Forecasting Natural Gas Consumption using ARIMA Models and Artificial Neural Networks

Cardoso, Carlos Alberto Villacorta; Cruz, Gustavo Lima

doi:10.1109/tla.2016.7530418

Cited by 32 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is especially important when forecasting multiple time series with different behaviour (such as nodes in the gas network representing different demands of suppliers, industrial or residential customers) since hybrid models enhance the advantages of the individual approaches. [20][21][22] It is important to notice that, although the traditional statistical and machine learning models generally have good forecast accuracy in real-world data applications, they often neglect the information available in the spatial-temporal correlations of high-dimensional, complex gas network data. Moreover, the prediction performances of traditional methods depend profoundly on feature engineering, which usually requires expert experience in the corresponding field.…”

Section: Related Workmentioning

confidence: 99%

“…Many research studies showed that hybrid models (combining or ensembling) improve performance and robustness of forecast relative to individual forecast models. This is especially important when forecasting multiple time series with different behaviour (such as nodes in the gas network representing different demands of suppliers, industrial or residential customers) since hybrid models enhance the advantages of the individual approaches 20‐22 …”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning for spatio‐temporal supply and demand forecasting in natural gas transmission networks

Petković

Koch

Zittel

2021

Energy Science & Engineering

View full text Add to dashboard Cite

Germany is the largest market for natural gas in the European Union, with an annual consumption of approx. 95 billion cubic meters. The German high‐pressure gas pipeline network's length is roughly 40 000 km, which enables highly fluctuating quantities of gas to be transported safely over long distances. Considering that similar amounts of gas are also transshipped through Germany to other EU states, it is clear that Germany's gas transport system is essential to the European energy supply. Since the average velocity of gas in a pipeline is only 25 km/h, an adequate high‐precision, high‐frequency forecasting of supply and demand is crucial for efficient control and operation of such a transmission network. We propose a deep learning model based on spatio‐temporal convolutional neural networks (DLST) to tackle the problem of gas flow forecasting in a complex high‐pressure transmission network. Experiments show that our model effectively captures comprehensive spatio‐temporal correlations through modeling gas networks and consistently outperforms state‐of‐the‐art benchmarks on real‐world data sets by at least 15%. The results demonstrate that the proposed model can deal with complex nonlinear gas network flow forecasting with high accuracy and effectiveness.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Deep learning for spatio‐temporal supply and demand forecasting in natural gas transmission networks

Petković

Koch

Zittel

2021

Energy Science & Engineering

View full text Add to dashboard Cite

show abstract

“…Zhang et al, used a least squares wavelet support vector machine (LSSVM) to obtain prediction parameters [15]. Villacorta et al, used the autoregressive integrated moving average model (ARIMA) time series forecasting model to predict the wind power time series data [16]. These methods have the advantages of a fast calculation speed, good estimation effect in nonlinear systems, and high accuracy [17,18].…”

Section: The Maximum Likelihood Estimationmentioning

confidence: 99%

Short-Term Direct Probability Prediction Model of Wind Power Based on Improved Natural Gradient Boosting

Wang

2020

Energies

View full text Add to dashboard Cite

Wind energy has been widely used in renewable energy systems. A probabilistic prediction that can provide uncertainty information is the key to solving this problem. In this paper, a short-term direct probabilistic prediction model of wind power is proposed. First, the initial data set is preprocessed by a box plot and gray correlation analysis. Then, a generalized method is proposed to calculate the natural gradient and the improved natural gradient boosting (NGBoost) model is proposed based on this method. Finally, blending fusion is used in order to enhance the learning effect of improved NGBoost. The model is validated with the help of measured data from Dalian Tuoshan wind farm in China. The results show that under the specified confidence, compared with the single NGBoost metamodel and other short-term direct probability prediction models, the model proposed in this paper can reduce the forecast area coverage probability while ensuring a higher average width of prediction intervals, and can be used to build new efficient and intelligent energy power systems.

show abstract

“…Reference [17] studied ARIMA models for forecasting natural gas consumption in Turkey on monthly basis. Reference [18] shows the daily basis forecasting for local distribution companies using ARIMA models and Artificial Neural Network. Reference [19] generate forecasting models for dynamic relationships among several potentially relevant time series variables.…”

Section: Related Workmentioning

confidence: 99%

Comparative Analysis of Univariate Forecasting Techniques for Industrial Natural Gas Consumption

Naim¹,

Mahara²

2018

IJIGSP

View full text Add to dashboard Cite

This paper seeks to evaluate the appropriateness of various univariate forecasting techniques for providing accurate and statistically significant forecasts for manufacturing industries using natural gas. The term "univariate time series" refers to a time series that consists of single observation recorded sequentially over an equal time interval. A forecasting technique to predict natural gas requirement is an important aspect of an organization that uses natural gas in form of input fuel as it will help to predict future consumption of organization.We report the results from the seven most competitive techniques. Special consideration is given to the ability of these techniques to provide forecasts which outperforms the Naive method. Naï ve method, Drift method, Simple Exponential Smoothing (SES), Holt method, ETS(Error, trend, seasonal) method, ARIMA, and Neural Network (NN) have been studied and compared.Forecasting accuracy measures used for performance checking are MSE, RMSE, and MAPE. Comparison of forecasting performance shows that ARIMA model gives a better performance.

show abstract

Forecasting Natural Gas Consumption using ARIMA Models and Artificial Neural Networks

Cited by 32 publications

References 8 publications

Deep learning for spatio‐temporal supply and demand forecasting in natural gas transmission networks

Deep learning for spatio‐temporal supply and demand forecasting in natural gas transmission networks

Short-Term Direct Probability Prediction Model of Wind Power Based on Improved Natural Gradient Boosting

Comparative Analysis of Univariate Forecasting Techniques for Industrial Natural Gas Consumption

Contact Info

Product

Resources

About