基于遺傳算法的機(jī)會(huì)約束規(guī)劃區(qū)間估計(jì).pdf

1、西南交通大學(xué)碩士學(xué)位論文基于遺傳算法的機(jī)會(huì)約束規(guī)劃區(qū)間估計(jì)姓名：陳高波申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：應(yīng)用數(shù)學(xué)指導(dǎo)教師：劉海燕2003.3.1西南交通大學(xué)碩士研究生學(xué)位論文第1l頁(yè)AbstractStochasticprogrammingisanimportantbranchofmathematicalprogrammingHoweveritisverydifferentfromordinarymathematicalprogrammingHo

2、wtosolveitismuchmorecomplexthanthatofordinarymathematicalprogrammingbecauseofitsrandomcoefficientsThispapertriestostudystochastieprogramming，especiallychanceCOflstrfljnedprogrammingOffthetheoryofprobabilityandstatistiesA

3、tpresenttherearetwomainmethodstosolvingstochasticprogrammingThefirstistransformingitintoequivalentdeterministicprogrammingandthensolvingitbyusingthetheoryofdeterministicprogrammingthathasbeendevelopedsuccessfullyAnotheri

4、sgettingtheapproximateoptimumvalueandoptimumsolutionofchance—constrainedprogrammingthroughsomecertaingeneticalgorithmbasedonrandomsimulatedtechnologyThispapersummarizestwomethodsofchanceconstrainedprogrammingAccordingtot

5、hefirstmethod，thisarticlegeneralizesthecoefficienttypeofthosethatcanbetransformedintodeterministicprogrammingtoexponentialfamilyFormoregeneralchanceconstrainedprogramming。wehaveobtaineditsestimatedintervalandhavediscusse

6、dthefactorsthataffecttheprecisionofestimatedoptimumvalueandpointedoutthemethodthatraisesestimatedprecisionThisestimatedintervalcontainedanestimatedvalueofgoalfunctionInviewofthefactthatthegeneticalgorithmofstochasticprog

7、rammingbasedonrandomsimulatedtechnologyhassucceedgreatly，thispaperpointsoutthatchangingparametersofgeneticalgorithmcan曲tainasequenceofoptimumvaluesofgoalfunctionTakingthesegeneticalgorithmvaluesassamplingdata，wecangetfit

8、tingoptimumfunctionbyusingmultivariatesplineregressionandgettheLipschitzsconstantofthefittingoptimumfunctionSoforanychanceconstrainedprogrammingproblem，wecangetitsintervalestimatekeywords：StochasticProgramming，Chancecons