Green and Distributed Architecture for Managing Big Data of Biodiversity
Résumé
The biodiversity term refers to the totality of genes, species, and ecosystems of a region or the globe. Biodiversity’s impact on the human health and the ecosystem is without a doubt very significative. Therefore, the conservation of the biodiversity is becoming an international political and scientific issue since it may have a drawback on climate and the human health or survival. For a sustainable development perspective, several ongoing studies are conducted to analyze, predict, and face biodiversity changes. Such studies require a huge volume of data collected, stored, shared, and exploited intensively by researchers through the world by using web technologies and information systems as GEOBON, LifeWacth, GBIF, MosquitoMap. These systems handle an important amount of computing and database resources that must be optimized for avoiding maintaining useless resources while reducing considerably the energy usage. Actually, the goal of such optimization that we propose in this chapter is to adapt (increase or decrease) the number of resources for dealing with data of biodiversity based on the current load (or number of requests) while ensuring good performances. The benefits of doing so are manifold. First, it fits perfectly with the objectives of green computing or green IT that suggest to define computing systems efficiently and effectively with minimal or no impact on the environment. Second, it is well suited for African developing countries that encounter frequently energy problems and that miss enough funds to maintain complex infrastructures.