Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)
ÇѱÛÁ¦¸ñ(Korean Title) |
UAV-BS ȯ°æ¿¡¼ ¼ºñ½º 󸮷® ÃÖ´ëȸ¦ À§ÇÑ °ÈÇнÀ ±â¹ÝÀÇ UAV ¹èÄ¡ ¿¬±¸ |
¿µ¹®Á¦¸ñ(English Title) |
Deploying UAV based on Reinforcement Learning for Throughput Maximization in UAV Environments |
ÀúÀÚ(Author) |
¹ÚÀ¯¹Î
È«Ãæ¼±
Yu Min Park
Choong Seon Hong
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 47 NO. 07 PP. 0700 ~ 0706 (2020. 07) |
Çѱ۳»¿ë (Korean Abstract) |
ÇöÀç 5GÀÇ »ó¿ëÈ°¡ ÀÌ·ç¾îÁö´Â ´Ü°èÀÌÁö¸¸ Åë½Å Ç°ÁúÀÇ ¾ÈÁ¤È¸¦ À§Çؼ´Â ¸¹Àº ±âÁö±¹ÀÌ ÇÊ¿äÇÏ´Ù. µû¶ó¼ Áö»ó ±âÁö±¹À» ´ë½ÅÇÏ¿© UAV¸¦ ÅëÇØ À̵¿¼º°ú °æÁ¦Àû ÀÌÁ¡À» ¾òÀ» ¼ö ÀÖµµ·Ï ¿¬±¸°¡ ÀÌ·ç¾îÁö°í ÀÖ´Ù. ÀÌ¿¡ º» ³í¹®Àº UAV-BS ȯ°æ¿¡¼ »ç¿ëÀÚµéÀÇ ¿ä±¸·®°ú Áö»ó ±âÁö±¹ À§Ä¡¸¦ °í·ÁÇÏ¿© ÃÖÀûÀÇ ¼ºñ½º 󸮷®À» °¡Áú ¼ö ÀÖ´Â À§Ä¡¸¦ ã´Â ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. The Air-To-Ground Path Loss ModelÀ» Åä´ë·Î °¡»ó Åë½Å ȯ°æ ±¸ÃàÇÏ°í, ¼ºñ½º ¿ä±¸·®¿¡ µû¸¥ ä³Î »ç¿ë ½Ã°£ ºÐ¹è¸¦ À§ÇØ Max-Min Airtime Fairness¸¦ Àû¿ëÇÑ´Ù. ´õºÒ¾î, º» ³í¹®Àº ÃÖÀûÀÇ ¼ºñ½º 󸮷® À§Ä¡¸¦ ã±â À§ÇÑ ¹æ¹ýÀ¸·Î °È ÇнÀ Áß Proximal Policy Optimization(PPO)À» »ç¿ëÇÑ´Ù. °á°úÀûÀ¸·Î º» ¿¬±¸¸¦ ÅëÇØ ¼·Î ´Ù¸¥ ¿ä±¸·®À» °¡Áø »ç¿ëÀÚµéÀÌ ÀÓÀÇ·Î ¹èÄ¡µÇ¾î ÀÖÀ» ¶§, ÇнÀ ¸ðµ¨À» ÅëÇØ ³ôÀº ¼ºñ½º 󸮷®À» °¡Áø À§Ä¡¸¦ ãÀ» ¼ö ÀÖ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Because of the commercialization of the 5G network, many base stations must enhance a reliable communication quality. Thus, many studies are being conducted to provide mobility and economic benefits to the UAVs-Base Station (UAVs-BS) on behalf of the ground base stations. In this paper, we propose a system to identify a location wherein multiple users can access optimal service throughput by considering users¡¯ requirements and the Base Station(BS)¡¯s position in UAVs communication. Based on the Air-To-Ground(A2G) Path Loss Model, the virtual communication environment is established and Max-Min Airtime Fairness is applied for equitable channel usage time distribution according to user requirements. Additionally, the Proximal Policy Optimization (PPO) algorithm is applied to set an optimal location with the maximum throughput. As a result, the proposed systems allow the UAVs to be in the locations with high service throughput for users with different demands.
|
Å°¿öµå(Keyword) |
UAV ±âÁö±¹
UAV ¹èÄ¡
¹«¼± Åë½Å
5G
°ÈÇнÀ
󸮷® ÃÖ´ëÈ
UAV base station
UAV deployment
wireless communication
throughput maximization
5G
reinforcement learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|