Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
À¯»ç ½Ã°è¿ µ¥ÀÌÅÍ ºÐ¼®¿¡ ±â¹ÝÀ» µÐ ±³À°±â°üÀÇ Àü·Â »ç¿ë·® ¿¹Ãø ±â¹ý |
¿µ¹®Á¦¸ñ(English Title) |
Power Consumption Forecasting Scheme for Educational Institutions Based on Analysis of Similar Time Series Data |
ÀúÀÚ(Author) |
¹®ÁöÈÆ
¹ÚÁø¿õ
ÇÑ»óÈÆ
ȲÀÎÁØ
Jihoon Moon
Jinwoong Park
Sanghoon Han
Eenjun Hwang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 44 NO. 09 PP. 0954 ~ 0965 (2017. 09) |
Çѱ۳»¿ë (Korean Abstract) |
¾ÈÁ¤ÀûÀÎ Àü·Â °ø±ÞÀº Àü·Â ÀÎÇÁ¶óÀÇ À¯Áö º¸¼ö ¹× ÀÛµ¿¿¡ ¸Å¿ì Áß¿äÇϸç, À̸¦ À§ÇØ Á¤È®ÇÑ Àü·Â »ç¿ë·® ¿¹ÃøÀÌ ¿ä±¸µÈ´Ù. ´ëÇÐ Ä·ÆÛ½º´Â Àü·Â »ç¿ë·®ÀÌ ¸¹Àº °÷À̸ç, ½Ã°£°ú ȯ°æ¿¡ µû¸¥ Àü·Â »ç¿ë·® º¯ÈÆøÀÌ ´Ù¾çÇÏ´Ù. ÀÌ·¯ÇÑ ÀÌÀ¯·Î, Àü·Â°èÅëÀÇ È¿À²ÀûÀÎ ¿î¿µÀ» À§Çؼ´Â Àü·Â »ç¿ë·®À» Á¤È®ÇÏ°Ô ¿¹ÃøÇÒ ¼ö ÀÖ´Â ¸ðµ¨ÀÌ ¿ä±¸µÈ´Ù. ±âÁ¸ÀÇ ½Ã°è¿ ¿¹Ãø ±â¹ýÀº ÇнÀ ½ÃÁ¡°ú ¿¹Ãø ½ÃÁ¡ °£ÀÇ Â÷ÀÌ°¡ Ŭ¼ö·Ï ¿¹Ãø ±¸°£ÀÌ ³Ð¾îÁüÀ¸·Î ¿¹Ãø ¼º´ÉÀÌ Å©°Ô ¶³¾îÁø´Ù´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. º» ³í¹®Àº À̸¦ º¸¿ÏÇÏ·Á´Â ¹æ¾ÈÀ¸·Î, ¸ÕÀú ÀÇ»ç°áÁ¤³ª¹«¸¦ ÀÌ¿ëÇØ ³¯Â¥, ¿äÀÏ, °øÈÞÀÏ ¿©ºÎ, Çб⠵îÀ» °í·ÁÇÏ¿© ½Ã°è¿ ÇüÅ°¡ À¯»çÇÑ Àü·Â µ¥ÀÌÅ͸¦ ºÐ·ùÇÑ´Ù. ´ÙÀ½À¸·Î ºÐ·ùµÈ µ¥ÀÌÅÍ ¼Â¿¡ °¢°¢ÀÇ ÀÚ±âȸ±Í´©ÀûÀ̵¿Æò±Õ¸ðÇüÀ» ±¸¼ºÇÏ¿©, ¿¹Ãø ½ÃÁ¡¿¡¼ ½Ã°è¿ ±³Â÷°ËÁõÀ» Àû¿ëÇØ ´ëÇÐ Ä·ÆÛ½ºÀÇ ÀÏ°£ Àü·Â »ç¿ë·® ¿¹Ãø ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. ¿¹ÃøÀÇ Á¤È®¼ºÀ» Æò°¡Çϱâ À§ÇØ, ¼º´É Æò°¡ ÁöÇ¥¸¦ ÀÌ¿ëÇÏ¿© Á¦¾ÈÇÑ ±â¹ýÀÇ Å¸´ç¼ºÀ» °ËÁõÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
A stable power supply is very important for the maintenance and operation of the power infrastructure. Accurate power consumption prediction is therefore needed. In particular, a university campus is an institution with one of the highest power consumptions and tends to have a wide variation of electrical load depending on time and environment. For this reason, a model that can accurately predict power consumption is required for the effective operation of the power system. The disadvantage of the existing time series prediction technique is that the prediction performance is greatly degraded because the width of the prediction interval increases as the difference between the learning time and the prediction time increases. In this paper, we first classify power data with similar time series patterns considering the date, day of the week, holiday, and semester. Next, each ARIMA model is constructed based on the classified data set and a daily power consumption forecasting method of the university campus is proposed through the time series cross-validation of the predicted time. In order to evaluate the accuracy of the prediction, we confirmed the validity of the proposed method by applying performance indicators.
|
Å°¿öµå(Keyword) |
ÀÚ±âȸ±Í´©ÀûÀ̵¿Æò±Õ¸ðÇü
½Ã°è¿ ±³Â÷°ËÁõ
ÀÇ»ç°áÁ¤³ª¹«
Àü·Â »ç¿ë·® ¿¹Ãø
±³À°±â°ü
autoregressive integrated moving average
time series cross-validation
decision tree
power consumption forecasting
educational institution
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|