A Multi-level Artificial Neural Network for Gasoline Demand Forecasting of Iran

Kazemi, Aliyeh; Ganjavi, Hamed Shakouri; Menhaj, Mohammadbagher; Mehregan, Mohammad Reza; Taghizadeh, M. R.; Asl, Amir Foroughi

doi:10.1109/iccee.2009.118

Cited by 11 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks have been applied to various problems such as classification, optimization, pattern recognition, forecasting, clustering and function approximation. In the field of energy, to mention just a few, ANNs have been successfully used to forecast; economic dependence between town development policy and increasing energy effectiveness in Poland (Skiba, Mrówczyńska and Bazan-Krzywoszańska, 2017), available ramp up and down capacity of a virtual power plant (Macdougall et al , 2017), annual transport energy demand in Iran (Kazemi et al , 2010), long-term energy consumption in Greece (Ekonomou, 2010), thermohydraulics of advanced nuclear heat exchangers in USA (Ridluan et al , 2009) and future annual electricity demand in Turkey (Günay, 2016). Achievements in these and other areas suggest that ANN models could serve as a valuable add-on to the toolkits of economists and econometricians (Kuan and White, 1994).…”

Section: Methodsmentioning

confidence: 99%

Deploying artificial neural networks for modeling energy demand: international evidence

Bannor

Acheampong

2019

IJESM

View full text Add to dashboard Cite

Purpose This paper aims to use artificial neural networks to develop models for forecasting energy demand for Australia, China, France, India and the USA. Design/methodology/approach The study used quarterly data that span over the period of 1980Q1-2015Q4 to develop and validate the models. Eight input parameters were used for modeling the demand for energy. Hyperparameter optimization was performed to determine the ideal parameters for configuring each country’s model. To ensure stable forecasts, a repeated evaluation approach was used. After several iterations, the optimal models for each country were selected based on predefined criteria. A multi-layer perceptron with a back-propagation algorithm was used for building each model. Findings The results suggest that the validated models have developed high generalizing capabilities with insignificant forecasting deviations. The model for Australia, China, France, India and the USA attained high coefficients of determination of 0.981, 0.9837, 0.9425, 0.9137 and 0.9756, respectively. The results from the partial rank correlation coefficient further reveal that economic growth has the highest sensitivity weight on energy demand in Australia, France and the USA while industrialization has the highest sensitivity weight on energy demand in China. Trade openness has the highest sensitivity weight on energy demand in India. Originality/value This study incorporates other variables such as financial development, foreign direct investment, trade openness, industrialization and urbanization, which are found to have an important effect on energy demand in the model to prevent underestimation of the actual energy demand. Sensitivity analysis is conducted to determine the most influential variables. The study further deploys the models for hands-on predictions of energy demand.

show abstract

Section: Methodsmentioning

confidence: 99%

Deploying artificial neural networks for modeling energy demand: international evidence

Bannor

Acheampong

2019

IJESM

View full text Add to dashboard Cite

show abstract

“… Energy demands: The demand constraints are generated for each sector to ensure that the energy outputs from the demand technologies are greater than or equal to the demands of end users. The actual demand for total energy, petroleum products, natural gas, and electricity for each sector is predicted by using the neural networks and linear regression models based on socioeconomic indicators :

\begin{matrix} x_{sr} (T) + x_{or} (T) + x_{gr} (T) + x_{er} (T) \geq {\tilde{D}}_{r} (T) & x_{or} (T) \geq {\tilde{D}}_{or} (T) x_{gr} (T) \geq {\tilde{D}}_{gr} (T) x_{er} (T) \geq {\tilde{D}}_{er} (T) x_{oi} (T) + x_{gi} (T) + x_{ei} (T) \geq {\tilde{D}}_{i} (T) x_{oi} (T) \geq {\tilde{D}}_{oi} (T) x_{gi} (T) \geq {\tilde{D}}_{gi} (T) x_{ei} (T) \geq \end{matrix}

…”

Section: Energy Supply Model Of Iranmentioning

confidence: 99%

A fuzzy linear programming model for allocation of oil and gas resources in iran with the aim of reducing the greenhouse gases

Kazemi

Shakouri

Mehregan

et al. 2012

Env Prog and Sustain Energy

Self Cite

View full text Add to dashboard Cite

Energy plays a key role in sustainable development. Formulation of an energy model will help in the proper allocation of available energy resources. The objective of this article is to allocate optimally to each end user a certain amount of energy to be supplied by a given resource in Iran to reduce greenhouse gases. For this purpose, energy demands of end users are forecasted, and the outcomes are used in a fuzzy linear programming model, which determines the best allocation of energy resources in Iran from 2012 to 2020. The result shows a large portion of crude oil and natural gas will be allocated for exports. Transportation sector will be the major consumer of the petroleum products. Higher amounts of natural gas compared with the petroleum products will be allocated to power plants. Moreover, a considerable portion of natural gas should be injected into the oil reservoirs. These analyses would provide scientific basis for the optimal allocation of energy resources in meeting the future energy demand in Iran. © 2012 American Institute of Chemical Engineers Environ Prog, 32: 854–859, 2013

show abstract

“…Causal models utilize least-square fitting method to extract forecasted load demand in terms of its determinants e.g., temperature, humidity and lagged data [23]. Different casual methods e.g., linear regression (LR) [24], non-linear regression (NLR) [25,26,27,28,29], Logistic or logit regression (LoR) [30] were widely utilized in the literature.…”

Section: Introductionmentioning

confidence: 99%

ParDeeB: A Graph Framework for Load Forecasting Based on Parallel DeepNet Branches

2021

View full text Add to dashboard Cite

Recently, energy demand forecasting has emerged as a significant area of research because of its prominent impact on greenhouse gases (GHGs) emission and global warming. The problems of load forecasting are characterized by complex and nonlinear nature and also long-term historical dependency.Up to now, several approaches from statistical to computational intelligent have been applied in this research filed. The literature agrees with the fact that deep learning approach is more capable in dealing with these characteristics among existing approaches. However, the recent state-of-the-art deep network models are not robust against different historical dependency. In this

show abstract

A Multi-level Artificial Neural Network for Gasoline Demand Forecasting of Iran

Cited by 11 publications

References 12 publications

Deploying artificial neural networks for modeling energy demand: international evidence

Deploying artificial neural networks for modeling energy demand: international evidence

A fuzzy linear programming model for allocation of oil and gas resources in iran with the aim of reducing the greenhouse gases

ParDeeB: A Graph Framework for Load Forecasting Based on Parallel DeepNet Branches

Contact Info

Product

Resources

About