پديد آورنده :
مشار ي، امير
عنوان :
پيش بيني كوتاه مدت بار به كمك شبكه هاي عصبي با پالايش داده هاي غير عادي و ارائه يك مدل مناسب براي روزهاي تعطيل
مقطع تحصيلي :
كارشناسي ارشد
محل تحصيل :
اصفهان : دانشگاه صنعتي اصفهان ، دانشكده برق و كامپيوتر
صفحه شمار :
ده ،209 ، [II] ص .: مصور ، جدول ، نمودار
يادداشت :
ص. ع. به فارسي و انگليسي
استاد راهنما :
اكبر ابراهيمي ، سعيد صدري
توصيفگر ها :
پرسپترون , روش PCAF
تاريخ نمايه سازي :
10/5/86
دانشكده :
مهندسي برق و كامپيوتر
چكيده فارسي :
به فارسي و انگليسي : قابل رويت در نسخه ديجيتال
چكيده انگليسي :
AbstractThere are two main sources that produce anomalous load profiles and introduce error inShort Term Load Forecasting in power systems anomalous situation in power system suchas various contingencies of overload and interruptions imposed load shedding voltagecollapse etc and the shortcomings of operators in manual recording data without error Inthis thesis with precise examination of load profiles in a real power system variousmethods of filtering anomalous data is used and a new method based on PrincipalComponent Analysis PCA is suggested that can be used efficiently to recognize unusualprofiles Then a Short Term Load Forecasting system STLF is designed according to theFeed Forward Neural Networks FFNN and its various parameters are optimally tuned byerror sensitivity analysis To fulfill minimum error and simplicity of implementation several models are presented and the model with proper precision and less error is selected It is shown that elimination of temperature input does not make considerable error in theforecasted loads Independence of the algorithm to temperature data can be considered asan advantage of the procedure Special load profile and small number of patterns in data cause high error rate inforecasting the load profile in holidays Accordingly in this thesis to forecast load profilefor these days a proper procedure is presented The result indicates that it has acceptableperformance and reasonable precision
استاد راهنما :
اكبر ابراهيمي ، سعيد صدري
