Optimization of Photovoltaic System Efficiency in Building Envelope Designs Using Genetic Algorithms: Comparative Analysis of Cost Metrics, Energy Savings, and Payback Periods

¹ Peter the Great St. Petersburg Polytechnic University, Saint Petersburg 195251, Russian Federation
² Lovely Professional University, Phagwara, Punjab, India ;
³ Department of CSE(DS), GRIET, Bachupally, Hyderabad, Telangana, India.
⁴ Department of Mechanical Engineering, KG Reddy College of Engineering and Technology, Chilkur(Vil), Moinabad(M), Ranga Reddy(Dist), Hyderabad, 500075, Telangana, India.
⁵ Uttaranchal University, Dehradun - 248007, India
⁶ Centre of Research Impact and Outcome, Chitkara University, Rajpura - 140417, Punjab, India
⁷ Chitkara Centre for Research and Development, Chitkara University, Himachal Pradesh - 174103 India
⁸ Rayat Bahra Institute of Pharmacy, Hoshiarpur - Chandigarh Road, Hoshiarpur, Punjab 146001, India
⁹ Faculty of Pharmaceutical Sciences, Research & Incubation Centre, Rayat Bahra University, Chandigarh-Ropar NH 205, Greater Mohali, Punjab, 140103, India

^* Corresponding author: vafaeva.khm@gmail.com

Abstract

This study examines how genetic algorithms (GA) can be used to make protective structures for photovoltaic (PV) systems more efficient. We tried to increase the efficiency of solar cell systems in five different construction scenarios with regard to costs, energy savings, and payback time. To optimize this, we used construction parameters such as width, height, depth, insulation thickness, shading, and roof angle. An evolutionary algorithm generated the most efficient individual with parameters of 32.89 m width, 8.83 m height, 1.46 m depth, WWR = 32.52%, insulation = 8.96 cm, shading = 7.94 m², and roof angle = 72.08°. The solar panels had an efficiency of 31.27%. According to the cost analysis, Building 4, which had installation costs of $40,000 and annual maintenance costs of $1,500, provided the greatest energy savings of $7,000 per year and a payback period of five years. The features that distinguished Building 2 were installation cost, $ 25000; the pay back of installation was seven years; annual maintenance cost $ 800 per year. But it also saved less power which was around four thousand dollars for the year consumption. In Building 3 the greatest energy savings were found and pay back period was also five years In Buildings 3 and 5 average cost and performance was observed. According to the practical outcomes of the study, it has been perceived that applying of genetic algorithms can lead to enhancement of the economic efficiency of the solar power plants including energy saving aspects. It is therefore argued here that these skills can be applied to building design such that possible returns on solar panel systems are boosted.