Search

Long-term evolution in unlicensed spectrum (LTE-U) can make use of centralized scheduling, interference coordination and other technologies to achieve better spectrum efficiency (SE). As the evolution of cloud computing, mobile edge computing (MEC) sinks the computing and storage capacity from the centralized data center to the edge of the network, which is the key technology to achieve low delay and high speed. However, the traditional centralized scheme in small cell networks (SCNs) structure will bring huge signal overheads. In order to adapt to the complex and changeable network system, this paper proposes a distributed resource and power allocation scheme under MEC environment, which enables small base stations (SBSs) to work autonomously. The SBSs need only little information exchange through the information cloud (IC) and finally obtain the global optimal SE. Simulation results confirm the correctness and effectiveness of the proposed scheme, and demonstrate the superiority of the distributed scheme over the centralized scheme.

We develop and commercialize autonomous machines, such as logistic robots and self-driving cars, around the globe. A critical challenge to our—and any—autonomous machine is accurate and efficient localization under resource constraints, which has fueled specialized localization accelerators recently. Prior acceleration efforts are point solutions in that they each specialize for a specific localization algorithm. In real-world commercial deployments, however, autonomous machines routinely operate under different environments and no single localization algorithm fits all the environments. Simply stacking together point solutions not only leads to cost and power budget overrun, but also results in an overly complicated software stack.This paper demonstrates our new software-hardware co-designed framework for autonomous machine localization, which adapts to different operating scenarios by fusing fundamental algorithmic primitives. Through characterizing the software framework, we identify ideal acceleration candidates that contribute significantly to the end-to-end latency and/or latency variation. We show how to co-design a hardware accelerator to systematically exploit the parallelisms, locality, and common building blocks inherent in the localization framework. We build, deploy, and evaluate an FPGA prototype on our next-generation self-driving cars. To demonstrate the flexibility of our framework, we also instantiate another FPGA prototype targeting drones, which represent mobile autonomous machines. We achieve about $2 \times$ speedup and $4 \times$ energy reduction compared to widely-deployed, optimized implementations on general-purpose platforms.

As a fundamental component in the autonomous driving technology stack, High Definition Maps (HD map) provide high-precision descriptions of the environment. It enables extremely accurate perception and localization while improving the efficiency of path planning. However, the HD map’s extremely large data volume poses great challenges for the real-time and safety requirements of autonomous driving. Based on our real-world deployment experiences, we first demonstrate how the existing data transmission mechanism is weak in supporting HD map services. To address this problem, we propose an HD map data service mechanism on top of Vehicle-to-Infrastructure (V2I) data transmission under a tight time and energy budget. By this mechanism, the selected road side unit (RSU) nodes cooperate on map provisioning tasks and transmit HD map data proportionately. Furthermore, we model the real-time map data service into a partial knapsack problem and develop a greedy data transmission algorithm. Experimental results confirm that the proposed mechanism can ensure the real-time HD map data service meanwhile meeting the energy limits.

The large software applications of today provide abstractions of the real-life systems that they support. A digital model of the system, and of the changes that occur within, are being maintained and updated, as triggered by real-life events. Morphologically, such applications contain several distinct architectural entities: databases holding the state, central components describing how the system reacts to external events and mechanisms through which the user can view the current state and issue new commands. Each of these entities may use distinct paradigms and employ different technologies. A production-ready software application ends up assembling a relatively high technology stack and provides the final abstractions for both the problem and its solution. In this paper we propose a short-circuit for the long chain of technologies that are usually employed in large, production-ready software applications. The resulting architecture is a distributed, message-based system which behaves as a hybrid between a database and a runtime environment. The system operates with persistent and live entities, encapsulating both state and operations and therefore easily assimilated with OOP classes.

Emerging smart services, such as indoor smart parking or patient monitoring and tracking in hospitals, incur a significant technical roadblock stemming primarily from a lack of cost-effective and easily deployable localization framework that impedes their widespread deployment. To address this concern, in this paper we present a low-cost, indoor localization and navigation system, which performs continuous and real-time processing of Bluetooth Low Energy (BLE) and IEEE 802.15.4a compliant Ultra-wideband (UWB) sensor data to localize and navigate the concerned entity to its desired location. Our approach depends upon fusing the two feature sets, using the UWB to calibrate the BLE localization mechanism.

