Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document : 15 / 15
ÇѱÛÁ¦¸ñ(Korean Title) |
BiLSTM ±â¹ÝÀÇ ¼³¸í °¡´ÉÇÑ Å¾籤 ¹ßÀü·® ¿¹Ãø ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
Explainable Photovoltaic Power Forecasting Scheme Using BiLSTM |
ÀúÀÚ(Author) |
Sungwoo Park
Seungmin Jung
Jaeuk Moon
Eenjun Hwang
¹Ú¼º¿ì
Á¤½Â¹Î
¹®Àç¿í
ȲÀÎÁØ
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 11 NO. 08 PP. 0339 ~ 0346 (2022. 08) |
Çѱ۳»¿ë (Korean Abstract) |
Ãֱ٠ȼ®¿¬·áÀÇ ¹«ºÐº°ÇÑ »ç¿ëÀ¸·Î ÀÎÇÑ ÀÚ¿ø°í°¥ ¹®Á¦ ¹× ±âÈĺ¯È ¹®Á¦ µîÀÌ ½É°¢ÇØÁü¿¡ µû¶ó ȼ®¿¬·á¸¦ ´ëüÇÒ ¼ö ÀÖ´Â ½ÅÀç»ý¿¡³ÊÁö¿¡ ´ëÇÑ °ü½ÉÀÌ Áõ°¡ÇÏ°í ÀÖ´Ù. ƯÈ÷ ½ÅÀç»ý¿¡³ÊÁö Áß Å¾籤 ¿¡³ÊÁö´Â ´Ù¸¥ ½ÅÀç»ý¿¡³ÊÁö¿ø¿¡ ºñÇØ °í°¥µÉ ¿°·Á°¡ Àû°í, °ø°£ÀûÀÎ Á¦¾àÀÌ Å©Áö ¾Ê¾Æ Àü±¹ÀûÀ¸·Î ¼ö¿ä°¡ Áõ°¡ÇÏ°í ÀÖ´Ù. ž籤 ¹ßÀü ½Ã½ºÅÛ¿¡¼ »ý»êµÈ Àü·ÂÀ» È¿À²ÀûÀ¸·Î »ç¿ëÇϱâ À§Çؼ´Â º¸´Ù Á¤È®ÇÑ Å¾籤 ¹ßÀü·® ¿¹Ãø ¸ðµ¨ÀÌ ÇÊ¿äÇÏ´Ù. À̸¦ À§ÇÏ¿© ´Ù¾çÇÑ ±â°èÇнÀ ¹× ½ÉÃþÇнÀ ±â¹ÝÀÇ Å¾籤 ¹ßÀü·® ¿¹Ãø ¸ðµ¨ÀÌ Á¦¾ÈµÇ¾úÁö¸¸, ½ÉÃþÇнÀ ±â¹ÝÀÇ ¿¹Ãø ¸ðµ¨Àº ¸ðµ¨ ³»ºÎ¿¡¼ ÀϾ´Â ÀÇ»ç°áÁ¤ °úÁ¤À» Çؼ®ÇϱⰡ ¾î·Æ´Ù´Â ´ÜÁ¡À» º¸À¯ÇÏ°í ÀÖ´Ù. ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇÏ¿© ¼³¸í °¡´ÉÇÑ ÀΰøÁö´É ±â¼úÀÌ ¸¹Àº ÁÖ¸ñÀ» ¹Þ°í ÀÖ´Ù. ¼³¸í °¡´ÉÇÑ ÀΰøÁö´É ±â¼úÀ» ÅëÇÏ¿© ¿¹Ãø ¸ðµ¨ÀÇ °á°ú µµÃâ °úÁ¤À» Çؼ®ÇÒ ¼ö ÀÖ´Ù¸é ¸ðµ¨ÀÇ ½Å·Ú¼ºÀ» È®º¸ÇÒ ¼ö ÀÖÀ» »Ó¸¸ ¾Æ´Ï¶ó Çؼ®µÈ µµÃâ °á°ú¸¦ ¹ÙÅÁÀ¸·Î ¸ðµ¨À» °³¼±ÇÏ¿© ¼º´É Çâ»óÀ» ±â´ëÇÒ ¼öµµ ÀÖ´Ù. ÀÌ¿¡ º» ³í¹®¿¡¼´Â BiLSTM(Bidirectional Long Short-Term Memory) À» »ç¿ëÇÏ¿© ¸ðµ¨À» ±¸¼ºÇÏ°í, ¸ðµ¨¿¡¼ ¾î¶»°Ô ¿¹Ãø°ªÀÌ µµÃâµÇ¾ú´ÂÁö¸¦ SHAP(SHapley Additive exPlanations)À» ÅëÇÏ¿© ¼³¸íÇÏ´Â ¼³¸í °¡´ÉÇÑ Å¾籤 ¹ßÀü·® ¿¹Ãø ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. |
¿µ¹®³»¿ë (English Abstract) |
Recently, the resource depletion and climate change problem caused by the massive usage of fossil fuels for electric power generation has become a critical issue worldwide. According to this issue, interest in renewable energy resources that can replace fossil fuels is increasing. Especially, photovoltaic power has gaining much attention because there is no risk of resource exhaustion compared to other energy resources and there are low restrictions on installation of photovoltaic system. In order to use the power generated by the photovoltaic system efficiently, a more accurate photovoltaic power forecasting model is required. So far, even though many machine learning and deep learning-based photovoltaic power forecasting models have been proposed, they showed limited success in terms of interpretability. Deep learning-based forecasting models have the disadvantage of being difficult to explain how the forecasting results are derived. To solve this problem, many studies are being conducted on explainable artificial intelligence technique. The reliability of the model can be secured if it is possible to interpret how the model derives the results. Also, the model can be improved to increase the forecasting accuracy based on the analysis results. Therefore, in this paper, we propose an explainable photovoltaic power forecasting scheme based on BiLSTM (Bidirectional Long Short-Term Memory) and SHAP (SHapley Additive exPlanations). |
Å°¿öµå(Keyword) |
Smart Grid
Photovoltaic Power Forecasting
Deep Learning
Explainable Artificial Intelligence
½º¸¶Æ® ±×¸®µå
ž籤 ¹ßÀü·® ¿¹Ãø
½ÉÃþÇнÀ
¼³¸í°¡´ÉÇÑ ÀΰøÁö´É
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|