Special issue: Towards market-oriented clouds

Vol. 65, n° 11-12, November-December 2010
Content available on Springerlink

Guest editors
Maurice Gagnaire, Telecom ParisTech, France
Pascale Vicat-Blanc Primet, INRIA, ENS Lyon, France
Dimitra Simeonidou, University of Essex, UK


M. Gagnaire, P. Vicat-Blanc Primet, D. Simeonidou

A marketplace and its market mechanism for trading commoditized computing resources

Jörn Altmann*, Costas Courcoubetis**, Marcel Risch*

*Seoul National University, Korea
**Athens University of Economics and Business, Greece

Abstract This paper presents the design and implementation of the GridEcon Marketplace. In addition to supporting a market mechanism for trading computing resources on a payper- use basis, this marketplace also provides an environment for integrating value-added support services. These valueadded services help consumers to use the utility computing market more efficiently. The GridEcon Market Mechanismfor virtual machines specifies in detail the unit-of-trade, the bids and asks, as well as the matching algorithm. The marketplace and market mechanism are validated by using the GridEcon Platform, which is a service-oriented platform for composing market scenarios. Our validation results show that the Grid- Econ Marketplace fulfills all functional requirements and that the GridEcon Market Mechanism is computationally and economically efficient.

Keywords Grid economics . Cloud computing . Computing resource market . Market mechanism design . Utility

A market-oriented dynamic collaborative cloud services platform

Mohamad Mehedi Hassan, Biao Song, Eui-Nam Huh

Kyung Hee University, Korea

Abstract Currently, interoperability and scalability are two major challenging issues for cloud computing. Forming a dynamic collaboration (DC) platform among cloud providers (CPs) can help to better address these issues. A DC platform can facilitate expense reduction, avoiding adverse business impacts and offering collaborative or portable cloud services to consumers. However, there are two major challenges involved in this undertaking; one is to find an appropriate market model to enable a DC platform, and the other one is to minimize conflicts among CPs that may occur in a marketoriented DC platform. In this paper, we present a novel combinatorial auction (CA)-based cloud market (CACM) model that enables a DC platform in CPs. To minimize conflicts among CPs, a new auction policy is proposed that allows a CP to dynamically collaborate with suitable partner CPs to form groups and publishes their group bids as a single bid to compete in the auction. However, identifying a suitable combination of CP partners to form the group and reduce conflicts is a NP-hard problem. Hence, we propose a promising multi-objective (MO) optimization model for partner selection using individual information and past collaborative relationship information, which is seldom considered. A multi-objective genetic algorithm (MOGA) called MOGA-IC is proposed to solve the MO optimization problem. This algorithm is developed using two popular MOGAs, the non-dominated sorting genetic algorithm (NSGA-II) and the strength pareto evolutionary genetic algorithm (SPEA2). The experimental results show that MOGA-IC with NSGA-II outperformed the MOGA-IC with SPEA2 in identifying useful pareto-optimal solution sets. Other simulation experiments were conducted to verify the effectiveness of the MOGA-IC in terms of satisfactory partner selection and conflict minimization in the CACM model. In addition, the performance of the CACM model was compared to the existing CA model in terms of economic efficiency.

Keywords Cloud market . Combinatorial auction . Dynamic collaboration . Interoperability . Partner selection . Multi-objective genetic algorithm

