Hybrid control algorithm based on LQR and genetic algorithm for active support weight compensation system

Belyaev, A.; Sumenkov, O. Yu.

doi:10.1016/j.ifacol.2021.10.486

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GA is a metaheuristic exploring system that advises solutions for optimization work by simulating the development of natural partiality (Turing, 2004). It has been executed in numerous technical branches of learning for solving decision-building problems (Jana and Bhattacharjee, 2017;Abdullah, 2020;Belyaev and Sumenkov, 2021). The essential phases of GA are as follows (Jana and Bhattacharjee, 2017): 1) establishing vital components like population measure, reappearance level, prospects for crossover and mutation procedures; 2) deriving the chromosomes indiscriminately; 3) assessing the fittingness of distinctive components; 4) starting the crossover activity; 5) completing the mutation practice; 6) weighing the relevance of the contemporary entities transformed by crossover and mutation stratagems; and 7) postulating the most enhanced upshot deeming the selection-makers attachment.…”

Section: Proposed Algorithmmentioning

confidence: 99%

Improving the Yearly Profit of Wind Farm with Artificial Intelligence Technique

Bhattacharjee,

Jana,

Bhattacharya

2022

MJST

View full text Add to dashboard Cite

Owing to the escalating environmental and social problems linked to climate change and the hastily depleting stock of hydrocarbon-based fuels, renewable power generation modes have attained massive prominence. Wind power is an important renewable energy generation technology that contributed to 5% of the planet’s power generation in 2020. However, for sustaining the Paris Agreement targets, the global wind power generation sector necessitates evolving at a fleeter pace. To expand the green switch of the worldwide power generation businesses, wind farms are expected to remain financially more advantageous than fossil fuel-based power plants. The present work focused on elevating the annual profit of wind farms by employing an amended genetic algorithm (GA). A fresh approach to dynamically apportioning the crossover and mutation prospects for a GA-enabled profit growth algorithm was suggested to amplify the capability of the GA. Three dissimilar terrain conditions with diverse obstruction configurations and a randomly generated non-uniform wind flow pattern were used for assessing the competence of the proposed algorithm for profit maximization. The results showed that the annual yields for Terrain Layouts 1, 2 and 3 obtained by the amended GA were higher by 10.34, 5.09 and 0.51%, respectively, than the typical one, which substantiated the superior proficiency of the former.

show abstract

Section: Proposed Algorithmmentioning

confidence: 99%

Improving the Yearly Profit of Wind Farm with Artificial Intelligence Technique

Bhattacharjee,

Jana,

Bhattacharya

2022

MJST

View full text Add to dashboard Cite

show abstract

“…1 Airflow Pattern in Kayathar, India III. PROPOSED OPTIMIZATION ALGORITHMGA has been exercised in numerous technical fields for resolving decision-constructing conundrums[23][24][25][26][27][28][29][30][31][32][33][34][35][36]. It is a bio-motivated metaheuristic investigating technique to suggest outcomes for optimization analysis by mimicking the advancement of natural preference[37].…”

mentioning

confidence: 99%

Increasing Annual Profit of Wind Farm Using Improved Genetic Algorithm

Bhattacharjee

Bhattacharya

2023

IJANSER

View full text Add to dashboard Cite

Wind energy, a prominent renewable source of energy, has expanded rapidly in the past few decades. This paper focuses on raising the yearly profit of a possible wind farm in the Kayathar area of India using an enhanced genetic algorithm. Novel dynamic techniques for assigning the probabilities of crossover and mutation operations have been applied for the genetic algorithm-based optimization method along with the conventional static approach. Non-linear functions have been applied for dynamically allocating the crossover and mutation factors for the genetic algorithm-based optimization process. The analysis outcomes of the proposed technique have been compared with the solutions attained by the genetic algorithm with the standard static approach of allocating the crossover and mutation factors. The evaluation outcomes confirm the superiority of the novel non-linearly incrementing methodology over the non-linearly decrementing and static approach of allocating the crossover and mutation probabilities for attaining a more optimal annual profit.

show abstract