Plithogenic Machine Learning Solutions to Material Selection in Renewable Energy Systems

Abstract

Plithogenic-based decision models are more effective in designing optimal solutions to intricate problems. This study work proposes an integrated decisioning model conjoining plithogeny and machine learning algorithms. This study considers the decision-making problem of selecting smart and sustainable materials for the effective functioning of renewable energy systems. The decisioning model has ten evaluation criteria and considers alternatives for materials subjected to five categories of photovoltaic, thermoelectric, piezoelectric, phase change, supercapacitor, and electrochromic. This work employs the algorithm of a random forest classifier in determining the most crucial criteria for selecting smart and sustainable materials. The plithogenic-based decision method of TOPSIS (Technique for Order of Preference by Similarity to Ideal Solution) is employed in ranking materials of each kind. The proposed decisioning approach is the combination of a machine learning algorithm and a plithogenic decision approach, which is further facilitated by the intervention of Python programming. The criteria selection accuracy is compared with a support vector machine algorithm to demonstrate the efficacy of this integrated decision approach in ranking the materials used in formulating robust renewable energy systems. Sensitivity analysis is also performed to exhibit the efficacy of this proposed model. This model has few limitations, as it considers a few selected materials under each of the categories.