on this subject based on the ideXlab platform.
-
accelerating checkpoint operation by Node Level write aggregation on multicore systems
International Conference on Parallel Processing, 2009Co-Authors: Xiangyong Ouyang, Karthik Gopalakrishnan, Dhabaleswar K. PandaAbstract:Clusters and applications continue to grow in size while their mean time between failure (MTBF) is getting smaller. Checkpoint/Restart is becoming increasingly important for large scale parallel jobs. However, the performance of the Checkpoint/Restart mechanism does not scale well with increasing job size due to constraints within the file system. Furthermore, with the advent of multi-core architecture, the situation is aggravated due to larger number of processes running on the same Node, trying to checkpoint simultaneously. This results in increased number of file writes at the time of checkpointing which leads to performance degradation. As a result, deployment of Checkpoint/Restart mechanisms for large scale parallel applications is limited. In this work, we explore the Checkpoint/Restart mechanism in MVAPICH2, which uses BLCR as the checkpointing library. Our profiling of the checkpoints for the NAS parallel benchmarks revealed a large number of small file writes interspersed with large writes. Based on these observation we propose to optimize checkpoint creation by classifying checkpoint file writes into small writes, medium writes and large writes based on their size of data to write, and use write aggregation to optimize the small and medium writes. At the aggregation threshold of 512KB, the implementation of our design in BLCR shows improvements from 27% to 32% over the original BLCR in terms of time cost to checkpoint an MPI application.
-
ICPP - Accelerating Checkpoint Operation by Node-Level Write Aggregation on Multicore Systems
2009 International Conference on Parallel Processing, 2009Co-Authors: Xiangyong Ouyang, Karthik Gopalakrishnan, Dhabaleswar K. PandaAbstract:Clusters and applications continue to grow in size while their mean time between failure (MTBF) is getting smaller. Checkpoint/Restart is becoming increasingly important for large scale parallel jobs. However, the performance of the Checkpoint/Restart mechanism does not scale well with increasing job size due to constraints within the file system. Furthermore, with the advent of multi-core architecture, the situation is aggravated due to larger number of processes running on the same Node, trying to checkpoint simultaneously. This results in increased number of file writes at the time of checkpointing which leads to performance degradation. As a result, deployment of Checkpoint/Restart mechanisms for large scale parallel applications is limited. In this work, we explore the Checkpoint/Restart mechanism in MVAPICH2, which uses BLCR as the checkpointing library. Our profiling of the checkpoints for the NAS parallel benchmarks revealed a large number of small file writes interspersed with large writes. Based on these observation we propose to optimize checkpoint creation by classifying checkpoint file writes into small writes, medium writes and large writes based on their size of data to write, and use write aggregation to optimize the small and medium writes. At the aggregation threshold of 512KB, the implementation of our design in BLCR shows improvements from 27% to 32% over the original BLCR in terms of time cost to checkpoint an MPI application.
-
PVM/MPI - Impact of Node Level Caching in MPI Job Launch Mechanisms
Recent Advances in Parallel Virtual Machine and Message Passing Interface, 2009Co-Authors: Jaidev K. Sridhar, Dhabaleswar K. PandaAbstract:The quest for petascale computing systems has seen cluster sizes expressed in terms of number of processor cores increase rapidly. The Message Passing Interface (MPI) has emerged as the defacto standard on these modern, large scale clusters. This has resulted in an increased focus on research into the scalability of MPI libraries. However, as clusters grow in size, the scalability and performance of job launch mechanisms need to be re-visited. In this work, we study the information exchange involved in the job launch phase of MPI applications. With the emergence of multi-core processing Nodes, we examine the benefits of caching information at the Node Level during the job launch phase. We propose four design alternatives for such Node Level caches and evaluate their performance benefits. We propose enhancements to make these caches memory efficient while retaining the performance benefits by taking advantage of communication patterns during the job startup phase. One of our cache design --- Hierarchical Cache with Message Aggregation, Broadcast and LRU (HCMAB-LRU) reduces the time involved in typical communication stages to one tenth while capping the memory used to a fixed upper bound based on the number of processes. This enables scalable MPI job launching for next generation clusters with hundreds of thousands of processor cores.
N. Prabakaran - One of the best experts on this subject based on the ideXlab platform.
-
Fusion Centric Decision Making for Node Level Congestion in Wireless Sensor Networks
ICT and Critical Infrastructure: Proceedings of the 48th Annual Convention of Computer Society of India- Vol I, 2014Co-Authors: N. Prabakaran, K. Naresh, R. Jagadeesh KannanAbstract:The data-centric wireless sensor networks comprise numerous autonomous tiny Nodes forms random topology in nature. Applications oriented WSNs immensely used for monitoring harsh environment. Its unique constrains are distinguishing it from traditional networks by energy, lifetime, fault tolerance, scalability and computational power. When they are deployed randomly sensing & generating vast amount of data, for which they are being used. Network meets Congestion, if huge volume of data passed. To eradicate it, misbehaving Nodes are identified and skilled for self-healing without human intervention. Existing approaches focus on controlling link Level congestions not Node Level. Our proposed fusion-centric scheme controls Node congestion. To achieve this, selectively concentrate on intermediate Level. Misbehaving Nodes are identified by using their historic data based on fault Level occurred. Lifetime is determined by allocation-rate and more radio signal usage. Our scheme keeps the network without consuming much resource. Node Level control is needed for self-configuring WSNs.
