Ammar Rayes

A survey on resource allocation in high performance distributed computing systems

Classification of high performance computing (HPC) systems is provided.Current HPC paradigms and industrial application suites are discussed.State of the art in HPC resource allocation is reported.Hardware and software solutions are discussed for optimized HPC systems. An efficient resource allocation is a fundamental requirement in high performance computing (HPC) systems. Many projects are dedicated to large-scale distributed computing systems that have designed and developed resource allocation mechanisms with a variety of architectures and services. In our study, through analysis, a comprehensive survey for describing resource allocation in various HPCs is reported. The aim of the work is to aggregate under a joint framework, the existing solutions for HPC to provide a thorough analysis and characteristics of the resource management and allocation strategies. Resource allocation mechanisms and strategies play a vital role towards the performance improvement of all the HPCs classifications. Therefore, a comprehensive discussion of widely used resource allocation strategies deployed in HPC environment is required, which is one of the motivations of this survey. Moreover, we have classified the HPC systems into three broad categories, namely: (a) cluster, (b) grid, and (c) cloud systems and define the characteristics of each class by extracting sets of common attributes. All of the aforementioned systems are cataloged into pure software and hybrid/hardware solutions. The system classification is used to identify approaches followed by the implementation of existing resource allocation strategies that are widely presented in the literature.

Enabling Smart Cloud Services Through Remote Sensing: An Internet of Everything Enabler

The recent emergence and success of cloud-based services has empowered remote sensing and made it very possible. Cloud-assisted remote sensing (CARS) enables distributed sensory data collection, global resource and data sharing, remote and real-time data access, elastic resource provisioning and scaling, and pay-as-you-go pricing models. CARS has great potentials for enabling the so-called Internet of Everything (IoE), thereby promoting smart cloud services. In this paper, we survey CARS. First, we describe its benefits and capabilities through real-world applications. Second, we present a multilayer architecture of CARS by describing each layers functionalities and responsibilities, as well as its interactions and interfaces with its upper and lower layers. Third, we discuss the sensing services models offered by CARS. Fourth, we discuss some popular commercial cloud platforms that have already been developed and deployed in recent years. Finally, we present and discuss major design requirements and challenges of CARS.

Toward better horizontal integration among IoT services

Several divergent application protocols have been proposed for Internet of Things (IoT) solutions including CoAP, REST, XMPP, AMQP, MQTT, DDS, and others. Each protocol focuses on a specific aspect of IoT communications. The lack of a protocol that can handle the vertical market requirements of IoT applications including machine-to-machine, machine-to-server, and server-to-server communications has resulted in a fragmented market between many protocols. In turn, this fragmentation is a main hindrance in the development of new services that require the integration of multiple IoT services to unlock new capabilities and provide horizontal integration among services. In this work, after articulating the major shortcomings of the current IoT protocols, we outline a rule-based intelligent gateway that bridges the gap between existing IoT protocols to enable the efficient integration of horizontal IoT services. While this intelligent gateway enhances the gloomy picture of protocol fragmentation in the context of IoT, it does not address the root cause of this fragmentation, which lies in the inability of the current protocols to offer a wide range of QoS guarantees. To offer a solution that stems the root cause of this protocol fragmentation issue, we propose a generic IoT protocol that is flexible enough to address the IoT vertical market requirements. In this regard, we enhance the baseline MQTT protocol by allowing it to support rich QoS features by exploiting a mix of IP multicasting, intelligent broker queuing management, and traffic analytics techniques. Our initial evaluation of the lightweight enhanced MQTT protocol reveals significant improvement over the baseline protocol in terms of the delay performance.

Energy-Efficient Resource Allocation and Provisioning Framework for Cloud Data Centers

Energy efficiency has recently become a major issue in large data centers due to financial and environmental concerns. This paper proposes an integrated energy-aware resource provisioning framework for cloud data centers. The proposed framework: i) predicts the number of virtual machine (VM) requests, to be arriving at cloud data centers in the near future, along with the amount of CPU and memory resources associated with each of these requests, ii) provides accurate estimations of the number of physical machines (PMs) that cloud data centers need in order to serve their clients, and iii) reduces energy consumption of cloud data centers by putting to sleep unneeded PMs. Our framework is evaluated using real Google traces collected over a 29-day period from a Google cluster containing over 12,500 PMs. These evaluations show that our proposed energy-aware resource provisioning framework makes substantial energy savings.

