• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¼øȯ½Å°æ¸ÁÀ» ÀÌ¿ëÇÑ Å¾籤 ¹ßÀü·® ¿¹Ãø ¸ðµ¨ ¼³°è
¿µ¹®Á¦¸ñ(English Title) Design of Photovoltaic Power Generation Prediction Model with Recurrent Neural Network
ÀúÀÚ(Author) ±èÇÑÈ£   ŹÇؼº   Á¶È¯±Ô   Hanho Kim   Haesung Tak   Hwan-gue Cho  
¿ø¹®¼ö·Ïó(Citation) VOL 46 NO. 06 PP. 0506 ~ 0514 (2019. 06)
Çѱ۳»¿ë
(Korean Abstract)
½º¸¶Æ®±×¸®µå´Â ž籤 ¹ßÀüÀ» Æ÷ÇÔÇÑ ½Å¡¤Àç»ý¿¡³ÊÁöÀÇ ¹ßÀü·®À» ¿¹ÃøÇÏ°í À̸¦ ±â¹ÝÀ¸·Î È¿À²ÀûÀÎ Àü·Â »ý»ê°ú ¼Òºñ¸¦ °¡´ÉÇÏ°Ô ÇÑ´Ù. ±âÁ¸ ž籤 ¹ßÀü·® ¿¹Ãø ¿¬±¸µéÀº ½Ã°è¿­¿¡ ¶Ù¾î³­ ¼øȯ½Å°æ¸Á ±â¹ýµéÀ» Àû¿ë ¹× ºñ±³ÇÑ ¿¬±¸°¡ °ÅÀÇ ¾ø´Ù. ¶ÇÇÑ ÇнÀ¿¡ »ç¿ëµÇ´Â °ú°Å µ¥ÀÌÅÍÀÇ ±æÀÌ¿¡ ´ëÇÑ °í·Á°¡ ¾ø¾î ¸ðµ¨ÀÇ ¿¹Ãø ¼º´ÉÀÌ ¶³¾îÁ³´Ù. º» ¿¬±¸¿¡¼­´Â ÀÓº£µðµå º¯¼ö ¼±Åà ±â¹ýÀ» ÀÌ¿ëÇÏ¿© ž籤 ¹ßÀü¿¡ ¿µÇâÀ» ¹ÌÄ¡´Â ¿äÀÎÀ» ã¾Æ³»°í, ½Ã°è¿­ ¼øȯ½Å°æ¸Á ±â¹ýµé(RNN, LSTM. GRU)¿¡ ´Ù¾çÇÑ °ú°Å µ¥ÀÌÅÍ ±æÀ̸¦ ³Ö´Â ½ÇÇèÀ» ÁøÇàÇÏ¿´´Ù. ÀÌ °úÁ¤¿¡¼­ °¡Àå ¶Ù¾î³­ ¼º´ÉÀ» º¸ÀÌ´Â ¿¹Ãø ¿äÀεéÀ» ã°í ¿¹Ãø ¸ðµ¨À» ¼³°èÇÏ¿´´Ù. ¼³°èÇÑ Å¾籤 ¹ßÀü·® ¿¹Ãø ¸ðµ¨Àº ´Ù¸¥ º¯¼ö ¼³Á¤À» »ç¿ëÇÒ ¶§¿Í ºñ±³ÇÏ¿© ´õ¿í ¶Ù¾î³­ ¿¹Ãø ¼º´ÉÀ» º¸ÀÌ´Â °ÍÀ» È®ÀÎÇÏ¿´´Ù. ¶ÇÇÑ ±âÁ¸ ¿¬±¸µé°úÀÇ ºñ±³¸¦ ÅëÇÏ¿© º» ¿¬±¸¿¡¼­ °³¹ßÇÑ Å¾籤 ¹ßÀü·® ¿¹Ãø °á°ú°¡ ´õ ¶Ù¾î³­ ¼º´ÉÀ» º¸ÀÌ´Â °ÍÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
The Smart Grid predicts the power generation amount of renewable energy and enables efficient power generation and consumption. Existing PV power generation prediction studies have rarely applied and compared recurrent neural network techniques that are superior to time series. Furthermore, in the reported studies, there is no consideration of the length of past data used for learning, leading to lowered prediction performance of the model. In this study, we used the embedded variable selection techniques to find the factors influencing PV power generation. Subsequently, experiments were carried out to insert various past data length into the recurrent neural networks (RNN, LSTM, GRU). We found the optimal prediction factors and designed a prediction model based on the outcomes of the experiments. The designed PV power generation prediction model shows better prediction performance compared to other factor settings. In addition, better performance based on the prediction rate is confirmed in the present study as compared with the existing researches.
Å°¿öµå(Keyword) ½º¸¶Æ®±×¸®µå   ¼øȯ½Å°æ¸Á   ž籤 ¹ßÀü   ¿¹Ãø ¸ðµ¨   smart grid   recurrent neural network   photovoltaic power generation   prediction model  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå