the proceedings contain 56 papers. the topics discussed include: should I stay or should I go? maximizing lifetime with relays;network lifetime maximization in delay-tolerant sensor networks with a mobile sink;achievi...
ISBN:
(纸本)9780769547077
the proceedings contain 56 papers. the topics discussed include: should I stay or should I go? maximizing lifetime with relays;network lifetime maximization in delay-tolerant sensor networks with a mobile sink;achieving high lifetime and low delay in very large sensors networks using mobile sinks;efficient mobile data collection with mobile collect;throughput maximization in mobile WSN scheduling with power control and rate selection;coverage estimation in heterogeneous visual sensor networks;adaptive synchronization control with multi-level buffer in wireless multimedia sensor networks;timely report delivery in social swarming applications;personal marks and community certificates: detecting clones in wireless mobile social networks;a ubiquitous publish/subscribe platform for wireless sensor networks with mobile mules;and distributed subspace projection in wireless sensor networks using computational codes.
Commodity multi-core SMPs may generate an enormous amount of coherency traffic. However, the impact of coherence traffic and snoop filtering on parallel program scalability has not attracted sufficient attention. We e...
详细信息
ISBN:
(纸本)9780769547497
Commodity multi-core SMPs may generate an enormous amount of coherency traffic. However, the impact of coherence traffic and snoop filtering on parallel program scalability has not attracted sufficient attention. We experimentally analyze the shared data access patterns of four typical applications having different memory layout. An OpenMp optimized execution model is derived for each application with emphasis on data dependencies and implied coherence messages. Using an 8-core SMP we present the obtained speedups versus change in the number of cores and problem scale. A discussion of potential limitation on scalability due to the application or SMP is presented. To assess the coherence behavior and its impact on scalability of parallel programs, a synthetic benchmark which alternates the data block ownership among two cores of the same or different processors is presented. It is found that coherence overheads including snoop filtering are responsible of significant limitation on parallel program scalability. For 8-core SMPs, speedup can be reduced by factors of 2.5 and 5 for row-major and column-major access patterns as compared to the use of private data, respectively. A truly parallel coherence protocol implementation is needed to provide truly scalable shared-memory model.
Emerging technologies such as the Internet of things generate huge amounts of network traffic and data which lead to significant challenges in a) ensuring availability of resources on-demand, b) recognizing emergent a...
详细信息
ISBN:
(纸本)9781467327404;9781467327404
Emerging technologies such as the Internet of things generate huge amounts of network traffic and data which lead to significant challenges in a) ensuring availability of resources on-demand, b) recognizing emergent and abnormal behavior, and c) making effective decisions for efficient network operations. Network traffic data exhibit spatiotemporal patterns. Learning and maintaining the currently elusive rich semantics based on analyzing such patterns would help in mitigating those challenges. In this paper, we propose the concept of a network "memory" (or NetMem) to support smarter data-driven network operations as a foundational component of next generation networks. NetMem will enable networking objects to understand autonomously, at real-time, on-demand, and at low cost semantics with different levels of granularity and related to various network elements. Guided by the fact that human activities exhibit spatiotemporal data patterns;and the human memory extracts and maintains semantics to enable accordingly learning and predicting new things, we design NetMem to mimic functionalities of that memory. NetMem provides capabilities for semantics management through uniquely integrating data virtualization for homogenizing massive data originating from heterogeneous sources, cloud-like scalable storage, associative rule learning to recognize data patterns, and hidden Markov models for reasoning and extracting semantics clarifying normal/abnormal behavior. NetMem provides associative access to data patterns and relevant derived semantics to enable enhancements in early anomaly detection, more accurate behavior prediction and satisfying QoS requirements with better utilization of resources. We evaluate NetMem using simulation. Preliminary results demonstrate the positive impact of NetMem on various network management operations.
A distributed computation is usually modeled as a finite partially ordered set (poset) of events. Many operations on this poset require computing meets and joins of subsets of events. the lattice of normal cuts of a p...