Edge environments are generating an increasingly large amount of data due to the proliferation of edge devices. Accommodating this large influx of data at edge servers is a challenging issue. While some data can be processed as it is generated, others must be stored for later access. This paper proposes the features that a new edge-native storage system must possess including support for user mobility and node fluctuation. To motivate this, we first describe several emerging edge applications and their data needs. We then describe the challenges in meeting these needs. We then evaluate an out-of-the-box cloud storage system, Cassandra, to assess it’s suitability as an edge storage system due to many edge-friendly features. We determined that while a cloud-based storage system can be ported to the edge meeting some of the challenges, other challenges require new solutions. Based on the challenges and the results of Cassandra case study, we propose a set of design principles for a new edge-native storage system.

Fog computing (also known as edge computing) is a decentralized computing architecture that seeks to minimize service latency and average response time in IoT applications by providing compute and network services physically close to end-users. Fog environment consists of a network of fog nodes and IoT applications are composed of containerized microservices communicating with each other. Due to limited resources of fog nodes, it is often not possible to deploy all the containers of an application on a single fog node. Therefore, communicating containers need to be distributed on multiple fog nodes. Distribution and management of containerized IoT applications is always a critical issue to the system performance in a fog environment. Kubernetes, an open-source system, has grown into a container orchestration standard by simplifying the deployment and management of containerized applications. Despite the progress made by the academia and industry with respect to container management and the wide-scale acceptance of Kubernetes in cloud environments, container management in fog environment is still in the early stage in terms of research and practical deployment. This article aims to fill this gap by analyzing the expediency of Kubernetes container orchestration tool in the fog computing model. The paper also highlights limitations with the current Kubernetes approach and provide ideas for further research to adapt to the needs of the fog environment. Lastly, we provide experiments that demonstrate the feasibility and industrial practicality of deploying and managing containerized IoT applications in the fog computing environment.

Neural networks are widely used in many applications ranging from classification to control. While these networks are composed of simple arithmetic operations, they are challenging to formally verify for properties such as reachability due to the presence of nonlinear activation functions. In this paper, we make the observation that Lipschitz continuity of a neural network not only can play a major role in the construction of reachable sets for neural-network controlled systems but also can be systematically controlled during training of the neural network. We build on this observation to develop a novel verification-aware knowledge distillation framework that transfers the knowledge of a trained network to a new and easier-to-verify network. Experimental results show that our method can substantially improve reachability analysis of neural-network controlled systems for several state-of-the-art tools.

Modern society relies on smart systems like internet of things (IoT) and cyber physical systems (CPS) to monitor and control physical processes. The widespread deployment of IoT and CPSs result in fast growth of sensor data as physical processes are constantly monitored by billions of IP-enabled sensors (44 zettabytes by 2020). Hence, fog nodes are deployed to make network edge rich in computing resources to enable real-time data analytics using artificial intelligence/machine learning (AI/ML) for Big data generated from IoT and CPSs. This paper proposes IoT/CPS ecosystem for smart grid (SG) utilizing industry 4.0 concept to manage and control the loads using an intelligent predictive controller based on artificial neural network (ANN). The ANN is trained to predict the loads in certain districts based on previous smart meter readings installed at consumers and substations. This is a novel approach which integrates IoT/CPSs ecosystem into electric power system to deliver energy to consumers with high efficiency, reduce the cost, optimize the energy consumption, improve the reliability and enable real-time monitoring of power consumption.

Survivability is an important component in the requirements in elastic optical networks (EONs). We examine here the significance of network survivability design against multiple-link failures under dedicated protection, shared risk link group (SRLG) and bandwidth squeezing schemes. The proposed mixed integer linear programming (MILP) formulation seeks to derive some different types of protection considering routing, spectrum assignment, grooming, modulation format as well as shared risk link group constraints. The proposed MILP provides efficient survivability results and resource savings (in terms of spectrum) for a full design of modern EONs.

This paper presents enhancements of Service Oriented SystemJ (SOSJ) framework, which extends a system-level language based on GALS model of computation SystemJ with services, into a new programming paradigm amenable for designing dynamic distributed automation systems such as reconfigurable manufacturing systems. The new paradigm combines correct-by-construction software systems development available in SystemJ with the dynamic features of service oriented architecture. The new approach introduces macro states into fundamental concurrent and distributed entities of SOSJ, called clock domains, which address typical behaviors in dynamic distributed systems. We showcase the use of the new paradigm on an example of reconfigurable manufacturing scenarios in a dynamic manufacturing system.

