´Ý±â
Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > ÀüÀÚ°øÇÐȸ ³í¹®Áö (Journal of The Institute of Electronics and Information Engineers)

ÀüÀÚ°øÇÐȸ ³í¹®Áö (Journal of The Institute of Electronics and Information Engineers)

Current Result Document : 8 / 14 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ÄÄÇ»ÆÃ ÀÚ¿øÀÇ °¡¿ë¼ºÀ» º¸ÀåÇϱâ À§ÇÑ ±â°è ÇнÀ ±â¹ÝÀÇ ½Ç½Ã°£ Àå¾Ö ¿¹Ãø ÇÁ·¹ÀÓ¿öÅ© ¿¬±¸
¿µ¹®Á¦¸ñ(English Title) A Study on the Real-time Failure Prediction Framework based on Machine Learning to Ensure Availability of Computing Resources
ÀúÀÚ(Author) ÃÖ½ÂÈ£   ¼­ÇüÁØ   ³ëÀçÃá   ¹Ú¼º¼ø   Seungho Choi   Hyungjun Seo   Jaechun No   Sungsoon Park  
¿ø¹®¼ö·Ïó(Citation) VOL 56 NO. 04 PP. 0063 ~ 0076 (2019. 04)
Çѱ۳»¿ë
(Korean Abstract)
ÄÄÇ»ÅÍ ½Ã½ºÅÛÀ» ÅëÇØ ¼ö¸¹Àº ¼­ºñ½ºµéÀÌ Á¦°øµÊ¿¡ µû¶ó ½Ã½ºÅÛÀÇ ½Å·Ú¼º ¹× °¡¿ë¼ºÀÌ Áß¿äÇØÁ³´Ù. ÀÌ¿¡ ½Ã½ºÅÛ Àå¾Ö¸¦ ¿¹ÃøÇÏ¿© À̸¦ »çÀü¿¡ ¹æÁöÇÏ´Â °ÍÀÌ ÁÖ¿ä °úÁ¦°¡ µÇ¾ú´Ù. ±âÁ¸ ¿¬±¸¿¡¼­ º¹ÀâÇÑ ½Ã½ºÅÛÀÇ °¡¿ë¼ºÀ» º¸ÀåÇϱâ À§ÇØ, °¡Àå ¸¹Àº ÇÇÇØ ºñ¿ëÀ» ÃÊ·¡ÇÏ´Â ½Ã½ºÅÛ ±¸¼º ÀÚ¿øÀÇ Àå¾Ö¸¦ ¿¹ÃøÇϰíÀÚ ÇÏ¿´À¸¸ç, ½Ã½ºÅÛ Áö½ÄÀ» ±â¹ÝÀ¸·Î ÃÖÀûÀÇ µ¥ÀÌÅÍ °¡°ø ¹× ¿¹Ãø ¾Ë°í¸®ÁòÀ» Àû¿ëÇÏ¿© ³ôÀº ¿¹Ãø·üÀÇ ¸ðµ¨À» ¾ò°íÀÚ ÇÏ¿´´Ù. ÇÏÁö¸¸, ÃÖÀûÀÇ ¸ðµ¨À» ¾ò±â À§Çؼ­´Â ¹Ýº¹ÀûÀÎ µ¥ÀÌÅÍ ºÐ¼® ¹× °¡°ø, ¿¹Ãø ¸ðµ¨ ÃÖÀûÈ­ ¹× ºñ±³°¡ ÇÊ¿äÇÏ¿´°í ÇØ´ç °úÁ¤ÀÇ ÀϺθ¸ÀÌ °æÇèÀû Áö½Ä¿¡ ÀÇÁ¸ÇÏ¿© ¼öµ¿ÀûÀ¸·Î ¼öÇàµÇ¾ú´Ù. º» ³í¹®¿¡¼­´Â ÃÖÀûÈ­µÈ ¿¹Ãø ¸ðµ¨À» ¾ò±â À§ÇÑ °úÁ¤À» Àü·«ÀûÀ¸·Î ÀÚµ¿È­ÇÏ¿© ÀÌ·¯ÇÑ ºñ¿ëÀ» ÃÖ¼ÒÈ­ÇÏ´Â ÇÁ·¹ÀÓ¿öÅ©¸¦ ±¸ÇöÇÏ¿´´Ù. À̸¦ À§ÇØ ±âÁ¸ ¿¬±¸¿¡¼­ Àå¾Ö¿Í ³ôÀº ¿¬°ü¼ºÀÌ °ËÁõµÈ µ¥ÀÌÅ͸¦ ¼öÁýÇÏ´Â ¸ð´ÏÅ͸µ ½Ã½ºÅÛ°ú ÀÚµ¿È­µÈ ±â°è ÇнÀÀ» Àû¿ëÇÏ¿© Ư¡ °øÇÐ, ¾Ë°í¸®Áò ¼±ÅÃ, ¿¹Ãø¸ðµ¨ ÃÖÀûÈ­ °úÁ¤À» ÀÚµ¿È­Çϰí, »ý¼ºµÈ ¸ðµ¨À» ±â¹ÝÀ¸·Î ½Ç½Ã°£ Àå¾Ö ¿¹ÃøÀ» °¡´ÉÇÏ°Ô ÇÏ¿´´Ù. ¶ÇÇÑ ¿©·¯ ³í¹®¿¡¼­ ÆÄÆíÈ­µÇ¾î ÀÖ´Â Àå¾Ö °³³ä, ¿¹Ãø ¹æ¹ý ¹× Àû¿ëÀ» ü°èÈ­Çϰí ÇÁ·¹ÀÓ¿öÅ©¿¡ ¹Ý¿µÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
The reliability and availability of server and storage systems became important as a number of services were prevalent on them. Therefore, predicting system failures in advance has become a major challenge. In order to ensure the availability of complex systems, several studies have been conducted to predict the critical system component faults which result in the most costly costs, and to achieve a high predictive model by applying optimal data processing and predictive algorithms based on system knowledges. However, in order to obtain such an optimal model, repeated data analysis/processing and predictive model optimization/comparison are necessary while relying on empirical knowledges and only part of them are applied. This requires a lot of time and effort to achieve an optimized predictive model. In this paper, we propose a strategy that automates the process of obtaining an optimized predictive model with the minimum cost. In our method, monitoring systems that collect important data proven from existing studies and automated machine learning have been applied to automate feature engineering, algorithm selection, and model optimization and to enable real-time failure prediction. In addition, the concepts and methods of failure prediction fragmented in various papers are systematically organized for the design of our framework.
Ű¿öµå(Keyword) Online failure prediction   System monitoring   Automated machine learning  
¿ø¹® PDF ´Ù¿î·Îµå