強(qiáng)跟蹤濾波與小波分析理論在短期電力載荷預(yù)測(cè)中的應(yīng)用研究.pdf

1、杭州電子科技大學(xué)碩士學(xué)位論文強(qiáng)跟蹤濾波與小波分析理論在短期電力載荷預(yù)測(cè)中的應(yīng)用研究姓名：余利文申請(qǐng)學(xué)位級(jí)別：碩士專業(yè)：信號(hào)與信息處理指導(dǎo)教師：文成林20091101杭州電子科技大學(xué)碩士學(xué)位論文IIAbstractInautomaticcontrolaerospacecomputersciencewkmanagementpowersystemmanyotherfieldsofengineeringpracticesscientificre

2、searchesthefecastingestimationfromloadinghaveboththeeticalpracticalimptance.Theromloadingsignalsaregenerallynonstationarywhichcanbefurtherregardedasthesumofastationarysignalanunsteadysignal.Howeverthenonsteadypartisoften

3、influencedbyotherexternalunsteadyfactswhichaddsmanydifficultiestothefecastingestimationofthenonstationaryromloadingsignal.Toovercomethedifficultiesthefollowingresearchwksaredeveloped:(1)Onaccountoftheeffectsofsomeunstabl

4、eromfactsuchasweatherconditiononthemeasurementsoftheromloadingsignalsthemeasurementequationisremodeledasthenonlinearequationofstateparameters.Furthermethemodelofstateequationisnotaccurate.ThustheextendedKalmanfilter(EKF)

5、strongtrackingfilter(STF)arerespectivelyusedtoestimatethesystemloadtheinfluencefact.ThesimulationresultsarepresentedtoverifythattherealtimetrackingperfmanceofbreaksofstatesparametersofSTFisbetterthanthatofEKF.(2)Mostnons

6、tationaryromsignalsinpowerwkseconomicotherobservationsystemshaveanobviousperiodicity.Basedon(1)usingtheromwalkacteristicsoftheirwaveletcoefficientsanewalgithmnamedaswaveletSTFhybridestimationpredictionalgithmisdevelopedt

7、ofecastthepowerloadsignals.Thewaveletanalysisisintroducedtomakeamultiscaletransfmoftheromsignalssothattheobtainedsignalscanbedecomposedintomultiscalespace.Becausethenewalgithmcanupdateallstatevectsonthesameperiodbasedone

8、achmeasurementthepredictionaccuracylengthareimproved.Thesimulationresultsindicatethatthisalgithmisapplicablefshttermloadpredictionalsohasgoodrobustnesstomodeluncertaintyanexcellenttrackingcapabilityofthebreakofparameters