|
|
|
Çѱ¹¼öÀÚ¿øÇÐȸ / v.36, no.2, 2003³â, pp.195-209
|
Ãß°èÇÐÀû¸ðÇü°ú ½Å°æ¸Á¸ðÇüÀ» ¿¬°èÇÑ º´·ÄÀú¼öÁö±ºÀÇ À¯ÀÔ·®»êÁ¤
( Streamflow Estimation using Coupled Stochastic and Neural Networks Model in the Parallel Reservoir Groups ) |
| ±è¼º¿ø; µ¿¾ç´ëÇб³ Áö±¸È¯°æ½Ã½ºÅÛ°øÇаú;
|
|
|
 |
|
| |
| ÃÊ ·Ï |
| º» ¿¬±¸¿¡¼´Â ³«µ¿° »ó·ùÀ¯¿ªÀÇ º´·Ä ´Ù¸ñÀû´ï±ºÀÎ ¾Èµ¿ ¹× ÀÓÇÏ´Ù¸ñÀû ´ïÀÇ Àå±â°£ À¯ÀÔ·®À» »êÁ¤Çϴµ¥ °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀÌ »ç¿ëµÇ¾ú´Ù. °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀº ¿ªÀüÆÄ ¾Ë°í¸®ÁòÀ¸·Î LMBP¿Í BFGS-QNBP¸¦ °¢°¢ »ç¿ëÇÏ¿´´Ù. °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀÇ ±¸Á¶´Â ÀÔ·ÂÃþ, Àº´ÐÃþ ¹× Ãâ·ÂÃþÀÇ 3°³ÀÇ Ãþ°ú Â÷·Ê´ë·Î 8-8-2°³ÀÇ ³ëµå·Î ±¸¼ºµÇ¾î ÀÖ´Ù. ÀÔ·ÂÃþ ³ëµå´Â ¾Èµ¿ ¹× ÀÓÇÏ´Ù¸ñÀû ´ïÀÇ ¿ùÆò±ÕÀ¯ÀÔ·®, ¿ù¸éÀû°¿ì·®, ¿ùº° Áõ¹ßÁ¢½Ã Áõ¹ß·®°ú ¿ùÆò±Õ±â¿ÂÀ¸·Î ±¸¼ºµÇ¾î ÀÖÀ¸¸ç, ÀÚ·á½Ã°è¿Àº ½Ã°£ÀûÀ¸·Î Â÷À̰¡ ÀÖ´Ù. °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀÇ ÈÆ·ÃÀ» À§ÇÏ¿© Ãß°èÇÐÀû ¸ðÇüÁß ÇϳªÀÎ PARMA(1,1)¿¡ ÀÇÇØ¼ ÈÆ·ÃÀڷḦ ¸ðÀǹ߻ý½ÃÄ×À¸¸ç, ¸ðÀǹ߻ýµÈ ÀÚ·á´Â °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀÇ ÈÆ·Ã¿¡ »ç¿ëµÇ¾ú´Ù. ÈÆ·ÃÀ» ÅëÇÏ¿© °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀÇ ¸Å°³º¯¼öÀÎ ÃÖÀû¿¬°á°µµ¿Í ÆíÂ÷¸¦ »êÁ¤ÇÏ¿´´Ù. »êÁ¤µÈ ¸Å°³º¯¼ö´Â ¾Èµ¿ ¹× ÀÓÇÏ´Ù¸ñÀû ´ïÀÇ ½ÇÃøÀڷḦ ÀÌ¿ëÇÏ¿© °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀÇ °ËÁõ¿¡ ÀÌ¿ëµÇ¾úÀ¸¸ç, Åë°èºÐ¼®°ú ¼ö¹®°î¼±ÀÇ ºñ±³¸¦ ÅëÇÏ¿© ¿ì¼öÇÑ °á°ú¸¦ ³ªÅ¸³»¾ú´Ù. µû¶ó¼ °ø°£Ãß°è ½Å°æ¸Á¸ðÇüÀº ³«µ¿° »ó·ùÀ¯¿ªÀÇ º´·ÄÀú¼öÁö±ºÀÇ Àå±â°£ ¿¬°è¿î¿µ±â¹ý °³¹ßÀ» À§ÇÏ¿© ±âÃÊÀûÀÎ ÀڷḦ Á¦°øÇϰí, ¿ë¼öºÐ¹è ¹× °ü¸®¿¡ µµ¿òÀ» ÁÙ °ÍÀÌ´Ù. |
|
| Spatial-Stochastic Neural Networks Model(SSNNM) is used to estimate long-term streamflow in the parallel reservoir groups. SSNNM employs two kinds of backpropagation algorithms, based on LMBP and BFGS-QNBP separately. SSNNM has three layers, input, hidden, and output layer, in the structure and network configuration consists of 8-8-2 nodes one by one. Nodes in input layer are composed of streamflow, precipitation, pan evaporation, and temperature with the monthly average values collected from Andong and Imha reservoir. But some temporal differences apparently exist in their time series. For the SSNNM training procedure, the training sets in input layer are generated by the PARMA(1,1) stochastic model and they covers insufficient time series. Generated data series are used to train SSNNM and the model parameters, optimal connection weights and biases, are estimated during training procedure. They are applied to evaluate model validation using observed data sets. In this study, the new approaches give outstanding results by the comparison of statistical analysis and hydrographs in the model validation. SSNNM will help to manage and control water distribution and give basic data to develop long-term coupled operation system in parallel reservoir groups of the Upper Nakdong River. |
| |
| Ű¿öµå |
| °ø°£Ãß°è ½Å°æ¸Á¸ðÇü;º´·Ä Àú¼öÁö±º;Spatial-Stochastic Neural Networks Model;PARMA(1,1);LMBP;BFGS-QNBP;parallel reservoir groups;PARMA(1,1);LMBP;BFGS-QNBP; |
| |
|
|
 |
|
Çѱ¹¼öÀÚ¿øÇÐȸ³í¹®Áý / v.36, no.2, 2003³â, pp.195-209
Çѱ¹¼öÀÚ¿øÇÐȸ
ISSN : 1226-6280
UCI : G100:I100-KOI(KISTI1.1003/JNL.JAKO200311921617958)
¾ð¾î : Çѱ¹¾î |
|
| ³í¹® Á¦°ø : KISTI Çѱ¹°úÇбâ¼úÁ¤º¸¿¬±¸¿ø |
|
|
|
|
|
|