Telefonaktiebolaget Lm Ericsson (publ)

Ann Devitt

Javier Baliosian

Boris Danev

The present invention relates to an arrangement for network management and adapted to be provided in or associated with a network node to be managed. It comprises, or is in communication with, modeling means adapted to, using substantially non-formal descriptions, model network domain and behavior using formal ontologies comprising inference capabilities by means of an inference engine, thus providing a formal ontology model describing domain and behavior. It also comprises annotating means adapted to add semantic information to the formal domain and behavior ontology model, generating means adapted to, using said formal ontology model and said inference engine, elaborate an algorithm adapted to generate and update a probabilistic causal network graph structure representing the domain and its behavior.

Arrangement and method for network management

The present invention relates to an arrangement for monitoring performance in a network comprising a number of network devices or nodes, services and users, in real-time. The arrangement comprising information collecting means, generating means for generating performance KPI indicators depending on a number of definition performance parameters for one or more of said network nodes. The generating means comprise or communicate with decision graph generating means adapted to generate decision graph structures representing respective KPI values and combination probabilities in dependence of KPI definition performance parameters and in dependence of additional or correlation parameters. The generating means comprise decision graph content updating means adapted to update the decision graph structure or structures using said collected information to enable prediction of KPI status/behavior and message sending means are provided which are adapted to send out messages or notifications relating to one or more prediction results.

Arrangement and a method relating to performance monitoring

Method for forecasting instable policy enforcement, is described, wherein a behavior dynamic Bayesian network (DBN) model and a policy finite state transducers extended with tautness functions and identities (TFFST) model is analytically composed to derive predictions of the consequences of enforcing a given policy, in particular to detect flip-flop configuration changes in a system. The method comprises the steps of&#x2014;translating () the Bayesian network that holds the Behavior Model (BM) into a finite state transducers extended with tautness functions and identities (TFFST); &#x2014;computing () the union of the Bayesian network (BM) and Policy Model (PM) finite state transducers extended with tautness functions and identities (TFFSTs); &#x2014;composing () the finite state transducers extended with tautness functions and identities (TFFST) produced in the previous step with itself; and&#x2014;detecting () repetitions of events in the input and the output of every possible path; &#x2014;if at least one repetition is found, detecting a possible instability ().

Growing community of inventors

Dublin, Ireland

Ann Devitt