Performance improvement of the contract net protocol using Instance Based Learning

The contract net protocol (CNP) is a widely used coordination mechanism in multiagent systems. It has been shown that its performance degrades drastically when the number of communicating agents and the number of tasks announced increases. Hence it has problems of scalability. In order to overcome this limitation, an Instance Based Learning (IBL) mechanism is incorporated with CNP that avoids the expensive bidding process and uses previously stored instances to select a target agent. The scheme is implemented in a simulated distributed, hospital system where the CNP is used for resource sharing across hospitals. Experimental results demonstrate that with the incorporation, of the IBL, the system performance improves significantly.