Sustainability Intelligent Evaluation of Regional Microgrid Interconnection System Based on Combination Entropy Weight Rank Order-TOPSIS and NILA-KELM

Sustainability evaluation of regional microgrid interconnection system is conducive to a profound and comprehensive understanding of the impact of interconnection system projects.In order to realize the comprehensive and scientific intelligent evaluation of the system,this paper proposes an evaluation model based on combination entropy weight rank order-technique for order preference by similarity to an ideal solution(TOPSIS)and Niche Immune Lion Algorithm-Extreme Learning Machine with Kernel(NILAKELM).Firstly,the sustainability evaluation indicator system of the regional microgrid interconnection system is constructed fromfour aspects of economic,environmental,social,and technical characteristics,and the evaluation indicators are explained.Then,the classical evaluationmodel based on TOPSIS is constructed,and the entropy weight method and rank order method(RO)are coupled to obtain the indicator weight.The niche immune algorithm is used to improve the lion algorithm,and the improved lion algorithm is used to optimize the parameters of KELM,and the intelligent evaluation model based on NILA-KELM is obtained to realize fast real-time calculation.Finally,the scientificity and accuracy of themodel proposed in this paper are verified.The model proposed in this paper has the lowest RMSE,MAE and RE values,indicating that its intelligent evaluation results are the most accurate.This study is conducive to the horizontal comparison of the overall performance of regional microgrid interconnection system projects,helps investors to choose the most promising project scheme,and helps the government to find feasible project.

A Review on Ranking of Z-numbers

There are numerous studies about Z-numbers since its inception in 2011.Because Z-number concept reflects human ability to make rational decisions,Z-number based multi-criteria decision making problems are one of these studies.When the problem is translated from linguistic information into Z-number domain,the important question occurs that which Z-number should be selected.To answer this question,several ranking methods have been proposed.To compare the performances of these methods,benchmark set of fuzzy Z-numbers has been created in time.There are relatively new methods that their performances are not examined yet on this benchmark problem.In this paper,we worked on these studies which are relative entropy based Z-number ranking method and a method for ranking discrete Z-numbers.The authors tried to examine their performances on the benchmark problem and compared the results with the other ranking algorithms.The results are consistent with the literature,mostly.The advantages and the drawbacks of the methods are presented which can be useful for the researchers who are interested in this area.

Ordinal Decision Trees

In many decision making tasks,the features and decision are ordinal.Several ordinal classification learning algorithms have been developed in recent years,it is shown that these algorithms are sensitive to noisy samples and do not work in real-world applications.In this work,we propose a new measure of feature quality, called rank mutual information.Then,we design an ordinal decision tree(REOT) construction technique based on rank mutual information.The theoretic and experimental analysis shows that the proposed algorithm is effective.