بهره برداري بهنگام و ترتيبي مخزن با استفاده از الگوريتم جستجوي هارموني و سيگنال بزرگ مقياس اقليمي

چكيده انگليسي :

Hybrid Modeling of Sequential Reservoir Operation using Large Scale Climate Signals Mohammad Kiani Falavarjani m kiani@cv iut ac ir Date of Submission 2011 06 25 Department of Civil Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language FarsiSupervisor Dr keyvan asghari kasghari@cc iut ac ir AbstractDevelopment and capacity expansion of water infrastructures such as reservoirs is part of challengesauthorities face in meeting the regional water needs Another part of this challenge and the essential one isthe management and operation of water resources systems After a serious depletion of alternative waterresources such as groundwater the most important sources of water in most countries including Iran isthe water which is supplied from dam reservoirs Operational management of these water reservoirs as acomplex system is very critical and needs careful attention in order to guarantee the sustainability of watersupply in severe conditions In this research a hybrid method has been presentedwhich enables us to introduce alternative optimizedscenario for future planning and also to have a real time time operation ofreservoir systems Combination ofseveral soft computational methods has been employed to demonstrate the competency of these techniques HarmonySearch algorithm HS and SupportVector Machines SVM are the two main approaches foroptimization of reservoir releases and forecasting of the inflow to reservoir and ultimately determining areal time strategy for operation of a reservoir HS algorithm is one of the new methods of optimizationwhich is based on its successful and remarkable performance in recent years compare to other meta heuristic optimization techniques SVM method based on structural risk minimization principlehas beenintroduced as a powerful method for learning processes and forecasting phenomenon In addition themutual information MI has been used to select the efficient and reliable parameters within immenseamount of large scale regional signals to forecast the annual inflows Regional signals can be considered asparameters and indicators when their changes in terms of time in different stations show the changes inrainfall and temperature which will happen in another time or another place The proposed methodology is applied to Zayandehrud reservoir and the application explored the model saccuracy and its potential for real time prediction of reservoir monthly releases for adaptive planning andmanagement Besides the runoff from the Zayandeh rud basin diverted flow from neighboring basinscontribute to the reservoir inflows This reservoir is the main water structure to reduce the shortages andhelp to balance the monthly water needs based on limited supply in the region Historical data indicate thatthe region is susceptible to hydrological drought periods where consecutive years of below average annualstreamflow occur Fifty six years 1954 2009 of monthly inflow data were used for this study The results from forecasting modeling indicate closeness of the calculated error of the models in trainingand testing periodsand show the high generalization competence The optimized model is sequential whichmeans that after every three months results are updated and oldend of the year reservoirvolume iscorrected The process is repeated every three months to determine the optimized monthly outflow till endof the year Using three performance criteria reliability resiliency and vulnerability the goodness ofresults were examined

كياني فلاورجاني، محمد

بهره برداري بهنگام و ترتيبي مخزن با استفاده از الگوريتم جستجوي هارموني و سيگنال بزرگ مقياس اقليمي

پيش بيني بلند مدت , ماشين هاي بردار پشتيبان