A Comparative Study of Photovoltaic Power Prediction Model with Different Inputs by Long Short-Term Memory Network
- Resource Type
- Conference
- Authors
- Ma, Jiao; Zhang, Yunpeng; Zhou, Hai; Sun, Shumin; Wu, Ji; Hu, Siyu; Guan, Yifei; Yuan, Shuai
- Source
- 2023 International Conference on Power System Technology (PowerCon) Power System Technology (PowerCon), 2023 International Conference on. :1-5 Sep, 2023
- Subject
- Engineering Profession
Power, Energy and Industry Applications
Photovoltaic systems
Analytical models
Fluctuations
Meteorological factors
Weather forecasting
Predictive models
Feature extraction
photovoltaic
prediction
LSTM
input features
- Language
The randomness and fluctuation of photovoltaic (PV) power brings new challenges to power system operation. Accurate PV power generation prediction is critical to power system dispatch. The prediction of PV power generation can provide reference for power system dispatching, which is conducive to the safe and stable operation of the power grid. Since PV generation is a continuous process, the variation of PV power at each moment is related to the meteorological characteristics or power information at the historical moment. This paper applies long short-term memory network (LSTM) to forecast short-term PV power and the results of different input features are compared and analyzed. The results show that the highest prediction accuracy is obtained when both historical power data and irradiance data are used as input features.