DISTRIBUTING DATA AMONG DATA STORAGE PARTITIONS BASED ON A FORECASTED DEMAND IN A NETWORKED COMPUTING ENVIRONMENT

摘要

Embodiments of the present invention provide an approach to forecast a potential demand for partitioned/sharded data and to distribute the data among a set of data partitions based on forecasted demand to optimize network characteristics (e.g., network bandwidth) and/or expedite data retrieval. For example, the data may be distributed among the partitions based on a quantity of trends/requests/hits on the data, so that requests for the data can be balanced among the partitions geographically.