Opportunistic Channel Selection Strategy for Better QoS in Cooperative Networks with Cognitive Radio Capabilities

Mission-oriented MANETs are characterized by implicit common group objectives which make inter-node cooperation both logical and feasible. We propose new techniques to leverage two optimizations for cognitive radio networks that are specific to such contexts: opportunistic channel selection and cooperative mobility. We present a new formal model for MANETs consisting of cognitive radio capable nodes that are willing to be moved (at a cost). We develop an effective decentralized algorithm for mobility planning, and powerful new Altering and fuzzy based techniques for both channel estimation and channel selection. Our experiments are compelling and demonstrate that the communications infrastructure-specifically, connection bit error rates-can be significantly improved by leveraging our proposed techniques. In addition, we find that these cooperative/opportunistic optimization spaces do not trade-off significantly with one another, and thus can be used simultaneously to build superior hybrid schemes. Our results have significant applications in high-performance mission-oriented MANETs, such as battlefield communications and domestic response & rescue missions.

Toward energy-efficient cloud computing: Prediction, consolidation, and overcommitment

Energy consumption has become a significant concern for cloud service providers due to financial as well as environmental factors. As a result, cloud service providers are seeking innovative ways that allow them to reduce the amount of energy that their data centers consume. They are calling for the development of new energy-efficient techniques that are suitable for their data centers. The services offered by the cloud computing paradigm have unique characteristics that distinguish them from traditional services, giving rise to new design challenges as well as opportunities when it comes to developing energy-aware resource allocation techniques for cloud computing data centers. In this article we highlight key resource allocation challenges, and present some potential solutions to reduce cloud data center energy consumption. Special focus is given to power management techniques that exploit the virtualization technology to save energy. Several experiments, based on real traces from a Google cluster, are also presented to support some of the claims we make in this article.

Software-defined networking security: pros and cons

Software-defined networking (SDN) is a new networking paradigm that decouples the forwarding and control planes, traditionally coupled with one another, while adopting a logically centralized architecture aiming to increase network agility and programability. While many efforts are currently being made to standardize this emerging paradigm, careful attention needs to be paid to security at this early design stage too, rather than waiting until the technology becomes mature, thereby potentially avoiding previous pitfalls made when designing the Internet in the 1980s. This article focuses on the security aspects of SDN networks. We begin by discussing the new security advantages that SDN brings and by showing how some of the long-lasting issues in network security can be addressed by exploiting SDN capabilities. Then we describe the new security threats that SDN is faced with and discuss possible techniques that can be used to prevent and mitigate such threats.

