Scenario-Based Generation and Reduction for Renewable Energy Uncertainty in Sustainable Microgrids

Engineering notes

Engineering notes will be added by the Power for Solar editorial team.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为光伏效率、钙钛矿太阳能电池、储能技术、太阳能热利用、BIPV、并网技术等高价值论文补充中文说明。

Original abstract

Conventional energy sources such as coal, petroleum and natural gas are becoming increasingly unsustainable due to environmental concerns and resource depletion, accelerating the global shift toward renewable energy sources, in which photovoltaic (PV) and wind energy have gained widespread adoption; however, their output is highly stochastic and difficult to predict. To address this, the proposed work employs statistical modelling of renewable sources using annual data of solar irradiance, temperature, and wind speed for a specific location and the Latin Hypercube Sampling (LHS) approach is utilized to generate a diverse set of PV and wind generation scenarios. Analysing such a huge array of PV and wind generation scenarios poses significant challenges. The unsupervised machine learning techniques, such as autoencoder, K-means clustering and Principal Component Analysis (PCA), are employed to reduce the generated scenarios to streamline the set of PV and wind power generation profiles. The Silhouette Score and Davis - Bouldin Index (DBI) are used to decide the best approach for scenario reduction. The aim of this work is to detect the efficient scenario reduction approach for Uncertainty in PV and wind energy generation profile for effective decision-making in renewable energy generation scheduling in microgrid networks.

Links and sources

Comments