Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Bücher
Zeitschriften
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
MTZ-Fachkongress

Antriebe und Energiesysteme von morgen


Austausch von Automobil- und Energiewirtschaft

Am 14./15. Mai geht es in Chemnitz um die Mobilitätswende durch Elektro- und Wasserstofffahrzeuge.
Erweiterte Suche
Anmelden
nach oben

2017 | Buch

On the Future of Solution Composition in Software Ecosystems Kapitel lesen Erstes Kapitel lesen

Economics of Grids, Clouds, Systems, and Services

13th International Conference, GECON 2016, Athens, Greece, September 20-22, 2016, Revised Selected Papers

herausgegeben von: José Ángel Bañares, Konstantinos Tserpes, Jörn Altmann

Verlag: Springer International Publishing

Buchreihe : Lecture Notes in Computer Science

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

This book constitutes the refereed proceedings of the 13th International Conference on Economics of Grids, Clouds, Systems, and Services, GECON 2016, held in Athens. Greece, in September 2016.

The 11 revised full papers and 11 short papers presented were carefully reviewed and selected from 38 submissions.

This volume has been structured following the seven sessions that comprised the conference program (three of which are work-in-progress sessions):

Session 1: Business Models

Session 2: Work in Progress on Quality of Services and Service Level Agreements

Session 3: Work in Progress on Cloud Economics

Session 4: Energy Consumption

Session 5: Resource Allocation

Session 6: Work in Progress on Resource Allocation

Session 7: Cloud Applications

Inhaltsverzeichnis

Frontmatter

Business Models

Frontmatter
On the Future of Solution Composition in Software Ecosystems
Abstract
The trend of application stores is currently at a peak. However, the lack of dynamic composition for complex solutions is the largest downside of the app store model, since solutions are increasingly created as compositions of multiple solutions, APIs, and applications. Therefore, in this vision paper, a superior model, solution composers, is proposed to the app store model. A conceptual framework is established to illustrate the inner workings of solution composers in software ecosystems. In order to outline that solution composers are significant for the future of software development, several industry cases are presented and compared to support this concept, further indicating that a standard for solution composition should be considered. In addition, the vision is evaluated through expert reviews at several leading platform providers and challenges for practice and implementation are identified.
Zherui Yang, Slinger Jansen, Xuesong Gao, Dong Zhang
The Rise of Cloud Brokerage: Business Model, Profit Making and Cost Savings
Abstract
Cloud computing has succeeded in transforming the ICT industry, making computing services more accessible to businesses. Nowadays, many cost effective solutions are available to users. However, searching for the best provider or the best bundle is not always an easy decision for the client. The cloud broker is a widely known business model derived from this necessity. It is a third-party business which assists clients to make the best decision in choosing the most suitable cloud provider and the most effective service bundle for their needs, in terms of performance and price. Into that context, this paper describes the cloud broker business model and its promising future. It highlights the broker’s vital role and the benefits that arise from the use of its services, explores on the same time the drawbacks that derive from the intermediation of cloud broker. The economic context of the cloud broker model is also examined by reviewing the contemporary literature for the pricing methods that can be adopted by a cloud broker in order to achieve cost savings.
Evangelia Filiopoulou, Persefoni Mitropoulou, Christos Michalakelis, Mara Nikolaidou

