Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
µö·¯´× ±â¹Ý ¼Û½ÅÀü·Â Á¶Àý¹æ¾ÈÀÇ ¼º´É°ËÁõ |
¿µ¹®Á¦¸ñ(English Title) |
Performance Verification of Deep Learning based Transmit Power Control |
ÀúÀÚ(Author) |
ÀÌ¿õ¼·
±è¼ºÈ¯
·ùÁ¾¿
¹ÝÅ¿ø
Woongsup Lee
Seong Hwan Kim
Jongyeol Ryu
Tae-Won Ban
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 23 NO. 03 PP. 0326 ~ 0332 (2019. 03) |
Çѱ۳»¿ë (Korean Abstract) |
ÃÖ±Ù µö·¯´× ±â¼úÀÌ Å« °ü½ÉÀ» ¹ÞÀ¸¸ç ´Ù¾çÇÑ ºÐ¾ß¿¡ Àû¿ëµÇ°í ÀÖ´Ù. ƯÈ÷ ´Ù¾çÇÑ ¹«¼±Åë½Å±â¼ú¿¡ µö·¯´×À» Á¢¸ñÇÏ¿© ±âÁ¸ Åë½Å½Ã½ºÅÛÀÇ ÇѰ踦 ¶Ù¾î³ÑÀ¸·Á´Â ½Ãµµ°¡ ÀÌ·ç¾îÁö°í ÀÖ´Ù. º» ³í¹®¿¡¼´Â µö·¯´× ±â¹Ý ¹«¼±Åë½Å ½Ã½ºÅÛ ¼Û½ÅÀü·Â Á¶Àý¹æ¾ÈÀÇ ¼º´É°ËÁõÀ» ¼öÇàÇÏ¿´´Ù. µö·¯´× ±â¹Ý ¼Û½ÅÀü·Â Á¶Àý¹æ¾È¿¡¼´Â ¼öÇÐÀû ÃÖÀûÈ ¹®Á¦¸¦ Á÷Á¢ Ç®¾î¼ ÃÖÀûÀÇ Àü·ÂÀ» °áÁ¤ÇÏ´Â ±âÁ¸ ¹æ½Ä°ú ´Þ¸® ½ÉÃþ½Å°æ¸Á ±¸Á¶¸¦ ÇнÀ½ÃÄѼ ä³Î¿¡ µû¶ó ÃÖÀûÀÇ ¼Û½ÅÀü·ÂÀ» ã´Â General solver¸¦ µµÃâÇÏ¿© À̸¦ ÀÌ¿ëÇÑ´Ù. ƯÈ÷ ½Ã½ºÅÛÀÇ ÁÖÆļö È¿À²À» ½ÉÃþ½Å°æ¸Á ÇнÀÀÇ ¼Õ½ÇÇÔ¼ö·Î »ç¿ëÇÔÀ¸·Î½á ¶óº§¾øÀÌ ÇнÀÀ» °¡´ÉÄÉ ÇÑ´Ù. º» ³í¹®¿¡¼´Â Tensorflow ±â¹Ý ¼º´ÉºÐ¼®À» ÅëÇØ µö·¯´× ±â¹Ý ¼Û½ÅÀü·Â Á¶Àý¹æ¾È°ú ÃÖÀû¹æ¾ÈÀÇ ¼º´ÉÀÌ ÀÏÄ¡ÇÔÀ» º¸¿´°í, ¶ÇÇÑ Á¦¾È ¹æ¾ÈÀÌ ±âÁ¸ÀÇ ¹æ½Ä¿¡ ºñÇؼ 1/200ÀÇ °è»êº¹Àâµµ·Î ¼Û½ÅÀü·ÂÀ» ãÀ» ¼ö ÀÖÀ½À» º¸ÀÓÀ¸·Î½á ½ÇÁ¦ ¹«¼±Åë½Å½Ã½ºÅÛ¿¡¼ÀÇ Àû¿ë°¡´É¼ºÀ» °ËÁõÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Recently, the deep learning technology has gained lots of attention which leads to its application to various fields. Especially, there are recent attempts to overcome the limit of wireless communications systems through the use of the deep learning. In this paper, we have verified the performance of deep learning based transmit power control scheme. Unlike previous transmit power control schemes where the optimal transmit power is derived by solving the optimization problem explicitly, in the deep learning based transmit power control, the general solver for the optimization problem is derived through the deep neural network (DNN). Especially, by using the spectral efficiency as the loss function of DNN, the training can be performed without needing labels. Through simulation based on Tensorflow, we confirm that the transmit power control based on deep learning can achieve the optimal performance while reducing the computational complexity by 1/200.
|
Å°¿öµå(Keyword) |
µö·¯´×
Àü¼ÛÆÄ¿öÁ¶Àý
¹«¼±Åë½Å½Ã½ºÅÛ
ÃÖÀûÈ
°ËÁõ
Deep learning
Transmit power control
Wireless communication systems
Optimization
Verification
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|