It is presented theoretical statements about decentralized systems technology, blockchain networks, their structure as well as main functioning principles, structure and material about Hyperledger platform. It is examined Hyperledger services architecture, spheres of use and such important aspects as smart-contracts and their application, as well as advantages of using this platform. It is also modelled and explained the algorithm and schematic diagram of voting network built with Hyperledger platform.

In this article, we develop a comprehensive framework to characterize the coverage probability of backscatter communication empowered cellular Internet-of-Things (IoT) sensor networks (SNs). The developed framework considers hierarchical cellular type deployment topology which is practically useful for various IoT applications. In contrast to existing studies, the framework is geared towards system level performance analysis. Our analysis explicitly considers the dyadic fading experienced by the links and spatial randomness of the network nodes. To ensure tractability of analysis, we develop novel closed-form bounds for quantifying the coverage probability of SNs. The developed framework is corroborated using Monte Carlo simulations. Lastly, we also demonstrate the impact of various underlying parameters and highlight the utility of the derived expressions for network dimensioning.

As the number of cores grow in HPC systems, so does the effect of system noise on applications running on these systems. With the knowledge that future large-scale parallel computer systems, including exascale systems, will operate under an overall power bound, we claim to have found a solution that can counter the effects of noise. We present two methods that estimate the effects of noise on an application and then optimally redistributes power among nodes, such that the effects of noise are "hidden".

Smart grid systems for onshore oil fields use real-time, high-speed field data from intelligent electronic devices (IEDs) to make fast and intelligent decisions that increase power system reliability and minimize power outages. For an efficient smart grid system, a reliable communications network to the IEDs and centralized controllers is critical for high-speed control and data collection. Communications networks that use conventional fiber networks are not always cost-effective for large dispersed oil fields, which have hundreds of miles of medium-voltage overhead distribution systems. This paper discusses the implementation of a smart grid system for a large dispersed oil field using radios as its communications network. The solution includes high-speed load shedding, online monitoring, event reporting, oscillography, and engineering access. This paper also discusses the process used to design and test the radio technology, including the evaluation of its success metrics, network security, radio path study, and optimization.

Multi-source data fusion to support intelligent transportation system (ITS) is a promising service offered by mobile edge computing (MEC). With the fusion results delivered in near real-time, drivers or autonomous vehicles can peak around the corner, extend sensing range, reinforce and validate local observations to make safer and smarter driving decisions. However, downloading too much data increases the service delay thus undermines the fusion computing service performance. In this paper, we analyze the optimal downloading strategies of vehicles. By establishing the optimization indicator to monitor and evaluate fusion computing service, we use a hierarchical game, which is equivalent to a mathematical programming with equilibrium constraints (MPEC), to formulate the intersection between the MEC and vehicles. Through analysis, we transform the MPEC problem into a solvable single-layer optimization problem. We also provide an unpractical centralized approach, which has immense signaling overhead and exponentially-growing complexity, as a performance upper bound. Numerical results validate the theoretical analysis and demonstrate that the proposed downloading strategy has near-optimal performance in terms of system utility and service delay.

Intelligent cyber-physical systems, such as robots, are emerging computing devices that autonomously and directly interact with the physical world. The new characteristics of these devices motivate further research questions different from those addressed in traditional computing technology. Based on an in-depth investigation of the relationship between a typical example, robotic perception, and distributed computing, this paper tries to explore the challenges and opportunities brought by intelligent cyber-physical systems to distributed computing. The preliminary answers to three questions are given: "Why should we introduce distributed computing into cyber-physical intelligence", "What kind of distributed architecture can contribute to cyber-physical intelligence" and "What challenges brought by intelligent cyber-physical systems to distributed computing infrastructure?" A multi-scale hybrid distributed architecture for cyber-physical intelligence named as Music as well as our initial practices towards enabling this architecture is also presented.

The rapid mainstream adoption of cloud computing and the corresponding spike in the energy usage of big data systems make the efficient management of cloud computing resources a more pressing issue than ever before. To this end, numerous online algorithms such as Receding Horizon Control and Online Balanced Descent have been designed. However it is difficult for cloud service providers to select the best control algorithm dynamically for resource provisioning when confronted with consumer resource demands that are notoriously unpredictable and volatile. Furthermore, it highly possible that it might not be the case for any one algorithm to consistently perform well over the months-long contract period. In this paper, we first exemplify the need to address non-stationarity in cloud computing by showcasing traces from MS Azure. We then develop a novel meta-algorithm that combines change point detection and online optimization. The new algorithm is shown to outperform existing solutions in real-world trace-driven simulations.

