Reactive power optimization (RPO) is an important technique which is concerned with the security and economy of operation of a power system. It uses all the reactive power sources judiciously, while planning suitable location and size of VAr compensation in a system. With increasing fuel costs and capital investments, the economics of reactive power planning and scheduling have a tremendous effect on the profitable and reliable operation of a power system. One of the important operating tasks of electric power utilities is to keep the voltage within an allowable range for high quality customer services. Reactive power optimization, in addition to control of voltage in the power system, may have other advantages, such as reduction of real power losses and improvement of power factor. This paper presents evolutionary computation techniques such as genetic and particle swarm optimization algorithms for solving the nonlinear reactive power optimization problem. Voltage bus magnitude, transformer tap setting and the reactive power generation of capacitor banks are the control variables. The proposed algorithms have been applied to the standard IEEE 30-bus and 118-bus systems and they have been found to be more effective than existing methods.