Load profile synthesis and wind power generation prediction for an isolated power system

This paper investigates the load composition by load survey study and predicts the wind power generation with a probabilistic network for an isolated power system. The power consumption by each customer-class with the application of load patterns and the total power consumption of all customers within the same class can be obtained and calculated. Probabilistic neural network (PNN) solves the wind power generation based on the wind speed for an offshore island in Taiwan. With the hourly wind speed and load composition, the power generation of diesel generators has been obtained. Results of this study demonstrate that wind power generation can economically and effectively replace the generation of the diesel power plant and provide partial power supply capability for the net peak load requirement