Mobile edge computing (MEC) systems face unevenly distributed communication and computation traffics over both time and space. In order to match with the traffics, it is beneficial for different neighboring MEC systems to cooperate in sharing their distributed communication and computation resources. This paper considers two neighboring MEC systems each with one access point (AP) serving one user, where each user can offload the computation tasks to the respective AP for remote execution. We propose a new joint computation and spectrum cooperation approach, such that the two systems can share their computation and spectrum resources to enhance their respective system performance. In particular, we minimize the weighted sum energy consumption (for both communication and computation) of the two MEC systems, by jointly optimizing the task offloading decisions at the users (for computation resource sharing) and the spectrum bands shared between the two systems. We obtain the optimal solution to the formulated problem in a semi-closed form by applying standard convex optimization techniques. Numerical results show that the proposed joint cooperation design significantly reduces the energy consumption of the two systems, as compared to other benchmark schemes without such joint cooperation.

While disaggregation has been successfully used for more than two decades to separate storage from compute (i.e., SAN/NAS systems), disaggregating tightly coupled resources like CPU, memory or accelerators has been so far considered unfeasible due to the hard dependency between their performance and the latency and bandwidth provided by their physical interconnect. We argue that modern optical networks make full datacenter disaggregation feasible in practice. We present our ongoing work on disaggregation by introducing the dReDBox architecture that completely separates datacenter resources into modular physical units interconnected via a high speed reconfigurable optical network. We discuss the current prototype and highlight challenges and work ahead.

This work aims to formulate a procedure to establish a graded trust system within autonomous vehicular networks. A trust management system in VANETs typically falls into one of two categories: centralized or distributed. Our solution is a hybrid system which merges the two canonical designs of a centralized and distributed structure that utilizes to capabilities of both systems. In this paper we provide the design of a trust system that takes into account both central and local evaluations to establish trust. In order to validate the trust system we design a simulation model in MATLAB that captures the interaction between different vehicles and between the vehicles and the Central Authority. The simulations show a high decision performance for the trust management system and validate the proposed scheme as a coherent grading system.

With rapid increases in Cloud users and their workload, the Qos (quality of service) is decreasing proportionally. Providing better computing services, managing large number of cloud users and reducing time as well as energy on cloud data center can only be achieved by efficient live VM migration technique. Modern cloud computing service mainly depends upon live VM migration. In this paper we have reviewed all the existing live VM migration techniques with their advantages and disadvantages. Their working and application with future scope has been stated briefly. Comparisons have been done between Pre-copy and Post-copy VM Migration techniques by simulation corresponding to CPU uses, Memory and Network as parameters. Then a Hybrid VM Migration technique has been proposed and by comparison we proved it is better than the pre copy and post copy.

A majority of multi-rate real-time systems are constrained by a multitude of timing requirements, in addition to the traditional deadlines on well-studied response times. This means, the timing predictability of these systems not only depends on the schedulability of certain task sets but also on the timely propagation of data through the chains of tasks from sensors to actuators. In the automotive industry, four different timing constraints corresponding to various data propagation delays are commonly specified on the systems. This paper identifies and addresses the source of pessimism as well as optimism in the calculations for one such delay, namely the reaction delay, in the state-of-the-art analysis that is already implemented in several industrial tools. Furthermore, a generic framework is proposed to compute all the four end-to-end data propagation delays, complying with the established delay semantics, in a scheduler and hardware-agnostic manner. This allows analysis of the system models already at early development phases, where limited system information is present. The paper further introduces mechanisms to generate job-level dependencies, a partial ordering of jobs, which need to be satisfied by any execution platform in order to meet the data propagation timing requirements. The job-level dependencies are first added to all task chains of the system and then reduced to its minimum required set such that the job order is not affected. Moreover, a necessary schedulability test is provided, allowing for varying the number of CPUs. The experimental evaluations demonstrate the tightness in the reaction delay with the proposed framework as compared to the existing state-of-the-art and practice solutions.

Wireless sensor network are widely used in different area application, especially in the field of surveillance and monitoring tasks. So for the implementation in practical life many constraint and challenge arise. In the present paper we are focused on one of main such constraint called deployment of sensor node for better coverage. In this paper we review on the different techniques on deployment like artificial bee colony, particle swarm optimization, genetic algorithm, artificial immune system and compare them on different aspects like complexity, scalability, region of interest, suitability to static or mobile wireless sensor network and applicability to multiple objective etc. We also present pseudo codes for each planned algorithm.

