Reza Rasinojehdehi; Seyyed Esmaeil Najafi
Abstract
An indispensable aspect of human life is energy. The escalating global population and the subsequent rise in the human need for energy, coupled with the constraints of fossil fuels, have compelled researchers to explore innovative techniques for energy production and the adoption of renewable energy ...
Read More
An indispensable aspect of human life is energy. The escalating global population and the subsequent rise in the human need for energy, coupled with the constraints of fossil fuels, have compelled researchers to explore innovative techniques for energy production and the adoption of renewable energy sources. The construction of renewable power plants emerges as a paramount solution for achieving clean energy, a strategy successfully implemented in various countries globally, including India, China, the USA, Central Asian nations, and Africa. Strategically located and blessed with significant solar potential, Iran is a promising candidate for establishing solar power plants. Despite its high potential for constructing solar power plants, Iran faces limitations that require careful consideration. Investing in renewable power plant projects in Iran necessitates addressing various risks and uncertainties. This paper introduces an innovative approach to assessing the risks associated with solar power plants, utilizing an integrated method that combines Data Envelopment Analysis (DEA) and Support Vector Machine (SVM). In the initial phase, DEA cross-efficiency measures risk factors derived from Failure Modes and Effects Analysis (FMEA). This approach not only overcomes certain drawbacks of FMEA but also eliminates several limitations of DEA, enhancing the discrimination capability for decision units. Subsequently, a SVM is developed to monitor the process, concluding with tailored risk treatment and monitoring processes specifically designed for the unique context of Iran's solar energy landscape.
Ghassem Farajpour Khanaposhtani
Abstract
There are numerous and various methods for solving the Multi-Attribute Decision-Making (MADM) problems in the literature, such as Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), Elimination and Choice Expressing Reality (ELECTRE), Analytic Hierarchy Process (AHP), etc. We ...
Read More
There are numerous and various methods for solving the Multi-Attribute Decision-Making (MADM) problems in the literature, such as Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), Elimination and Choice Expressing Reality (ELECTRE), Analytic Hierarchy Process (AHP), etc. We have explored Support Vector Machine (SVM) as an efficient method for solving MADM problems. The SVM technique was proposed for classifying data at first. At the same time, in the current research, this popular method will be used to sort the preference alternatives in a MADM problem with interval data. The accuracy of the proposed technique will be compared with a popular extended method for interval data, say interval TOPSIS. Numerical experiments showed that admissible results can be obtained by the new method.