Share
تبؤ الاحمال الكهربائية للشبكة العراقية للمدة القصيرة باعتماد نظام المنطق الضبابي == Short - Term Electrical Load Forecasting For Iraqi Power System Based On Fuzzy Logic System
Author name:
هدى منهي عبد العباس
Supervisor name:
Firas Mohammed Tuaimah
General topic:
Electrical, Electronic and Communications Engineering
Specific topic:
Electrical Engineering
Degree:
Master
University:
University of Baghdad - College Of Engineering - Department Of Electrical Engineering
Language:
English
University location:
Baghdad
First pages:
34T495 - p.pdf
Abstract:
Load forecasting is used by participants in electric energy generation, transmission, distribution, and marketing for a variety of decision - making processes, such as economic dispatch, unit commitment, hydro - thermal coordination, transaction evaluation, and expansion planning. However, the need for accurate forecasts has intensified in the last decade due to the energy industry deregulation. Taking this into account as well as the rapid fluctuations in demand and abrupt changes in weather condition, access to reliable models for accurate forecast of load demand is essential. Due to the need for accurate load forecasts, numerous statistical and artificial intelligence methods have been proposed for the short - term load forecasting problem.In this study, the Multiple Linear Regression (MLR) method, which is one of the statistical methods, and an Interval Type - 2 Takagi - Sugeno - Kang Fuzzy Logic System (IT - 2 TSK FLS), which is one of the artificial methods and an extension of the conventional fuzzy logic system, were applied. Developed models were trained using the genetic algorithm. With the purpose of an objective assessment, the available dataset was split into training samples (80%, ????????????) and test samples (20%, ??????????). The training data used in this study covered the period from January 1, 2012 to February 1, 2012 for winter season and the period from July 1, 2012 to August 1, 2012 for summer season. The actual load forecasting period started from January 22, till 28, 2012 for winter model and from July 22 till 28, 2012 for summer model.This work suggested two models; the first model was for hourly (24 hour) load forecasting for one day ahead and the second model was for one week ahead in hourly forecasting (from one until 168 hour). For each model, winter and summer seasons were presented. The Main average percentage error (MAPE) term is an index that provides information about the bias of the model and how close forecasts or predictions are to the eventual outcomes. Experiments conducted with real datasets for the Iraqi power system showed that IT2 TSK FLS models precisely approximated future load demands with an acceptable accuracy.The real data for Iraqi power system were taken from Iraqi Operation and Control Office which belongs to the Ministry of Electricity.A computer program, written in MATLAB programming languages, was developed to represent the proposed method.
