Research Information System
Thesis Type: Postgraduate
Institution Of The Thesis: Gazi Üniversitesi, Fen Bilimleri Enstitüsü, Turkey
Approval Date: 2019
Student: GÖKHAN AYDOĞDU
Supervisor: OKTAY YILDIZ
Open Archive Collection: AVESIS Open Access Collection
Abstract:The purpose of planning electric energy systems is to provide quality and cheap electrical energy to consumers by foreseeing the process needs of electrical energy from production to consumption. The determination of these needs is crucial to ensure that the plans meet the requirements and prevent inadequate or inefficient investments. With this study, it is aimed to show the importance of electricity demand forecasts and models, analyze the demand forecasts generated by experimental studies and official demand forecasts produced by public institutions in Turkey and compare the results between the models based on the projections and the results of the forward time demand forecast. In this study, the importance of electrical energy, planning in electrical systems and methods of forecasting electrical energy demand are emphasized. In the experimental study conducted, yearly peak load and electrical energy consumption of Turkey and its provinces are estimated. For these forecasts, multivariable regression analysis, time series and artificial neural networks methods are used. While creating the models with these methods, the validity of the models with the past-time estimations of the created models was questioned and the most suitable model was selected and the future instantaneous peak load and electricity energy consumption estimations were made. The data obtained from the estimates made are compared with the official estimates. The maximum, minimum and mean absolute error values that occurred in the testing of the models are also calculated.