Finding the optimal combination of power plants alternatives: a multi response Taguchi-neural network using TOPSIS and fuzzy best-worst method


With increasing growth of electricity consumption in developed and developing countries, the necessity of constructing and developing of power plants is inevitable. There are two main resources for electricity generation includes fossil and renewable energies which have some different characteristics such as manufacturing technology, environmental issues, accessibility and etc. In developing plans, it is important to consider and address the policy makers’ indicators such as environmental, social, economic and technical criteria. In this paper, an integrated multi response Taguchi-neural network-fuzzy best-worst method (FBWM) -TOPSIS approach is applied to find an optimal level of five different power plants including: gas, steam, combined cycle, wind and hydroelectric. Taguchi method is used to design combinations and calculate some of the signal to noise (S/N) ratios. Then, neural network is applied to estimate the rest of S/N ratios. Finally, FBWM and TOPSIS methods are used for weighing sub-indicators and selecting the best combination, respectively. To illustrate the usefulness of the proposed approach, a case study on the development of power plants in Iran is considered and the results are discussed. According to the results, in general, small size power plants for fossil resources are preferable. In contrast, medium and larger size power plants for renewable resources are preferable.

Publication DOI:
Divisions: College of Business and Social Sciences > Aston Business School > Operations & Information Management
College of Business and Social Sciences > Aston Business School
Additional Information: © 2018, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Uncontrolled Keywords: Power plants; Eco-efficiency; Taguchi method; Neural network; Fuzzy best worst method; TOPSIS
Publication ISSN: 1879-1786
Last Modified: 22 Apr 2024 07:20
Date Deposited: 23 Aug 2018 12:28
Full Text Link:
Related URLs: https://linking ... 959652618325873 (Publisher URL)
PURE Output Type: Article
Published Date: 2018-12-01
Published Online Date: 2018-08-23
Accepted Date: 2018-08-22
Authors: Omrani, Hashem
Alizadeh, Arash
Emrouznejad, Ali (ORCID Profile 0000-0001-8094-4244)

Export / Share Citation


Additional statistics for this record