Improvement of Short-Term Load Forecasting by Bag-of-Words Representation

Short term load forecasting (STLF) plays an essential role for reliable and economic operation of a power system. In general, the accuracies of the STLF algorithms are dependent on the representation of the input raw data. This paper proposes to use Bag of Words (BoW) model as the data representation to achieve improved accuracy of STLF. As verified in the experiments, the proposed representation of time series load data can drastically improve various STLF algorithms for a microgrid system --- a rather challenging case for load forecasting due to its smaller capacity and higher randomness.