Abstract: In the world of Peer-to-Peer (P2P) networking
different protocols have been developed to make the resource sharing
or information retrieval more efficient. The SemPeer protocol is a
new layer on Gnutella that transforms the connections of the nodes
based on semantic information to make information retrieval more
efficient. However, this transformation causes high clustering in the
network that decreases the number of nodes reached, therefore the
probability of finding a document is also decreased. In this paper we
describe a mathematical model for the Gnutella and SemPeer
protocols that captures clustering-related issues, followed by a
proposition to modify the SemPeer protocol to achieve moderate
clustering. This modification is a sort of link management for the
individual nodes that allows the SemPeer protocol to be more
efficient, because the probability of a successful query in the P2P
network is reasonably increased. For the validation of the models, we
evaluated a series of simulations that supported our results.
Abstract: Virtually all existing networked system management
tools use a Manager/Agent paradigm. That is, distributed agents are
deployed on managed devices to collect local information and report
it back to some management unit. Even those that use standard
protocols such as SNMP fall into this model. Using standard protocol
has the advantage of interoperability among devices from different
vendors. However, it may not be able to provide customized
information that is of interest to satisfy specific management needs.
In this dissertation work, different approaches are used to
collect information regarding the devices attached to a Local Area
Network. An SNMP aware application is being developed that will
manage the discovery procedure and will be used as data collector.