Regional forecasts of photovoltaic power generation according to different data availability scenarios: a study of four methods

• Published in: Progress in photovoltaics 2015-10, Vol.23 (10), p.1203-1218
• Main Authors: Fonseca Junior, Joao Gari da Silva, Oozeki, Takashi, Ohtake, Hideaki, Takashima, Takumi, Ogimoto, Kazuhiko
• Format: Article
• Language: English
• Subjects: Availability; Error correction; Errors; Photovoltaic cells; photovoltaic systems; Power generation; principal component analysis; regional power generation; Sampling; Solar cells; stratified sampling; support vector regression; Weather conditions; Weather forecasting
• ISSN: 1062-7995; 1099-159X
• DOI: 10.1002/pip.2528

The development of methods to forecast photovoltaic (PV) power generation regionally is of utmost importance to support the spread of such power systems in current power grids. The objective of this study is to propose and to evaluate methods to forecast regional PV power 1 day ahead of time and to compare their performances. Four forecast methods were regarded, of which two are new ones proposed in this study. Together, they characterize a set of forecast methods that can be applied in different scenarios regarding availability of data and infrastructure to make the forecasts. The forecast methods were based on the use of support vector regression and weather prediction data. Evaluations were performed for 1 year of hourly forecasts using data of 273 PV systems installed in two adjacent regions in Japan, Kanto, and Chubu. The results show the importance of selecting the proper forecast method regarding the region characteristics. For Chubu, the region with a variety of weather conditions, the forecast methods based on single systems' forecasts and the one based on stratified sampling provided the best results. In this case, the best annual normalized root mean square error (RMSE) and mean absolute error (MAE) were 0.25 and 0.15 kWh/kWhavg, respectively. For Kanto, with homogeneous weather conditions, the four methods performed similarly. In this case, the lowest annual forecast errors were 0.33 kWh/kWhavg for the normalized RMSE and 0.202 kWh/kWhavg for the normalized MAE. Copyright © 2014 John Wiley & Sons, Ltd. Main findings: 1Method 1, based on single‐system information, yielded the lowest forecast errors in all regions. 2Method 2, based on stratified sampling with weight correction for the rated power, presented a forecast error accuracy close to the that of method 1, being a good alternative to it. 3The lowest annual forecast mean absolute errors, normalized by the average annual photovoltaic power generation found for Chubu and Kanto, were 0.156 and 0.202 kWh/kWhavg, respectively.