Hourly-Similarity Based Solar Forecasting Using Multi-Model Machine Learning Blending

With the increasing penetration of solar power into power systems, forecasting becomes critical in power system operations. In this paper, an hourly-similarity (HS) based method is developed for 1-hour-ahead (1HA) global horizontal irradiance (GHI) forecasting. This developed method utilizes diurnal patterns, statistical distinctions between different hours, and hourly similarities in solar data to improve the forecasting accuracy. The HS-based method is built by training multiple two-layer multi-model forecasting framework (MMFF) models independently with the same-hour subsets. The final optimal model is a combination of MMFF models with the best-performed blending algorithm at every hour. At the forecasting stage, the most suitable model is selected to perform the forecasting subtask of a certain hour. The HS-based method is validated by 1-year data with six solar features collected by the National Renewable Energy Laboratory (NREL). Results show that the HS-based method outperforms the non-HS (all-in-one) method significantly with the same MMFF architecture, wherein the optimal HS-based method outperforms the best all-in-one method by 10.94% and 7.74% based on the normalized mean absolute error and normalized root mean square error, respectively.

[1]  Nathan S Lewis,et al.  Research opportunities to advance solar energy utilization , 2016, Science.

[2]  Soteris A. Kalogirou,et al.  Machine learning methods for solar radiation forecasting: A review , 2017 .

[3]  X. Wen,et al.  A wavelet-coupled support vector machine model for forecasting global incident solar radiation using limited meteorological dataset , 2016 .

[4]  C. K. Simoglou,et al.  Comparison of SARIMAX, SARIMA, modified SARIMA and ANN-based models for short-term PV generation forecasting , 2016, 2016 IEEE International Energy Conference (ENERGYCON).

[5]  Xiaozhe Wang,et al.  Characteristic-Based Clustering for Time Series Data , 2006, Data Mining and Knowledge Discovery.

[6]  Mathieu David,et al.  A Neural Network Post-processing Approach to Improving NWP Solar Radiation Forecasts , 2014 .

[7]  Jie Zhang,et al.  Short-term global horizontal irradiance forecasting based on sky imaging and pattern recognition , 2017, 2017 IEEE Power & Energy Society General Meeting.

[8]  Jie Zhang,et al.  A data-driven multi-model methodology with deep feature selection for short-term wind forecasting , 2017 .

[9]  Lei Wang,et al.  An ANN-based Approach for Forecasting the Power Output of Photovoltaic System , 2011 .

[10]  Chee Keong Chan,et al.  Prediction of hourly solar radiation with multi-model framework , 2013 .

[11]  Bernhard Sick,et al.  Deep Learning for solar power forecasting — An approach using AutoEncoder and LSTM Neural Networks , 2016, 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[12]  M. Davida,et al.  Probabilistic forecasting of the solar irradiance with recursive ARMA and GARCH models DTU Orbit (24/10/2017) , 2017 .

[13]  R. Urraca,et al.  Review of photovoltaic power forecasting , 2016 .

[14]  M. Raza,et al.  On recent advances in PV output power forecast , 2016 .

[15]  Jie Zhang,et al.  Characterizing Time Series Data Diversity for Wind Forecasting , 2017, BDCAT.