A Fast Method for Probabilistic Reliability Assessment of Bulk Power System Using FSOM Neural Network as System States Filters

For solving the problem that Monte-Carlo sampling technique normally used in power system probabilistic simulation has low efficiency, this paper proposes a fast method using fuzzy self organizing map (FSOM) neural network as system states filter to evaluate the reliability of bulk power system for the first time. SOM is especially appropriate to estimate the reliability of power system because it's training time shorter than other neural network. Invalid system states can be filtered by fuzzy SOM neural network, it reduces significantly the number of system states should be evaluated. The new method of FSOM neural network combined with sequential Monte-Carlo simulation results in a significant reduction in the computational effort required to compute complex power system reliability indices. Case study of the IEEE-RTS test system and a practical large-scale system are presented to demonstrate the effectiveness and feasibility of the developed algorithm