Options
LEADS: Large-Scale Elastic Architecture for Data as a Service
LEADS works on answering the demand of companies wishing to exploit the wealth of public data available on today's Internet. Large IT-oriented companies can crawl, store, and query large amounts of data in their own premises. Small companies and companies that are not on the Internet analytics business may still want to:
- Analyze the Web graph to extract business intelligence;
- Match company-specific private data to public data;
- Monitor in real-time public data evolution and detect trends, identify opinion leaders, etc.;
- Propose novel data-enabled services: complex graph analytics, real-time data aggregation, ...
Yet, many companies may not be able or willing to crawl, store and process in-house, because of its associated high cost, complexity, or simply because they miss the necessary expertise. Can these companies rely on larger ones for accessing and processing public content? Querying capabilities, and data freshness and comprehensiveness would depend on the provider's good will. Also, there are little guarantees on confidentiality. Data is power, and power is seldom willingly shared.
LEADS proposes Data-as-a-Service as a solution to the need for small actors to take advantage of big public data, by mutualizing the costs of extracting, storing and processing public data, while offering rich and extensible possibilities, including privacy-protecting querying on public and private data including data updated in real-time, and more.
TOPiCo: detecting most frequent items from multiple high-rate event streams
2015, Schiavoni, Valerio, Rivière, Etienne, Sutra, Pierre, Felber, Pascal, Matos, Miguel, Oliveira, Rui
A Practical Distributed Universal Construction with Unknown Participants
2014, Sutra, Pierre, Rivière, Etienne, Felber, Pascal
UniCrawl: A Practical Geographically Distributed Web Crawler
2015, Quoc, Do, Fetzer, Christof, Felber, Pascal, Rivière, Etienne, Schiavoni, Valerio, Sutra, Pierre
On the Support of Versioning in Distributed Key-Value Stores
2014, Felber, Pascal, Pasin, Marcelo, Rivière, Etienne, Schiavoni, Valerio, Sutra, Pierre, Coelho, Fábio, Oliveira, Rui, Matos, Miguel, Vilaça, Ricardo
Construction universelle d’objets partagés sans connaissance des participants
2015-6-2, Sutra, Pierre, Rivière, Etienne, Felber, Pascal
Une construction universelle est un algorithme permettant à un ensemble de processus concurrents d’accéder à un objet partagé en ayant l’illusion que celui-ci est disponible localement. blue Nous présentons un algorithme permettant la mise en œuvre d’une telle construction dans un système à mémoire partagée. Notre construction est sans verrou, et contrairement aux approches proposées précédemment, ne nécessite pas que les processus accédant à l’objet partagé soient connus. De plus, elle est adaptative : en notant n le nombre total de processus dans le système et k < n le nombre de processus qui utilisent l’objet partagé, tout processus effectue Θ(k) pas de calcul en l’absence de contention.
ZooFence: Principled Service Partitioning and Application to the ZooKeeper Coordination Service
2014, Halalai, Raluca, Sutra, Pierre, Rivière, Etienne, Felber, Pascal