SELECTING A PREFERRED ELECTRICAL SUPPLY SYSTEM DEVELOPMENT SOLUTION BASED ON NEURAL NETWORKS TECHNOL-OGY
DOI:
https://doi.org/10.14529/power180305Keywords:
development of electrical networks, decision support systems, multi-criteria evaluation system, neural networksAbstract
The decision on the development of electrical supply systems is based on the analysis of a large amount of information, comparison of multiple options, and the evaluation of the solution long-term impact.
This complicates the selection process for the alternative to the development of the electrical network (ADEN). Thus an automated decision support system, facilitating the determination of the preferred ADEN, is required.
The article presents the selection procedure for the mathematical apparatus to solve the specified task, and substantiates its characteristics. It is suggested to use the technology of artificial neural networks (ANN), based on the developed multi-criteria system for estimating ARES, which allows ranking the alternatives based on
the degree of their preference. The architecture of the ANN, the algorithm for optimizing weights, and their efficiency at various parameters are substantiated. The F-measure and the percentage of correctly accepted decisions were selected as efficiency indicators. They amounted to 0.9794 and 97.83 %, respectively, for optimal network parameters. The received INS was successfully tested in the software package.
Downloads
References
Glazunov A.A., Leshchinskaya T.B., Shvedov G.V. [Algorithm for Solving Multicriteria Optimization Problems with Indefinite Information on the Example of Optimal Power Selection for a Deep High-voltage Input]. Electrical Technology Russia, 2004, no. 10, pp. 8–14. (in Russ.)
Pankrat'ev P.S., Shakirov V.A. [Decision Making Support at the Pre-Feasibility Study Stage Based on Two Level Multi-Attribute Analysis]. Mezhdunarodnyy nauchno-issledovatel'skiy zhurnal [International Research Journal], 2013, vol. 2, no. 8 (15), pp. 71–73. (in Russ.)
Lyubchenko V.Ya., Manusov V.Z., Pavlyuchenko D.A. [Genetic Algorithm for Optimizing Power System Modes by Active Power]. Elektro [Electro], 2003, no. 3, pp. 71–73. (in Russ.)
Bulatov B.G., Tarasenko V.V [Algorithms for Optimal Distribution Network Reconfiguration]. Bulletin of South Ural University. Ser. Power Engineering, 2013, vol. 13, no. 2, pp. 14–18. (in Russ.)
Berdin A.S., Kokin S.E., Semenova L.A. [Optimization of the Power Supply System in Conditions of Uncertainty]. Promyshlennaya energetika [Industrial Power Engineering], 2010, no. 4, pp. 29–35 (in Russ.)
Ramsay B., McPherson A., Eastwood R., Ozveren C.S., Glare J. Oatley. A Decision Support System for Electricity Distribution Network Refurbishment Projects. Electric Power Systems Research, 1997, no. 40, pp. 27–35.
Bova V.V., Dukkardt A.N. [Application of Artificial Neural Networks for Collective Decision of Complex Intelligent Problems]. Izvestiya YuFU. Tekhnicheskie nauki [Bulletin of Southern Federal University. Technical Science.], 2012, no. 7, pp. 131–138. (in Russ.)
Kamenev A.S., Korolev S.Yu, Sokotushchenko V.N. Neyromodelirovanie kak instrument intellektualizatsii energoinformatsionnykh setey [Neuro-Modeling as a Tool of Energy Information Networks Intellectualization], Moscow, Energiya Publ., 2012. 124 p.
Medvedev V.S., Potemkin V.G. Neyronnye seti. MATLAB 6 [Neural Networks. MATLAB 6], Moscow, DIALOG Publ., 2001. 630 p.
Ananicheva S.S., Mezentsev P.E., Myzin A.L. Modeli razvitiya elektroenergeticheskikh sistem: uchebnoe posobie [Models of Development of Electric Power Systems: Textbook], Ekaterinburg, Ural Federal University Publ., 2014. 148 p.
Andervazh M‐R., Javadi S., Aliabadi M. Hosseini. Decision Support System for Multicriteria Reconfiguration of Power Distribution Systems Using CSO and Efficient Graph Traversal and Repository Management Techniques. International Transactions on Electrical Energy Systems, 2018, e2579. https://doi.org/10.1002/etep.2579
Haykin S. Neural Networks and Learning Machines. Pearson Prentice Hall Publ., 2009. 906 p.
Dianov R.S., Protalisnkiy O.M. [Decision Support System for the Development of Gas Condensate Deposits Based on Neural Networks]. Avtomatizatsiya v promyshlennosti [Automation in the Industry], 2005, no. 7, pp. 50–52. (in Russ.)
Gajowniczek K., Nafkha R., Tomasz Z. Electricity Peak Demand Classification with Artificial Neural Networks. Proceedings of the Federated Conference on Computer Science and Information Systems, 2017, pp. 307–315. DOI: 10.15439/2017F168
Davis J., Goadrich M. The Relationship between Precision-Recall and ROC Curves. Proceedings of the 23rd International Conference on Machine Learning, 2006, pp. 233–240. DOI: 10.1145/1143844.1143874
Downloads
Published
How to Cite
Issue
Section