-
Data propelling scheme for Node Level congestion control in WSNs
2012Co-Authors: N. Prabakaran, K. Geetha, K. JananiAbstract:The rising data centric Wireless sensor network (WSN) is recently emerging technology, which offers the key to isotonic situation in an un-interruptible environment application. It has the ability of keen observation and ties the information with outside world. WSN tenuously collects the dense amount of data, further communicates with the sink through various intermediate Nodes. It delivers reckonable response, when unpredictable variation occurs in the environment. Rushing of the enormous data directs to overcrowd in the routing path, which affects vibrant strength of the network. Many of the existing schemes focused on link Level congestion. We propose data propelling scheme, which discusses the congestion free environment in Node Level congestion. Once congestion notification bit is set, new data buffer Node awakened, which is near-by to congested Node. After its activation, all the data are re-directed to the data buffer occurred further CN bit is cleared. Aspire is, make processing rate which is to be equal to transmitting rate to avoid funneling effect. Our scheme is not consuming too much of energy of new data buffers and resources. It annotates that Nodes are intended for working for long time without human intervention. Further our scheme is concentrating on congestion free critical environmental applications, otherwise which drastically decrease the performance of the network.
-
Rate Optimization Scheme for Node Level Congestion in Wireless Sensor Networks
2011 International Conference on Devices and Communications (ICDeCom), 2011Co-Authors: N. Prabakaran, B. Shanmuga Raja, R. Prabakaran, V. R. Sarma DhulipalaAbstract:The Application specific wireless sensor network differs basically from the general data network. It focuses on tight communication but restricted in storage, lifetime, power and energy. The WSNs consists of unbelievable network load and it leads to energy wastage and packet loss. Many of the existing concepts are developed for link Level congestion control. The Rate optimization technique for Node Level congestion will assist to control the traffic at Node Level. Except source and sink Node the remaining Nodes may participate in forwarding the packets towards the communication direction. The rate based adjustment technique is applied to avoid packet dropping in order to save the network resources. We are proposing this scheme to avoid the buffer overflow and it is not taking too much energy consumption in the communication. This scheme will assist to improve the throughput, efficiency and resource saving. Node Level congestion control is effectively needed for WSN, because the Node deployment can be anywhere. We are Introducing this scheme using the network simulators extended tool called mannasim.
-
Open stream scheme for Node Level congestion control in WSNs
3rd International Conference on Trendz in Information Sciences & Computing (TISC2011), 2011Co-Authors: N. Prabakaran, K. Geetha, K. JananiAbstract:The data centric Wireless sensor network (WSN) is firmly emerging technology, which addresses the solution to a un tethered environment applications. It has the ability to observe the target and makes the link to outside world. WSN remotely collects the huge volume of data and communicating the signal from the Sink. It provides measurable response to the changes in the environment. Rushing of the enormous data directs to jamming in the network, which affects large portions of the network. Many of the existing schemes focused on link Level congestion. We propose open stream scheme, which discusses the congestion free environment in Node Level congestion. It maintains stream called open stream. Open stream is followed, when abnormal changes occurred in the environment and rest is for normal data flow. Aspire is, the Node should be able to identify which is to be forwarded and ignored and it should not drop the real time information because it cannot be replaced by recent information. Our scheme is not spending too much of energy and resources. It annotates that which real time information should be broadcasted towards the sink properly, since Node deployment is in large scale environment. Further our scheme is concentrating on congestion free and less energy consumption for critical environmental applications.
-
Data Propelling Scheme for Node Level Congestion Control in WSNs
Data mining and knowledge engineering, 2010Co-Authors: N. Prabakaran, K. Geetha, K. JananiAbstract:The rising data centric Wireless sensor network (WSN) is recently emerging technology, which offers the key to isotonic situation in an un-interruptible environment application. It has the ability of keen observation and ties the information with outside world. WSN tenuously collects the dense amount of data, further communicates with the sink through various intermediate Nodes. It delivers reckonable response, when unpredictable variation occurs in the environment. Rushing of the enormous data directs to overcrowd in the routing path, which affects vibrant strength of the network. Many of the existing schemes focused on link Level congestion. We propose data propelling scheme, which discusses the congestion free environment in Node Level congestion. Once congestion notification bit is set, new data buffer Node awakened, which is near-by to congested Node. After its activation, all the data are re-directed to the data buffer and retrieved back in need even at unusual changes occurred further CN bit is cleared. Aspire is, make processing rate which is to be equal to transmitting rate to avoid funneling effect. Our scheme is not consuming too much of energy of new data buffers and resources. It annotates that Nodes are intended for working for long time without human intervention. Further our scheme is concentrating on congestion free critical environmental applications, otherwise which drastically decrease the performance of the network.