Synthetic Wind Speed Scenarios Generation using Artificial Neural Networks for Probabilistic Analysis of Hybrid Energy Systems

Abstract

Hybrid energy systems, which consist of multiple energy inputs and multiple energy outputs, have been proposed in literature to enable ever increasing penetration of clean energy. In order to properly design and analyze HES configuration, extensive data sets of renewable resources for the given location are required, whose availability may be limited due to insufficient historical measurement. This paper focuses on the methodology to generate synthetic scenarios of renewable resources, e.g., wind speed. Specifically, artificial neural networks (ANN) is utilized to characterize historical wind speed measurements and to generate synthetic scenarios, allowing Monte Carlo simulation of HES for probabilistic analysis. In addition, Fourier transformation is used to characterize the low frequency components in historical data, allowing the synthetic scenarios to preserve seasonal trend. Case study of probabilistic analysis is then performed on a particular HES configuration, which includes nuclear power plant, wind farm, battery storage, EV charging station, and desalination plant. Wind power availability and requirements on component ramping rate are then investigated.