Indexing
All Issues
Submission
Author Guidelines
Reviewers
Editorial Members
Publication Fee
Vol.5 , No. 3, Publication Date: Sep. 3, 2018, Page: 20-29
 <i>vis-à-vis</i> randomly-varying, daily electric-power demand in a service area. Relevantly, the method pursued uses an artificial neural network (ANN) in prescribing the said RLC within a cone-of-error (specified between a pair of stochastic bounds). Pertinent modeling and approach use a set of available (case-study) data; and, the closeness of the RLC deduced is cross-verified against relevant (existing) results derived <i>via</i> fuzzy K-mean method. The study concludes on adopting the bound-specified RLC towards formulating pertinent tariff considerations within a range of error-bar. The alternative ANN-approach proposed here has been found to produce accurate results close to FKM-results. However, it is an improvement over the FKM method in that the RLC is specified within a cone-of-error, accounting duly for the associated stochastic implications with the load-curve profile. Thus, rather than yielding a rigid RLC (yielding a rigid tariff policy), any tariff policy derived by this ANN-based method combined with stochastical bounds will have the judicious basis of technoeconomics of the utility in question. The method proposed here is novel and not hitherto done; and leads to optimal integrated planning for electricity towards load-demand <i>versus</i> tariffication decisions.&picture=http://www.aascit.org/aascit/decorators/img/journal/925.jpg)
| [1] | Dolores De Groff, College of Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA. |
| [2] | Roxana Melendez, College of Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA. |
| [3] | Perambur Neelakanta, College of Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA. |
This paper is specific to the background of ad hoc predictive modeling of electric power-distribution and related tariff issues by deducing objectively, a representative load-curve (RLC) vis-à-vis randomly-varying, daily electric-power demand in a service area. Relevantly, the method pursued uses an artificial neural network (ANN) in prescribing the said RLC within a cone-of-error (specified between a pair of stochastic bounds). Pertinent modeling and approach use a set of available (case-study) data; and, the closeness of the RLC deduced is cross-verified against relevant (existing) results derived via fuzzy K-mean method. The study concludes on adopting the bound-specified RLC towards formulating pertinent tariff considerations within a range of error-bar. The alternative ANN-approach proposed here has been found to produce accurate results close to FKM-results. However, it is an improvement over the FKM method in that the RLC is specified within a cone-of-error, accounting duly for the associated stochastic implications with the load-curve profile. Thus, rather than yielding a rigid RLC (yielding a rigid tariff policy), any tariff policy derived by this ANN-based method combined with stochastical bounds will have the judicious basis of technoeconomics of the utility in question. The method proposed here is novel and not hitherto done; and leads to optimal integrated planning for electricity towards load-demand versus tariffication decisions.
Keywords
Representative Load Curve, Artificial Neural Network, Smart-Grid, Load Distribution, Stochastical Error Bounds
Reference
| [01] | B. Phan. “Representative Load Curve and the Tariff Impact Analyzing”, American Journal of Energy and Power Engineering, Vol. 2, No. 5, pp. 51-55, 2015. |
| [02] | G. E. P. Box, G. M. Jenkins. Time Series Analysis, Forecasting and Control, Holden-Day. San Francisco, Calif. 1970. |
| [03] | G. Chicco, R. Napoli, P. Postolache, M. Scutariu and C. Toader, “Customer Characterization Options for Improving the Tariff Offer”, IEEE Trans Power Syst., Vol 18, No. 1, pp. 381-387, Feb. 2003. |
| [04] | B. Efron, “Bootstrap Methods: Another Look at the Jackknife”, Annals of Statistics, Vol 7, No. 1, pp. 1 – 26, 1979. |
| [05] | P. S. Neelakanta, D. De Groff, Neural Network Modeling: Statistical Mechanics and Cybernetic Perspectives, CRC Press. Boca Raton, Fl. 1994. |
| [06] | D. De Groff, P. S. Neelakanta, “Faster Convergent Artificial Neural Networks”, International Journal of Computers and Technology, Vol. 17, No. 1, pp. 7126-7132, 2018. https://cirworld.com/index.php/ijct/article/view/7106 |
| [07] | N. Alabbas, J. Nyangon, “Weather-based Long-term Electricity Demand Forecasting Model for Saudi Arabia: A Hybrid Approach Using End-use and Econometric Methods for Comprehensive Demand Analysis”, Proceedings of USAEE, pp. 1 – 20, 2016. http://www.usaee.org/usaee2016/submissions/OnlineProceedings/9699-AlabbasN.pdf |
| [08] | V. A. Venikov, Cybernetics in Electric Power Systems, Mir Publishers, Moscow, 1978. |
| [09] | Australian Energy Market Operator (AEMO), “Forecasting Methodology Information Paper”, 2012 National Electricity Forecasting Report, 2012. http://www.aemo.com.au/-/media/Files/Electricity/NEM/Planning_and_Forecasting/NEFR/2012/Forecasting-Methodology-Information-Paper---2012-NEFR---Final.pdf |
| [10] | B. Dong, Z. Li, S. M. M. Rahman, R. Vega, “A Hybrid Model Approach for Forecasting Future Residential Electricity Consumption”, Energy and Buildings, Vol. 117, No. 1, pp. 341-351, 2016. https://www.sciencedirect.com/science/article/pii/S0378778815302735?via%3Dihub |
| [11] | “IEEE P2030 Draft-guide for Smart-grid Interoperability of Energy technology and Information Technology Operation With the Electric Power System (EPS), and End-use Applications and Loads”, Connectivity Week, PAR Approved, under IEEE SCC21, March 19, 2009. |
| [12] | N. Phuangpornpitak, S. Tia, “Opportunities and Challenges of Integrating Renewable Energy in Smart Grid System”, Energy Procedia, Vol. 34, 282-290, 2013. |
| [13] | M. S. Thomas, J. D. McDonald Power System SCADA and Smart Grids, CRC Press: Taylor & Francis group, Boca Raton, FL. 2015. |
