Version 1
: Received: 20 October 2020 / Approved: 22 October 2020 / Online: 22 October 2020 (10:46:56 CEST)
How to cite:
Garlík, B. Application of Neural Networks and Evolutionary Algorithms to Solve Energy Optimization and Unit Commitment for a Smart City. Preprints2020, 2020100459. https://doi.org/10.20944/preprints202010.0459.v1
Garlík, B. Application of Neural Networks and Evolutionary Algorithms to Solve Energy Optimization and Unit Commitment for a Smart City. Preprints 2020, 2020100459. https://doi.org/10.20944/preprints202010.0459.v1
Garlík, B. Application of Neural Networks and Evolutionary Algorithms to Solve Energy Optimization and Unit Commitment for a Smart City. Preprints2020, 2020100459. https://doi.org/10.20944/preprints202010.0459.v1
APA Style
Garlík, B. (2020). Application of Neural Networks and Evolutionary Algorithms to Solve Energy Optimization and Unit Commitment for a Smart City. Preprints. https://doi.org/10.20944/preprints202010.0459.v1
Chicago/Turabian Style
Garlík, B. 2020 "Application of Neural Networks and Evolutionary Algorithms to Solve Energy Optimization and Unit Commitment for a Smart City" Preprints. https://doi.org/10.20944/preprints202010.0459.v1
Abstract
The optimization problem of two or more special-purpose functions of the energy system is subjected to an analysis. Based on experience of our research and general knowledge of partial solutions of energy system optimization at the level of control of production and power energy supply by energy companies in the Czech Republic, a special-purpose (cost) function has been defined. By analysing the special-purpose function, penalty and limitations have been defined. Using the fuzzy logic, a set of suitable solutions for the special-purpose function is accepted. An optimum of the special-purpose function is looked for using the simulated annealing method. The history of electricity consumption is sorted by day and by hour, representing the multidimensional data. When using the cluster analysis, type daytime diagrams of consumption are defined. Type daytime diagrams form prototypes of identified clusters. The so-called self-organizing neural network with Kohonen map attached is used to perform the cluster analysis. The result of our research is presented by an experiment.
Computer Science and Mathematics, Algebra and Number Theory
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
