Distribution electricity network planning needs consolidated regional and national views of predicted future loads. A power utility established load forecasting tool requires load profile data that will be used in calculating coincidence factors between loads of different classes and sub-classes as per economic activity and geospatial location. Regional industrial and commercial electricity load profile subclass models were developed for planning using clustering, geospatial significance testing and a BIC (Bayesian information criterion) technique to trade-off regional subclass complexity with overall profile model accuracy.
展开▼
