Abstract: Service oriented networks are distributed computing infrastructures that provide widely distributed resources. These networks are dynamic and their size and complexity continue to increase and allow to users a ubiquitous access to available resources and services. Therefore, efficient query routing approaches in large and highly distributed service oriented networks are required and need to be adaptive in order to cope with a dynamically changing environment. In this paper, a query routing approach based on mobile agents and random walks with a reinforcement learning technique is presented. By enhancing random walks with a reinforcement learning mechanism centered on users’ satisfaction, this approach allows dynamic and self-adaptive location of required resources. Peers incorporate knowledge from past and present queries which will be used during next searches by mobile agents to select their next hops. This approach is analyzed through two query routing techniques using the network simulator ns2.
Abstract: Sophisticated on-chip interconnects using packet and circuit switching techniques were recently proposed as a solution to non-scalable shared-bus schemes currently used in Systems-on-Chip (SoCs) implementation. Different interconnect architectures have been studied and adapted for SoCs to achieve high throughput, low latency and energy consumption, and efficient silicon area. Recently, a new on-chip interconnect architecture by adapting the WK-recursive network topology structure has been introduced for SoCs. This paper analyses and compares the energy consumption and the area requirements of Wk-recursive network with five common on-chip interconnects, 2D Mesh, Ring, Spidergon, Fat-Tree and Butterfly Fat-Tree. We investigated the effects of load and traffic models and the obtained results show that the traffic models and load that ends processing elements has a direct effect on the energy consumption and area requirements. In these results, WK-recursive interconnect generally has a higher energy consumption and silicon
area requirements in heavy traffic load.
Abstract: Network on Chip (NoC) is a discipline research path that primarily addresses the global communication in System on Chip (SoC). It is inspired and uses the same routing and switching techniques needed in multi-computer networks. Current shared-bus based on-chip communication architectures generally have limited scalability due to the nature of the buses especially when complex on-chip communication SoC is needed. The main goal is to have a dedicated communication infrastructure in the system that can scale up while minimizing the area and power. The selected topology of the components interconnects plays prime rule in the performance of NoC architecture as well as routing and switching techniques that can be used. In this paper, we introduce a new NoC architecture by adapting a recursive topology structure. An experimental study is performed to compare this structure with basic NoC topologies represented by 2D mesh and Spidergon. The analysis illustrates the main features of this topology and its unique benefits. The simulation results show that recursive network outperforms 2D mesh and Spidergon in main performance metrics.
Abstract: Ubiquitous computing deals with providing users accesses to a wide range of services at any time, every where, and from a variety of devices. The monitoring and controlling accesses to these services are one of the fundamental issues that must be faced in the context of ubiquitous computing environments. To address this issue, an access control must be granted to services in order to regulate their usage. In this paper, a secure approach based on contract negotiation and electronic signature for monitoring and controlling accesses to services in ubiquitous environments is presented. In this approach, client agents and server agents are bounded by contracts: the server agent expects that the client agent will not attempt to access other services than those it required, and the client agent expects that the server agent will provide the required service. The specification and modeling of electronic signature process using Petri net together with the validation of its properties are presented.
Abstract: The Partitioned Global Address Space (PGAS) programming paradigm offers ease-of-use in expressing parallelism through a global shared address space while emphasizing performance
by providing locality awareness through the partitioning of this address space. Therefore, the interest in PGAS programming languages is growing and many new languages have emerged and
are becoming ubiquitously available on nearly all modern parallel architectures. Recently, new parallel machines with multiple cores are designed for targeting high performance applications. Most of the
efforts have gone into benchmarking but there are a few examples of real high performance applications running on multicore machines. In this paper, we present and evaluate a parallelization technique
for implementing a local DNA sequence alignment algorithm using a PGAS based language, UPC (Unified Parallel C) on a chip multithreading architecture, the UltraSPARC T1.
