Nik Bessis

Exploring decentralized dynamic scheduling for grids and clouds using the community-aware scheduling algorithm

Job scheduling strategies have been studied for decades in a variety of scenarios. Due to the new characteristics of the emerging computational systems, such as the grid and cloud, metascheduling turns out to be an important scheduling pattern because it is responsible for orchestrating resources managed by independent local schedulers and bridges the gap between participating nodes. Equally, to overcome issues such as bottleneck, single point failure, and impractical unique administrative management, which are normally led by conventional centralized or hierarchical schemes, the decentralized scheduling scheme is emerging as a promising approach because of its capability with regards to scalability and flexibility.In this work, we introduce a decentralized dynamic scheduling approach entitled the community-aware scheduling algorithm (CASA). The CASA is a two-phase scheduling solution comprised of a set of heuristic sub-algorithms to achieve optimized scheduling performance over the scope of overall grid or cloud, instead of individual participating nodes. The extensive experimental evaluation with a real grid workload trace dataset shows that, when compared to the centralized scheduling scheme with BestFit as the metascheduling policy, the use of CASA can lead to a 30%-61% better average job slowdown, and a 68%-86% shorter average job waiting time in a decentralized scheduling manner without requiring detailed real-time processing information from participating nodes. Highlights? We introduce a decentralized scheduling algorithm without requiring detailed node information. ? Our algorithm is able to adapt to the changes in grids through time by rescheduling. ? Comparisons with the known BestFit algorithm within a centralized scheduling scheme are made. ? Our algorithm leads to a 30%-61% better average job slowdown. ? Our algorithm leads to a 68%-86% shorter average job waiting time.

A survey on multihop ad hoc networks for disaster response scenarios

Disastrous events are one of the most challenging applications of multihop ad hoc networks due to possible damages of existing telecommunication infrastructure. The deployed cellular communication infrastructure might be partially or completely destroyed after a natural disaster. Multihop ad hoc communication is an interesting alternative to deal with the lack of communications in disaster scenarios. They have evolved since their origin, leading to different ad hoc paradigms such as MANETs, VANETs, DTNs, or WSNs. This paper presents a survey on multihop ad hoc network paradigms for disaster scenarios. It highlights their applicability to important tasks in disaster relief operations. More specifically, the paper reviews the main work found in the literature, which employed ad hoc networks in disaster scenarios. In addition, it discusses the open challenges and the future research directions for each different ad hoc paradigm.

The Big Picture, from Grids and Clouds to Crowds: A Data Collective Computational Intelligence Case Proposal for Managing Disasters

Much work is underway within the broad next generation technologies community on issues associated with the development of services to foster collaboration via the integration of distributed and heterogeneous data systems and technologies. Various technology-driven paradigms have emerged, including Web Services, Web 2.0, Pervasive, Grids and Cloud Computing. Recently, some new paradigms have emerged, including Situated Computing and Crowd Sourcing. In this exploratory paper, we aim to be visionary, thus, we offer an overview highlighting relationships between these paradigms, the goal is to present how these fit into the broader picture of IT. More specifically, to discuss how these could help coin and prompt future direction of their usage (integration) in various real-world scenarios. A disaster management scenario is presented to illustrate the big picture’s model architecture, as well as briefly discuss the potential impact resulting from the collective computational intelligence approach.

Big Data and Internet of Things: A Roadmap for Smart Environments

This book presents current progress on challenges related to Big Data management by focusing on the particular challenges associated with context-aware data-intensive applications and services. The book is a state-of-the-art reference discussing progress made, as well as prompting future directions on the theories, practices, standards and strategies that are related to the emerging computational technologies and their association with supporting the Internet of Things advanced functioning for organizational settings including both business and e-science. Apart from inter-operable and inter-cooperative aspects, the book deals with a notable opportunity namely, the current trend in which a collectively shared and generated content is emerged from Internet end-users. Specifically, the book presents advances on managing and exploiting the vast size of data generated from within the smart environment (i.e. smart cities) towards an integrated, collective intelligence approach. The book also presents methods and practices to improve large storage infrastructures in response to increasing demands of the data intensive applications. The book contains 19 self-contained chapters that were very carefully selected based on peer review by at least two expert and independent reviewers and is organized into the three sections reflecting the general themes of interest to the IoT and Big Data communities:Section I: Foundations and Principles Section II: Advanced Models and Architectures Section III: Advanced Applications and Future Trends The book is intended for researchers interested in joining interdisciplinary and transdisciplinary works in the areas of Smart Environments, Internet of Things and various computational technologies for the purpose of an integrated collective computational intelligence approach into the Big Data era.

Meta-scheduling issues in interoperable HPCs, grids and clouds

Over the last years, interoperability among resources has been emerged as one of the most challenging research topics. However, the commonality of the complexity of the architectures (e.g., heterogeneity) and the targets that each computational paradigm including HPC, grids and clouds aims to achieve (e.g., flexibility) remain the same. This is to efficiently orchestrate resources in a distributed computing fashion by bridging the gap among local and remote participants. Initially, this is closely related with the scheduling concept which is one of the most important issues for designing a cooperative resource management system, especially in large scale settings such as in grids and clouds. Within this context, meta-scheduling offers additional functionalities in the area of interoperable resource management, this is because of its great agility to handle sudden variations and dynamic situations in user demands. Accordingly, the case of inter-infrastructures, including InterCloud, entitle that the decentralised meta-scheduling scheme overcome issues like consolidated administration management, bottleneck and local information exposition. In this work, we detail the fundamental issues for developing an effective interoperable meta-scheduler for e-infrastructures in general and InterCloud in particular. Finally, we describe a simulation and experimental configuration based on real grid workload traces to demonstrate the interoperable setting as well as provide experimental results as part of a strategic plan for integrating future meta-schedulers.

