Neurocontroller for buffer overload control in a packet switch

J. Aweya, L. Orozco-Barbosa

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


The authors describe a buffer overload control scheme, which adaptively matches the buffer input rate to prevailing conditions in the queueing system, for efficient utilisation of the system resources. They propose an adaptive feedback control algorithm which uses neural network modelling of the system dynamics and a gradient-based control optimisation technique for buffer overload control. Using a simple dynamic queueing model, it is shown that this technique can regulate buffer occupancy levels (or queueing delays) to minimise congestion in the queueing system.

Original languageBritish English
Pages (from-to)227-233
Number of pages7
JournalIEE Proceedings: Communications
Issue number4
StatePublished - 1998


Dive into the research topics of 'Neurocontroller for buffer overload control in a packet switch'. Together they form a unique fingerprint.

Cite this