ÇѱÛÁ¦¸ñ(Korean Title) |
ž籤 ¿¡³ÊÁö ¿¹ÃøÀ» À§ÇÑ SVM ¹× ANN ¸ðµ¨ÀÇ ¼º´É ºñ±³ |
¿µ¹®Á¦¸ñ(English Title) |
Performance comparison of SVM and ANN models for solar energy prediction |
ÀúÀÚ(Author) |
Á¤¿ø¼®
Á¤¿µÈ
¹Ú¹®±Ô
ÀÌâ±³
¼Á¤¿í
Wonseok Jung
Young-Hwa Jeong
Moon-Ghu Park
Chang-Kyo Lee
Jeongwook Seo
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 22 NO. 02 PP. 0626 ~ 0628 (2018. 10) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼ ±â»ó µ¥ÀÌÅ͸¦ »ç¿ëÇÏ¿© ž籤 ¿¡³ÊÁö¸¦ ¿¹ÃøÇϱâ À§ÇØ ±â°èÇнÀ ¸ðµ¨ÀÎ SVM(Support Vector Machine)°ú ANN(Artificial Neural Network)ÀÇ ¼º´ÉÀ» ºñ±³ÇÑ´Ù. Àå¤ý´ÜÆÄ º¹»ç¼± Æò±Õ, °¼ö·®, ¿Âµµ µî 15°¡Áö Á¾·ùÀÇ ±â»ó µ¥ÀÌÅ͸¦ »ç¿ëÇÏ¿© µÎ ¸ðµ¨À» »ý¼ºÇÏ°í, ½ÇÇèÀ» ÅëÇØ ÃÖÀûÀÇ SVMÀÇ RBF (Radial Basis Function) ÆĶó¹ÌÅÍ¿Í ANNÀÇ Àº´ÐÃþ°ú ³ëµå °³¼ö, Á¤±ÔÈ ÆĶó¹ÌÅ͸¦ µµÃâÇÏ¿´´Ù. SVM°ú ANN ¸ðµ¨ÀÇ ¼º´ÉÀ» ºñ±³Çϱâ À§ÇÑ ÁöÇ¥·Î¼ MAPE(Mean Absolute Percentage Error)¿Í MAE(Mean Absolute Error)¸¦ »ç¿ëÇÏ¿´´Ù. ½ÇÇè °á°ú SVM ¸ðµ¨Àº MAPE=21.11, MAE=2281417.65ÀÇ ¼º´ÉÀ» ´Þ¼ºÇÏ¿´°í ANNÀº MAPE=19.54, MAE=2155345.10776ÀÇ ¼º´ÉÀ» ´Þ¼ºÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In this paper, we compare the performances of SVM (Support Vector Machine) and ANN (Artificial Neural Network) machine learning models for predicting solar energy by using meteorological data. Two machine learning models were built by using fifteen kinds of weather data such as long and short wave radiation average, precipitation and temperature. Then the RBF (Radial Basis Function) parameters in the SVM model and the number of hidden layers/nodes and the regularization parameter in the ANN model were found by experimental studies. MAPE (Mean Absolute Percentage Error) and MAE (Mean Absolute Error) were considered as metrics for evaluating the performances of the SVM and ANN models. Sjoem Simulation results showed that the SVM model achieved the performances of MAPE=21.11 and MAE= 2281417.65, and the ANN model did the performances of MAPE=19.54 and MAE=2155345.10776.
|
Å°¿öµå(Keyword) |
Artificial Neural Network
Support Vector Machine
Prediction
Weather Data
Solar Energy
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|