A next generation emerging technologies roadmap for enabling collective computational intelligence in disaster management

Much work is underway within the broad next generation emerging technologies community on issues associated with the development of services to foster synergies and collaboration via the integration of distributed and heterogeneous resources, systems and technologies. In previous works, we have discussed how these could help coin and prompt future direction of their fit-to-purpose use in various real-world scenarios including but not limited to disaster management, healthcare, vehicular networking and knowledge cities. In this exploratory paper, we brief and then build upon our previous works and specifically, we present a roadmap highlighting the possible use of next generation emerging technologies for enabling collective computational intelligence in managing disaster situations. A relevant scenario is used to illustrate the model architecture, as well as to detail the proposed roadmap.

Modelling and assessing ad hoc Networks in disaster scenarios

Ad hoc networks have been proved to be suitable for disaster scenarios since any infrastructure needs to be deployed in order to establish a wireless network. Routing protocols play an important role in the performance of mobile ad hoc networks. Routing protocols are responsible for deciding how the information is going to move through the network. Although one paramount parameter of ad hoc networks is the mobility of nodes, little effort has been made to evaluate the performance of mobile ad hoc networks under mobility models where the movements of rescue teams during evacuating operations are modelled. The objective of this paper is to evaluate real case disaster scenarios in terms of performance using several well-known routing protocols metrics.

An evolutionary computation approach for optimizing connectivity in disaster response scenarios

This article presents an evolutionary computation approach for increasing connectivity in disaster scenarios. Connectivity is considered to be of critical importance in disaster scenarios due to constrained and mobile conditions. We propose the deployment of a number of auxiliary static nodes whose purpose is to increase the reachability of broadcast emergency packets among the nodes which are participating in the disaster scenario. These nodes represent people and vehicles acting in rescue operations. The main goal is to find the optimum positions for the auxiliary nodes, reinforcing the communications in points where certain lack of connectivity is found. These points will depend on the movements of the rescue teams, which are influenced by tactical reasons. Due to the complexity of the problem and the number of parameters to be considered, a genetic algorithm combined with the network simulator NS-2 is proposed to find the optimum positions of the auxiliary nodes. Specifically, NS-2 is used to model the communication layers and provide the fitness function guiding the genetic search. The proposed approach has been tested using the disaster mobility model included in the motion generator BonnMotion. The simulation results obtained demonstrate the feasibility of the proposed approach and illustrate its applicability in other scenarios where lack of connectivity is evident.

Advanced ICTs for Disaster Management and Threat Detection: Collaborative and Distributed Frameworks

The Medical Information System (MedISys) is a fully automatic 24/7 public health surveillance system monitoring human and animal infectious diseases and chemical, biological, radiological and nuclear (CBRN) threats in open-source media. In this article, we explain the technology behind MedISys, deJens P. Linge Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy Ralf Steinberger Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy Flavio Fuart Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy Stefano Bucci Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy Jenya Belyaeva Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy Monica Gemo Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy Delilah Al-Khudhairy Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy Roman Yangarber University of Helsinki, Department of Computer Science, Finland Erik van der Goot Joint Research Centre of the European Commission Institute for the Protection and Security of the Citizen Global Security and Crisis Management Unit, Italy DOI: 10.4018/978-1-61520-987-3.ch009In the developed world, an ever better and finer understanding of the processes leading to natural hazards is expected. This is in part achieved using the invaluable tool of numerical modeling, which offers the possibility of applying scenarios to a given situation. This in turn leads to a dramatic increase in the complexity of the processes that the scientific community wants to simulate. A numerical model is becoming more and more like a galaxy of various sub-process models, each with their own numerical characteristics. The traditional approach to High Performance Computing (HPC) can hardly face this challenge without rethinking its paradigms. A possible evolution would be to move away from the Single Program, Multi Data (SPMD) approach and towards an approach that leverages the well known Object Oriented approach. This evolution is at the foundation of the POP parallel programming model that is presented here, as well as its C++ implementation, POP-C++.Disaster management is a dynamic and fluid area, which requires the involvement of expertise from different authorities and organizations. There is a need to prepare and plan in advance actions in response to disaster related events in order to support sustainable livelihood by protecting lives, property and the environment. Advanced ICTs for Disaster Management and Threat Detection: Collaborative and Distributed Frameworks demonstrates how strategies and state-of-the-art ICT have and/or could be applied to serve as a vehicle to advance disaster management approaches, decisions and practices. This book provides both a conceptual and practical guidance to disaster management while also identifying and developing effective and efficient approaches, mechanisms, and systems using emerging technologies to support an effective operation. This state-of-the-art reference collection attempts to prompt the future direction for disaster managers to identify applicable theories and practices in order to mitigate, prepare for, respond to and recover from various foreseen and/or unforeseen disasters.

Using a novel message-exchanging optimization (MEO) model to reduce energy consumption in distributed systems

The concept of optimizing energy efficiency in distributed systems has gained particular interest. Most of these efforts are focused on the core management concepts like resource discovery, scheduling and allocation without focusing on the actual communication method among system entities. Specifically, these do not consider the number of exchanged messages and the energy that they consume. In this work, we propose a model to optimize the energy efficiency of message-exchanging in distributed systems by minimizing the total number of messages when entities communicate. So we propose an efficient messaging-exchanging optimization (MEO) model that aims to minimize the sum of requests and responses as a whole rather than only the number of requests. The view is to optimize firstly the energy for communication (e.g. latency times) and secondly the overall system performance (e.g. makespan). To demonstrate the effectiveness of MEO model, the experimental analysis using the SimIC is based on a large-scale inter-cloud setting where the implemented algorithms offer optimization of various criteria including turnaround times and energy consumption rates. Results obtained are very supportive.