Work in Progress on Quality of Services and Service Level Agreements

Frontmatter
Robust Content-Centric SLA Enforcement in Federated Cloud Environments
Abstract
In this paper we present a system for declaring and enforcing SLAs in Cloud environments. The SLAs proposed are enriched with content terms, storlets and federation capabilities and provide high degrees of customizability for clients. A mechanism for SLA enforcement has been designed and implemented which, based on policies, measurements, usage data computations, and monitoring methods permits proactive SLA violation detection and handling. SLA renegotiation is supported as well. The proposed framework has been developed and evaluated in challenging scenarios in a variety of different application domains.
Nikoletta Mavrogeorgi, Athanasios Voulodimos, Vassilios Alexandrou, Spyridon Gogouvitis, Theodora Varvarigou
Structural Specification for the SLAs in Cloud Computing (S3LACC)
Abstract
Cloud service providers generally offer service level agreements (SLAs) in descriptive format which is not directly consumable by a machine/system. The SLA written in natural language may impede the utility of rapid elasticity in a cloud service. Automation of different phases of the SLA life cycle (e.g. negotiation, monitoring and management) is also dependent on the availability of a machine readable SLA. In this work, we propose a Structural Specification for the SLAs in Cloud Computing (S3LACC) for the automation of complete SLA life cycle i.e. negotiation, monitoring, management and recycling. S3LACC is specifically designed for cloud domain to meet latest standards and complex requirements of the cloud services such as service composition, dynamic negotiations, automated monitoring and formalization of qualitative parameters. Additionally, S3LACC defines a single SLA structure to be used as an SLA template and as a final agreement as well.
Waheed Aslam Ghumman, Alexander Schill
Load Balancing in In-Memory Key-Value Stores for Response Time Minimization
Abstract
In-memory key-value stores (IMKVS) have now turned into a mainstream technology in order to meet with demanding temporal application requirements under heavy loads. This work examines the factors that affect the load distribution in IMKVS clusters as well as migration policies that cure the problem of unbalanced loads as a means to provide response time guarantees. Experiments are conducted in a Redis deployment under various settings. The results show that the key distribution and key length are contributing factors to the load balancing problem and impact the cluster’s response times. On the contrary, key popularity and query volume seem to have minor or no effect at all.
Antonios Makris, Konstantinos Tserpes, Dimosthenis Anagnostopoulos
Fault-Tree-Based Service Availability Model in Cloud Environments: A Failure Trace Archive Approach
Abstract
In a cloud computing environment with capabilities such as live migration and elastic resource provisioning, with a mandatory request for critical availability of the service, our challenge consists in how to use basic fault tree analysis for assessing the health state of a node/service instance and perform load balancing in an autonomous manner. We propose a model that extracts event abstraction from the run-time logs, aiming to assess whether the primary service instance or its replica is reliable or unreliable. We employ replication or live migration processes to keep the service availability at an acceptable level. The model is a probabilistic one and is validated using the LANL HPC Failure Trace Archive (FTA) data set.
Alexandru Butoi, Gheorghe Cosmin Silaghi

Work in Progress on Cloud Economics

Frontmatter
An Economical Security Architecture for Multi-cloud Application Deployments in Federated Environments
Abstract
Contemporary multi-cloud application deployments require increasingly complex security architectures, especially within federated environments. However, increased complexity often leads to higher efforts and raised costs for managing and securing those applications. This publication establishes an economical and comprehensive security architecture that is readily instantiable, pertinent to concrete users’ requirements, and builds upon up-to-date protocols and software. We highlight its feasibility by applying the architecture within the CYCLONE innovation action, deploying federated Bioinformatics applications within a cloud production environment. At last, we put special emphasis on the reduced management efforts to highlight the economic benefit of following our approach.
Mathias Slawik, Begüm Ilke Zilci, Axel Küpper, Yuri Demchenko, Fatih Turkmen, Christophe Blanchet, Jean-François Gibrat
Efficient Context Management and Personalized User Recommendations in a Smart Social TV Environment
Abstract
With the emergence of Smart TV and related interconnected devices, second screen solutions have rapidly appeared to provide more content for end-users and enrich their TV experience. Given the various data and sources involved - videos, actors, social media and online databases- the aforementioned market poses great challenges concerning user context management and sophisticated recommendations that can be addressed to the end-users. This paper presents an innovative Context Management model and a related first and second screen recommendation service, based on a user-item graph analysis as well as collaborative filtering techniques in the context of a Dynamic Social & Media Content Syndication (SAM) platform. The model evaluation provided is based on datasets collected online, presenting a comparative analysis concerning efficiency and effectiveness of the current approach, and illustrating its added value.
Fotis Aisopos, Angelos Valsamis, Alexandros Psychas, Andreas Menychtas, Theodora Varvarigou
When Culture Trumps Economic Laws: Persistent Segmentation of the Mobile Instant Messaging Market
Abstract
This paper discusses the general characteristics of the mobile instant messaging market from a competition point of view. Positive feedback and indirect network effects, which strongly influence the mobile instant messaging market, tend to facilitate the development of one quasi-monopoly. Even after several years of market maturation, however, no mobile instant messaging application has yet established such a monopoly, seemingly contradicting economic theory. In order to resolve this contradiction, this paper deconstructs the global instant messaging landscape using theoretical insights into local bias and distinct cultural needs. We find that differences between high- and low-context cultures provide the most compelling explanation for market fragmentation and derive possible strategies for single applications’ global market expansion.
Maria C. Borges, Max-R. Ulbricht, Frank Pallas

