Research

Interests

Autonomic Computing
Economic Based Resource Allocation Algorithms
Grid Computing
Service Oriented Architectures
Self-* properties of large scale distributed systems

PhD Research

An Economic Based Framework for Self-Adaptive Grid Middleware

For Grids, with its intrinsic distribution, heterogeneity and multi-institutional setups, the direct engineering of management mechanism capable of handling the complexity of the environment and the user demands has become an unattainable task. Autonomic Computing has emerged as an alternative to build computing environments able to modify its own behavior in response to changes in its operating conditions However, some significant challenges still exits for the definition of conceptual models, software architectures, middleware platforms and application programming models for such systems.

The objective of my PhD research is the definition of a middleware architecture that will use markets as a mechanism for self-adaptation. Using principles from micro-economics and bounded rationality, this middleware will translate user's objectives about application behavior to economic goals and pursue them by competing in markets for the virtualized resources provided by the grid platform. Resulting interactions are expected to lead the system to a self-organized, self-configured and self-optimized state of affairs.

Publications

2008

Chacin, P., León, X., Brunner, R., Freitag, F., Navarro, L. Core Services for Grid Markets, CoreGrid Simposyum, Gran Canaria, Spain, Agust 2008.

Abstract. Markets are a powerful model for the coordination of distributed systems and, in particular, in the face of incomplete information and changing environments. The application of markets for the resource allocation in grid systems has recently been researched as an alternative to traditional approaches. However, the proper implementation of sophisticated markets capable of handling diverse trading models (various auctions types, bargaining) and structures (direct negotiation, brokering, etc.) requires a set of supporting services to provide participants a proper environment to engage in negotiations. Grid Market Middleware (GMM) is a framework that aims to ease the development of market based grid systems. In this paper we present its architecture, the services it provides and describe how they can be used to implement diverse market models. We also discuss our experience with the implementation of prototypes for various core services.

2007

Chacin, P., Navarro, L. Collectives: A Framework for Self-adaptive P2P Applications. 6th Workshop on Adaptive and Reflexive Middleware (ARM2007) in conjuction with the 8th ACM/IFIP/USENIX International Middleware Conference, New Port Beach, California, USA. 2007.

Abstract. The development of a self-adaptive P2P applications faces many challenges ranging from the proper modeling of the application’s behavior to the definition of the distributed algorithms required to support its functionalities and finally to its implementation in a particular platform. Collectives is a framework that addresses this issues by providing the modeling concepts and the implementation architecture required to separate the diverse adaptation concerns at the proper level of abstraction.

Freitag, F., Chacin, P., Chao, I., Brunner, R., Navarro, L., Ardaiz, O. Performance Measuring Framework for Grid Market Middleware, 4th European Performance Engineering Workshop (EPEW 2007), Berlin, Germany,
2007

Abstract. Current implementations of Grid infrastructures provide frameworks which aim at achieve on-demand computing. In such a scenario, contribution and use of resources will be governed by business models. The challenge is to provide multi-level performance information which enables the participation of the different actors in such a system. In this paper we describe the performance measuring framework developed for Grid Market Middleware, a middleware which supports economic-model based selection of service-oriented Grid applications. This middleware is a distributed infrastructure, which we have implemented for providing a market of services and resources to be assigned to Grid applications. The objectives of the performance measuring framework is first to assess the behaviour of the middleware and the used economic models in a deployed system, and secondly allow the provision of metrics for the components of the middleware itself. We describe the design of the performance measuring framework, its implementation and show its capability and usefulness for our objectives by experiments.

Joita L., Rana O.F., Chao I., Chacin P., Freitag F., Navarro L., and Ardaiz, O. Service Level Agreements in Catallaxy-based Grid Markets, Workshop on Usage of Service Level Agreements in Grids, in conjuction with The 8th IEEE International Conference on Grid Computing (Grid 2007),Austin, Texas, USA, 2007

Abstract. Grid computing is an important paradigm for managing computationally demanding applications composed of a collection of services. This paper presents the experience of using Service Level Agreements (SLAs) within the context of a Catallactic enabled “proof-of-concept” prototype, where the dynamic discovery of services and resources, and the selection of a particular service instance are based on Catallactic oriented Grid markets. The Catallactic-enabled applications are introduced and evaluated via the social utility economic factor.

Brunner R., Chao I., Chacin P., Freitag F., Navarro L., Ardaiz O., Joita L., and Rana O.F. Assessing a distributed market infrastructure for eco-nomics-based service selection. International Conference on Grid computing, High-Performance and Distributed Applications (GADA'07), Algarve, Portugal, 2007

Abstract. Service selection is an important issue for market-oriented Grid infrastructures. However, few results have been published on the use and evaluation of market models in deployed prototypes, making it difficult to assess their capabilities. In this paper we study the integration of an extended version of Zero Intelligence Plus (ZIP) agents in a middleware for economics-based selection of Grid services. The advantages of these agents compared to alternatives is their fairly simple messaging protocol and negotiation strategy. By deploying the middleware on several machines and running experiments we observed that services are proportionally assigned to competing traders as should be in a fair market. Furthermore, varying the environmental conditions we show that the agents are able to respond to the varying environmental constraints by adapting their market prices.

