Optimal Electric-Power Distribution and Load-Sharing on Smart-Grids: Analysis by Artificial Neural Network

  • Dolores De Groff Florida Atlantic University
  • Roxana Melendez Florida Atlantic University
  • Perambur Neelakanta Florida Atlantic University
  • Hajar Akif
Keywords: Artificial neural network, Backpropagation algorithm, Load-sharing, Smart-grid, Electric-power grid


This study refers to developing an electric-power distribution system  with optimal/suboptimal load-sharing in the complex and expanding metro power-grid infrastructure.  That is, the relevant exercise is to indicate a smart forecasting strategy on optimal/suboptimal power-distribution to consumers served by a smart-grid utility.  An artificial neural network (ANN) is employed to model the said optimal power-distribution between generating sources and distribution centers.  A compatible architecture of the test ANN with ad hoc suites of training/prediction schedules is indicated thereof. Pertinent exercise is to determine smartly the power supported on each transmission-line  between generating to distribution-nodes.  Further, a “smart” decision protocol prescribing  the constraint that no transmission-line carries in excess of a desired load.  An algorithm is developed to implement the prescribed constraint via the test ANN; and, each value of the load  shared by each distribution-line  (meeting the power-demand of the consumers) is elucidated from the ANN output. The test ANN includes the use of a traditional multilayer architecture with feed-forward and backpropagation techniques; and,  a fast convergence algorithm (deduced in terms of eigenvalues of a Hessian matrix associated with the input data) is adopted. Further, a novel method based on information-theoretic heuristics (in Shannon’s sense) is invoked towards model specifications. Lastly, the study results are discussed with exemplified computations using appropriate field data.    


Download data is not yet available.

Author Biographies

Dolores De Groff, Florida Atlantic University

Dolores De Groff, Ph.D., is Associate Professor of Computer and Electrical Engineering & Computer Science at Florida Atlantic University in Boca Raton.

She received her Ph.D. in Electrical Engineering from Florida Atlantic University in 1993. She has received several teaching awards from the same institution, coauthored a book in the neural network area and authored/coauthored other journal articles and conference papers.




Roxana Melendez, Florida Atlantic University

Roxana Melendez holds a Master of Electrical Engineering from Florida Atlantic University and is a Ph.D. candidate at the same institution.  She received her Bachelor of Electrical Engineering from the Universidad del Norte, Colombia and Specialist in Engineering Project Management from Pontificia Universidad Javeriana, Colombia.  She was a full time faculty at Palm Beach State College in the area of Engineering Technology and has other teaching and industry experience.

Perambur Neelakanta, Florida Atlantic University


Perambur S. Neelakanta is Professor of Computer and Electrical Engineering & Computer Science at Florida Atlantic University in Boca Raton.


Dr. Perambur S. Neelakanta received the Ph.D. (electrical engineering) degree in 1975 from the Indian Institute of Technology (IIT), Madras, India.  He had been a faculty member at the Indian Institute of Science, Indian Institute of Technology (Madras), University of Science, Penang (Malaysia), National University of Singapore and the University of South Alabama, Mobile, Alabama, USA.  Also, he was a Research Fellow at Technical University, Aachen, Germany and the Director of Research at RIT Research Corporation, Rochester, NY, USA.  He is currently a Professor of Computer and Electrical Engineering & Computer Science at Florida Atlantic University, Boca Raton, FL., USA.   Dr. Neelakanta has published extensively  and has authored several books  including,  “Neural Network Modeling” (with Dr. De Groff as the co-author).

Hajar Akif

Hajar Akif received the B. S. degree  in electrical engineering (Summa Cum Laude) from Florida Atlantic University, Boca Raton, in Dec. 2017.  She received numerous scholarships and academic awards while attending the same institution.  Her research interests include radar, artificical neural networks, and power systems. 


She now is employed as a transmission engineer for Florida Power & Light Co. in Jupiter, Florida. 


1. Borberly, A., Kreider, J. D., Distributed Generation: The Power Paradigm for the New Millennium. CRC Press, Boca Raton, Fl. 2001.
2. Neelakanta, P. S., Yassin, R., “A Co-evolution of Competitive Mobile Platforms: Technoeconomic Perspectives”, Journal of Theoretical and Applied Electronic Commerce Research, Vol. 6, Issue 2, pp. 31-49, 2011.
3. Shannon, C. E., “A Mathematical Theory of Communication”, The Bell System Technical Journal, Vol. 27, pp. 379-423, 623-656, 1948.
4. Efron, B., “Bootstrap Methods: Another Look at the Jackknife”, Annals of Statistics, Vol 7, No. 1, pp. 1-26, 1979.
5. Neelakanta, P. S., De Groff, D., 1994. Neural Network Modeling: Statistical Mechanics and Cybernetic Perspectives. CRC Press, Boca Raton.
6. 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
How to Cite
De Groff, D., Melendez, R., Neelakanta, P., & Akif, H. (2019). Optimal Electric-Power Distribution and Load-Sharing on Smart-Grids: Analysis by Artificial Neural Network. INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 18, 7431-7439. https://doi.org/10.24297/ijct.v18i0.8059