SpaceWire is valuable because it facilitates the development of spacecraft subsystems such as payload instruments, mass memory, and onboard computers. On the other hand, it takes much time and effort for developers to configure an initiator of the SpaceWire network because they have to take account of the entire SpaceWire network in a spacecraft. As the target network becomes larger, the path addressing and the packet collision-free timeslot allocation are harder for the developers to configure. Furthermore, the configuration tables of the initiator should satisfy various constraints, such as the bandwidth limitation and priority of specific packets. These constraints are different in each spacecraft. In order that the developers can design the large-scale SpaceWire network efficiently, automatic configuration table generation under the constraints is indispensable. This paper presents a constraint-based configuration table generator (CTG) that automatically provides reliable redundant path routing and collision-free timeslot allocation for required transactions in the target topology. We apply a constraint solver to the CTG to set many kinds of user-defined constraints in the network. For example, the bandwidth limitation, priority of the packets, and other various constraints can be easily inputted into the CTG. The CTG automatically generates configuration tables satisfying these constraints. Additionally, the CTG reports network topology views with bandwidth utilization ratios. This helps developers to verify whether a generated configuration is just as designed. The CTG can also notify developers that their requirements cannot be solved. In this paper, we show the feasibility and effectiveness of this tool through evaluation using a large-scale SpaceWire network case.

Electrical distribution networks worldwide are facing frequent capacity challenges due to the widespread roll out of various distributed energy resources (DERs). A number of demand response (DR) mechanisms have been developed in order to circumvent the problems and enhance the flexibility of the distribution network. While the existing centralized control system remains its crucial role for reliable and secure grid operation, distributed intelligence is a complement technology with a focus on dividing the control task into a number of simpler problems and solve them with minimum exchange of information. Based on the recent developments of distributed intelligence, this paper discusses a decentralized approach to enable demand response for managing the congestions more efficiently. The approach is validated with simulations for representative Dutch low-voltage (LV) networks.

As more than 40K service providers are advertising 600K or more IP prefixes, scalability of routing has emerged to be a matter of great concern. In this paper, to explore a spectrum of designs, we consider a Cloud-Assisted Routing (CAR) framework which follows a hybrid and opportunistic approach by keeping the high priority tasks at the router and use an adaptive router-cloud integration when beneficial. In particular, it maintains most of the control plane functions at the cloud and least of it at local router and vice versa for the data plane. Comparing the performance and monetary cost benefits between CAR, we discuss: i) What is the break-even point? ii) What are the key components of CAR to be monetarily beneficial? iii) What are the constraints that will make the traditional routing favorable than CAR?

Data Centers (DCs) continue to become increasingly complex, due to comprising multiple functional entities (e.g. routing, orchestration). Managing the multitude of interconnected components in the DC becomes difficult and error prone, leading to slow service provisioning, lack of QoS support, etc. Moreover, the lack of simple solutions for managing the configuration and behavior of the DC components makes the DC hard to configure and slow in adapting to changes in business needs. In this paper, we propose a model-driven framework for policy-based management for DCs, to simplify not only the service provisioning but also the configuration management of the various DC components. The implemented prototype is presented and a series of tests are performed to assess its performance and to gain key insights about policy based management.

Cloud computing that is based on Infrastructure as a Services model, allows the system administrators to identify resources or services to deploy their applications. Selection of the most appropriate provider for a particular application is a difficult task as there are huge numbers of services offered by considerable number of providers that are not directly comparable and have similar functionality. Additionally these systems must comply with non-functional requirements as they evolve. Certain traditional techniques are employed to verify the non-functional properties of critical systems at design time. In this paper, a new framework is suggested that supports the process of deploying applications in cloud providers, using a comparison of high level requirements predominantly non-functional requirements (NFR). Experiments have already been conducted with conclusive results wherein matching of user constraints during service selection process is done. The experiment uses Aspect Oriented Paradigm (AOP), XML and graph transformation. The relevance of the framework is illustrated using the Remote Patient Monitoring (RPM) scenario. The results demonstrate that the model considerably improves the process by identifying conflicting NFR. Based on this work done, the next logical step is to extend it to Cloud Computing.