Energy Consumption

Frontmatter
Energy Efficiency Support Through Intra-layer Cloud Stack Adaptation
Abstract
Energy consumption is a key concern in cloud computing. The paper reports on a cloud architecture to support energy efficiency at service construction, deployment, and operation. This is achieved through SaaS, PaaS and IaaS intra-layer self-adaptation in isolation. The self-adaptation mechanisms are discussed, as well as their implementation and evaluation. The experimental results show that the overall architecture is capable of adapting to meet the energy goals of applications on a per layer basis.
Karim Djemame, Richard Kavanagh, Django Armstrong, Francesc Lordan, Jorge Ejarque, Mario Macias, Raül Sirvent, Jordi Guitart, Rosa M. Badia
Energy-Aware Pricing Within Cloud Environments
Abstract
The Adapting Service lifeCycle towards EfficienT Clouds (ASCETiC) project aims to provide novel methods and tools to support software developers aiming to optimize energy efficiency resulting from designing, developing, deploying and running software at the different layers of the cloud stack architecture, while maintaining other quality aspects of software to meet the agreed levels. The Pricing Modeler is a component within the ASCETiC architecture, which is responsible for the price estimation and billing of cloud applications or Virtual Machines (VMs) based on their energy consumption. In this paper, we propose a set of novel energy-aware pricing schemes implemented within the Pricing Modeler component, as well as a set of envisaged service plans which aim to facilitate the gradual adoption of the ASCETiC architecture.
Alexandros Kostopoulos, Eleni Agiatzidou, Antonis Dimakis
Energy Prediction for Cloud Workload Patterns
Abstract
The excessive use of energy consumption in Cloud infrastructures has become one of the major cost factors for Cloud providers to maintain. In order to enhance the energy efficiency of Cloud resources, proactive and reactive management tools are used. However, these tools need to be supported with energy-awareness not only at the physical machine (PM) level but also at virtual machine (VM) level in order to enhance decision-making. This paper introduces an energy-aware profiling model to identify energy consumption for heterogeneous and homogeneous VMs running on the same PM and presents an energy-aware prediction framework to forecast future VMs energy consumption. This framework first predicts the VMs’ workload based on historical workload patterns using Autoregressive Integrated Moving Average (ARIMA) model. The predicted VM workload is then correlated to the physical resources within this framework in order to get the predicted VM energy consumption. Compared with actual results obtained in a real Cloud testbed, the predicted results show that this energy-aware prediction framework can get up to 2.58 Mean Percentage Error (MPE) for the VM workload prediction, and up to −4.47 MPE for the VM energy prediction based on periodic workload pattern.
Ibrahim Alzamil, Karim Djemame
An Energy Aware Cost Recovery Approach for Virtual Machine Migration
Abstract
Datacenters provide an IT backbone for today’s business and economy, and are the principal electricity consumers for Cloud computing. Various studies suggest that approximately 30% of the running servers in US datacenters are idle and the others are under-utilized, making it possible to save energy and money by using Virtual Machine (VM) consolidation to reduce the number of hosts in use. However, consolidation involves migrations that can be expensive in terms of energy consumption, and sometimes it will be more energy efficient not to consolidate. This paper investigates how migration decisions can be made such that the energy costs involved with the migration are recovered, as only when costs of migration have been recovered will energy start to be saved. We demonstrate through a number of experiments, using the Google workload traces for 12,583 hosts and 1,083,309 tasks, how different VM allocation heuristics, combined with different approaches to migration, will impact on energy efficiency. We suggest, using reasonable assumptions for datacenter setup, that a combination of energy-aware fill-up VM allocation and energy-aware migration, and migration only for relatively long running VMs, provides for optimal energy efficiency.
Muhammad Zakarya, Lee Gillam

