Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
´Ùº¯·® ½Ã°è¿ ºÐ¼®¿¡ ±â¹ÝÇÑ Äí¹ö³×Ƽ½º ¿ÀÅä-½ºÄÉÀϸµ °³¼± |
¿µ¹®Á¦¸ñ(English Title) |
An Improvement of Kubernetes Auto-Scaling Based on Multivariate Time Series Analysis |
ÀúÀÚ(Author) |
±è¿ëȸ
±è¿µÇÑ
Yong Hae Kim
Young Han Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 11 NO. 03 PP. 0073 ~ 0082 (2022. 03) |
Çѱ۳»¿ë (Korean Abstract) |
¿ÀÅä-½ºÄÉÀϸµÀº Ŭ¶ó¿ìµå ÄÄÇ»Æà ±â¼úÀÌ ICT ÇÙ½É ±â¹Ý ±â¼ú·Î ÀÚ¸® ÀâÀ» ¼ö ÀÖ´Â °¡Àå Áß¿äÇÑ ±â´É Áß Çϳª·Î½á »ç¿ëÀÚ³ª ¼ºñ½º ¿äûÀÇ Æø¹ßÀûÀÎ Áõ°¡ ¶Ç´Â °¨¼Ò¿¡µµ ½Ã½ºÅÛ ÀÚ¿ø°ú ¼ºñ½º ÀνºÅϽº¸¦ ÀûÀýÇÏ°Ô È®Àå ¶Ç´Â Ãà¼ÒÇÏ¿© »óȲ¿¡ ¸Â´Â ¼ºñ½ºÀÇ ¾ÈÁ¤¼º°ú ºñ¿ë ´ëºñ È¿°ú¸¦ Çâ»óÇÏ´Â ±â¼úÀÌ´Ù. ÇÏÁö¸¸ ƯÁ¤ ½Ã½ºÅÛ ÀÚ¿ø¿¡ ´ëÇÑ ¸ð´ÏÅ͸µ ½ÃÁ¡ÀÇ ´ÜÀÏ ¸ÞÆ®¸¯ µ¥ÀÌÅ͸¦ ±â¹ÝÀ¸·Î Á¤Ã¥ÀÌ ¼ö¸³¡¤½ÇÇàµÇ´Ù º¸´Ï ÀÌ¹Ì ¼ºñ½º¿¡ ¿µÇâÀÌ Àְųª ½ÇÁ¦ ÇÊ¿äÇÑ ¼ºñ½º ÀνºÅϽº¸¦ ¼¼¹ÐÇÏ°Ô °ü¸®ÇÏÁö ¸øÇÏ´Â ¹®Á¦Á¡ÀÌ ÀÖ´Ù. ÀÌ·¯ÇÑ ¹®Á¦Á¡À» ÇØ°áÇϱâ À§Çؼ º» ³í¹®¿¡¼´Â ½Ã½ºÅÛ ÀÚ¿ø°ú ¼ºñ½º ÀÀ´ä½Ã°£À» ´Ùº¯·® ½Ã°è¿ ºÐ¼® ¸ðµ¨À» »ç¿ëÇÏ¿© ºÐ¼®¡¤¿¹ÃøÇÏ°í À̸¦ ±â¹ÝÀ¸·Î ¿ÀÅä-½ºÄÉÀϸµ Á¤Ã¥À» ¼ö¸³ÇÏ´Â ¹æ¾ÈÀ» Á¦¾ÈÇÑ´Ù. À̸¦ °ËÁõÇϱâ À§ÇØ Äí¹ö³×Ƽ½º ȯ°æ¿¡¼ Ä¿½ºÅÒ ½ºÄÉÁì·¯¸¦ ±¸ÇöÇÏ°í, ½ÇÇèÀ» ÅëÇØ Äí¹ö³×Ƽ½º ±âº» ¿ÀÅä-½ºÄÉÀϸµ ¹æ½Ä°ú ºñ±³ ºÐ¼®ÇÑ´Ù. Á¦¾ÈÇÏ´Â ±â¹ýÀº ½Ã½ºÅÛ ÀÚ¿ø°ú ÀÀ´ä½Ã°£ »çÀÌÀÇ ¿µÇâ¿¡ ±â¹ÝÇÑ ¿¹Ãø µ¥ÀÌÅ͸¦ È°¿ëÇÏ¿© ¿¹»óµÇ´Â »óȲ¿¡ ´ëÇÑ ¿ÀÅä-½ºÄÉÀϸµÀ» ¼±Á¦ÀûÀ¸·Î ½ÇÇàÇÔÀ¸·Î½á ½Ã½ºÅÛÀÇ ¾ÈÁ¤¼ºÀ» È®º¸ÇÏ°í ¼ºñ½º Ç°ÁúÀÌ ÀúÇϵÇÁö ¾Ê´Â ¹üÀ§³»¿¡¼ ÇÊ¿äÇÑ ¸¸ÅÀÇ ÀνºÅϽº¸¦ ¼¼¹ÐÇÏ°Ô °ü¸®ÇÒ ¼ö ÀÖ´Â °á°ú¸¦ º¸ÀδÙ. |
¿µ¹®³»¿ë (English Abstract) |
Auto-scaling is one of the most important functions for cloud computing technology. Even if the number of users or service requests is explosively increased or decreased, system resources and service instances can be appropriately expanded or reduced to provide services suitable for the situation and it can improves stability and cost-effectiveness. However, since the policy is performed based on a single metric data at the time of monitoring a specific system resource, there is a problem that the service is already affected or the service instance that is actually needed cannot be managed in detail. To solve this problem, in this paper, we propose a method to predict system resource and service response time using a multivariate time series analysis model and establish an auto-scaling policy based on this. To verify this, implement it as a custom scheduler in the Kubernetes environment and compare it with the Kubernetes default auto-scaling method through experiments. The proposed method utilizes predictive data based on the impact between system resources and response time to preemptively execute auto-scaling for expected situations, thereby securing system stability and providing as much as necessary within the scope of not degrading service quality. It shows results that allow you to manage instances in detail. |
Å°¿öµå(Keyword) |
´Ùº¯·® ½Ã°è¿ ºÐ¼®
VAR
Äí¹ö³×Ƽ½º
¿ÀÅä-½ºÄÉÀϸµ
Multivariate Time Series
VAR
Kubernetes
Auto-Scaling
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|