Interval forecasting of renewable power generation

• Main Author: Boey, Sin Yee
• Other Authors: Xu Yan
• Format: Final Year Project
• Language: English
• Published: 2019
• Subjects: DRNTU::Engineering::Electrical and electronic engineering
• Online Access: http://hdl.handle.net/10356/77773
• Institution: Nanyang Technological University

Energy generated from natural resources that can be replenished is called renewable energy. Solar, wind, geothermal and hydro are examples of renewable energy. The most promising renewable energy source for Singapore’s electricity or power generation is Solar.Development of renewable power generation is on the rise and it is a hot topic in the power sector. In addition, forecasting of renewable power generation output is to regard as important in the power sector. It is crucial to have accurate prediction of solar power so that grid operator can manage the energy management (scheduling of power) efficiently and ensuring reliability. In this report, the topic we will be discussing about is interval forecasting of solar power output. Comparison between Non-Linear Autoregressive Exogenous (NARX) and Long Short Term Memory (LSTM) is done and LSTM shown to be a better approach in this report. The data used in this report is February 2018 to December 2018 Solar PV Output values (in MWac) taken from an actual site and time extracted is from 7am to 7pm. Software used in this project is Matlab.