High-resolution peak demand estimation using generalized additive models and deep neural networks

This paper covers predicting high-resolution electricity peak demand features given lower-resolution data.This is a relevant setup as it answers whether limited higher-resolution monitoring helps to estimate future high-resolution peak loads when the high-resolution data is no longer available.That question is particularly interesting for network operators considering replacing high-resolution monitoring by predictive models due to economic considerations.We propose models to predict half-hourly minima and maxima of high-resolution(every minute)electricity load data while model inputs are of a lower resolution(30 min).We combine predictions of generalized additive models(GAM)and deep artificial neural networks(DNN),which are popular in load forecasting.We extensively analyze the prediction models,including the input parameters’importance,focusing on load,weather,and seasonal effects.The proposed method won a data competition organized by Western Power Distribution,a British distribution network operator.In addition,we provide a rigorous evaluation study that goes beyond the competition frame to analyze the models’robustness.The results show that the proposed methods are superior to the competition benchmark concerning the out-of-sample root mean squared error(RMSE).This holds regarding the competition month and the supplementary evaluation study,which covers an additional eleven months.Overall,our proposed model combination reduces the out-of-sample RMSE by 57.4%compared to the benchmark.

Improvement of the prediction accuracy of polar motion using empirical mode decomposition

Previous studies revealed that the error of pole coordinate prediction will significantly increase for a prediction period longer than 100 days, and this is mainly caused by short period oscillations. Empirical mode decomposition （EMD）, which is increasingly popular and has advantages over classical wavelet decomposition, can be used to remove short period variations from observed time series of pole co- ordinates. A hybrid model combing EMD and extreme learning machine （ELM）, where high frequency signals are removed and processed time series is then modeled and predicted, is summarized in this paper. The prediction performance of the hybrid model is compared with that of the ELM-only method created from original time series. The results show that the proposed hybrid model outperforms the pure ELM method for both short-term and long-term prediction of pole coordinates. The improvement of prediction accuracy up to 360 days in the future is found to be 24.91% and 26.79% on average in terms of mean absolute error （MAE） for the xp and yp components of pole coordinates, respectively.