Split and migrate: Resource-driven placement and discovery of microservices at the edge
International audience
International audience
Understanding the performance of a multi-threaded application is difficult. The threads interfere when they access the same resource, which slows their execution down. Unfortunately, current profiling tools focus on identifying the interference causes, not their effects.The developer can thus not know if optimizing the interference reported by a pr...
A commonplace issue with portable technology is battery efficiency. While many industries are trying their best to improve battery life without sacrificing a product's quality and efficiency, we believe that further can be done to improve battery consumption on one's mobile device-from tablets to smartphones to laptops to everything else. Many appl...
Deep learning has shown tremendous results on various machine learning tasks, but the nature of the problems being tackled and the size of state-of-the-art deep neural networks often require training and deploying models on distributed infrastructure. DIANNE is a modular framework designed for dynamic (re)distribution of deep learning models and pr...
Cloud computing platforms allow users to deploy geographically distributed applications on servers around the world. Applications may be simple to deploy on these platforms, but it is up to the user and the application to decide which regions and servers to use for application placement. Furthermore, network conditions and routing between the geo-d...
Current research in Agronomy has produced a vast amount of genomic, genetic and phenomic data. To deal with the Volume, Variety and Velocity of those data, it is necessary to first refine to candidate datasets through data discovery then to integrate them through semantic web technologies. Data discovery is an approach that allows to easily search ...
The ever increasing complexity of distributed systems mandates to formally verify their design and implementation. Unfortunately, the common approaches and existing tools to formally establish the correctness of these systems remain hardly applicable to the kind of legacy applications that are commonly found in the HPC community. We present how sys...
Le mobile crowdsensing est une nouvelle forme de collecte de données exploitant la foule de terminaux intelligents déjà déployés à travers le monde pour collecter massivement des données environnementales ou comportementales d'une population.Ces dernières années, ce type de collecte de données a suscité l'intérêt d'un grand nombre d'acteurs industr...
Published in Journal of Internet Services and Applications
A human computation system can be viewed as a distributed system in which the processors are humans, called workers. Such systems harness the cognitive power of a group of workers connected to the Internet to execute relatively simple tasks, whose solutions, once grouped, solve a problem that systems equipped with only machines could not solve sati...
This paper presents a methodology to guide the evaluation of social distributed applications in mobile environments. Even when applications are already designed, they exhibit a number of tuning parameters upon which network operators can act in order to improve performance. Accordingly, evaluation can be a valuable tool to determine for a particula...