详细信息
In this paper, we describe an evolution of the mobile Evolved Packet Core (EPC) utilizing Software Defined Networking (SDN) that allows the EPC control plane to be moved into a data center. the EPC is a mobile aggrega...
详细信息
distributed and multi-agent systems come in many forms, serving various purposes and spanning a large variety of properties. they include networked processors communicating via message-passing, shared-memory systems i...
详细信息
ISBN:
(纸本)9783642280726
distributed and multi-agent systems come in many forms, serving various purposes and spanning a large variety of properties. they include networked processors communicating via message-passing, shared-memory systems in which processes interact by reading from and writing to shared variables, and even systems of robots that coordinate their actions by viewing each others8217; actions and locations, and perform no explicit communication actions. While distinct systems may differ completely in their detailed structure and operation, fundamental to all distributed systems is the fact that decisions are performed based on a local, partial, view of the the state of the system. Proper coordination among different sites of such a system requires information flow among them, to ensure that decisions are taken based on appropriate knowledge. Reasoning about when elements of the system do or do not know relevant facts is therefore a central aspect of the design and construction of distributed systems and distributed protocols.
the problem of robust distributed estimation in wireless sensor network (WSN) when few sensor nodes are faulty is addressed here. In WSN, each sensor node collects scalar measurements of some unknown parameters and th...
详细信息
ISBN:
(纸本)9783642280726;9783642280733
the problem of robust distributed estimation in wireless sensor network (WSN) when few sensor nodes are faulty is addressed here. In WSN, each sensor node collects scalar measurements of some unknown parameters and then estimates the parameter of interest from the data collected across the network. An iterative distributed linear parameter estimated algorithm is proposed here by using diffusion co-operation. Each node updates its information by using the data collected by it and the information received from the neighbours. the mean square error (MSE) of distributed estimation schemes increases whenever any faulty sensor node in the network fails to transmit correct information, which leads to inaccurate estimation. Hence a robust diffusion linear estimation algorithm using Hubber's cost function is proposed here in order to improve the accuracy of the estimation.
this paper presents the design of a distributed multi-physics integration tool, withthe aim of providing high-level support for the integration of existing applications into full featured multi-physics simulation too...
详细信息
In wireless sensor network each sensor node collects data related to some unknown parameters, corrupted by independent Gaussian noise. then the objective is to estimate the parameter from the data collected across the...
详细信息
ISBN:
(纸本)9783642280726;9783642280733
In wireless sensor network each sensor node collects data related to some unknown parameters, corrupted by independent Gaussian noise. then the objective is to estimate the parameter from the data collected across the network in distributed manner. the distributed estimation algorithm should be energy efficient, provides high estimation accuracy, and is fast in convergence. But the conventional distributed algorithm involves significant communication overhead and is also not robust to the impulsive noise which is common in wireless sensor network environment. Consequently these algorithms defeat the basic purpose of wireless sensor network. this paper studies the problem of robust adaptive estimation in impulsive noise environment using robust cost function like Wilcoxon norm and Huber cost function. Further in order to reduce the amount of communication overhead, block distributed LMS is incorporated.
Loosely connected distributedcomputing systems present a changing environment to the programs that they execute. Dynamic load balancing (DLB) algorithms are employed to address the problem of relocating tasks when pa...
详细信息
ISBN:
(纸本)9783642326509
Loosely connected distributedcomputing systems present a changing environment to the programs that they execute. Dynamic load balancing (DLB) algorithms are employed to address the problem of relocating tasks when parts of a distributedcomputing system become unavailable while other parts become idle. this paper presents a novel DLB algorithm based on cemetery formation in ant colonies. the algorithm builds on previous work to formulate ant-inspired DLB algorithms that aim to reduce the time needed to complete the parallel execution of multiple, independent tasks, where resources as well as tasks are diverse with respect to their performances and durations, respectively. the new algorithm is compared with its predecessors, based on division of labour in ant colonies, and pure, opportunistic load balancing, established as the baseline.
暂无评论