Tim Stevens

Graph partitioning algorithms for optimizing software deployment in mobile cloud computing

As cloud computing is gaining popularity, an important question is how to optimally deploy software applications on the offered infrastructure in the cloud. Especially in the context of mobile computing where software components could be offloaded from the mobile device to the cloud, it is important to optimize the deployment, by minimizing the network usage. Therefore we have designed and evaluated graph partitioning algorithms that allocate software components to machines in the cloud while minimizing the required bandwidth. Contrary to the traditional graph partitioning problem our algorithms are not restricted to balanced partitions and take into account infrastructure heterogenity. To benchmark our algorithms we evaluated their performance and found they produce 10%-40% smaller graph cut sizes than METIS 4.0 for typical mobile computing scenarios. Highlights? Algorithms for partitioning software on the cloud are presented. ? KL-based algorithm allows fast partitioning for realtime use. ? Simulated annealing improves solution quality at the cost of computation capacity. ? Hybrid approach combines both. ? Comparison to METIS shows our algorithms find 10%-40% better graph cuts.

Dynamic deployment and quality adaptation for mobile augmented reality applications

Abstract: With the increasing popularity of smartphones and netbooks, more and more applications are developed for the mobile platform. Notwithstanding the recent advances in mobile hardware, most mobile devices still lack sufficient resources (e.g. CPU power and memory) to execute complex multimedia applications such as augmented reality. Application developers also have difficulties to cope with the changing device context (e.g. network connectivity and remaining battery life) and the many different hardware platforms and operating systems to run applications on. Therefore, we introduce the concept where the developer can provide different configurations of an application, each having different resource requirements and a different quality offered to the end user. The middleware framework presented in this paper will select and deploy the configuration offering the best quality possible for the current connectivity and available resources. As these change over time, the framework will dynamically adapt the configuration and deployment at runtime, enhancing the quality by offloading parts of the application when a remote server is discovered, or gracefully degrading the quality when the network connection is lost. Based on experimental results on the augmented reality use case the performance and effectiveness of our middleware has been characterized in different scenarios.

Multi-cost job routing and scheduling in Grid networks

A key problem in Grid networks is how to efficiently manage the available infrastructure, in order to satisfy user requirements and maximize resource utilization. This is in large part influenced by the algorithms responsible for the routing of data and the scheduling of tasks. In this paper, we present several multi-cost algorithms for the joint scheduling of the communication and computation resources that will be used by a Grid task. We propose a multi-cost scheme of polynomial complexity that performs immediate reservations and selects the computation resource to execute the task and determines the path to route the input data. Furthermore, we introduce multi-cost algorithms that perform advance reservations and thus also find the starting times for the data transmission and the task execution. We initially present an optimal scheme of non-polynomial complexity and by appropriately pruning the set of candidate paths we also give a heuristic algorithm of polynomial complexity. Our performance results indicate that in a Grid network in which tasks are either CPU- or data-intensive (or both), it is beneficial for the scheduling algorithm to jointly consider the computational and communication problems. A comparison between immediate and advance reservation schemes shows the trade-offs with respect to task blocking probability, end-to-end delay and the complexity of the algorithms.

Design and control of optical grid networks

Grid computing aims to realize a high-performance computing environment, while increasing the usage efficiency of installed resources. This puts considerable constraints on the network technology, and ultimately has led to the development of Grids over optical networks. In this paper, we investigate the fundamental question of how to optimize the performance of such Grid networks. We start with an analysis of different architectural approaches (and their respective technological choices) to integrate Grid computing with optical networks. This results in models and algorithms to design optical Grid networks, and we show the importance to combine both dimensioning (offline) and scheduling (online) in the design phase of such systems. Finally, the concept of anycast routing is introduced and motivated. Both exact and heuristic algorithms are proposed, and their performance in terms of blocking probability and latency is presented.

ASTAS: Architecture for scalable and transparent anycast services

Native information provider (IP) anycast suffers from routing scalability issues and the lack of stateful communication support. For this reason, we propose architecture for scalable and transparent anycast services (ASTAS), a proxy-based architecture that provides support for stateful anycast communications, while retaining the transparency offered by native anycast. Dynamic re- source assignment for each initiated session guarantees that a connection is established with the most suitable target server, based on network and server conditions. Traffic engineering in the overlay can be realized in an effective way due to the dissemination of aggregated state information in the anycast overlay. To minimize the total deployment cost for ASTAS architectures, we propose optimized proxy placement and path finding heuristics based on look-ahead information gathered in network nodes. Contrary to a regular integer linear program (ILP) formulation, these heuristics allow to optimize proxy placement in large networks. A use case on a European reference network illustrates that lower proxy costs enable proxy deployment closer to the end-users, resulting in a reduced network load.