Resource Allocation

Frontmatter
The Design and Evaluation of a Heaviness Metric for Cloud Fairness and Correct Virtual Machine Configurations
Abstract
Fairness problems in data centers have been pointed out frequently over the last years. To enforce fairness in data centers, the application of job/Virtual Machine (VM) scheduling impels the traditional solution. Scheduling determines the order in which VMs/jobs are started. However, it is insufficient to enforce fairness, when jobs/VMs run over long periods and/or their PR utilization is highly fluctuant. Clouds form a special case of data centers in which this can be observed.
To overcome this shortcoming, previous work suggested to enforce fairness by handicapping VMs of heavy users and prioritizing VMs of light users during runtime. The Greediness Metric (GM) was developed and shown to be a well suited heaviness measure for that purpose. This work here defines an allocation to be GM Fair (GMF) if all users have the same greediness and resources are allocated efficiently. GM is refined such that enforcing GMF provides incentives to users to configure virtual resources of their VMs in-line with the VMs’ subsequent resource PR utilization allowing cloud providers to schedule these VMs more efficiently. Finally, this work here proves that GMF provides for the same desirable characteristics as Dominant Resource Fairness, including especially sharing incentive, strategy proofness, envy-freeness, and Pareto-efficiency.
Patrick Poullie, Burkhard Stiller
A History-Based Model for Provisioning EC2 Spot Instances with Cost Constraints
Abstract
The increasing demand of computing resources has boosted the use of cloud computing providers. This has raised a new dimension in which the connection between resource usage and costs has to be considered from an organizational perspective. As a part of its EC2 service, Amazon introduced spot instances (SIs) as a cheap public infrastructure, but at the price of not ensuring reliability of the service (hired SIs can be terminated by the service when necessary). The interface for managing SIs is based on a bidding strategy that depends on non-public Amazon pricing strategies, which makes complicated for users to apply any scheduling or resource provisioning strategy based on such (cheaper) resources. Although it is believed that the use of the EC2 SIs infrastructure can reduce costs for final users, a deep review of literature concludes that their characteristics and possibilities have not yet been deeply explored. In this work we present and evaluate a framework for the analysis of the EC2 SIs infrastructure that uses the price history of such resources in order to generate a provisioning plan by means of a simulation algorithm considering cost constraints.
Javier Fabra, Sergio Hernández, Pedro Álvarez, Joaquín Ezpeleta, Álvaro Recuenco, Ana Martínez

Work in Progress on Resource Allocation

Frontmatter
Enabling Business-Preference-Based Scheduling of Cloud Computing Resources
Abstract
Although cloud computing technology gets increasingly sophisticated, a resource allocation method still has to be proposed that allows providers to take into consideration the preferences of their customers. The existing engineering-based and economics-based resource allocation methods do not take into account jointly the different objectives that engineers and marketing employees of a cloud provider company follow. This article addresses this issue by presenting the system architecture and, in particular, the business-preference-based scheduling algorithm that integrates the engineering aspects of resource allocation with the economics aspects of resource allocation. To show the workings of the new business-preference-based scheduling algorithm, which integrates a yield management method and a priority-based scheduling method, a simulation has been performed. The results obtained are compared with results from the First-Come-First-Serve scheduling algorithm. The comparison shows that the proposed scheduling algorithm achieves higher revenue than the engineering-based scheduling algorithm.
Azamat Uzbekov, Jörn Altmann
Bazaar-Score: A Key Figure Measuring Market Efficiency in IaaS-Markets
Abstract
Today’s economy creates the need for dynamic, adaptive and autonomous building of enterprise value chains consisting of arbitrary virtualized computing resources, as hardware and software services. The current key technology for service provisioning is the cloud computing framework. In the course of this development digital service markets are becoming business reality.
Consumers in these digital markets apply typically the classical “take-it-or-leave-it” supermarket approach, which limits market performance. A solution to this problem is the so called Bazaar-based market, which extends the classical supermarket approach by enabling multi-round negotiation processes. Hereby business strategies of providers and consumers can be reflected in the negotiation processes to allow for smarter and more effective agreements in the market. In this paper we present a novel genetic algorithm based multi-round negotiation strategy between providers and consumers of services. This approach is realized within a Bazaar-Extension for CloudSim. To compare the market efficiency of resource allocations we introduce a novel key figure, the Bazaar-Score metric, which allows the evaluation of different business strategies.
Benedikt Pittl, Werner Mach, Erich Schikuta
Understanding Resource Selection Requirements for Computationally Intensive Tasks on Heterogeneous Computing Infrastructure
Abstract
Scientists and researchers face challenges in efficiently configuring their scientific computing tasks so that they can be run in a timely and cost-effective manner. While the increasing availability of different types of computing platforms provides many opportunities to users, it can further complicate the job configuration process. In this paper we present work-in-progress to develop an approach to assist with identifying the most suitable computing platform and configuration for a computational task based on a user’s financial and temporal constraints, using a decision support system. We use Nekkloud, a web-based tool for running computations via the Nektar++ spectral/hp element framework, as an exemplar and build a table that scores a range of properties for four example computing platforms to help select the most suitable platform for a job. We demonstrate our approach using three sample task scenarios.
Jeremy Cohen, Thierry Rayna, John Darlington
Towards Usage-Based Dynamic Overbooking in IaaS Clouds
Abstract
IaaS Cloud systems enable the Cloud provider to overbook his data centre by selling more virtual resources than physical resources available. This approach works if on average the resource utilisation of a virtual machine is lower than the virtual machine boundaries. If this assumption is violated only locally, Cloud users will experience performance degradation and poor quality of service. This paper proposes the introduction of dynamic overbooking in the sense that the overbooking factors are not equal for all physical resources, but vary dynamically depending on the resource demands of the virtual resources they host. It allows new pricing models that are dependent on the overbooking a Cloud customer is willing to accept. Additionally, we discuss prerequisites for supporting its realisation in an OpenStack private Cloud, including a monitoring system, dedicated metrics to be monitored, as well as performance models that predict the performance degradation depending on the overbooking.
Athanasios Tsitsipas, Christopher B. Hauser, Jörg Domaschka, Stefan Wesner

