Open Access

ARTICLE

Optimization of the Active Composition of the Wind Farm Using Genetic Algorithms

Nataliya Shakhovska^1,*, Mykola Medykovskyy², Roman Melnyk², Nataliya Kryvinska³

1 Department of Artificial Intelligence, Lviv Polytechnic National University, Lviv, 79013, Ukraine
2 Department of Automared Systems Control, Lviv Polytechnic National University, Lviv, 79013, Ukraine
3 Faculty of Management, Comenius University, Bratislava, 81499, Slovakia

* Corresponding Author: Nataliya Shakhovska. Email:

Computers, Materials & Continua 2021, 69(3), 3065-3078. https://doi.org/10.32604/cmc.2021.018761

Received 19 March 2021; Accepted 20 April 2021; Issue published 24 August 2021

Abstract

The article presents the results of research on the possibilities of using genetic algorithms for solving the multicriteria optimization problem of determining the active components of a wind farm. Optimization is carried out on two parameters: efficiency factor of wind farm use (integrated parameter calculated on the basis of 6 parameters of each of the wind farm), average power deviation level (average difference between the load power and energy generation capabilities of the active wind farm). That was done an analysis of publications on the use of genetic algorithms to solve multicriteria optimization problems. Computer simulations were performed, which allowed us to analyze the obtained statistical data and determine the main optimization indicators. That was carried out a comparative analysis of the obtained results with other methods, such as the dynamic programming method; the dynamic programming method with the general increase of the set loading; the modified dynamic programming method, neural networks. It is established that the average power deviation for the genetic algorithm and for the modified dynamic programming method is located at the same level, 33.7 and 28.8 kW, respectively. The average value of the efficiency coefficient of wind turbine used for the genetic algorithm is 2.4% less than for the modified dynamic programming method. However, the time of finding the solution by the genetic algorithm is 3.6 times less than for the modified dynamic programming method. The obtained results provide an opportunity to implement an effective decision support system in energy flow management.

---

Keywords

---