Short Term Load Forecasting Using Deep Neural Networks
Abstract
Electricity load forecasting plays an important role in the energy planning such as generation and distribution. However, the nonlinearity and dynamic uncertainties in the smart grid environment are the main obstacles in forecasting accuracy. Deep Neural Network (DNN) is a set of intelligent computational algorithms that provide a comprehensive solution for modelling a complicated nonlinear relationship between the input and output through multiple hidden layers. In this paper, we propose DNN based electricity load forecasting system to manage the energy consumption in an efficient manner. We investigate the applicability of two deep neural network architectures Feed-forward Deep Neural Network (Deep-FNN) and Recurrent Deep Neural Network (Deep-RNN) to the New York Independent System Operator (NYISO) electricity load forecasting task. We test our algorithm with various activation functions such as Sigmoid, Hyperbolic Tangent (tanh) and Rectifier Linear Unit (ReLU). The performance measurement of two network architectures is compared in terms of Mean Absolute Percentage Error (MAPE) metric.
Cite
@article{arxiv.1811.03242,
title = {Short Term Load Forecasting Using Deep Neural Networks},
author = {Faisal Mohammad and Ki Boem Lee and Young-Chon Kim},
journal= {arXiv preprint arXiv:1811.03242},
year = {2018}
}
Comments
6 pages, 8 figures, International Symposium on Information Technology Convergence 2018, South Korea