Graph partition quality affects the overall performance of parallel graph computation systems. The quality of a graph partition is measured by the balance factor and edge cut ratio. A balanced graph partition with small edge cut ratio is generally preferred since it reduces the expensive network communication cost. Many distributed computing applications are based on a graph　whose nodes　and edges　correspond to computations　and communications. The self-navigation of autonomous objects is attractive to solve such　graph based problems in parallel because of the inherent parallelism by　object propagations over network and the encapsulation of graph　algorithms inside objects when the quality of partition scheme is improved. Therefore, these systems handle the local messages and remote messages unequally and only optimize the processing of remote messages. The system apply the graph traversal algorithms BFS techniques, When the graph is partitioned into sub-graphs from source node to destination, each sub graph has smaller size, and hence the overall performance will be improved with each worker having less workload. In this project, the system proposes a novel partition aware graph computation engine to support computation tasks with different partitioning qualities efficiently.