Probabilistic prediction of solar PV power output

• Main Author: Ang, Sherman Jun Xiong
• Other Authors: Xu Yan
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/140276
• Institution: Nanyang Technological University

The rapid increase of interest in renewable energy sources, like wind and solar energies, are inexhaustible and poses less damage to the environment, enabling their usage into modern power grids. However, due to its stochastic and highly uncertain nature, the integration of solar energy faced quite a significant amount of challenges in its integration to the modern power grids, especially in the aspect of operation and control where it did not have much significant impact on the power control system. The main reason was that a proper forecasting method to control the variability and uncertainty of the power output was not in place. Hence, probabilistic prediction of the solar PV power output is essential and crucial task for power generation. The intent of this project is to develop interval forecasting methods to predict both the point value and the variation range of the renewable power generation. The interval predictions can better model the uncertainty and variability of the power output. The prediction results can be directly used for a robust operation of the power systems.