Abstract: In this paper, a reinforcement learning approach based on the creation of affinity relationships between users having similar preferences and interests is presented. This approach suits pervasive environments to promote computerbased human interactions for spontaneous service emergence. By mimicking the human immune system behavior for the implementation of pervasive applications, services or user interests are represented by agents that can establish relationships based on affinities. Affinity corresponds to the adequacy with which two services could bind to share common interest attributes. These affinities are adjusted or reinforced by users’ satisfaction regarding their interaction and dynamic network condition changes.
Abstract: The clonal selection is a mechanism used by the natural immune system to select cells that recognize the antigens to proliferate. The proliferated cells are subject to an affinity maturation process, which improves their affinity to the selective antigens. The concept of clonal selection is a vitally important one to the success of the human immune system, and it provides an excellent example of the principles of selection at work. The Positive and negative selection is another interesting mechanism in the immune system that work together to both retain cells that recognize the self peptides, while also removing cells that recognize any self peptides. In this paper, a cloning-based algorithm inspired by the clonal and the positive/negative selection mechanism of the natural immune system is presented. This algorithm is inherently parallel and the cloning strategy employs greedy criteria which lends to an adaptive approach. The well known TSP is used to illustrate the approach with experimental comparison with Ant approach. Simulations demonstrate that this approach generates good solutions to traveling salesman problem and greatly improve the convergence speed compared to the Ant-based optimization approach.
Abstract: Large scale networks such as computational Grid is a distributed computing infrastructure that can provide globally available network resources. Their size and complexity continue to increase and permit an almost ubiquitous availability of resources; users become able to access network resources irrespective to their location. Therefore, new resource management and access models are required and need to be highly flexible with self-organizing capabilities in order to cope with a dynamically changing environment. In this paper, a distributed and adaptive holonic multi-agent system for resource discovery in Grids is presented. Simulations are presented to demonstrate that structuring servers into holons improves the performance of request resolution processes in dynamic Grid environment.
Abstract: Since its creation in 1990, World Wide Web has increased the popularity of Internet which becomes an important source of information or services for all people over the world. The dynamic nature of the Web draws attention to the need for continuous support and updating of Web information retrieval systems. Web crawling is the process of discovery and maintenance of large-scale web data. Crawlers achieve this process by following the Web pages hyperlinks to automatically download a partial snapshot of the Web. In this paper, an agent-based approach, through three scenarios, for parallel and distributed Web crawling is presented. Simulations with ns2 show that the cloning based mobile agents scenario outperforms the single and multiple mobile agents scenarios.
Abstract: In this chapter, alternative operational models to the traditional Client/server paradigm (CSP) to design and development of ubiquitous and pervasive applications are presentend: Adaptive Servers/Client Paradigm (SCP) and Spontaneous Service Emergence Paradigm (SEP). Service discovery and composition systems based on these three paradigms and proposed in the literature are also presented with emphasis on a self-organizing and self-adapting approaches inspired by the immune system to implement SCP and SEP.
Abstract: VANETs are emerging as new network environments for developing future automotive applications. Numerous research issues have recently been identified and should be tackled before real implementations of pervasive vehicular applications and services. The design and the implementation of efficient and scalable routing protocols constitute one main issue. In this paper, we study and evaluate the performance of a geographical protocol in VANETs using real vehicle mobility scenarios. Performance metrics such as the control load and the average latency are evaluated using ns2
Abstract: With the increasing complexity of Multi-Core System-on-Chip (MCSoC) and its communications requirement, Network-on-Chip (NoC) has emerged as a solution of non-scalable shared bus schemes currently used in MCSoC implementation. Recently, a new NoC structure based on WK-recursive network was analyzed and compared to 2D Mesh structure based on several performance metrics such as packet losses, throughput, message delay, and network load. In this paper, we focus on the evaluation of energy consumption because of the importance of this feature in mobile systems that are typically battery-based systems and have to be energy efficient. A simple energy model is presented and simulation results are conducted to compare the Wk-recursive and 2D Mesh on-chip interconnects. The main objective is to provide the designer with initial insight on this network on-chip interconnect and the relationship between application traffics and energy consumption
Abstract: Network-on-chip has been proposed as an alternative to bus-based system to achieve high performance and scalability. The topology of on-chip interconnect plays a crucial role in system on chip performance, energy, and area requirements. In this paper, an on-chip interconnects architecture based on WK-recursive network is proposed. WK-recursive structure is analyzed and compared to 2D mesh and Spidergon structures. Simulation results show that WK-recursive on-chip interconnect generally outperforms the other architectures.
