Intelligent Network Control Using Neuro-Fuzzy Term-Rewriting

In this paper, we discuss the use of the expert system shell FuzzyCLIPS to define the network model in the Distribution Management System (DMS) for the Indonesian State Power system (PLN). Although, the DMS is implemented by a mixed FuzzyCLIPS/C++ system, the rules defining the behavior of the system are developed using the framework of Object-Oriented Term-Rewriting (OOTR) to guarantee the asynchronous characteristics of the program’s execution. Another advantage of using OOTR is that we can describe both the power propagation in the network, and the alarm conditions, which have to be monitored in a uniform fashion. We will show how implementing a neurofuzzy solution will not only provide a more intuitive approach to the propagation problem, but also a more accurate solution. We discuss the performance of the system, and the general approach of using OOTR as part of a rapid-prototyping methodology for power networks and other reactive systems.