Anycast Routing Algorithms for Effective Job Scheduling in Optical Grids

Effective job scheduling in optical grids requires concurrent optimisation of resource and network path selection. To enable this functionality, practical anycast routing algorithms are proposed, and simulation analysis is used to compare their performance to a pseudo-optimal bound and to several heuristics.

Adaptive Online Deployment for Resource Constrained Mobile Smart Clients

Nowadays mobile devices are more and more used as a platform for applications. Contrary to prior generation handheld devices configured with a predefined set of applications, today leading edge devices provide a platform for flexible and customized application deployment. However, these applications have to deal with the limitations (e.g. CPU speed, memory) of these mobile devices and thus cannot handle complex tasks. In order to cope with the handheld limitations and the ever changing device context (e.g. network connections, remaining battery time, etc.) we present a middleware solution that dynamically offloads parts of the software to the most appropriate server. Without a priori knowledge of the application, the optimal deployment is calculated, that lowers the cpu usage at the mobile client, whilst keeping the used bandwidth minimal. The information needed to calculate this optimum is gathered on the fly from runtime information. Experimental results show that the proposed solution enables effective execution of complex applications in a constrained environment. Moreover, we demonstrate that the overhead from the middleware components is below 2%.

Distributed Service Provisioning Using Stateful Anycast Communications

Notwithstanding IP anycasts introduction in Internet standards dates back to 1993 and its more recent adoption in IPv6 standards, its use in production environments is limited to date. This is mainly because native IP anycast lacks routing scalability and does not support session-based communications, thereby limiting its applicability to single request-response services such as DNS. For this reason, we propose a transparent anycast overlay architecture that retains the strengths of native anycast and neutralizes above-mentioned limitations. The resulting proxy infrastructure unleashes the power of anycast by opening up new opportunities for transparent distributed service provisioning. Taking into account user demands, available resources, network overhead and anycast infrastructure costs, we provide near- optimal heuristics for the placement of proxy nodes and dimensioning the infrastructure in large networks. We show that even modest overlay infrastructures, consisting of a small number of proxy routers, provide an effective stateful anycast solution where the detour via the proxy routers is negligible in terms of extra network load. Furthermore, simulation results illustrate that server state aggregation in the proxy nodes lessens control plane overhead, which contributes significantly to service robustness.

Distributed Job Scheduling based on Multiple Constraints Anycast Routing

As the popularity of resource-constrained devices such as hand-held computers increases, a new network service off loading complex processing tasks towards computational resources located in the access- or core network, sounds very promising. In a consumer-oriented environment, characterized by a large diversity in connected devices, a transparent network-based request processing strategy offers a clear flexibility advantage, as the installation and configuration of extra software components on all client devices can be avoided. In this work, this is achieved by linking computational resources to an any cast group, which allows intermediate router nodes to decide upon the target server. It is shown in the paper that the anycast routing problem can be reduced to unicast routing. Consequently, unicast multiple constraints routing algorithms can be applied to compute an optimal path based on several server selection criteria, including server load, path delay, path cost, etc. For this purpose, we envision the SAMCRA algorithm. A new evaluation ordering strategy for previously computed sub-paths is introduced, which guarantees optimality for the complete SAMCRA path between source and destination. Simulation results show that an effective distribution of the job scheduling requests over the available resources can be achieved by applying the described algorithm.

Deployment of service aware access networks through IPv6

Substantial research effort is currently devoted to the development of a future, low-cost access and edge network, enabling the delivery of broadband multimedia services to subscribers. As the world is moving away from current ATM (Asynchronous Transfer Mode) and PPP (Point-to-Point Protocol) access network architectures for a number of reasons, including lack of Quality of service (QoS) and autoconfiguration support, this paper presents how IPv6 can fill the hole that ATM and PPP leave behind in a very convenient, packet-oriented way. The described architecture allows multiple edge nodes to be present, increasing robustness in case of edge node failure, but also increasing scalability as non-local traffic can be balanced across multiple edge nodes. The ability to process local traffic without edge involvement further increases scalability, due to the growing peer-to-peer traffic volume. Since the architecture is independent of the under- lying layer-2 technology used for the aggregation network, a phased and smooth migration from ATM to Ethernet equipment, which is claimed cheaper and easier to maintain, is possible. For some selected broadband access topologies, an efficient IPv6 subnetting scheme, minimizing routing tables through hierarchical addressing, is introduced and evaluated. Solutions for forcing non-local traffic to the correct ISP edge, in a multi-ISP environment, are presented. Finally, the deployment of the described architecture in an actual IPv6 test bed is discussed.