Abstract: On-Chip Interconnect (OCI) plays a prime role in the entire system-on-chip performance, energy consumption, and area requirements. OCI has become a successful research field given the dramatic increase in the number of processors and other functional units (IPs) that need to be integrated on a single chip. Current Systems-on-Chip (SoCs) use bus-based systems which become a bottleneck because of scalability, energy efficiency and frequency limitations. New sophisticated interconnects were recently proposed as a research direction in SoC design, including distinct topologies and specific routing and switching techniques. This paper analyzes and compares five common NoC configurations, 2D Mesh, Ring, Spidergon, Fat-Tree(FT) and Butterfly Fat-Tree (BFT). These configurations are simulated for different traffic scenarios that imitate certain application domains, and comparison results for different performance metrics are presented.
Abstract: Position-based routing protocols were recently proposed as a solution to non-scalable topology-based routing protocols for large scale mobile ad hoc networks. In these position-based routing protocols, nodes may not maintain explicit routes. Each node needs only to know its own position and the position of its one-hop neighbors to forward packets. In this paper, a performance evaluation of the position-based routing protocol DREAM for large scale ad hoc networks is presented. Several performance metrics such as the control load and the average latency are evaluated using ns2 for up to 500 nodes generated according to the realistic mobility model RealMobgen.
Abstract: Many new Partitioned Global Address Space (PGAS) programming languages have recently emerged and are becoming ubiquitously available on nearly all modern parallel architectures. PGAS programming languages provide ease-of-use through a global shared address space while emphasizing performance by providing locality awareness and a partition of the address space. Examples of PGAS languages include the Unified Parallel C (UPC), Co-array Fortran, and Titanium languages. Therefore, the interest in complexity design and analysis of PGAS algorithms is growing and a complexity model to capture implicit communication and fine-grain programming style is required. In this paper, a complexity model is developed to characterize the performance of algorithms based on the PGAS programming model. The experimental results shed further light on the impact of data distributions on locality and performance and confirm the accuracy of the complexity model as a useful tool for the design and analysis of PGAS-based algorithms.
Abstract: In this paper, a distributed and adaptive approach for resource discovery in peer-to-peer networks is presented. This approach is based on the mobile agent paradigm and the random walk technique with reinforcement learning to allow for dynamic and self-adaptive resource discovery. More precisely, this approach augments random walks with a reinforcement learning technique where mobile agents are backtracked over the walked path in the network. A metric recording an affinity value that incorporates knowledge from past and present searches is maintained between nodes. The affinity value is used during a search to influence the selection of the next hop. This approach is evaluated with the network simulator ns2.
Abstract: Ubiquitous and pervasive computing are recent paradigms with a goal to provide computing and communication services anytime and everywhere. In ubiquitous computing, the main objective is to provide users the ability to access services and resources all the time and irrespective to their location, while in pervasive computing, the main objective is to provide spontaneous emergent services created on the fly by mobiles that interact by ad hoc connections. The design and development of ubiquitous and pervasive applications require new protocols and architectures to efficiently use resources and services. Gaber's classification of interaction paradigms emphasizes two alternative paradigms to the traditional client-to-server paradigm (CSP) to design and implement Ubiquitous and Pervasive applications, which are the Adaptive Services-to-Client Paradigm (SCP) and the Spontaneous Service Emergence Paradigm (SEP). These paradigms involve context awareness, auto-adaptive and emergence principles that could be implemented by self-organizing and reactive intelligent networks.
