Project COMMUNE

Start date

Why do network and service providers struggle with huge budgets for operations and management while the research community has been working on self-configuration, self-optimization, self-healing, and self-protection for several years? Most experts would say it is due to the inherent complexity of the network, which makes self-x algorithms unstable and unreliable. The COMMUNE consortium agrees and, therefore, plans to tackle the root of this problem by “robust yet fragile” binding of novel self-x technologies with network management systems in a range of real networking scenarios.

COMMUNE is based on the hypothesis that one key reason for the immature state of self-x in real operational environment is uncertainty. Classical network management is predicated on an intrinsic design principle: automation requires an accurate view of the network, and this is only possible when the state of all existing entities is available at any given moment in time. This approach has been successfully applied to networks of limited scale but it is not appropriate for the management of complex networks like the Future Internet. In addition, automation is even more necessary than before to enable smooth and dependable network operation.

Uncertainty cannot be underestimated or dismissed as an undesirable collateral effect; it is an intrinsic property of telecom networks. In the real world, only human operators are able to do the required reasoning to deal with this problem and that is a heavy burden for automation.

COMMUNE aims to build an innovative solution for cognitive network management under uncertainty. COMMUNE will seek to mitigate the practical effects of uncertainty by exploring the latest advances in knowledge based reasoning and other relevant cognitive methods. This approach is chosen due to the intuitive applicability of these models and their computational efficiency. The developed COMMUNE Management System shall be thoroughly tested through a combination of network trials (a proper mix of current wireless and wireline Internet technologies) and simulation campaigns. Special attention will be paid to access networks, focusing on two relevant scenarios: LTE and FTTH.