A Taxonomy of Data Scheduling in Data Grids and Data Centers: Problems and Intelligent Resolution Techniques

Scheduling in traditional distributed systems has been mainly studied for system performance parameters without data transmission requirements. With the emergence of Data Grids (DGs) and Data Centers, data-aware scheduling has become a major research issue. DGs arise quite naturally to support needs of scientific communities to share, access, process, and manage large data collections geographically distributed. In fact, DGs can be seen as precursors of Data Centers of Cloud Computing platforms, which serve as basis for collaboration at large scale. In such computational infrastructures, the large amount of data to be efficiently processed is a real challenge. One of the key issues contributing to the efficiency of massive processing is the scheduling with data transmission requirements. Data-aware scheduling, although similar in nature with Grid scheduling, is giving rise to the definition of a new family of optimization problems. New requirements such as data transmission, decoupling of data from processing, data replication, data access and security are the basis for the definition of a whole taxonomy of data scheduling problems from an optimization perspective. In this work we present the modelling of such requirements and define data scheduling problems. We exemplify the methodology for the case of data-ware independent batch task scheduling and present several heuristic resolution methods for the problem.