Clustering based day-ahead and hour-ahead bus load forecasting models

Abstract

The importance of Short-Term Load Forecasting (STLF) in power systems planning and management is reflected by the plethora of the related researches. STFL is a popular technical field in the power systems community and already counts many years of research activities and applications. The vast majority of the studies focus at the aggregated system load. Little attention is placed at small size loads, i.e. in buses of the transmission and distribution systems. Since there is a continuous advancement of smart grids technologies involving small size loads, bus STLF is a potentially important tool in smart grid applications. In contrast to system load, bus load presents a high level of stochasticity. Thus a robust forecaster should be able to capture and simulate the attributes of bus loads. The scope of the study is to develop bus forecasting models for day-ahead and hour-ahead load predictions. The models are based on Artificial Neural Networks (ANNs). Using a clustering methodology, the forecasting accuracy of the ANNs is enhanced leading to the formulation of hybrid forecasting models that are characterized by high level of parameterization and efficiency. The developed models are tested on a set of buses covering urban, sub-urban and industrial loads.