Skip to main content
main-content

Über dieses Buch

This book constitutes the refereed proceedings of the 9th International Workshop on Economics of Grids, Clouds, Systems, and Services, GECON 2012, held in Berlin, Germany, in November 2012. The 12 revised full papers presented together with 6 work in progress papers were carefully reviewed and selected from more than 36 submissions. The papers are organized in the following topical sections: market mechanisms, pricing and negotiation; resource allocation, scheduling and admission control; work in progress on tools and techniques for cost-efficient service selection; market modeling; trust; cloud computing in education; and work in progress on cloud adoption and business models.

Inhaltsverzeichnis

Frontmatter

Session A: Market Mechanisms, Pricing and Negotiation

A Protocol Development Framework for SLA Negotiations in Cloud and Service Computing

As businesses transit towards cloud and service oriented economy, agents are employed to efficiently negotiate service level agreements (SLAs) on services procured automatically to match changes in demand. This ‘pay-as-you-go’ trading model affords flexibility with reliability, but requires customized and seamless interactions enabled by negotiation protocols that best serve the market domain. To this end, we present a domain-independent framework based on a protocol development lifecycle, comprising four distinct phases namely modeling, verification, rule-based implementation and generic execution.
We illustrate all phases by introducing the Simple Bilateral Negotiation Protocol (SBNP) - a multi-tier, multi-round and customizable negotiation protocol. We exemplify its adoption among chains of service providers that serve SaaS, PaaS and IaaS offerings. We show that SBNP is well-formed, deterministic and deadlock-free. We evaluate state space scalability for SBNP and verify its correctness using Linear Temporal Logic (LTL). Finally, we show that rule-based implementation allows for generic execution of multiple protocols on our negotiation platform, which provides businesses the agility to sustain competitive advantage.
Edwin Yaqub, Ramin Yahyapour, Philipp Wieder, Kuan Lu

The Use of Provision Point Contracts for Improving Cloud Infrastructure Utilisation

The on-demand capability of cloud computing allows consumers to purchase only the computing resources they require, as and when they need it. However, without a view of future demand, cloud providers’ faces challenges in optimising the use of their infrastructure. In this paper, we propose a pricing method for cloud computing which allows providers to schedule virtual machines more efficiently through the use of provision point contracts (PPCs), commonly used for deal-of-the day websites such as Groupon. We show that the model can achieve a reduction of around 2% on the mean number of servers utilised. This may seem a modest percentage, but it can equate to freeing up thousands of physical servers in a single industrial-scale cloud computing data-centre. Additionally, our pricing model prevents discounts being offered where no increase in server efficiency is likely to be achieved. This suggests that the model can be implemented with little risk of it negatively affecting the efficiency of server provisioning. Finally, our results indicate that the cloud-service users who engage with the PPC method can achieve savings of over 20%.
Owen Rogers, Dave Cliff

An Economic Agent Maximizing Cloud Provider Revenues under a Pay-as-you-Book Pricing Model

The Cloud computing paradigm offers the illusion of infinite resources accessible to end-users anywhere at anytime. In such dynamic environment, managing distributed heterogeneous resources is challenging. A Cloud workload is typically decomposed into advance reservation and on-demand requests. Under advance reservation, end-users have the opportunity to reserve in advance the estimated required resources for the completion of their jobs without any further commitment. Thus, Cloud service providers can make a better use of their infrastructure while provisioning the proposed services under determined policies and/or time constraints. However, estimating end-users resource requirements is often error prone. Such uncertainties associated with job execution time and/or SLA satisfaction significantly increase the complexity of the resource management. Therefore, an appropriate resource management by Cloud service providers is crucial for harnessing the power of the underlying distributed infrastructure and achieving high system performance. In this paper, we investigate the resource provisioning problem for advance reservation under a Pay-as-you-Book pricing model. Our model offers to handle the extra-time required by some jobs at a higher price on a best-effort basis. However, satisfying these extra-times may lead to several advance reservations competing for the same resources. We propose a novel economic agent responsible for managing such conflicts. This agent aims at maximizing Cloud service provider revenues while complying with SLA terms. We show that our agent achieves higher return on investment compared to intuitive approaches that systematically prioritize reserved jobs or currently running jobs.
Felipe Díaz Sánchez, Elias A. Doumith, Sawsan Al Zahr, Maurice Gagnaire

