A Regional Demand Forecast by NN Method for Distributed Autonomous Voltage and Reactive Power Control System

Abstract

This paper describes technology required for advanced intelligent voltage and reactive secondary control systems enabling co-ordination of voltage control between main and local power systems. Firstly, the paper describes the general structure of a power system control and the concept of a proposed autonomous voltage and reactive power control system. Then, the paper comments on the inadequate behavior of voltage and reactive power control systems, such as up-and-down fluctuations, which sometimes occur during off-peak load times, and explains the reasons for voltage fluctuations. The capacity of distributed generation is increasing in accordance with deregulation of electric supply. In order to enhance voltage stability of power system, the voltage control system requires the more detail information and data of its local network systems, such as local demand forecast, distributed generation and characteristics of power systems. The paper briefly describes two previously developed intelligent component functions, namely, flexible feed forward control to prevent voltage fluctuation, and on-line acquisition of voltage characteristics by neural network technology. The paper describes local demand forecasting one or two hours in advance by the NN method. This method is also applicable to the forecast of the total demand of a power system.