2006

Joita, L.; Rana, O.F.; Chacin, P.; Chao, I.; Freitag, F.; Navarro, L.; Ardaiz, O., "Application Deployment on Catallactic Grid Middleware," Distributed Systems Online, IEEE , vol.7, no.12, pp.1-1, Dec. 2006

Abstract. An architecture based on a decentralized market view integrates grid applications with catallactic middleware. A prototype application showed the concept's feasibility, as well as the middleware's effectiveness in balancing query-request workload across multiple grid services. Grid computing researchers have shown significant interest in using an economic paradigm for exchanging grid resources and services. With this approach, applications can use a market mechanism to schedule services access, thus giving them a fair, efficient way to share resources in high-demand periods. Most existing approaches rely on centralized brokers to coordinate resource access, and they're typically implemented over existing grid middleware. We propose an alternative approach based on F.A. Hayek's Catallaxy mechanism. Catallaxy's free-market, self-organizing coordination mechanisms adjust prices within the market based on the particular demands for a specific (scarce) resource

Pablo Chacin, Liviu Joita, Björn Schnizler, Felix Freitag, Flexible Architecture for Supporting Auctions in Grids, Workshop in Smart Grid Technologies on the Internacional Conference on Autonomic Computing (ICAC 2006), Dublin, Ireland, July 16, 2006

Abstract. Efficient and flexible resource allocation is one of the key factors for a wide application of Grids in business and scientific areas. Recently, the use of auctions for scheduling and allocating Grid resources has been proposed in literature. Hitherto, however, only few of the proposed mechanisms are integrated in Grid infrastructures. Furthermore, none of these proposals are applied in commercial settings. One reason for this lays in technical challenges such as replacing discovery and matchmaking mechanisms by auctions have to be overcome in order to integrate an auction mechanism into a Grid platform. Another barrier for a wide deployment of Grid auctions is that an allembracing auction mechanism may not exist. A technical and economic sound architecture thus has to support the simultaneous deployment of multiple different auction instances. The paper introduces a flexible economic Grid middleware which abstracts from the underlying technical infrastructure and supports the simultaneous instances and management of a wide spectrum of different auction. The design concepts of such system are outlined and an ongoing prototype is presented, using the integration of a MACE auction as a case study.
[pdf]

2005

Liviu Joita, Omer Rana, Pablo Chacin, Oscar Ardaiz, Isaac Chao, Felix Freitag, Leandro Navarro, Application Deployment Using the Catallactic Grid Middleware, I Workshop on Middleware for Grid Computing in the ACM/USENIX/IFIP Middleware 2006, Grenoble, France, November 28-29, 2005

Abstract. In this paper we describe an application deployment using a Catallactic Grid-enabled middleware, which is based on the Catallaxy “free market” self-organisation approach described by von Hayek, who understood the market as a decentralised coordination mechanism opposite to a centralised command economy. The implementation makes use of Globus Toolkit, JXTA and WSRF. The paper envisages the resource virtualization in the WSRF context as the main driver for a proper connection middleware-base platform (on the broad scenario of grid applications).
[pdf]

Pablo Chacin, Felix Freitag, Leandro, Isaac Chao, Navarro, Oscar Ardaiz, Integration of Decentralized Economic Models for Resource Self-Management in Application Layer Networks, Second IFIP TC6 International Workshop on Autonomic Communications, Athens, Greece, Octuber 3-5, 2005

Abstract. Resource allocation is one of the challenges for self-management of large scale distributed applications running in a dynamic and heterogeneous environment. Considering Application Layer Networks (ALN) as a general term for such applications including computational Grids, Content Distribution Networks and P2P applications, the characteristics of the ALNs and the environment preclude an efficient resource allocation by a central instance. The approach we propose integrates ideas from decentralized economic models into the architecture of a resource allocation middleware, which allows the scalability towards the participant number and the robustness in very dynamic environments.At the same time, the pursuit of the participants for their individual goals should benefit the global optimization of the application. In this work, we describe the components of this middleware architecture and introduce an ongoing prototype.
[pdf]

Oscar Ardaiz, Pablo Chacin, Isaac Chao, Felix Freitag, Leandro Navarro, An Architecture for Incorporating Decentralized Economic Models in Application Layer Networks, International Journal on Multiagent and Grid Systems. Special Issue on Smart Grid Technologies Vol. 1(4), 2005

Abstract. Efficient resource discovery and allocation is one of the challenges of any large scale Application Layer Network (ALN) such as computational Grids, Content Distribution Networks and P2P applications. In centralized approaches, the user requests can easily be matched to the most convenient resource. These approaches, however, present scalability limits in the highly dynamic and complex ALN environments. This paper, explores an architecture for incorporating fully decentralized economic mechanisms for resource allocation. These mechanisms are implemented by a set of trading agents that operate on behalf of the clients and service providers, interacting over an overlay network and interfacing with the underlying resources of the platform. A prototype of the proposed architecture is presented and the practical implications of its implementation in a grid scenario are discussed.
[pdf]