Session B: Resource Allocation, Scheduling and Admission Control

Economic Co-allocation and Advance Reservation of Network and Computational Resources in Grids

The introduction of economic principles allows Resource Management Systems (RMS) to better deal with conflicting user requirements by incorporating user valuations and externalities such as the usage cost of resources into the planning and scheduling logic. This allows economic RMSs to create more value for the participants than traditional system centric RMSs. It is important for an RMS to take the data requirements of an application into account during the planning phase. Traditional RMSs have been presented supporting co-allocation and advance reservation of both network and computational resources. However, to the best of our knowledge no economic RMSs proposed in the literature possesses these capabilities. In this paper we present ENARA, an economic RMS with advance reservation and co-allocation support for both network and computational resources. We will demonstrate that ENARA can significantly increase the user value compared to an online approach.
Wim Depoorter, Kurt Vanmechelen, Jan Broeckhove

Revenue-Based Resource Management on Shared Clouds for Heterogenous Bursty Data Streams

When data from multiple sources (sensors) are processed over a shared distributed computing infrastructure, it is necessary to often provide some Quality of Service (QoS) guarantees to each data stream. Service Level Agreements (SLAs) identify the cost that a user must pay to achieve the required QoS, and a penalty that must be paid to the user in case the QoS cannot be met. Assuming the maximisation of the revenue as the provider’s objective, then it must decide which streams to accept for storage and analysis; and how many (computational / storage) resources to allocate to each stream in order to improve overall revenue. We propose an infrastructure for supporting QoS for concurrent data streams to be composed of self-regulating nodes. Each node features an envelope process to accept user streams; and a resource manager to enable resource allocation, admission control and selective SLA violations, while maximizing revenue.
Rafael Tolosana-Calasanz, José Ángel Bañares, Congduc Pham, Omer F. Rana

The ISQoS Grid Broker for Temporal and Budget Guarantees

We introduce our Grid broker that uses SLAs in job submission with the aim of ensuring jobs are computed on time and on budget. We demonstrate our broker’s ability to perform negotiation and to select preferentially higher priority jobs, in a tender market and discuss the architecture that makes this possible. We additionally show the effects of rescheduling and how careful consideration is required in order to avoid price instability. We therefore make recommendations upon how to maintain this stability, given rescheduling.
Richard Kavanagh, Karim Djemame

Session C:Work-in-Progress on Tools and Techniques for Cost-Efficient Service Selection

Let the Clouds Compute: Cost-Efficient Workload Distribution in Infrastructure Clouds

With cloud computing, a virtually inexhaustible pool of computing capacity has become available to IT users. However, given the large number of Infrastructure as a Service offers with differing pricing options, the cost-efficient distribution of workloads poses a complex challenge. In this work-in-progress paper, we formally describe the Cloud-oriented Workload Distribution Problem and propose an exact as well as a heuristic optimization approach. Through an evaluation that is based on realistic data from the cloud market, we examine the performance and practical applicability of these approaches.
Ulrich Lampe, Melanie Siebenhaar, Ronny Hans, Dieter Schuller, Ralf Steinmetz

A Declarative Recommender System for Cloud Infrastructure Services Selection

The cloud infrastructure services landscape advances steadily leaving users in the agony of choice. Therefore, we present CloudRecommender, a new declarative approach for selecting Cloud-based infrastructure services. CloudRecommender automates the mapping of users’ specified application requirements to cloud service configurations. We formally capture cloud service configurations in ontology and provide its implementation in a structured data model which can be manipulated through both regular expressions and SQL. By exploiting the power of a visual programming language (widgets), CloudRecommender further enables simplified and intuitive cloud service selection. We describe the design and a prototype implementation of CloudRecommender, and demonstrate its effectiveness and scalability through a service configuration selection experiment on most of today’s prominent cloud providers including Amazon, Azure, and GoGrid.
Miranda Zhang, Rajiv Ranjan, Surya Nepal, Michael Menzel, Armin Haller

Retrieving, Storing, Correlating and Distributing Information for Cloud Management

The emergence of Cloud technologies ultimately affected the service computing ecosystem introducing new roles and relationships as well as new architectural and business models. The increase of the capabilities and potentials of the service providers raised the need for managing the information being available in an efficient way. In this paper we introduce a service management architecture as well as the corresponding information model, which is the placeholder for the information needed to perform management operations. The design of the proposed model was based on the case of a storage service being provided through a cloud infrastructure, but the approach is implemented in a flexible and modular fashion in order to support any service provided through a cloud environment.
Spyridon V. Gogouvitis, Gregory Katsaros, Dimosthenis Kyriazis, Athanasios Voulodimos, Roman Talyansky, Theodora Varvarigou

