كاربرد ماشين هاي بردار پشتيبان در پيش بيني جريان ورودي مخازن و عملكرد بهينه آن

چكيده انگليسي :

Application of Support Vector Machines SVM for Reservoir Inflow Prediction and Optimized Operation Hesam Kiani h kyani@cv iut ac ir 6 May 2009 Department of Civil Engineering Isfahan University of Technology Isfahan 84156 83111 IranDegree M Sc Language FarsiDr Keyvan Asghari kasghari@cc iut ac ir AbstractThis investigation presents a new method for real time forecasting in operation of reservoirs Potential impacts ofclimate variability on hydrology and consequently its influence on water resource systems planning such asreservoir operations is the core of this research The central part of Iran water system and supplying its waterdemands is highly dependent on a short seasonal precipitation and hence has great potential to suffer fromunbalanced distribution of both demand and supply sides of water Reservoirs in this region are the main waterstructures to reduce the shortages and help to balance the monthly water needs based on limited supply Historical data indicates that the region is susceptible to hydrological drought periods where consecutive years ofbelow average annual streamflow occur A developed integrated data driven simulation method with anevolutionary optimization algorithm constituted a hybrid model to determine suitable reservoir operating policiesduring uncertain periods Reservoir operation is evaluated under different climate conditions and the impacts ondownstream water needs are investigated Using the Harmony Search HS algorithm the optimal strategy forreservoir releases are determined based on actual monthly inflows for different climatic conditions SupportVector Machines SVMs method for regression modeling is applied as a state of the art modeling tool Theproposed methodology is applied to Zayandeh rud reservoirs system and the application explored the model saccuracy and its potential for real time prediction of reservoir monthly releases for adaptive planning andmanagement Based on the research objectives two real time operating models are developed in which the fundamentaldifferences are in the consideration of climate variation Effective information to train suggested models includeinflow runoff monthly demand and initial volume of reservoirs In terms of accuracy and generalizationperformances both models non climatic and climatic approaches indicate very small RMSE and closeagreement between training and testing phases of modeling Considering particular variables in the input vector to identify the climatic features of the system reduces the RMSE and hence the improvement of modelforecasting To compare the performances of the proposed methodologies with the results of previous studyusing average ruled curve method of operation monthly releases forecasted by SVM models were simulated forperiod of 44 years and the results indicated 15 and 11 percent improvement for climatic and non climaticapproached respectively of meeting the demands over the average ruled curve situation Key WordsReservoir real time operation Climate variability Support Vector Machines HarmonySearch

كياني فلاورجاني، حسام

كاربرد ماشين هاي بردار پشتيبان در پيش بيني جريان ورودي مخازن و عملكرد بهينه آن

بهره برداري , سيستم چند مخزنه , جستجوي هارموني , مدل بهره برداري اقليمي