Combinatorial auctions for exchanging resources over a grid network

Lucile Denoeud-Belgacem*, Eric Gourdin**, Ruby Krishnaswamy**, Adam Ouorou**

*FutureMaster, France
**Orange Labs, Issy les Moulineaux, France

Abstract In grid systems, users compete for different types of resources such that they may execute their applications. Traditional grid systems are formed of organisations that join together for the purpose of collaborative projects. Resources of each of the participating organisation are pooled such that members of individual organisations may access the shared infrastructure. In general, each participant is both a provider and a consumer of resources. Whilst such systems address large organisations, in this paper we address democratic grid systems to satisfy needs of small organisations and even individuals, where on-demand grids may be formed by drawing idling resources available on the Internet. Whilst traditional grid systems resort to allocations that satisfy system specific objectives such as maximization of the resource utilisation, market mechanisms try to obtain allocations that are efficient economically. Economic mechanisms permit to achieve equilibrium between supply and demand and furthermore provide incentives for providers. Combinatorial auction has been argued as an effective mechanism to address the problem of resource allocation within grid systems. Auctions within which multiple types of resources in varying quantities may be traded eliminate the exposure problem by addressing co-allocation. In this paper, we describe a combinatorial exchange where multiple providers and multiple consumers may participate. We describe the winner determination problem that incorporates the time dimension, i.e. resource bundles may be requested for different time ranges, and describe a set of heuristics that have been designed to be fast. We show that these achieve a high level of efficiency as compared to exact solutions. The second part focusses on the pricing problem. The objective is to compute prices that represent the state of the market and bring trustworthy feedback to participants. Drawing on the approach taken by Kwasnica et al. (Manage Sci 51(3):419–434, 2005), we propose a pricing model that computes per-item pricing. Per-item pricing allows users to deduce the price of bundles that they require by linear summation. Furthermore, we propose a model that computes prices as a function of time, thus permitting users, in particular consumers to adjust their demand trading off price and time of execution.

Keywords Combinatorial auction · Winner determination problem · Vickrey–Clarke–Groves prices

The representation and computation of QoS preference with its applications in grid computing environment

Quan Liang*, Yuanzhuo Wang**

*Fujian University of Technology, China
**Institute of Computing Technology, China

Abstract In Grid computing environment, quality of service (QoS) provisioning must be provided to the end users on the basis of their specific requirements. This paper proposes in a first step QoS attributes for Grid applications. In this matter, a mix of quantitative and qualitative parameters have to be considered. In the context, the analytical hierarchy process (AHP) technique [1] is a possible approach to formulate the QoS requirements of the users for Grid services. In order to apply QoS preference to actual application, we introduce a QoS function and a metric for user’s satisfaction degrees. These both tools can be used as an evaluation criterion by the user. Subsequently, an algorithm of service selection considering the user’s QoS preference is presented. Our empirical studies indicate that the application can reliably select the optimal service for users.

Keywords Grid computing . QoS preference .AHP. Satisfaction degree . Service selection

Network Virtualization for Cloud Computing

Fabio Baroncelli*, Barbara Martini*, Piero Castoldi**

*CNIT, Pisa, Italy
**Scuola Superiore Sant’Anna, Pisa, Italy

Abstract Cloud computing enables a transparent access to information technology (IT) services such that the users do not need to know the location and characteristics of the relevant resources. While IT resource virtualization and service abstraction have been widely investigated, data transport within the cloud and its efficient control have not received much attention in the technical literature. In fact, connectivity is, itself, a service that contributes to the overall performance of the cloud. This paper introduces a novel classification of the Network as a Service (NaaS) such that it can be orchestrated with other cloud services. Then, it proposes a network virtualization platform (NVP) as the mediation layer able to provide NaaS to cloud computing by exploiting the functionality provided by control plane (CP)-enabled networks. In particular, the proposed NVP maps the end-point addresses and perceived Quality of Service parameters of a NaaS requests in the parameters characterizing the connectivity as viewed by transport networks using the information obtained from the CP at the boundary of the network. The NVP uses these parameters to fulfill connectivity requests to the CP. Finally, this paper presents a complete design from both the software implementation and network signaling perspective of two use cases in which NaaS is involved as stand-alone facility for the connectivity service provisioning or is combined with other cloud services for a storage service provisioning.