Session D: Market Modeling

On Local Separation of Processing and Storage in Infrastructure-as-a-Service

When processing and storage are obtained as internet services, the actual location of the providing facility is undetermined. Factors like a robust and cheap power supply, cooling-relevant climate conditions as well as legal and risk-related considerations are important for selecting a facility’s site. As storage and processing facilities feature different economies of scale and location, their local separation is an alternative to combining them in one location. This paper contributes a game-theoretic model to investigate the market success of separate processing and storage facilities compared to a combined approach. It can be shown that stable market constellations with separate service specific facilities are possible.
Jörn Künsemöller, Holger Karl

Value Creation in IT Service Platforms through Two-Sided Network Effects

IT service businesses can achieve economies of scale and scope faster than in traditional product businesses. In particular, as IT service platforms will become the founding infrastructure of our economies, the analysis and understanding of the value that a service platform can generate is of great importance. IT service platforms provide all involved market participants with different values. For this paper, we consider application service users, service developers and service platform providers as market participants and analyze the interrelationship between the value creations of these market participants. The basis for the description of the values and their interrelationship is the identification of parameters. Based on these parameters, a simulation model has been developed. It helps inferring the relative impact of these parameters on the evolution of the IT service platform stakeholder values. The results imply that there is a two-sided network effect. All stakeholders of a service platform mainly benefit from a growing installed base of application users. The benefit of a large service variety, however, mainly benefits the service platform provider. Therefore, we can state that a large fraction of the value from two-sided network effects goes to the platform provider.
Netsanet Haile, Jörn Altmann

Session E: Trust

Cheat-Proof Trust Model for Cloud Computing Markets

Online Reputation Systems would help mitigate the information asymmetry between clients and providers in Cloud Computing Markets. However, those systems raise two main drawbacks: the disagreement for assuming the cost of ownership of such services and their vulnerability to reputation attacks from dishonest parties that want to increase their reputation. This paper faces both problems by describing a decentralized model that would not need from the intervention of a central entity for managing it. This model includes mechanisms for allowing participants to avoid such dishonest behaviour from other peers: each client statistically analyses the external reports about providers and accordingly weights them in the overall trust calculation. The validity of the model is demonstrated through experiments for several use cases.
Mario Macías, Jordi Guitart

Trust Factors for the Usage of Cloud Computing in Small and Medium Sized Craft Enterprises

Although many benefits of cloud computing exist for SMEs, the development and usage of cloud computing solutions still face various challenges. The decision for applying cloud computing solutions, depend mainly on the length of time an enterprise exists, the degree of specialization, and finally the degree of need for security. Therefore, one of the key obstacles towards the adoption of cloud computing is among technical issues the establishment of trust into the performance, security, data protection and other features of cloud services and their providers. However, trust strongly depends on the target users and their characteristics. Over 16 percent of German SMEs apply cloud computing and realize its potentials. In the research project CLOUDwerker, funded by the German Federal Ministry of Economic and Technology, software as a service solutions for SMEs in the craft sector are examined and developed. In order to increase the usage of cloud computing at the target group of those SMEs, the paper focus on identifying and comparing the factors which influence trust into cloud computing solutions from the craft-specific view of small and medium sized craft enterprises and craft-specific cloud service providers who both have been addressed and questioned in two separate surveys. The results are considered to improve the development of trusted cloud computing applications which achieve a high user acceptance.
Holger Kett, Harriet Kasper, Jürgen Falkner, Anette Weisbecker

Session F: Cloud Computing in Education

A Cost Analysis of Cloud Computing for Education

Educational institutions have become highly dependent on information technology to support the delivery of personalised material, digital content, interactive classes, and others. These institutions are progressively transitioning into Cloud Computing technology to shift costs from locally-hosted services to a “renting model” often with higher availability, elasticity, and resilience. However, in order to properly explore the cost benefits of the pay-as-you-go business model, there is a need for processes for resource allocation, monitoring, and self-adjustment that take advantage of characteristics of the application domain. In this paper we perform a numerical analysis of three resource allocation methods that work by (i) pre-allocating resource capacity to handle peak demands; (ii) reactively allocating resource capacity based on current demand; and (iii) proactively allocating and releasing resources prior to load increases or decreases by exploring characteristics of the educational domain and more precise information about expected demand. The results show that there is an opportunity for both educational institutions and Cloud providers to collaborate in order to enhance the quality of services and reduce costs.
Fernando Koch, Marcos D. Assunção, Marco A. S. Netto