Cloud Applications

Frontmatter
A Privacy-Preserving Top-k Query Processing Algorithm in the Cloud Computing
Abstract
Cloud computing has emerged as a new platform for storing and managing databases. As a result, a database outsourcing paradigm has gained much interests. To prevent the contents of outsourced databases from being revealed to cloud computing, databases must be encrypted before being outsourced to the cloud. Therefore, various Top-k query processing techniques have been proposed for encrypted databases. However, there is no existing work that can not only hide data access patterns, but also preserve the privacy of user query. To solve the problems, in this paper, we propose a new privacy-preserving Top-k query processing algorithm. Our algorithm protects the user query from the cloud and conceals data access patterns during query processing. A performance analysis shows that the proposed scheme provide good scalability without any information leakage.
Hyeong-Il Kim, Hyeong-Jin Kim, Jae-Woo Chang
A Network Edge Monitoring Approach for Real-Time Data Streaming Applications
Abstract
Renting very high bandwidth or special connection links is neither affordable nor economical for service providers. As a consequence, ensuring data streaming systems to be able to guarantee desired service quality experienced by the users has been a challenging issue due to real-time changes in the network performance of the Internet communications. This paper presents a network monitoring approach that is broadly applicable in the adaptation of real-time services running on network edge computing platforms. The approach identifies runtime variations in the network quality of links between application servers and end-users. It is shown that by identifying critical conditions, it is possible to continuously adapt the deployed service for optimal performance. Adaptation possibilities include reconfiguration by dynamically changing paths between clients and servers, vertical scaling such as re-allocation of bandwidth to specific links, horizontal scaling of application servers, and even live-migration of application components from one edge server to another to improve the application performance.
Salman Taherizadeh, Ian Taylor, Andrew Jones, Zhiming Zhao, Vlado Stankovski
Distributed Simulation of Complex and Scalable Systems: From Models to the Cloud
Abstract
Simulation is a standard technique to understand or to analyze complex Discrete Event Systems (DES). Distributed simulation techniques try to improve the elapsed time of sequential simulations for large DES models by dividing a monolithic simulation application into communicating concurrent Logical Processes. The performance of the simulator is usually evaluated on the basis of the time needed and the involved resources to complete a simulation run. Additionally, cloud computing, under a pay-per-use model, introduces the costs of the resources that must be allocated to run the simulation. In this paper, a Petri Net based modeling methodology for complex systems is presented producing hierarchical and modular models. From this model, an elaboration process produces a heterarchical model for efficient execution of the simulation over cloud platforms using well known techniques. The required partitioning of the model may be subject to different criteria such as cost, elapsed time, and synchronization constraints, where the structural properties of the Petri Nets can aid in this task.
Victor Medel, Unai Arronategui, José Ángel Bañares, José-Manuel Colom
Backmatter
Metadaten
Titel
Economics of Grids, Clouds, Systems, and Services
herausgegeben von
José Ángel Bañares
Konstantinos Tserpes
Jörn Altmann
Copyright-Jahr
2017
Electronic ISBN
978-3-319-61920-0
Print ISBN
978-3-319-61919-4
DOI
https://doi.org/10.1007/978-3-319-61920-0

Premium Partner

    Bildnachweise