|
|
Çѱ¹¼öÀÚ¿øÇÐȸ / v.40, no.9, 2007³â, pp.677-685
|
´Ù¸ñÀû À¯ÀüÀÚ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ Tank ¸ðÇü ¸Å°³º¯¼ö ÃÖÀûÈ(I): ¹æ¹ý·Ð°ú ¸ðÇü±¸Ãà
( Optimization of Tank Model Parameters Using Multi-Objective Genetic Algorithm (I): Methodology and Model Formulation ) |
±èżø;Á¤ÀÏ¿ø;±¸º¸¿µ;¹è´öÈ¿; ¿¬¼¼´ëÇб³ »çȸȯ°æ½Ã½ºÅÛ°øÇкÎ;¼¼Á¾´ëÇб³ Åä¸ñȯ°æ°øÇаú;³²¿ø°Ç¼³¿£Áö´Ï¾î¸µ;¼¼Á¾´ëÇб³ ¹°ÀÚ¿ø¿¬±¸¼Ò.Åä¸ñȯ°æ°øÇаú;
|
|
|
 |
|
|
ÃÊ ·Ï |
º» ¿¬±¸ÀÇ ¸ñÀûÀº °³³äÀûÀÎ °¿ì-À¯Ãâ¸ðÇüÀÎ Tank ¸ðÇüÀÇ ¸Å°³º¯¼ö¸¦ »êÁ¤Çϱâ À§ÇÑ ´Ù¸ñÀû À¯ÀüÀÚ¾Ë°í¸®ÁòÀÇ Àû¿ë¼ºÀ» Æò°¡ÇÏ´Â °ÍÀÌ´Ù. ´Ù¸ñÀû À¯ÀüÀÚ¾Ë°í¸®Áò ±â¹ýÀ¸·Î´Â ÃÖ±Ù¿¡ °¡Àå ¸¹ÀÌ »ç¿ëµÇ´Â ±â¹ýÁßÀÇ ÇϳªÀÎ NSGA-II¸¦ äÅÃÇÏ¿© Tank ¸ðÇü°ú °áÇÕÇÏ¿´À¸¸ç, 4°¡Áö ¸ñÀûÇÔ¼ö(À¯Ãâ¿ëÀû¿ÀÂ÷, Æò±ÕÁ¦°ö±Ù ¿ÀÂ÷, °í¼öÀ¯·® Æò±ÕÁ¦°ö±Ù ¿ÀÂ÷ ¹× Àú¼öÀ¯·® Æò±ÕÁ¦°ö±Ù ¿ÀÂ÷)°ªÀ» ÃÖ¼ÒÈÇÏ´Â ÇüÅÂÀÇ ¸ñÀûÇÔ¼ö¸¦ Àû¿ëÇÏ¿´´Ù. NSGA-II´Â ¸ñÀûÇÔ¼öÀÇ °³¼ö°¡ ¸¹¾ÆÁö¸é ÇÑ ¹øÀÇ ½ÇÇà¿¡ ÀÇÇØ ±²ÀåÈ÷ ¸¹Àº ¼öÀÇ ÆÄ·¹ÅäÃÖÀûÇØ¸¦ ±¸ÇÏ´Â ´ÜÁ¡À» °¡Áö°í Àֱ⠶§¹®¿¡ ±¸ÇØÁø ÆÄ·¹ÅäÃÖÀûÇØ Áß¿¡¼ ¾î¶² ÇØ°¡ ÃÖ¿ì¼±ÇØ ÀÎÁö¸¦ °áÁ¤ÇØ¾ß ÇÒ Çʿ䰡 ÀÖÀ¸¸ç, ÀÌ·¯ÇÑ °íÂ÷¿øÀûÀÎ ÀÇ»ç°áÁ¤À» À§ÇÏ¿© ¼±È£Àû¼ø¼È(preference ordering) ±â¹ýÀ» Àû¿ëÇÏ¿´´Ù. NSGA-II¸¦ ÀÌ¿ëÇÏ¿© Tank¸ðÇüÀÇ ¸Å°³º¯¼ö¸¦ ÃßÁ¤ÇÒ ¶§ ÃʱâÁ¶°ÇÀÌ ÃÖÀûȰúÁ¤¿¡ ¹ÌÄ¥ ¼ö ÀÖ´Â ¿µÇâÀ» ÃÖ¼ÒÈÇϱâ À§ÇØ ¼¼´ë¼ö(generation number)¿Í °³Ã¼±ºÀÇ Å©±â(population size)¿¡ ´ëÇÑ ¹Î°¨µµºÐ¼®À» ¼öÇàÇÏ¿´´Ù. ºÐ¼®°á°ú Tank¸ðÇüÀÇ ¸Å°³º¯¼ö ÃÖÀûȸ¦ À§ÇÑ ¼¼´ë¼ö¿Í °³Ã¼±º Å©±âÀÇ Ãʱ⠰ªÀ» °¢°¢ 900¹ø°ú 1000°³·Î ¼±Á¤ÇÏ´Â °ÍÀÌ ÀûÇÕÇÑ °ÍÀ¸·Î ³ªÅ¸³µ´Ù. |
|
The objective of this study is to evaluate the applicability of multi-objective genetic algorithm(MOGA) in order to calibrate the parameters of conceptual rainfall-runoff model, Tank model. NSGA-II, one of the most imitating MOGA implementations, is combined with Tank model and four multi-objective functions such as to minimize volume error, root mean square error (RMSE), high flow RMSE, and low flow RMSE are used. When NSGA-II is employed with more than three multi-objective functions, a number of Pareto-optimal solutions usually becomes too large. Therefore, selecting several preferred Pareto-optimal solutions is essential for stakeholder, and preference-ordering approach is used in this study for the sake of getting the best preferred Pareto-optimal solutions. Sensitivity analysis is performed to examine the effect of initial genetic parameters, which are generation number and Population size, to the performance of NSGA-II for searching the proper paramters for Tank model, and the result suggests that the generation number is 900 and the population size is 1000 for this study. |
|
Ű¿öµå |
´Ù¸ñÀû À¯ÀüÀÚ¾Ë°í¸®Áò;ÅÊÅ©¸ðµ¨;¼±È£Àû¼ø¼È;ÆÄ·¹Åä ÃÖÀûÈ;¹Î°¨µµ ºÐ¼®;Multi-objective genetic algorithm;Tank model;Preference ordering;Pareto optimal solution;Sensitivity analysis; |
|
|
|
 |
|
Çѱ¹¼öÀÚ¿øÇÐȸ³í¹®Áý / v.40, no.9, 2007³â, pp.677-685
Çѱ¹¼öÀÚ¿øÇÐȸ
ISSN : 1226-6280
UCI : G100:I100-KOI(KISTI1.1003/JNL.JAKO200734515981412)
¾ð¾î : Çѱ¹¾î |
|
³í¹® Á¦°ø : KISTI Çѱ¹°úÇбâ¼úÁ¤º¸¿¬±¸¿ø |
|
|
|
|
|