Keywords Network virtualization . Cloud computing .Networking

A New Framework for GLIF Interdomain Resource Reservation Architecture (GIRRA)

Gigi Karmous-Edwards*,**, Silvana Greco Polito*, Admela Jukan*, George Rouskas**

 *Technische Universität Carolo-Wilhelmina zu Braunschweig, Germany
**North Carolina State University, Raleigh, USA

Abstract Many existing and emerging Scientific highend applications (E-science) require end-to-end circuits interconnecting Grid resources for large data transfers. A few advanced networks, mainly National Research and Education Networks (NRENs), such as Surfnet, National Lambda Rail and Internet 2, now provide mechanisms for end-users to reserve and provision lightpaths via middleware referred to as Network Resource Mangers (NRMs). Although, some progress has been made in automated intra-domain lightpath services, inter-domain lightpath provisioning still requires manual intervention and presents several key challenges such as scalability of topology information exchanged, consistency and scalability of information model, security of access to the resources, hybrid networking and multi-layer lightpaths, and accounting and billing. In this paper, we describe a new architectural framework called Global Lambda Integrated Facility (GLIF) Interdomain Resource Reservation Architecture (GIRRA) with the goal to provide an integrated response to these challenges. We propose a new approach to model GLIF network domains and GOLEs as virtual switches and to describe their behavior, functionality, policy capabilities, and topology aggregation. We define an inter-domain path computation model to determine paths that meet constraints and access policy restrictions. We propose a security framework for authentication and authorization of users and a model for accounting and billing that aims to provide easy and secure access to the resources. Key aspects of the GIRRA solution are that it focuses on the inter-dependence between different challenges of interdomain path provision, and it is built around already existing solutions for intra-domain resource provisioning.

Keywords Inter-domain networking · Security · Path computation · GLIF · Middleware

A funding and governing model for achieving sustainable growth of computing e-infrastructures

Ashraf Bany Mohammed*, Jörn Altmann**

*Petra University, Jordan
**Seoul National University, Korea

Abstract The current access policies and funding schemes of computing e-infrastructures represent a huge challenge for the sustainable growth of computing e-infrastructures and a serious jeopardy for investments made into these e-infrastructures. In order to be able to address these issues, the economics of computing e-infrastructures has to be understood thoroughly. As a first step in this direction, this paper conducts a set of computing e-infrastructure case studies and discusses the economic issues of different global computing e-infrastructure efforts. The analyses results show that the major shortcomings that need to be resolved are the insufficient involvement of the private sector in the development of computing einfrastructures, the restricted user access to e-infrastructure resources, and the lack of sustainable funding. As a solution to these shortcomings, we propose a new funding and governing model for computing e-infrastructures. It follows a token-based market mechanism that allows a business-oriented operation of the computing e-infrastructure. We argue that this new model fosters the transition towards a sustainable computing einfrastructure, being another requirement for successfully implementing the cloud computing vision. Our arguments are supported by an analytical analysis.

Keywords Grid and cloud economics . Business models . Funding . Governance . Case study analysis . Sustainability. Grid computing . High-performance computing . Token-based market mechanism . Computing services . Analytical modeling

Brief report:

UNICORE 6 – Recent and Future Advancements

Achim Streit* et al.

 *Jülich Supercomputing Centre (JSC), Germany

Abstract UNICORE is a European Grid Technology with more than 10 years of history.Originating from the Supercomputing domain, the latest version UNICORE 6 has turned into a general-purpose Grid technology that follows established standards and offers a rich set of features to its users. The paper starts with an architectural insight into UNICORE 6, highlighting the workflow features, standards and the different clients. Next, the current state of advancement is presented by describing recent developments. The paper closes with an outlook on future planned developments.

Keywords Grid · Supercomputing · UNICORE · Middleware

Brief report:

D-Grid: A National Grid Infrastructure in Germany

Uwe Schwiegelshohn*

*TU Dortmund University, Germany

Abstract In 2005, Germany launched its ambitious DGrid initiative to establish a national Grid infrastructure. Although the initiative is open to all groups interested in Grid computing, the current focus is on four target groups: academic computing centers, academic and commercial service providers, academic research communities, and private–public partnership communities. More than 30 projects within the initiative cooperate to solve technical problems, to generate appropriate organizational structures, and to define interfaces between the target groups. In this paper, we explain the general concept, report on the progress of these projects, and describe the key issues that have been identified in hindsight. Furthermore, we discuss the development of the initiative with respect to new trends like the various forms of cloud computing.

Keywords National grid infrastructure · Grid communitie

Brief report:

The next generation ARC middleware

S Farid Ould-Saada* et al.

