Search results for "Distributed computing"
showing 10 items of 622 documents
Automatic Customization Framework for Efficient Vehicle Routing System Deployment
2017
Vehicle routing systems provide several advantages over manual transportation planning and they are attracting growing attention. However, deployment of these systems can be prohibitively costly, especially for small and medium-sized enterprises: the customization, integration, and migration is laborious and requires operations research expetise. We propose an automated configuration workflow for vehicle routing system and data flow customization, which provides the necessary basis for more experimental work on the subject. Our preliminary results with learning and adaptive algorithms support the assumption of applicability of the proposed configuration framework. The strategies presented h…
Streamlining distributed Deep Learning I/O with ad hoc file systems
2021
With evolving techniques to parallelize Deep Learning (DL) and the growing amount of training data and model complexity, High-Performance Computing (HPC) has become increasingly important for machine learning engineers. Although many compute clusters already use learning accelerators or GPUs, HPC storage systems are not suitable for the I/O requirements of DL workflows. Therefore, users typically copy the whole training data to the worker nodes or distribute partitions. Because DL depends on randomized input data, prior work stated that partitioning impacts DL accuracy. Their solutions focused mainly on training I/O performance on a high-speed network but did not cover the data stage-in pro…
A Distributed approach to the Remote Control and Programming Improvement
2006
The remote control of industrial plants through networks is becoming very important nowadays but it involves several issues that can degrade the performance and usability of the remote plant. This paper presents a distributed architecture improving a remote programming system which allows users to control and to program a plant remotely. The control system is based on a client/server architecture with many user interfaces that control the plant. The remote programming language is a mix of Java and client/server protocol in order to simplify the developing and to avoid the protocol/language translation. In order to obtain more efficiency, the program is developed in the client side and it is…
Migration Techniques in HPC Environments
2014
Process migration is an important feature in modern computing centers as it allows for a more efficient use and maintenance of hardware. Especially in virtualized infrastructures it is successfully exploited by schemes for load balancing and energy efficiency. One can divide the tools and techniques into three groups: Process-level migration, virtual machine migration, and container-based migration.
Scalable Monitoring System for Clouds
2013
Although cloud computing has become an important topic over the last couple of years, the development of cloud-specific monitoring systems has been neglected. This is surprising considering their importance for metering services and, thus, being able to charge customers. In this paper we introduce a monitoring architecture that was developed and is currently implemented in the EASI-CLOUDS project. The demands on cloud monitoring systems are manifold. Regular checks of the SLAs and the precise billing of the resource usage, for instance, require the collection and converting of infrastructure readings in short intervals. To ensure the scalability of the whole cloud, the monitoring system mus…
dSDiVN: A Distributed Software-Defined Networking Architecture for Infrastructure-Less Vehicular Networks
2017
In the last few years, the emerging network architecture paradigm of Software-Defined Networking (SDN), has become one of the most important technology to manage large scale networks such as Vehicular Ad-hoc Networks (VANETs). Recently, several works have shown interest in the use of SDN paradigm in VANETs. SDN brings flexibility, scalability and management facility to current VANETs. However, almost all of proposed Software-Defined VANET (SDVN) architectures are infrastructure-based. This paper will focus on how to enable SDN in infrastructure-less vehicular environments. For this aim, we propose a novel distributed SDN-based architecture for uncovered infrastructure-less vehicular scenari…
Mobile Encounter Network - the missing data link
2008
In this paper, we discuss about the applicability of a short-range wireless communication scheme called Mobile Encounter Network (MEN). Encounters between devices communicating while moving allows ad-hoc -type data transfer to be performed. A background for the emerging of such networks is given. The essential properties of the MEN data transfer are specified. Based on this, the role of MEN as a data transfer medium is discussed. The conclusion is that such networking technique may provide additional value compared to the traditional wireless communication.
An Optimized Roadside Units (RSU) Placement for Delay-Sensitive Applications in Vehicular Networks
2015
International audience; Over the last few years, a lot of applications have been developed for Vehicular Ad Hoc NETworks (VANETs) to exchange information between vehicles. However, VANET is basically a Delay Tolerant Network (DTN) characterized by intermittent connectivity, long delays and message losses especially in low density regions [1]. Thus, VANET requires the use of an infrastructure such as Roadside Units (RSUs) that permits to enhance the network connectivity. Nevertheless, due to their deployment cost, RSUs need to be optimally deployed. Hence, the main objective of this work is to provide an optimized RSUs placement for delay-sensitive applications in vehicular networks that imp…
Geographical Routing for Delay Tolerant Encounter Networks
2007
Delay Tolerant Networks (DTNs) are intermittently connected networks, where direct end--to--end path between communicating nodes may never exist. To achieve eventual delivery some nodes must store messages and wait opportunity to forward them. In mobile environment, one of the most challenging problems for routing protocols is to decide, which nodes should store the message to achieve eventual delivery as quick as possible. Common approach is to propagate message into large group of nodes, hoping one of them will reach the destination. These solutions, however, are not very scalable as they generate plenty of extra load and traffic to network. Further more, message carriers have no means to…
Random Slicing: Efficient and Scalable Data Placement for Large-Scale Storage Systems
2014
The ever-growing amount of data requires highly scalable storage solutions. The most flexible approach is to use storage pools that can be expanded and scaled down by adding or removing storage devices. To make this approach usable, it is necessary to provide a solution to locate data items in such a dynamic environment. This article presents and evaluates the Random Slicing strategy, which incorporates lessons learned from table-based, rule-based, and pseudo-randomized hashing strategies and is able to provide a simple and efficient strategy that scales up to handle exascale data. Random Slicing keeps a small table with information about previous storage system insert and remove operations…