This paper describes a new algorithm for solving the distributed aggregation problem in which individual values from N nodes have to be aggregated in an associative and commutative manner, and the final result must be either computed at all sites or communicated to them. The algorithm can be initiated by any node, and works by creating multiple parallel streams that collect partial aggregates and finally converge at a node to compute the final result.
All Science Journal Classification (ASJC) codes
- Information Systems
- Hardware and Architecture
- Information Systems and Management