Skip to Main Content
Global telecommunication systems are at the heart of the Internet revolution. To support Internet traffic they have built-in redundancy to ensure robustness and quality of service. This requires complex fault management. The traditional hard approach is to reduce the number of alarm events (symptoms) presented to the operating engineer through monitoring, filtering and masking. The goal of the soft approach is to automate the analysis fully so that the underlying fault is determined from the evidence available and presented to the engineer. This paper describes progress toward automated fault identification through a fusion between these soft and hard computing approaches.