Nowadays, generation and consumption points are constantly increasing in parallel with the increasing energy demand and power systems are rapidly growing. However, it is very important to plan, install and operate the power systems in a way that ensures safe, efficient and continuous operation. For this purpose, especially load flow analysis and also other analysis methods such as protection-coordination, constraints, stability, short circuit etc. are employed for power systems. In this study, the comparison of Gauss-Seidel, Newton-Raphson and Fast Decoupled methods, commonly used in load flow analysis has been made according to the number of iterations, the computation time, the total line losses and the produced and consumed active and reactive power considering different tolerance values. As the test systems, IEEE 6-, 14, 30- and 57-bus power systems have been used in the Matlab environment. In consequence of the load flow analyses conducted, the minimum number of iterations and the minimal power loss have been achieved by the Newton-Raphson method, while the power produced by generators according to load demands on the buses has been computed close to each other for all three methods.