Spyros Lalis

JaWS: An Open Market-Based Framework for Distributed Computing over the Internet

Harnessing the power of idle personal workstations remains a challenge for large scale distributed computing. In this paper, we present the Java Web-computing System (JaWS), which simplifies the connection of heterogeneous machines in a global computing grid as well as the development of applications that exploit this computing capacity. Machines are assigned to applications via a dynamic market-based mechanism that allows machine owners and clients to change their requirements even in the midst of a computation. The system takes care of the main communication issues offering basic programming primitives that can be extended to develop class hierarchies which in turn support distributed computing paradigms. Due to the object-oriented structuring of code, development becomes as simple as implementing a few methods.

A low-cost and simple-to-deploy peer-to-peer wireless network based on open source Linux routers

In this paper we present our work towards deploying a community wireless network with ad hoc communication and routing between its elements. We describe our network model and implementation of wireless routers, while motivating decisions and pointing out open issues. The main advantage of our approach is the low deployment cost and inherent flexibility in terms of adapting the network configuration with little or no human intervention, which in turn can be exploited to support the dynamic addition, removal and mobility of network elements.

OmniStore: a system for ubiquitous personal storage management

As personal area networking becomes a reality, the collective management of storage in portable devices such as mobile phones, cameras and music players will grow in importance. The increasing wireless communication capability of such devices makes it possible for them to interact with each other and implement more advanced storage functionality. This paper introduces OmniStore, a system which employs a unified data management approach that integrates portable and backend storage, but also exhibits self-organizing behavior through spontaneous device collaboration

Automated context aggregation and file annotation for PAN-based computing

This paper presents a method for automatically annotating files created on portable devices with contextual metadata. We achieve this through the combination of two system components. One is a context dissemination mechanism which allows devices in a personal area network (PAN) to maintain a shared aggregate contextual perception. The other is a storage management system that uses such context information to automatically decorate files created on personal devices with annotations. As a result, the user is able to flexibly browse and lookup files that were generated on the move, based on the contextual situation at the time of their creation. What is equally important is that the user is relieved from the cumbersome task of having to manually provide annotations in an explicit fashion. This is especially valuable when generating files on the move, using U/I-restricted portable devices.

Ad-hoc composition in wearable and mobile computing

Changing computing capabilities can be as easy as changing outfits.

Middleware Mechanisms for Agent Mobility in Wireless Sensor and Actuator Networks

This paper describes middleware-level support for agent mobility, targeted at hierarchically structured wireless sensor and actuator network applications. Agent mobility enables a dynamic deployment and adaptation of the application on top of the wireless network at runtime, while allowing the middleware to optimize the placement of agents, e.g., to reduce wireless network traffic, transparently to the application programmer. The paper presents the design of the mechanisms and protocols employed to instantiate agents on nodes and to move agents between nodes. It also gives an evaluation of a middleware prototype running on Imote2 nodes that communicate over ZigBee. The results show that our implementation is reasonably efficient and fast enough to support the envisioned functionality on top of a commodity multi-hop wireless technology. Our work is to a large extent platform-neutral, thus it can inform the design of other systems that adopt a hierarchical structuring of mobile components.

Implementing Replica Placements: Feasibility and Cost Minimization

Given two replication schemes Xold and Xnew, the replica transfer scheduling problem (RTSP) aims at reaching Xnew, starting from Xold, with minimal implementation cost. In this paper we generalize the problem description to include special cases, where deadlocks can occur while in the process of implementing Xnew. We address this impediment by introducing artificial (dummy) transfers. We then prove that RTSP-decision is NP-complete and propose two kinds of heuristics. The first attempts to replace dummy transfers with valid ones, while the second minimizes the implementation cost. Experimental evaluation of the algorithms illustrates the merits of our approach.

Market-driven service allocation in a QoS-capable environment

1. ABSTIL4CT In this paper we describe a prototype that supports end-to-end QoS for applications invoking services over an ATM switch. The required resource bundles are allocated to applications via auctions taking place in two independent markets. We report results of initial experiments with alternative configurations that have been performed to investigate the effects of market independence in the behavior of the system. 1.1

On minimizing the resource consumption of cloud applications using process migrations

According to the pay-per-use model adopted in clouds, the more resources an application running in a cloud computing environment consumes, the greater the amount of money the owner of the corresponding application will be charged. Therefore, applying intelligent solutions to minimize the resource consumption is of great importance. In this paper, we study the problem of identifying an assignment scheme between the interacting components of an application, such as processes and virtual machines, and the computing nodes of a cloud system, such that the total amount of resources consumed by the respective application is minimized. Because centralized solutions are deemed unsuitable for large distributed systems or large-scale applications, we propose a fully distributed algorithm (called DRA) to overcome scalability issues. DRA takes decisions concerning the transition from one assignment scheme to another in a dynamic way, based solely on local information. We also propose and test two modifications of the basic DRA algorithm to deal better with the heterogeneity of cloud servers in terms of capacity constraints. We must note that we capture heterogeneity regarding the network model. Through theoretical analysis, we formally prove that DRA achieves convergence and always provides an optimal solution for tree-based networks in the uncapacitated case. Moreover, we prove through experimental evaluation that DRA achieves up to 55% network cost reduction when compared to the most recent algorithm in the literature. We also show that the proposed modifications of DRA improve the algorithms performance considerably in the case where servers have limited capacity.

Runtime support for a dynamically composable and adaptive wearable system

We present a versatile personal system comprisingwearable and portable devices communicating via short-rangeradio. The system can be composed in an ad-hocfashion, by bringing individual devices in proximity witheach other. As a consequence it is possible for the user tobuild the desired system for a given task at hand in astraightforward way, via physical movement and withoutissuing any explicit configuration commands. System andapplications adapt their behavior as a function of theresources provided by the devices that are part of thecurrent system configuration. We give an overview of theruntime support provided to promote development in thishighly dynamic setting, with particular focus on adaptivemanagement of storage and user interface resources.