Argumentation-based fault diagnosis for home networks

Home networks are a fast growing market but managing them is a difficult task, and diagnosing faults is even more challenging. Current fault management tools provide comprehensive information about the network and the devices but it is left to the user to interpret and reason about the data and experiment in order to find the cause of a problem. Home users may not have motivation or time to learn the required skills. Furthermore current tools adopt a closed approach which hardcodes a knowledge base, making them hard to update and extend. This paper proposes an open fault management framework for home networks, whose goal is to simplify network troubleshooting for non-expert users. The framework is based on assumption-based argumentation that is an AI technique for knowledge representation and reasoning. With the underlying argumentation theory, we can easily capture and model the diagnosis procedures of network administrators. The framework is rule-based and extensible, allowing new rules to be added into the knowledge base and diagnostic strategies to be updated on the fly.The framework can also utilise external knowledge and make distributed diagnosi