Chaos-theoretic methods for load forecasting in the field of energy management systems
Sprache des Titels:
Power Systems Computation Conference (PSCC), Dresden, Germany, Aug 19-23
In modern signal analysis, chaos-theoretic methods, are becoming more and more popular. This paper introduces a new method based on information theory and applies this method to analyzing load profiles. Useful information such as the theoretical measure of predictability and the most significant past information can be extracted from the data alone without building a model. The results are compared to a regression model for load forecasting.