Machine learning applications for load, price and wind power prediction in power systems

This paper reviews main forecasting techniques used for power system applications. Available forecasting techniques have been discussed with focus on electricity load and price forecasting as well as wind power prediction. Forecasting problems have been classified based on time frame, application specific area and forecasting techniques. Appropriate examples based on data pertaining to the Victorian electricity market, Australia and the PJM electricity market, U.S.A. are used to demonstrate the functioning of the developed neural network (NN) method based on similar days approach to predict hourly electricity load and price, respectively. The other important problem faced by power system utilities are the variability and non-schedulable nature of wind farm power generation. These inherent characteristics of wind power have both technical and commercial implications for efficient planning and operation of power systems. To address the wind power issues, this paper presents the application of an Adaptive Neural Fuzzy Inference System (ANFIS) to very short-term wind forecasting utilizing a case study from Tasmania, Australia. © 2009 IEEE.