Network Modeling and Simulation: A Practical Perspective

Preface. Acknowledgements. 1 Basic Concepts and Techniques. 1.1 Why Is Simulation Important? 1.2 What Is a Model? 1.3 Performance Evaluation Techniques. 1.4 Development of Systems Simulation. 1.5 Summary. Recommended Reading. 2 Designing and Implementing a Discrete-Event Simulation Framework. 2.1 The Scheduler. 2.2 The Simulation Entities. 2.3 The Events. 2.4 Tutorial 1: Hello World. 2.5 Tutorial 2: Two-Node Hello Protocol. 2.6 Tutorial 3: Two-Node Hello through a Link. 2.7 Tutorial 4: Two-Node Hello through a Lossy Link. 2.8 Summary. Recommended Reading. 3 Honeypot Communities: A Case Study with the Discrete-Event Simulation Framework. 3.1 Background. 3.2 System Architecture. 3.3 Simulation Modeling. 3.4 Simulation Execution. 3.5 Output Analysis. 3.6 Summary. Recommended Reading. 4 Monte Carlo Simulation. 4.1 Characteristics of Monte Carlo Simulations. 4.2 The Monte Carlo Algorithm. 4.3 Merits and Drawbacks. 4.4 Monte Carlo Simulation for the Electric Car Charging Station. 4.5 Summary. Recommended Reading. 5 Network Modeling. 5.1 Simulation of Networks. 5.2 The Network Modeling and Simulation Process. 5.3 Developing Models. 5.4 Network Simulation Packages. 5.5 OPNET: A Network Simulation Package. 5.6 Summary. Recommended Reading. 6 Designing and Implementing CASiNO: A Network Simulation Framework. 6.1 Overview. 6.2 Conduits. 6.3 Visitors. 6.4 The Conduit Repository. 6.5 Behaviors and Actors. 6.6 Tutorial 1: Terminals. 6.7 Tutorial 2: States. 6.8 Tutorial 3: Making Visitors. 6.9 Tutorial 4: Muxes. 6.10 Tutorial 5: Factories. 6.11 Summary. Recommended Reading. 7 Statistical Distributions and Random Number Generation. 7.1 Introduction to Statistical Distributions. 7.2 Discrete Distributions. 7.3 Continuous Distributions. 7.4 Augmenting CASiNO with Random Variate Generators. 7.5 Random Number Generation. 7.6 Frequency and Correlation Tests. 7.7 Random Variate Generation. 7.8 Summary. Recommended Reading. 8 Network Simulation Elements: A Case Study Using CASiNO. 8.1 Making a Poisson Source of Packets. 8.2 Making a Protocol for Packet Processing. 8.3 Bounding Protocol Resources. 8.4 Making a Round-Robin (De)multiplexer. 8.5 Dynamically Instantiating Protocols. 8.6 Putting It All Together. 8.7 Summary. 9 Queuing Theory. 9.1 Introduction to Stochastic Processes. 9.2 Discrete-Time Markov Chains. 9.3 Continuous-Time Markov Chains. 9.4 Basic Properties of Markov Chains. 9.5 Chapman-Kolmogorov Equation. 9.6 Birth-Death Process. 9.7 Littles Theorem. 9.8 Delay on a Link. 9.9 Standard Queuing Notation. 9.10 The M/M/ 1 Queue. 9.11 The M/M/m Queue. 9.12 The M/M/ 1 /b Queue. 9.13 The M/M/m/m Queue. 9.14 Summary. Recommended Reading. 10 Input Modeling and Output Analysis. 10.1 Data Collection. 10.2 Identifying the Distribution. 10.3 Estimation of Parameters for Univariate Distributions. 10.4 Goodness-of-Fit Tests. 10.5 Multivariate Distributions. 10.6 Selecting Distributions without Data. 10.7 Output Analysis. 10.8 Summary. Recommended Reading. 11 Modeling Network Traffic. 11.1 Introduction. 11.2 Network Traffic Models. 11.3 Traffic Models for Mobile Networks. 11.4 Global Optimization Techniques. 11.5 Particle Swarm Optimization. 11.6 Optimization in Mathematics. 11.7 Summary. Recommended Reading. Index.

A survey on text mining in social networks

In this survey, we review different text mining techniques to discover various textual patterns from the social networking sites. Social network applications create opportunities to establish interaction among people leading to mutual learning and sharing of valuable knowledge, such as chat, comments, and discussion boards. Data in social networking websites is inherently unstructured and fuzzy in nature. In everyday life conversations, people do not care about the spellings and accurate grammatical construction of a sentence that may lead to different types of ambiguities, such as lexical, syntactic, and semantic. Therefore, analyzing and extracting information patterns from such data sets are more complex. Several surveys have been conducted to analyze different methods for the information extraction. Most of the surveys emphasized on the application of different text mining techniques for unstructured data sets reside in the form of text documents, but do not specifically target the data sets in social networking website. This survey attempts to provide a thorough understanding of different text mining techniques as well as the application of these techniques in the social networking websites. This survey investigates the recent advancement in the field of text analysis and covers two basic approaches of text mining, such as classification and clustering that are widely used for the exploration of the unstructured text available on the Web.

Efficient datacenter resource utilization through cloud resource overcommitment

We propose an efficient resource allocation framework for overcommitted clouds that makes great energy savings by 1) minimizing PM overloads via resource usage prediction, and 2) reducing the number of active PMs via efficient VM placement and migration. Using real Google traces collected from a cluster containing more than 12K PMs, we show that our proposed techniques outperform existing ones by minimizing migration overhead, increasing resource utilization, and reducing energy consumption.