Deterministic behavior is an important paradigm for verification and validation of real-time systems such as those on crewed space vehicles and robotic spacecrafts. Providing deterministic characteristics of the data transfer for the spacecraft that uses the SpaceWire technology is an essential problem, especially for autonomous vehicles like satellites. Deterministic data delivery guarantees that transmission of data from one node of the onboard network to the target node would not take longer than the specified time period. Such task is solved by using specific communication protocols that include a scheduling service. Modern space industry demands a protocol running over SpaceWire, which can provide deterministic data transmission characteristics. The scheduling problem becomes more complicated, when we consider a number of communication protocols simultaneously operating in every node of the network, e.g. RMAP, STP-ISS, CCSDS PTP. Traffic from different transport protocols can interfere especially while getting access to the SpaceWire link in a node. The paper presents Multiprotocol Scheduling Service — a new scheduling protocol for SpaceWire networks which provides deterministic data delivery in a network and performs arbitration of data coming from several transport protocols. Firstly, we give an overview of TDMA-based network protocols that have been developed for the ground-based and onboard networks. Then, we present Multiprotocol Scheduling Service which is based on the STP-ISS scheduling mechanism and extended with additional features.

In Service-Oriented Architecture (SOA), dedicatedintermediate nodes called load balancers are usually deployed in data centers (DC) in order to balance the load among multiple instances of an application service and to optimize the resource utilization. However, the addition of these nodes increases the installation and operational cost of DCs. These load balancers distribute incoming flows to multiple outgoing ports usually by hashing them. Several techniques are used in order to select the outgoing ports e.g. round robin, queue length, feedback from neighbors etc. Such load balancing approaches do not considergetting live feedback from the service end and therefore are not able to dynamically change the amount of allocated resources. In this paper, a distributed load management scheme isproposed for service oriented networks based on the currentInternet architecture. In this scheme, lightweight interconnected management agents are used to decide the availability for a particular service instance and help in optimal distribution of the flows. The proposed scheme can also be applied in other emerging internetworking architectures such as RINA.

Tarragon is an actor-based programming model and library for implementing latency tolerant asynchronous event driven simulations. It is novel in its support for meta data describing run time virtualized process structures, which may be optimized as a free-standing object. We demonstrate early results with a synthetic benchmark, and observe that Tarragon can mask communication costs with ongoing computation

Three-hop cascaded directed wireless relay network is considered, where relay nodes work in time division duplexing (TDD) mode. We investigate the optimal scheduling for capacity achieving with decode-and-forward (DF) strategy. By defining feasible network state (FNS), we formulate the problem into linear program, which schedules the activeness of all FNSs. Closed-form solution is obtained for general three-hop configuration, showing that DF is optimal to achieve the network capacity min{C 1 C 2 /C 1 +C 2 } = min(C 1 , C 3 )C 2 /min(C 1 , C 3 )+C 2 , where C k is the link capacity of the hop k. We also give the scheduling demonstration. Performance analyses are provided, including the degree of freedom (DoF) in multiple-input multiple-output (MIMO) scenario. Moreover, if extra single-hop message is allowed the network can support a higher DF rate as max(C 1 , C 3 )C 2 /min(C 1 , C 3 )+C 2 . The ultimate results with infinite relay capability are further deduced, which shows that the three-hop network can be superior to the corresponding two-hop scenario and indicates that the massive MIMO technique can be applied at the relay nodes to overcome the bottleneck of half duplexing constraint.

The focus of my Phd project is on the evaluation of the dependability of critical infrastructures, e.g. energy distribution and gas networks. The modeling formalism of hybrid Petri nets with random variables forms the basis of our modeling approach. We plan to rigorously evaluate dependability using discrete-event simulation and methods of Statistical Model Checking and extend existing approaches with methods of rare-event simulation.

The recent advances with respect to the costs, size, and power consumption of electronic components paved the way for System of Systems (SoS), Cyber-Physical Systems (CPS), or the Internet of Things (IoT). As a next stage, these developments currently motivate the consideration of Complex Swarm Systems (CSS), i.e., continuously running systems that will dynamically change after deployment and are connected by heterogeneous components which can join and leave the system at any time. Due to this dynamic nature and the constant reconfigurations, it is not possible to completely verify those systems with conventional verification methods anymore. Therefore, we propose a new methodology which follows a different scheme: Instead of trying to verify all possible behavior of a CSS (which, due to the vast number of possible instantiations or connections of the heterogeneous components, becomes an impracticable task anyway), we aim for verifying that, at least, no scenario which violates certain (safety-critical) forbidden actions is possible. To this end, solutions for model-based verification are employed. By means of a case study, the feasibility and promises of the proposed methodology are illustrated.