Delivering Cloud Services with QoS Requirements: An Opportunity for ICT SMEs

The acknowledged success and diffusion of Cloud computing is due to its great potential in terms of improving companies’ business model. Notwithstanding this opportunity, two main issues arise: the need of brokers supporting users in the selection of the most suitable offers, and the provisioning of dedicated services with higher levels of quality different from mere availability. This paper discusses the expected performance in a real-case scenario of a Cloud brokering tool delivering two services: e-Learning courses in virtual classroom and Risk Assessment evaluation, each with a specific set of non-functional requirements. The broker relies on the resources supplied by a hybrid Cloud infrastructure, allocated following different scheduling strategies, which dynamically select the proposals better satisfying the QoS requested by users. The objective is the execution of the highest amount of user requests along with the maximization of the profit of the private Cloud provider, in a context of posted price economic model.
Alfonso Quarati, Daniele D’Agostino, Antonella Galizia, Matteo Mangini, Andrea Clematis

Session G: Work-in-Progress on Cloud Adoption and Business Models

A Mixed-Methods Research Approach to Investigate the Transition from on-Premise to on-Demand Software Delivery

Verdicts on the advisability for software vendors to adopt on-demand delivery models are widespread in the business and technology press. Incumbent software vendors, in particular, are prompted to transition to on-demand and cannibalize their on-premise customer-base, in order to supposedly enjoy market expansion, economies of scale and revenue predictability. Yet, academic research addressing this strategic move is scarce. Relying on a mixed-methods research approach, I examined the transition of two software companies which originally entered the market as on-premise vendors and turned into pure on-demand players over time. Specifically, I performed a qualitative analysis of financial reports and transcripts to identify possible milestones in the course of the transition, followed by an econometric analysis of quarterly financial results to shed some light on the impact such milestones may have had on the vendors’ performances.
Francesco Novelli

Towards a Federated Cloud Ecosystem: Enabling Managed Cloud Service Consumption

While cloud computing has seen widespread usage, there exist domains where the diminishing of management capabilities associated with cloud computing prevent adoption. One such domain is the health sector, which is the focus of the TRESOR project. Enabling cloud computing usage under strict compliance constraints such as enterprise policies and legal regulations is the goal of TRESOR. The main approach consists of a distributed cloud proxy, acting as a trusted mediator between cloud consumers and service providers. In this paper we analyze issues which arise within the TRESOR context and show how an architecture for a proposed ecosystem bypasses these issues. The practicability of our solution is shown by a proof of concept proxy implementation. As all components of the architecture will be part of our proposed cloud ecosystem, we provide a holistic and generic proposal to regain management capabilities in cloud computing.
Dirk Thatmann, Mathias Slawik, Sebastian Zickau, Axel Küpper

Business Models for Semantic Content Providers

The Semantic Web, being the next phase in the evolution of the Web, relies on the existence of semantic annotations i.e., the documents describing the data and information using ontologies. The major barrier in the development of the Semantic Internet is that the process of creating semantic annotations is complex and labour-intensive. The lack of semantically annotated data on the one hand, and the need to create, disseminate and use standards for data description in the Semantic Web on the other, have created a niche on the market for suppliers of the semantic content. The purpose of this paper is to present business models of the semantic content providers and discuss the benefits and challenges in the delivery of semantically annotated artefacts.
Monika Kaczmarek, Agata Filipowska

Backmatter

Weitere Informationen

Premium Partner

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung

Unternehmen haben das Innovationspotenzial der eigenen Mitarbeiter auch außerhalb der F&E-Abteilung erkannt. Viele Initiativen zur Partizipation scheitern in der Praxis jedoch häufig. Lesen Sie hier  - basierend auf einer qualitativ-explorativen Expertenstudie - mehr über die wesentlichen Problemfelder der mitarbeiterzentrierten Produktentwicklung und profitieren Sie von konkreten Handlungsempfehlungen aus der Praxis.
Jetzt gratis downloaden!

Bildnachweise