Abstract

Service discovery requests’ messages have a vital role in sharing and locating resources in many of service discovery protocols. Sending more messages than a link can handle may cause congestion and loss of messages which dramatically influences the performance of these protocols. Re-send the lost messages result in latency and inefficiency in performing the tasks which user(s) require from the connected nodes. This issue become a serious problem in two cases: first, when the number of clients which performs a service discovery request is increasing, as this result in increasing in the number of sent discovery messages; second, when the network resources such as bandwidth capacity are consumed by other applications. These two cases lead to network congestion and loss of messages. This paper propose an algorithm to improve the services discovery protocols performance by separating each consecutive burst of messages with a specific period of time which calculated regarding the available network resources. In addition, this paper explains the impact of increasing the number of clients and the consumed network resources on the proposed algorithm.