Complex robotic systems like the DLR Hand Arm System integrates a huge amount of sensors and actuators. Hence system design and especially communication infrastructure design has to be flexible in a heterogeneous network of different bus systems. As basis, a modular electronic concept as well as a well-structured communication concept is necessary [1]-[3]. SpaceWire suites well to these requirements since on one hand it supports arbitrary topologies from point to point up complex network structures and on the other hand it is easy to implement and has a small footprint. Additionally its logical and regional addressing scheme enables changes in the topology during runtime simply by reprogramming the routing switches. However, such changes require expert knowledge. This work presents a graphical method to setup and configure SpaceWire network topologies. This enables non-experts to replace or integrate new components to the system or to set up a test bed to investigate a specific aspect. The developer provides a GraphML description [4] specifying the SpaceWire communication capabilities of each component. Thus the user is able to adapt the SpaceWire network topology or to set up a new one simply by merging the different GraphML descriptions of the used components. A post process is afterwards used to analyze the GraphML description and to generate the necessary configuration messages according to the topology. This enables faster development cycles and rapid prototyping. The approach is approved and explained using the SpaceWire network topology of the DLR Hand Arm System.

In this paper, we study how to cluster Remote Radio Heads (RRHs) into Virtual Base-Stations (VBSs) in a Cloud-based Radio Access Network to optimally manage the tradeoff between improving the performance of cell-edge users and maintaining high spatial reuse for the overall system. We develop Gibbs-sampling based algorithms that can find the desirable global VBS configuration from an arbitrarily given set of allowable VBS configurations. While Gibbs-sampling has been used to solve other wireless control problems, its application to VBS clustering faces new challenges both due to the difficulty in estimating the quality of a VBS configuration under rapid channel variations, and due to a new global coupling effect. We leverage Random Matrix Theory to develop a method that can quickly estimate the quality of a VBS configuration based only on average channel statistics. Further, we use perturbation analysis to develop a distributed approximation of the Gibbs sampler to circumvent the global coupling effect, which then allows different parts of the network to search for better VBS configurations in parallel. Our numerical results demonstrate how the proposed algorithm can be used as a general tool to evaluate the system performance under a variety of clustering constraints.

Cloud Computing has long extended beyond the original focus of providing scalable on-demand resources for web applications and is now also ubiquitous in batch-style data processing applications. Employing Cloud services for data analysis tasks is also a viable alternative for researchers who are limited by their locally available compute power and in the need for timely execution. However, the provisioning and deployment of machines and applications at Infrastructure-as-a-Service (IaaS) providers is a non-trivial task for the average scientist. Within this paper, we propose a framework for automating the deployment and execution of existing applications in a data-parallel fashion in Cloud environments with only negligible effort by the user. Our evaluation of a real-world scientific use case exhibits a significant speedup compared to local execution.

Cities, buildings, and spaces are smart when their "behavior" properly mimics their contexts, accommodating changes and evolving situations. This is only possible if they are able to collect data from the environment using distributed probes, and to filter, correlate, and analyze them appropriately. In this paper we adopt service-based solutions to abstract the probes that are distributed in the environment, as well as to provide the analysis capabilities required to make timely analyses on how a space is evolving. In such scenarios the amount of sensor data that one might need to deal with can be extremely high. Therefore, we provide an infrastructure that can manipulate high degrees of raw sensor data efficiently. The solution is based on complex event processing and recurring patterns, and is exemplified in the context of smart buildings.

Network service chaining allows composing services out of multiple service functions. Traditional network service functions include, e.g., firewalls, TCP optimizers, web proxies, or higher layer applications. Network service chaining requires flexible service function deployment models. Related work facilitating service chaining include, e.g., the network service header proposal discussed at the IETF or the complementary work on network function virtualization (NFV) at ETSI. This position paper presents a high-level concept and architecture to enable service chaining using Software Defined Networking (SDN), specifically OpenFlow in a telecommunication environment. The paper discusses required functionalities, challenges, and testbed aspects to implement and test such an approach. Finally, the set of implemented service functions and management interfaces are highlighted to demonstrate the approach as a proof of concept for a selection of relevant use cases.

