Abstract :The importance of energy demand continues to rise in parallel with the increasing population, urbanization, the spread of industry and technology. Load estimations higher than electricity demand cause too many power supply units to activate, initiating excessive energy intake and providing unnecessary reserves. Conversely, lower load forecasts may cause the system to operate in a risky region, resulting in insufficient supply reserves. At the same time, load forecasts form the basis of many decisions made in energy markets. Electric energy prices optimized according to load estimation results; It allows electricity markets to be planned and operated in an efficient, transparent, reliable manner and to meet the needs of the sector. In this study, the instantaneously peak electricity load was estimated using Artificial Neural Network and Linear Regression Methods. Gross domestic product, exports, imports, and population are used as based on input values from 1980 to 2019 to analyze these methods. Artificial Neural Network and Linear Regression Methods are among the methods frequently used in the literature. The results obtained using Artificial Neural Network and Linear Regression Methods were analyzed using statistical errors such as MAE, RMSE, and MSE. Keywords : Electricity Load Forecasting, Artificial Neural Network, Linear Regression Method
