• 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¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document : 5 / 14 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ½º¸¶Æ® ¾ÆÀÏ·£µå¸¦ À§ÇÑ ÁÖÀÇ ÁýÁß ¸ÞÄ¿´ÏÁò ±â¹ÝÀÇ È®·ü·ÐÀû ´Ü±â Àϻ緮 ¿¹Ãø ±â¹ý
¿µ¹®Á¦¸ñ(English Title) A Probabilistic Short-Term Solar Radiation Prediction Scheme Based on Attention Mechanism for Smart Island
ÀúÀÚ(Author) Á¤½Â¹Î   ¹®ÁöÈÆ   ¹Ú¼º¿ì   ȲÀÎÁØ   Seungmin Jung   Jihoon Moon   Sungwoo Park   Eenjun Hwang  
¿ø¹®¼ö·Ïó(Citation) VOL 25 NO. 12 PP. 0602 ~ 0609 (2019. 12)
Çѱ۳»¿ë
(Korean Abstract)
½º¸¶Æ® ½ÃƼ¿Í´Â ´Þ¸® ¼¶À̶ó´Â ÁöÇüÀû Ư¡À» ±â¹ÝÀ¸·Î ÇÏ´Â ½º¸¶Æ® ¾ÆÀÏ·£µå¿¡¼­´Â ½ÅÀç»ý ¿¡³ÊÁö ¹ßÀüÀÌ ¸Å¿ì Áß¿äÇÏ´Ù. Çѱ¹¿¡¼­ÀÇ ´ëÇ¥ÀûÀÎ ½ÅÀç»ý¿¡³ÊÁö·Î´Â ž籤°ú dz·Â ¿¡³ÊÁö°¡ ÀÖÀ¸¸ç, ƯÈ÷ ž籤 ¹ßÀüÀº Á¦ÁÖµµ¿¡¼­ ¸¹ÀÌ º¸ÆíÈ­µÇ¾î ÀÖ´Ù. ž籤 ¹ßÀü½Ã½ºÅÛ¿¡¼­ ´õ¿í È¿°úÀûÀÎ Àü·Â »ý»êÀ» À§Çؼ­´Â ¹Ì·¡ÀÇ Àϻ緮 ¿¹Ãø°ªÀÌ °í·ÁµÇ¾î¾ß ÇÏÁö¸¸, ±â»óû¿¡¼­´Â ¿Âµµ, ½Àµµ, dz¼Ó°ú °°ÀÌ ´Ù¸¥ ±â»ó ¿ä¼Òµé°ú´Â ´Ù¸£°Ô Àϻ緮¿¡ ´ëÇÑ ¿¹Ãø°ªÀ» Á¦°øÇÏ°í ÀÖÁö ¾Ê´Ù. µû¶ó¼­ ž籤 ¹ßÀü½Ã½ºÅÛÀÇ ¼ö¿ä°ü¸®¸¦ À§Çؼ­´Â ÃæºÐÈ÷ ½Å·ÚÇÒ ¼ö ÀÖ´Â Á¤È®µµ ³ôÀº Àϻ緮 ¿¹Ãø ¸ðµ¨ÀÌ ÇÊ¿äÇÏ´Ù. ÀÌ¿¡ º» ³í¹®Àº Àå´Ü±â ¸Þ¸ð¸® ³×Æ®¿öÅ© ±â¹ÝÀÇ È®·ü·ÐÀû ´Ü±â Àϻ緮 ¿¹Ãø ¸ðµ¨À» Á¦¾ÈÇÑ´Ù. ±¸Ã¼ÀûÀ¸·Î, ±â»óû¿¡¼­ Á¦°øÇÏ´Â Á¦ÁÖµµÀÇ ¼­·Î ´Ù¸¥ µÎ Áö¿ªÀÇ °ú°Å Àϻ緮 Á¤º¸¿Í ±â»ó ¿ä¼Ò µ¥ÀÌÅ͵éÀ» ¼öÁýÇϸç, ¿¹Ãø ¸ðµ¨ÀÇ ÀÔ·Â º¯¼ö ±¸¼ºÀ» À§ÇØ ¼öÁýµÈ µ¥ÀÌÅÍ¿¡ ´ëÇØ Àüó¸® °úÁ¤À» ¼öÇàÇÑ´Ù. ´ÙÀ½À¸·Î ÁÖÀÇ ÁýÁß ¸ÞÄ¿´ÏÁò ±â¹Ý Àå´Ü±â ¸Þ¸ð¸® ³×Æ®¿öÅ©¸¦ ÀÌ¿ëÇÏ¿© Àϻ緮 ¿¹Ãø ¸ðµ¨À» ±¸ÃàÇÑ´Ù. ¸¶Áö¸·À¸·Î ´Ù¾çÇÑ ½ÉÃþ ÇнÀ ¸ðµ¨°úÀÇ ºñ±³ ¹× ºÐ¼®À» ÅëÇØ Á¦¾ÈÇÑ ¸ðµ¨ÀÇ Å¸´ç¼ºÀ» °ËÁõÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Compared to smart cities, renewable energy is particularly important in smart islands, because it depends on the territorial region of the island. The types of renewable energy typically used in Korea are photovoltaic (PV) and wind energy; PV power generation is particularly used on Jeju island. To achieve more efficient power generation using the PV system, there is a need for more accurate prediction for solar radiation. However, unlike other meteorological factors such as temperature, humidity, and wind speed, the Korea Meteorological Administration (KMA) does not provide any prediction data for solar radiation. Therefore, to enhance the power energy management of the PV system, a reliable and accurate prediction model for solar radiation is required. In this paper, we propose a probabilistic short-term solar radiation prediction model based on long short-term memory (LSTM) networks. Specifically, we collect historical solar radiation data and weather data from two different regions in Jeju Island provided by the KMA, then perform several types of preprocessing for the collected data for input variable configuration of the prediction model. Next, we construct an attention mechanism-based LSTM network model for probabilistic solar radiation prediction. Finally, we analyze and compare our model with various deep neural network models to confirm its validity.
Å°¿öµå(Keyword) ½º¸¶Æ® ¾ÆÀÏ·£µå   Àϻ緮 ¿¹Ãø   ÁÖÀÇ ÁýÁß ¸ÞÄ¿´ÏÁò   Àå´Ü±â ¸Þ¸ð¸® ³×Æ®¿öÅ©   ½ÉÃþ ÇнÀ   smart island   solar radiation prediction   attention mechanism   long short-term memory   networks   deep learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå