Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model

Panapakidis, Ioannis P.; Dagoumas, Athanasios

doi:10.1016/j.energy.2016.12.033

Cited by 192 publications

(96 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The next year peak gas consumption was estimated at 83.14 GWh, which is approximately 13% lower than the 95,7 GWh determined by the mentioned standard. Panapakidis and Dagoumas [52] have examined the stability of a new hybrid model to predict the consumption one day in advance. The envisioned algorithm includes WT (GA), ANFIS, and FFNN.…”

Section: Prediction Accuracy Of Selected Applied Models In the Periodmentioning

confidence: 99%

Application of Predictive Models for Natural Gas Needs - Current State and Future Trends Review

et al. 2020

View full text Add to dashboard Cite

Nowadays, in terms of trading on the world scale, to foresee a natural gas consumption represents an essential activity. In the first part, the paper examines the current state of the Serbian natural gas sector and methodology applied for prediction and capacity planning. In addition, the study intends to give a comprehensive assessment of predictive algorithms for natural gas needs involved in the last decade with projections and suggestions for future applications. The primary task is to evaluate used predictive models with an emphasis on the accuracy of the predictions obtained. Additionally, the paper will analyse used parameters, consumption scale, prediction scope, forecast algorithms, and other related information. The main objective of this study is to review the new-fangled information related analyses data from peer-reviewed journals, international conferences, and books.

show abstract

Section: Prediction Accuracy Of Selected Applied Models In the Periodmentioning

confidence: 99%

Application of Predictive Models for Natural Gas Needs - Current State and Future Trends Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Market participants make decisions by considering the contingency of natural gas demand (U-tapao et al 2016;Zeng and Li 2016;Zhuang and Gabriel 2008). Panapakidis and Dagoumas (2017) forecast demand for natural gas based on a combination method of wavelet transform and an adaptive neuro-fuzzy inference system (ANFIS). Behrooz et al (2017) used an unscented transform to characterize the demand uncertainty in dynamic planning models of natural gas network.…”

Section: Indicesmentioning

confidence: 99%

Study of the impacts of upstream natural gas market reform in China on infrastructure deployment and social welfare using an SVM-based rolling horizon stochastic game analysis

Wang

McLellan

et al. 2018

Pet. Sci.

View full text Add to dashboard Cite

Natural gas is expected to play a much more important role in China in future decades, and market reform is crucial for its rapid market penetration. At present, the main gas fields, pipelines and liquefied natural gas (LNG) infrastructure are mainly monopolized by large state-owned companies, and one of the important market reform policies is to open up LNG import rights to smaller private companies and traders. Therefore, in the present study, a game theoretical model is proposed to analyze and compare the impacts of different market structures on infrastructure deployment and social welfare. Moreover, a support vector machine-based rolling horizon stochastic method is adopted in the model to simulate real LNG price fluctuations. Four market reform scenarios are proposed considering different policies such as business separation, third-party access (TPA) and their combinations. The results indicate that, with third-party access (TPA) entrance into the LNG market, the construction of LNG infrastructure will be promoted and more gas will be provided at lower prices, and thus the total social welfare will be improved greatly.Keywords LNG market reform Á Market structure Á Third-party access Á Rolling horizon stochastic method Á Game theory Abbreviations DP Domestic gas field producer LI Original LNG importer LT Subsequent LNG trader

show abstract

“…The online state estimators are mostly developed based on filter models (Durgut and Leblebicioğlu, 2016), which are applied to estimate the real time state of pipeline networks. Applications of machine learning for forecasting natural gas demands have drawn great attention from both research and practice perspectives (Panapakidis and Dagoumas, 2017;Yu and Xu, 2014). Many algorithms have been developed to predict natural gas demand over different time horizons.…”

Section: Introductionmentioning

confidence: 99%

A systematic hybrid method for real-time prediction of system conditions in natural gas pipeline networks

Zio

Zhang

et al. 2018

Journal of Natural Gas Science and Engineering

View full text Add to dashboard Cite

et al.. A systematic hybrid method for real-time prediction of system conditions in natural gas pipeline networks. A B S T R A C TThe current framework of management of natural gas pipeline systems, based on off-line simulation, is facing challenges because of the increasing complexity, uncertainty and a number of time-dependent factors. To be effective, it requires comprehensive knowledge of system characteristics, accurate initial and boundary conditions. In an attempt to circumvent these problems, in this work we propose to use the deep learning method in the natural gas transmission system operation and management context. A data-driven prediction method is developed from real-time data of operation pressure and gas consumption. Specifically, the deep learning method is combined with the data window method and structural controllability theory to predict the conditions of gas pipeline network components. The data window method is applied to reconstruct the data structure and build a "memory" for the deep learning method. Structural controllability theory is applied to extract critical parameters, for reducing the problem size. The developed method allows accurate and efficient predictions, especially in abnormal conditions. For demonstration, the method is applied to a complex gas pipeline network. The results show that the developed method can provide accurate real-time predictions useful for reducing potential losses in operation, and perform efficient and effective management of the gas pipeline system. In the case study, the average prediction accuracy is higher than 0.99.

show abstract

Day-ahead natural gas demand forecasting based on the combination of wavelet transform and ANFIS/genetic algorithm/neural network model

Cited by 192 publications

References 21 publications

Application of Predictive Models for Natural Gas Needs - Current State and Future Trends Review

Application of Predictive Models for Natural Gas Needs - Current State and Future Trends Review

Study of the impacts of upstream natural gas market reform in China on infrastructure deployment and social welfare using an SVM-based rolling horizon stochastic game analysis

A systematic hybrid method for real-time prediction of system conditions in natural gas pipeline networks

Contact Info

Product

Resources

About