Modular neural network-based directional relay for transmission line protection

This letter proposes the application of a modular neural network as a mechanism to discriminate the direction of faults for transmission line protection. The modular neural network approach solves a relatively complex problem by decomposing it into simpler subtasks that are easier to manage and then assembles the solution from the results of the subtasks. In addition to the obvious advantages of a neural network as a fault classifier, incorporation of modularity to the network structure provides more important positive attributes like model complexity reduction, better learning capability, etc. The modular neural network concept has been utilized successfully to develop a directional relay algorithm for a transmission system and subsequently implemented on a DSP TMS320F243 EVM-board.