A knowledge-based architecture for distributed fault analysis in power networks

Power industry around the world is facing several changes since deregulation with constant pressure put on improving security, reliability and quality of the power supply. Computational fault analysis and diagnosis of power networks have been active research topics with several theories and algorithms proposed. This paper proposes a distributed diagnostic algorithm for fault analysis in power networks. Distributed architecture for power network fault analysis (DAPFA) is an intelligent, model-based diagnostic algorithm that incorporates a hierarchical power network representation and model. The architecture is based on the industry’s substation automation implementation standards. The structural and functional model is a multi-level representation with each level depicting a more complex grouping of components than its predecessor in the hierarchy. The distributed functional representation contains the behavioral knowledge related to the components of that level in the structural model.The diagnostic algorithm of DAPFA is designed to perform fault analysis in pre-diagnostic and diagnostic levels. Pre-diagnostic phase provides real-time analysis while the diagnostic phase provides the final diagnostic analysis. The diagnostic algorithm incorporates knowledge-based and model-based reasoning mechanisms with one of the model levels represented as a network of neural nets. The relevant algorithms and techniques are discussed. The resulting system has been implemented on a New Zealand sub-system and the results are analyzed.