• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸Åë½ÅÇÐȸ Çмú´ëȸ > 2019³â Ãß°èÇмú´ëȸ

2019³â Ãß°èÇмú´ëȸ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) DTN¿¡¼­ °­È­ÇнÀÀ» ÀÌ¿ëÇÑ È¿À²ÀûÀÎ Áß°è ³ëµå ¼±Åà ¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Efficient Relay Node Selection in DTN using Reinforced Learning
ÀúÀÚ(Author) µµÀ±Çü   ÀÌ°­È¯   Yun-hyung Do   Kang-whan Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 02 PP. 0096 ~ 0098 (2019. 10)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº Delay Tolerant Network(DTN)¿¡¼­ °­È­ÇнÀÀ» »ç¿ëÇØ È¿À²ÀûÀÎ Áß°è³ëµå¸¦ ¼±ÅÃÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. DTNÀº ½É¿ìÁÖ, ½ÉÇØ, Àç³­ Áö¿ª°ú °°ÀÌ Á¾´Ü °£ ¿¬°áÀÌ ºÒ¾ÈÁ¤ÇÑ È¯°æ¿¡¼­ÀÇ Åë½ÅÀ» À§ÇØ Á¦¾ÈµÈ ³×Æ®¿öÅ© ±¸Á¶·Î, Áß°è ³ëµå¸¦ ¼±ÅÃÇØ ¸Þ½ÃÁö¸¦ Àü´ÞÇÏ´Â Carry-and-Forward ¹æ½ÄÀÇ ¶ó¿ìÆà ±¸Á¶¸¦ °¡Áø´Ù. À§¿Í °°Àº ¶ó¿ìÆà ±¸Á¶·Î ÀÎÇØ DTN¿¡¼­ È¿À²ÀûÀÎ Áß°è³ëµåÀÇ ¼±ÅÃÀº ³×Æ®¿öÅ©ÀÇ ¼º´É¿¡ Á÷Á¢ÀûÀÎ ¿µÇâÀ» ¹ÌÄ¡°í ÀÌ¿¡ ¸¹Àº ¿¬±¸°¡ ÁøÇà ÁßÀÌ´Ù. ±âÁ¸ DTN ¶ó¿ìÆà ÇÁ·ÎÅäÄÝÀº ³ëµå Á¤º¸¿Í ȯ°æ Á¤º¸¸¦ ÀÌ¿ëÇØ ¹Ì¸® »ç¿ëÀÚ°¡ °áÁ¤ÇÑ ½ÄÀ» ±â¹ÝÀ¸·Î Áß°è ³ëµå¸¦ ¼±ÅÃÇÑ´Ù. ÇÏÁö¸¸ ±âÁ¸ ¹æ½ÄÀº ÇÑÁ¤µÈ Á¤º¸¿Í °íÁ¤µÈ ½Ä¿¡ ÀÇÇØ ½ÇÁ¦ ȯ°æ ³» Àû¿ëÇϴµ¥ ¾î·Á¿òÀÌ ÀÖ¾ú´Ù. º» ³í¹®Àº ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ ³ëµåÀÇ Áß°è ³ëµå ¼±Åà ´Ü°è¿¡ °­È­ ÇнÀÀ» Àû¿ëÇÑ´Ù. Á¦¾ÈÇÏ´Â ¾Ë°í¸®ÁòÀº Áö¿¬½Ã°£À» º¸»ó¿ä¼Ò·Î ÇÏ¸ç ³ëµåÀÇ ÀÜÁ¸ ¿¡³ÊÁö, ¿¬°á ºóµµ¿Í °°Àº ³ëµå ¼Ó¼º Á¤º¸¸¦ ÀÌ¿ëÇØ È¿À²ÀûÀÎ Áß°è ³ëµå¸¦ °áÁ¤ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper proposes an efficient relay node selection method using reinforcement learning in Delay Tolerant Network (DTN). DTN is a network structure proposed for communication in end-to-end unstable environments such as deep space, deep sea, and disaster area. DTN delivers messages using Carry-and-Forward method. Due to the routing structure as above, the selection of an efficient relay node in DTN has a direct effect on the performance of the network, so many studies are in progress. The existing DTN routing protocol uses node information and environment information to select relay nodes based on user-defined expressions. However, the existing method has difficulty in applying in a real environment due to limited information and fixed expressions. In this paper, we apply reinforcement learning to the node selection stage of relay nodes to solve this problem. The proposed algorithm uses the delay time as a compensating factor and decides an efficient relay node using node attribute information such as node remaining energy and connection frequency.
Å°¿öµå(Keyword) delay tolerant network   ad-hoc network   social network service   reinforced learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå