An approach for metering real-time reactive power consumption using a neural network approach

Abstract

The current research focus on the spot pricing of electricity has led to development of complex spot pricing-based electricity rate models. As research matures to implementation stages, approaches to meter the actual power consumption in real-time are required. In this work, the authors model a real-time reactive power metering approach based on neural networks. A spot pricing model which incorporates the shortcomings of power factor penalties is used to determine the reactive power rates at each bus. A carefully designed artificial neural network (ANN) is trained to recognize the complex optimal operating point of an all-thermal electricity generating utility. A real time rate is allocated to each bus for a given power system's loading pattern and the recall process is instantaneous. The proposed approach is tested using a spot pricing model on 5 and 14 bus electric power systems. Different loading levels are used at each bus.