Improved estimation of electricity demand function by using of artificial neural network, principal component analysis and data envelopment analysis

Kheirkhah, Amir Saman; Azadeh, A.; Saberi, Morteza; Azaron, Amir; Shakouri, H.

doi:10.1016/j.cie.2012.09.017

Cited by 72 publications

(52 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They conclude inefficient utilities can adopt and develop strategic plans to improve performance. For an extensive review on applications of DEA on electricity distribution systems the reader is referred to Santos et al [55], Jamasb and Pollitt [33], Reyes and Tovar [53], Doraisamy [21], Kheirkhah et al [39] and de Souza et al [20].…”

Section: Literature Review On Electricity Distribution Efficiency Meamentioning

confidence: 99%

A framework for establishing the technical efficiency of Electricity Distribution Counties (EDCs) using Data Envelopment Analysis

Mullarkey

Caulfield

McCormack

et al. 2015

Energy Conversion and Management

View full text Add to dashboard Cite

Section: Literature Review On Electricity Distribution Efficiency Meamentioning

confidence: 99%

A framework for establishing the technical efficiency of Electricity Distribution Counties (EDCs) using Data Envelopment Analysis

Mullarkey

Caulfield

McCormack

et al. 2015

Energy Conversion and Management

View full text Add to dashboard Cite

“…ANNs and other soft computing techniques have been successfully applied to different real world problems including industrial engineering and energy management (e.g., Miranda et al 1998;Pino et al 2000Pino et al , 2008Annunziato et al 2004Annunziato et al , 2006Tien Pao 2007;Srinivasan 2008;Tsujimura et al 1997;Abdel-Aal 2008;Moghrabi and Eid 1998;Currie 1992;Daim et al 2010;Pizzuti et al 2013;Annunziato et al 2013;Najafzadeh et al 2013;Najafzadeh and Lim 2014;Najafzadeh and Azamathulla 2013a, b;Kaydani et al 2014;Najafzadeh et al 2012Najafzadeh et al , 2014a. ANNs have been used to predict the electricity demand in different countries such as Taiwan (Hsu and Chen 2003), Ireland (Ringwood et al 2001), Spain (Catalao et al 2007), Saudi Arabia (Abdel-Aal 2008), and Iran (Azadeh et al 2007(Azadeh et al , 2008aKheirkhah et al 2013). Support vector machine (SVM) is another soft computing technique that has been successfully applied to predict the electric consumption (Fan and Chen 2006;Hong 2009).…”

Section: Introductionmentioning

confidence: 99%

Towards estimation of electricity demand utilizing a robust multi-gene genetic programming technique

2015

View full text Add to dashboard Cite

Multi-gene genetic programming (MGGP) is a new nonlinear system modeling approach that integrates the capabilities of standard genetic programming and classical regression. This paper deals with the application of this robust technique for the prediction of annual electricity demand in Thailand. The predictor variables included in the analysis were population, gross domestic product, stock index, and total revenue from exporting industrial products. Several statistical criteria were used to verify the validity of the model. A sensitivity analysis was performed to evaluate the contributions of the input features. The correlation coefficients between the measured and predicted electricity demand values are equal to 0.999 and 0.997 for the calibration and testing data sets, respectively. In addition to its high accuracy, MGGP outperforms regression and other powerful soft computing-based techniques.

show abstract

“…Several TD studies have proposed different methods for modeling the residential and commercial energy, gas, and electricity demands. The works are mostly based on regression and auto-regressive models (Donatos and Mergos 1991;Hsing 1994;Lam 1998;Aras and Aras 2004;Zhang 2004;Ziramba 2008;Kialashaki and Reisel 2013;Soldo et al 2013;Catalina et al 2008Catalina et al , 2013Overcash and Bawaneh 2013;Pourazarm and Cooray 2013), time series analysis (Saad 2009;Dilaver and Hunt 2011;Taspınar et al 2013), panel cointegration (Narayan et al 2007;Nakajima and Hamori 2010), and neural networks (Kazemi et al 2010;Kheirkhah et al 2013;Kialashaki and Reisel 2013;Bilgili et al 2012;Soldo et al 2013;Taspınar et al 2013;Rodger 2014). For linear models to be identified, a sort of well-known methods from the ordinary least squares (OLS) to the prediction error method (PEM) (Ljung 1987) is widely and easily applicable.…”

Section: Introductionmentioning

confidence: 99%

Selection of the best ARMAX model for forecasting energy demand: case study of the residential and commercial sectors in Iran

Shakouri

Kazemi

2015

Energy Efficiency

View full text Add to dashboard Cite

The main purpose of the present study is to develop a simple yet proper top-down model for forecasting the energy demand of the residential and commercial sectors in Iran. This model can be used as a tool of scenario analysis to predict the emerging energy demand in future. The proposed model would be systematically developed and selected based on various quantified exogenous variables. For this purpose, a certain model out of a collection of 41,472 parallel models with different inputs and dynamics is chosen as the most appropriate model. According to the logical conjunctive relationships between the variables, the structure of all competing models is established to log-linear. Different possible combinations of various measures for the exogenous variables generate parallel models. Then, an automated fuzzy decision-making (FDM) process determines the best model. Finally, defining several scenarios, the energy demand of the residential and commercial sectors in Iran for the period of 2013 to 2021 is forecasted. The results showed that despite of desubsidization, which is included by a dummy variable, the energy demand will grow by an average rate of about 3 % annually. Keywords Energy demand forecasting . Model selection . Fuzzy decision making . Residential and commercial sectors Abbreviations AAEP Average absolute error percentage BIRR Bilion Iranian Rials BLD Book value of active buildings [10 4 BIRR] BU Bottom-up D Differencing operator DC Dynamicity criterion or the property index for the dynamics of a model DUM Dummy variable ER Energy consumption by the residential and commercial sectors [MTOE] FIT Fitness of simulation FPE Akaike's final prediction error GT The global Student t statistics HNT Household number [million persons] HVAC Heating, ventilation, and air conditioning INVC Gross fixed capital formation (investment) for the constructions [10 4 BIRR] JB Jarque-Bera tests of normality KBLD Cumulative sum of BLD [10 4 BIRR] KCD The same variable (KCT) calculated considering a 5 % annual depreciation rate KCT Total capital invested for buildings (constructions) [10 4 BIRR] Energy Efficiency

show abstract

Improved estimation of electricity demand function by using of artificial neural network, principal component analysis and data envelopment analysis

Cited by 72 publications

References 45 publications

A framework for establishing the technical efficiency of Electricity Distribution Counties (EDCs) using Data Envelopment Analysis

A framework for establishing the technical efficiency of Electricity Distribution Counties (EDCs) using Data Envelopment Analysis

Towards estimation of electricity demand utilizing a robust multi-gene genetic programming technique

Selection of the best ARMAX model for forecasting energy demand: case study of the residential and commercial sectors in Iran

Contact Info

Product

Resources

About