Short-Term Electric Load Forecasting Using Echo State Networks and PCA Decomposition Article Swipe

PDF

Related Concepts

Term (time) Echo state network Computer science Series (stratigraphy) Autoregressive integrated moving average Curse of dimensionality Time series Electric power system Autoregressive model Autoregressive–moving-average model Artificial neural network Electrical load Decomposition Lag Power (physics) Recurrent neural network Artificial intelligence Mathematics Statistics Machine learning Computer network Physics Biology Paleontology Ecology Quantum mechanics

Filippo Maria Bianchi , Enrico De Santis , Antonello Rizzi , Alireza Sadeghian ·

YOU? · · 2015 · Open Access · · DOI: https://doi.org/10.1109/access.2015.2485943 · OA: W1908962573

In this paper we approach the problem of forecasting a time-series of electrical load measured on the ACEA power grid, the company managing the electricity distribution in the city of Rome – Italy, with an Echo State Network considering two different leading times of 10 minutes and 1 day. We use a standard approach for predicting the load in the next 10 minutes while, for a forecast horizon of one day, we represent the data with a high dimensional multi-variate time-series, where the number of variables is equal to the quantity of measurements registered in a day. Through the orthogonal transformation returned by PCA decomposition, we reduce the dimensionality of the TS to a lower number k of distinct variables: this allow us to cast the original prediction problem in k different 1-step ahead predictions. The overall forecast can be effectively managed by k distinct prediction models, whose outputs are combined together to obtain the final result. We employ a genetic algorithm for tuning the parameters of the Echo State Network and we compare its prediction accuracy with a standard ARIMA model.