DynamoGraph: A Distributed System for Large-scale, Temporal Graph Processing, its Implementation and First Observations

Graph models have a long standing history as models for real world structures and processes. In recent research two important dimensions of graphs are described of particular importance. (1) Temporal aspects of graphs cannot be neglected for many current application scenarios such as social network analysis or the analysis of the global web graph. (2) The mentioned graph structures have grown to very large sizes such that traditional methodologies no longer hold. In this work a distributed computing framework designed for storing and processing of large-scale temporal graphs is presented. For this system a reference implementation in Java was created. In this paper first insight on the implementation and observations in using the system are discussed.