*University of Oslo, Norway 

Abstract The Advanced Resource Connector (ARC) is a light-weight, non-intrusive, simple yet powerful Grid middleware capable of connecting highly heterogeneous computing and storage resources. ARC aims at providing general purpose, flexible, collaborative computing environments suitable for a range of uses, both in science and business. The server side offers the fundamental job execution management, information and data capabilities required for a Grid. Users are provided with an easy to install and use client which provides a basic toolbox for job- and data management. The KnowARC project developed the next-generation ARC middleware, implemented as Web Services with the aim of standard-compliant interoperability.

Keywords Grid · Distributed computing · Middleware · Standardization · Interoperability · Web service

Open Topics

A load-aware energy-efficient and throughput-maximized asynchronous duty cycle MAC for wireless sensor networks

Muhammad Mostafa Monowar, Muhammad Mahbub Alam, Md. Obaidur Rahman, Choong Seon Hong and Sungwon Lee

Kyung Hee University, Korea

Abstract Being a pivotal resource, conservation of energy has been considered as the most striking issue in the wireless sensor network research. Several works have been performed in the last years to devise duty cycle based MAC protocols which optimize energy conservation emphasizing low traffic load scenario. In contrast, considering the high traffic situation, another research trend has been continuing to optimize both energy efficiency and channel utilization employing rate and congestion control at the MAC layer. In this paper, we propose A Load-aware Energy-efficient and Throughput-maximized Asynchronous Duty Cycle MAC (LET-MAC) protocol for wireless sensor networks to provide an integrated solution at the MAC layer considering both the low-and high-traffic scenario. Through extensive simulation using ns-2, we have evaluated the performance of LET-MAC. LETMAC achieves significant energy conservation during low traffic load (i.e., no event), compared to the prior asynchronous protocol, RI-MAC, as well as attains optimal throughput through maximizing the channel utilization and maintains lower delay in regard to the CSMA/CA-like protocol during a high volume of traffic (i.e., when an event occurs).

Keywords Wireless sensor networks · Energy conservation · MAC protocol

Connectivity evaluation and error performance of millimeter-wave wireless backhaul networks

Georgios T. Pitsiladis, Athanasios D. Panagopoulos and Phillip Constantinou

National Technical University of Athens, Greece

Abstract The general trend in the backhaul link technology arena is the increasing use of high-speed microwave solutions. The ever-rising demand for high capacities at low cost has recently enhanced the interest in wireless backhaul networks. Evaluating the connectivity of the wireless multihop backhaul networks is a significant task. Taking into account the high frequency of operation, a novel analytical and engineering propagation model is presented for the calculation of connectivity. Furthermore, the minimum required node density in order to keep the network connected is also calculated. The sensitivity of network connectivity on frequency operation, transmission power, and climatic conditions is also investigated. Finally, the error performance of the backhaul network links is finally presented, and some very useful conclusions are drawn.

Keywords Wireless backhaul networks . Isolation probability . Minimum node density . Error performance

Cross-layer design of multiple antenna multicast combining AMC with truncated HARQ

Tan Tai Do*, Jae Cheol Park*, Iickho Song** and Yun Hee Kim*

*Kyung Hee University, Korea
**Korea Advanced Institute of Science and Technology, Korea

Abstract Combining adaptive modulation and coding with truncated hybrid automatic request, this paper presents a cross-layer design for multiple antenna multicast over a common radio channel. In the design, the modulation and coding scheme of a multicast packet is selected based on the minimum signal-to-noise ratio (SNR) in the multicast group in such a way that the constraint on the packet loss rate is satisfied for all users in the group. A general expression for the throughput of the proposed design is derived in frequencyflat fading channel environment and specific results in Rayleigh, Nakagami, and Rician fading channels are provided. It is shown that the proposed multicast design provides a significant throughput gain compared to the unicast counterpart, in particular, in the mid- to high SNR region. It is also shown that a larger value of the diversity order, Nakagami parameter, and Rician factor is more beneficial to multicast than to unicast.

Keywords Wireless multicast · Cross-layer design · AMC · Truncated HARQ · SNR threshold