Document Type

Conference Proceeding

Language

eng

Publication Date

2017

Publisher

International Institute of Forecasters

Source Publication

International Symposium on Forecasting

Abstract

Marquette University’s GasDay Project specializes in short-term load forecasting of natural gas demand. Traditionally, this forecasting is done using artificial neural networks and linear regression. This paper examines the viability of using DNNs as component models in the GasDay ensemble. The ensemble of interest is evaluated using weighted MAPE on 88 natural gas data sets and compared to the current GasDay ensemble. The DNN-enhanced ensemble performs better on this metric than the current ensemble.

Comments

Published version. Published as part of the proceedings of the International Symposium on Forecasting, 2017. Publisher link. © The Authors. Used with permission.

Share

COinS