Mobile ad-hoc network is a collection of mobile nodes which forms an instant network without fixed topology and can be arranged dynamically. Energy saving and security are important issue in MANET. Network coding technique is used to reduce energy consumption by less transmissions in MANET. To achieve a security, there are many encryption scheme are available. Out of which p-coding technique is lightweight encryption scheme which provides confidentiality. P-coding is to let the source randomly permute the symbol of each packet. So eavesdropper can't obtain the meaningful information without knowing the permutation encryption function and coding vector.

In a mobile ad hoc network (MANET) there is a collection of wireless devices which moving in seemingly adventitious directions and communicating with one another without establishing the real infrastructure. Communicating nodes in a Mobile Ad hoc Network normally seek the help of other intermediate nodes to establish communication channels. Thus, the communication may be via many intermediate nodes from source to destination. Multi-path routing is better one than the single path routing in mobile ad hoc networks, this is because many path routing allows the lay foundation of many path between a single source and single destination node. But in multipath routing, there is a problem of overhead management and transportation performance. So the aim of this work is to design such a wireless system which uses reactive multipath routing protocol who gives better data transportation performance than baseline protocols. Also it improves throughput and packet delivery ratio with reduction in overhead and end to end delay. The proposed approach contains implementation of better routing protocol which provide proper route updates, set require parameters at proper value, generate wireless network which has low error rate and fast packet generation. We used ns-2 to simulate. Simulation results will show better data transportation performance than baseline protocols. Also it will show improvements in throughput and packet delivery ratio with reduction in overhead and end to end delay.

Free-space optical networks have serious block erasures due to atmospheric turbulence and require an entirely new network architecture from Layer 1 to Layer 4 for big data flows.

In this paper we describe the main features of the open-source Net2Plan tool. Built on top of a technology-agnostic vendor-neutral multilayer network representation, Net2Plan is designed to assist users in the evaluation of built-in or original user-developed planning algorithms. In addition, users can analyze their designs using either reports or a simulation tool for in-operation scenarios like network resilience, connection-admission-control, time-varying traffic resource allocation, or even combinations of them, using built-in or custom event generators or reaction algorithms. We motivate how a paradigm shift to an open-source view of network planning emphasizes the power of distributed peer-review, collaboration cycles and transparency to create high-quality software at an accelerated pace and lower cost.

Load in network is rapidly increases day by day by the user input or by the machine communication, so it will affect the performance of the computing nodes, if we will not justify the load of the computing node, it means we will not consider a desirable output from the computing node, load of the computing node is calculated on the basis of queue length and available memory. The main objective of this work is to improve the throughput as well as minimized the CPU time. Load balancing can be defined as a method of improving the performance of a distributed and parallel system by redistributing the load among the processors. Load balancing is control word wide wave for increasing demands so fast and Precise Load balancing is an important point in increasing efficiency of distributed system operation. But it is a difficult task in very large scale distributed system because the distributed systems always have dynamically changed global state. For high availability, throughput, and scalability the distributed system needs better and efficient load balancing. In this paper, we present an overview of the different techniques and methodology given by different researchers throughout the globe and try to analyse their effectiveness in improving the methods of load balancing.

Analytics of network telemetry data helps address many important operational problems. Traditional Big Data approaches run into limitations even as they push scale boundaries for processing data further. One reason for this is the fact that in many cases, the bottleneck for analytics is not analytics processing itself but the generation and export of the data on which analytics depends. The amount of data that can be reasonably collected from the network runs into inherent limitations due to bandwidth and processing constraints in the network itself. In addition, management tasks related to determining and configuring which data to generate lead to significant deployment challenges. In order to address these issues, we propose a novel distributed solution to network analytics that we have implemented as a proof of concept, called DNA (Distributed Network Analytics). In DNA, analytics processing is performed at the source of the data by specialized agents embedded within network devices, which also dynamically set up and reconfigure telemetry data sources as required by an analytics task. An SDN controller application orchestrates network analytics tasks across the network to allow users to interact with the network as a whole instead of individual devices one at a time. Our demonstration of DNA includes a GUI front end used to specify and monitor analytics tasks as well as visualize analytics results.

Parallel computing perform concurrently execution tasks on distributed nodes. Large application split up into tasks and run on number on nodes for high performance computing. Cluster environment composed with heterogeneous devices and software components capable of cost effective and high performance computing on parallel application. In heterogeneous cluster environment proper scheduling of tasks and allocation to nodes is important for high performance computing. Many task scheduling algorithms proposed for achieving high performance computing on heterogeneous computing. We proposed swarm technique methodology for task scheduling on heterogeneous cluster environment, which can perform better results for minimize make span, high performance and resource utilization compared to others.