Approaches and protocols that are mainly proposed to meet these requirements can be classified into two major research directions. The first direction addresses semantic languages to specify and describe application components, including complex planning mechanisms that utilize these descriptions to generate the whole application or composite service. The second direction aims to develop architectures that enable scalable, fault tolerance, and adaptive applications in dynamic environments. This talk will survey current approaches and protocols proposed to design and built ubiquitous and pervasive applications. We will present service-oriented architecture principles with service description languages. We will also highlight new research directions that can leverage the tremendous potential of this new category of applications.
Abstract: The design and development of ubiquitous and pervasive applications require new operational models that can permit an efficient use of resources and services and a reduction of the need for the administration effort typical in client-to-server networks. In ubiquitous computing, the main objective is to provide users the ability to access services and resources all the time and irrespective to their location, while in pervasive computing, the main objective is to provide spontaneous emergent services created on the fly by mobiles that interact by ad hoc connections. Service discovery and composition in ubiquitous and pervasive environments requires dealing with several issues such as service matching and selection, coordination and management, scalability, fault tolerance, and adaptive approaches to users' contexts and network conditions. Gabers' classification of interaction paradigms emphasizes two alternative paradigms to the traditional client-to-server paradigm (CSP) to design and implement Ubiquitous and Pervasive applications, which are the Adaptive Services-to-Client Paradigm (SCP) and the Spontaneous Service Emergence Paradigm (SEP). These paradigms involve context awareness, auto-adaptive and emergence principles that could be implemented by self-organizing and reactive intelligent networks.
This talk will survey the service discovery and composition methods. We will present the service-oriented architecture principles with service description languages, in particular, syntactic and semantic description languages and ontologies. We will demonstrate how to develop applications that suit ubiquitous and pervasive environments. We will also highlight new research directions that can leverage the tremendous potential of this new category of applications.
Abstract: PGAS programming languages provide ease-of-use through a global shared address space while emphasizing performance by providing locality awareness and a partition of the address space. Many new Partitioned Global Address Space (PGAS) programming languages have recently emerged and are becoming
ubiquitously available on nearly all modern parallel architectures. Examples of PGAS languages include the Unified Parallel C (UPC), Co-array Fortran, and
Titanium languages. In this tutorial, we will focus on the UPC programming language which is based on C and extended with global pointers and data
distribution declarations for shared data. In this language, a number of threads can work independently in a Simple Program Multiple Data (SPMD) model.
Threads communicate through the shared memory and can access shared data while a private object may be accessed only by its own thread. The PGAS
memory model, used in UPC, supports three different kinds of pointers: private pointers pointing to the shared address space, pointers living in shared
space that also point to shared data, and private pointers pointing to data in the thread’s own private space. Using these features, programmers need to
only specify the data to be distributed across threads and reference them through special global pointers. The aim of this tutorial is to show the features
provided by PGAS programming model in comparison with the other programming models such as the Message passing and data parallel models. The
focus will be on UPC as PGAS-based language by introducing their control structures and by showing its features using examples of programs.
Abstract: Ubiquitous and Pervasive Computing (UPC) are recent paradigms with a goal to provide computing and communication services anytime and everywhere. In Ubiquitous Computing (UC), the objective is to provide any mobile device an access to available services in an existing network all the time and everywhere. Pervasive Computing (PC), often considered the same as ubiquitous computing in the literature, is a related concept that can be distinguished from ubiquitous computing in terms of environment conditions. Building ubiquitous and pervasive applications to carry out these modes of interaction require new methodologies and architectures that involve many distributed and dynamically interacting components. In this tutorial, we will first reviews the latest research efforts addressing service discovery and composition issues in UPC. We present new research efforts and directions related to the efficient implementation of platforms for UPC. Furthermore, approaches that enable the design and development of practical applications in the context of ubiquitous and pervasive computing (UPC) will be presented.
