Daily Natural Gas Load Forecasting Based on a Hybrid Deep Learning Model

Nan Wei,Jinyuan Liu,Fanhua Zeng,Changjun Li,Jiehao Duan

doi:10.3390/en12020218

Nan Wei, Jinyuan Liu + Show 3 more

Open Access

https://doi.org/10.3390/en12020218

Copy DOI

Journal: Energies	Publication Date: Jan 11, 2019
Citations: 31	License type: CC BY 4.0

Affiliation: Southwest Petroleum University, University of Regina

Abstract

Forecasting daily natural gas load accurately is difficult because it is affected by various factors. A large number of redundant factors existing in the original dataset will increase computational complexity and decrease the accuracy of forecasting models. This study aims to provide accurate forecasting of natural gas load using a deep learning (DL)-based hybrid model, which combines principal component correlation analysis (PCCA) and (LSTM) network. PCCA is an improved principal component analysis (PCA) and is first proposed here in this paper. Considering the correlation between components in the eigenspace, PCCA can not only extract the components that affect natural gas load but also remove the redundant components. LSTM is a famous DL network, and it was used to predict daily natural gas load in our work. The proposed model was validated by using recent natural gas load data from Xi’an (China) and Athens (Greece). Additionally, 14 weather factors were introduced into the input dataset of the forecasting model. The results showed that PCCA–LSTM demonstrated better performance compared with LSTM, PCA–LSTM, back propagation neural network (BPNN), and support vector regression (SVR). The lowest mean absolute percentage errors of PCCA–LSTM were 3.22% and 7.29% for Xi’an and Athens, respectively. On these bases, the proposed model can be regarded as an accurate and robust model for daily natural gas load forecasting.

Highlights

Natural gas load forecasting (NGLF) is an essential procedure for policy makers and related organizations within a natural gas system
The results presented that the long short-term memory (LSTM)-based model received a lower mean absolute error (MAE) and root-mean-square error (RMSE) compared with artificial neural network (ANN) as well as other reference models, such as physical models
Affect natural load network, and reduce the redundant can automatically extract the components that affect natural gas load and the factors existing in the original dataset

Summary

Introduction

Natural gas load forecasting (NGLF) is an essential procedure for policy makers and related organizations within a natural gas system. Without accurate load forecasts, additional expenses due to uneconomic dispatch, over/under purchasing, and reliability uncertainty can cost a utility millions of dollars [1]. Many companies, organizations, and governments worldwide have already progressed the NGLF with versatile aspects [2]. Forecasted the natural gas demand of the United States, finding that it could be 26.55 trillion cubic feet as of 2035 and that the annual energy demand would increase by 0.7% [3]. Natural gas load is an important carrier in the energy mix and its accurate forecasting is of great significance to natural gas systems

Objectives

Results

Conclusion