A Hierarchical Recursive Method for Substantially Improving Trending of Small Area Load Forecasts

Abstract

A spatially recursive technique for structuring the trending of a small area load forecast is described. The method employs trending of more than just the individual small area loads. Computer implementation of the technique is simple and straightforward, and requires only slightly more computer time and memory than previous trending methods, while maintaining the low data requirements and ease of use common to such techniques. Forecasts obtained using the new method have only from one half to one fourth of the error of forecasts obtained from other trending methods.