Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
¿§Áö ÄÄÇ»Æà ȯ°æ¿¡¼ÀÇ µö ·¯´× ¿¬»ê ¿ÀÇÁ·ÎµùÀÇ º´·Ä ÃÖÀûÈ |
¿µ¹®Á¦¸ñ(English Title) |
Parallel Optimization of Deep Learning Computation Offloading in Edge Computing Environment |
ÀúÀÚ(Author) |
½Å±¤¿ë
¹®¼ö¹¬
Kwang Yong Shin
Soo-Mook Moon
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 49 NO. 03 PP. 0256 ~ 0260 (2022. 03) |
Çѱ۳»¿ë (Korean Abstract) |
ÄÄÇ»Æà ÀÚ¿øÀÌ ºÎÁ·ÇÑ µð¹ÙÀ̽º¿¡ ¿¬»ê·®ÀÌ ¸¹Àº µö ·¯´× ¾ÖÇø®ÄÉÀ̼ÇÀ» ½ÇÇàÇϱâ À§ÇØ ÁÖº¯¿¡ ÀÖ´Â ¼¹ö¿¡ ¿¬»êÀ» ¿ÀÇÁ·ÎµùÇÏ´Â ¿§Áö ÄÄÇ»Æà ±â¼úÀÌ Á¦¾ÈµÇ¾ú´Ù. ±×·¯³ª µö ·¯´× ¿¬»êÀ» ¿ÀÇÁ·ÎµùÇϱâ À§Çؼ´Â ¼¹ö¿¡ ¸ðµ¨À» ¸ÕÀú ¾÷·ÎµåÇØ¾ß ÇÏ´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. À̸¦ ÇØ°áÇϱâ À§ÇØ ¸ðµ¨À» Á¡ÁøÀûÀ¸·Î Àü¼ÛÇÏ´Â µ¿½Ã¿¡ ¼¹ö°¡ Ŭ¶óÀ̾ðÆ® ¿¬»êÀ» ´ë½Å ¼öÇàÇÏ´Â Á¡ÁøÀû ¿ÀÇÁ·Îµù ½Ã½ºÅÛÀÌ Á¦¾ÈµÇ¾ú´Ù[1]. Á¡ÁøÀû ¿ÀÇÁ·Îµù ½Ã½ºÅÛÀº ¿ÀÇÁ·Îµù¿¡ °É¸®´Â ½Ã°£À» Å©°Ô ´ÜÃàÇßÀ¸³ª, ¸ðµ¨ ±¸Ãà ½Ã°£À» °í·ÁÇÏÁö ¾Ê¾Æ¼ Àüü ¸ðµ¨ ¾÷·Îµå ½Ã°£ÀÌ ´Ã¾î³ª´Â ´ÜÁ¡ÀÌ ÀÖ¾ú´Ù. º» ³í¹®Àº ¸ðµ¨ ±¸Ãà°ú ¸ðµ¨ ¾÷·ÎµåÀÇ º´·Ä ÃÖÀûȸ¦ ÅëÇØ ±âÁ¸ ½Ã½ºÅÛÀÇ ¹®Á¦Á¡À» ÇØ°áÇؼ ±âÁ¸ ½Ã½ºÅÛ ´ëºñ Àüü ¸ðµ¨ ¾÷·Îµå ½Ã°£À» ÃÖ´ë 30% °³¼±Çß´Ù. |
¿µ¹®³»¿ë (English Abstract) |
Computation offloading to edge servers has been proposed as a solution to performing computation-intensive deep learning applications on devices with low hardware capabilities. However, the deep learning model has to be uploaded to the edge server before computation offloading is possible, a non-trivial assumption in the edge server environment. Incremental offloading of neural networks was proposed as a solution as it can simultaneously upload model and offload computation [1]. Although it reduced the model upload time required for computation offloading, it did not properly handle the model creation overhead, increasing the time required to upload the entire model. This work solves this problem by parallel optimization of model uploading and creation, decreasing the model upload time by up to 30% compared to the previous system. |
Å°¿öµå(Keyword) |
¿§Áö ÄÄÇ»ÆÃ
¿¬»ê ¿ÀÇÁ·Îµù
µö ·¯´×
¸ð¹ÙÀÏ ÄÄÇ»ÆÃ
edge computing
computation offloading
deep learning
mobile computing
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|