| Carl Friedrich Gauß Faculty | Department of Computer Science

Smart service state partitioning in BFT

SupervisorBijun Li
Wenbo Xu
ProfessorProf. Dr. Rüdiger Kapitza
IBR GroupDS (Prof. Kapitza)
TypeBachelor Thesis


The traditional BFT state machine replication system requires total order of all requests. However, there is already new mechanism exploiting parallelism in modern replication system. The service state is split into different partitions and only requires a partial order on requests visiting the same partition [0]. This arises the new challenge to define the partitions in a proper way, so that the requests crossing multiple partitions can be minimized.


This work is an extension of our previous wok [0], which is a multi-leader BFT mechanism. The objective is to develop an algorithm to smartly partition the service state according to the dependency of requests. One possible solution could be using machine learning and data mining approach to analyze underlying dependencies. A very good skill of Java and basic machine learning knowledge are required.

[0]: https://www.ibr.cs.tu-bs.de/theses/bli/ml-bft.html

last changed 2016-06-15, 12:30 by Bijun Li