论文信息 - Pattern Sequence Neural Network for Solar Power Forecasting

Pattern Sequence Neural Network for Solar Power Forecasting

We propose a new approach for time series forecasting, called PSNN, which combines pattern sequences with neural networks. It is a general approach that can be used with different pattern sequence extraction algorithms. The main idea is to build a separate prediction model for each pattern sequence type. PSNN is applicable to multiple related time series. We demonstrate its effectiveness for predicting the solar power output for the next day using Australian data from three data sources - solar power, weather and weather forecast. In our case study, we show three instantiations of PSNN by employing the pattern sequence extraction algorithms PSF, PSF1 and PSF2. The results show that PSNN achieved the most accurate results.

Irena Koprinska | Mashud Rana | Alicia Troncoso Lora | Yang Lin

[1] Francisco Martinez Alvarez,et al. Energy Time Series Forecasting Based on Pattern Sequence Similarity , 2011, IEEE Transactions on Knowledge and Data Engineering.

[2] Irena Koprinska,et al. Big data solar power forecasting based on deep learning and multiple data sources , 2019, Expert Syst. J. Knowl. Eng..

[3] H. Pedro,et al. Assessment of forecasting techniques for solar power production with no exogenous inputs , 2012 .

[4] Irena Koprinska,et al. 2D-interval forecasts for solar power production , 2015 .

[5] Zheng Wang,et al. Solar Power Forecasting Using Pattern Sequences , 2017, ICANN.

[6] Irena Koprinska,et al. Forecasting solar power generated by grid connected PV systems using ensembles of neural networks , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

[7] Yongping Yang,et al. Forecasting Power Output of Photovoltaic Systems Based on Weather Classification and Support Vector Machines , 2012 .

[8] Irena Koprinska,et al. Yearly and seasonal models for electricity load forecasting , 2011, The 2011 International Joint Conference on Neural Networks.