The elitist non-dominated sorting genetic algorithm with inheritance (i-NSGA-II) and its jumping gene adaptations for multi-objective optimization

Kumar, Manoj; Guria, Chandan

doi:10.1016/j.ins.2016.12.003

Cited by 56 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The individuals closer to the Pareto-optimal front and with higher VCDs are selected into P new . In addition, an elite preservation strategy [23] is applied to include in P new the individuals with the highest Step 9. Return X = decode (Pop) and the lowest NDR ranks, and the individuals with the highest and the lowest VCD ranks.…”

Section: A Double-strand Dna Genetic Algorithmmentioning

confidence: 99%

“…(2) Two new ranking criteria, the variant crowding distance (VCD) and the non-dominated rank with density (NRD), are introduced to help maintain diversity in the solution population. These ranking criteria improve the CD [23] and the non-dominated ranking [3] criteria and can be used to effectively identify well diversified solutions in the current Pareto-optimal front as well as in lateral fronts. (3) Extensive experiments are performed to compare the new algorithm with several state-of-the-art MOEAs, including NSGA-II [3], PAES [24], MOPSO [25] and NNIA [26], on a set of well-known benchmark bi-objective and tri-objective optimization test problems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Double-Strand DNA Genetic Algorithm for Multi-Objective Optimization

et al. 2019

View full text Add to dashboard Cite

Multi-objective optimization is important for many businesses, science, and engineering applications. Existing evolutionary algorithms for multi-objective optimization problems based on single chain encoding still have difficulties in obtaining high-quality results. This paper presents a new DNA genetic algorithm that uses a novel double-strand DNA encoding, a set of new genetic operators, and two new ranking criteria to obtain solutions that closely approximate the Pareto-optimal front. The extensive experiments were performed using a set of comprehensive benchmark bi-objective and tri-objective test problems. The experimental results show that this algorithm outperforms a set of the state-of-the-art evolutionary algorithms on several well-accepted performance metrics. INDEX TERMS Multi-objective optimization, DNA genetic algorithm, variant crowding distance, double strands, non-dominated sorting.

show abstract

Section: A Double-strand Dna Genetic Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Double-Strand DNA Genetic Algorithm for Multi-Objective Optimization

et al. 2019

View full text Add to dashboard Cite

show abstract

“…A preliminary assortment of a superior pool of randomly selected parent population is likely to generate a finer pool of daughter chromosome. Consequently, selecting the most appropriate group of the chromosome in the preliminary selection of random parent population assists to improve the speed of convergence to the true optimal global Pareto front [16]. For the assortment of a superior pool of initial random parent chromosomes, the solutions with the best fitness functions are selected and copied to the parent pool.…”

Section: Theory Of Parental Inheritancementioning

confidence: 99%

“…However, this approach has the difficulty of subjectivity, as it requires information about the preferred choice of objectives and it usually finds a single optimal solution. If the entire economic, technical, and ecological objectives are being considered for the allocation of the device, it turns into a problem of conflicting objectives, so, an efficient multi-objective algorithm ought to be employed [13][14][15][16][17][18]. To solve problems with contradictory objectives many multi-objective methodologies such as the strength-Pareto evolutionary algorithm (SPEA) [15], the multi-objective genetic algorithm (MOGA) [18], are developed in recent years.…”

Section: Introductionmentioning

confidence: 99%

Optimised planning of distribution network with photovoltaic system, battery storage, and DSTATCOM

Ghatak¹,

Sannigrahi

Acharjee

2018

IET Renewable Power Generation

View full text Add to dashboard Cite

In this circumstance of global warming, energy market deregulation, and enormous load growth, distribution network entails a proficient strategy to maintain the reliability and efficiency of the power service. Incorporation of solar photovoltaic (PV) system and battery storage (BS) in coordination with distributed static compensator (DSTATCOM) is a competent and practical approach to alleviate the power quality and reliability concern. In this study, a comprehensive strategic model is presented to optimally deploy PV, BS, and DSTATCOM to maximise voltage profile improvement, reliability, economic, and ecological benefit of the network. An accurate and precise novel voltage profile improvement indicator namely network voltage profile improvement index is proposed. Benefit-cost ratio and environment benefit index are proposed to quantify economic and environmental benefits, respectively. Similarly, reliability indices such as expected energy not served are used to appraise the system reliability. A fuzzy based extended version of NSGA II is utilised for the optimal deployment of the devices considering security limits. The proposed method is tested on 33-bus and 69-bus distribution networks considering time variant practical load models and the obtained results validate the efficacy and efficiency of the proposed method when compared with other multi-objective algorithms.

show abstract

“…An improved variant of the NSGA-II combined with a jumping gene named NSGA-II-JG [10] along with its different variants has been used to solve a different multi-objective problem, which resulted in better convergence with reduction of the central processing unit (CPU) time [11]. In [12,13], it was found that the NSGA-II with its adapted jumping gene operator (NSGA-II-aJG) outperforms other variants of NSGA-II on different evaluating matrices.…”

Section: Introductionmentioning

confidence: 99%

Multi‐objective‐based feature selection for DDoS attack detection in IoT networks

2020

View full text Add to dashboard Cite

In this study, the authors propose a multi-objective optimisation-based feature selection (FS) method for the detection of distributed denial of service (DDoS) attacks in an internet of things (IoT) network. An intrusion detection system (IDS) is one approach for the detection of cyber-attacks. FS is required to reduce the dimensionality of data and improve the performance of the IDS. One of the reasons for the failure of an IDS is incorrect selection of features because most of the FS methods are based on a limited number of objectives such as accuracy or relevance of data, but these are not enough as they can be misleading for attack detection the contribution of this work is to develop appropriate FS method. They have implemented the nondominated sorting algorithm with its adapted jumping gene operator to solve the optimisation problem and exploited an extreme learning machine as the classifier for FS based on six important objectives for an IoT network. Experimental results verify that the proposed method performs well for FS and have achieved 99.9% and has reduced the total number of features by nearly 90%. The proposed method outperforms other proposed FS methods for the detection of DDoS attacks by an IDS.

show abstract

The elitist non-dominated sorting genetic algorithm with inheritance (i-NSGA-II) and its jumping gene adaptations for multi-objective optimization

Cited by 56 publications

References 27 publications

A Novel Double-Strand DNA Genetic Algorithm for Multi-Objective Optimization

A Novel Double-Strand DNA Genetic Algorithm for Multi-Objective Optimization

Optimised planning of distribution network with photovoltaic system, battery storage, and DSTATCOM

Multi‐objective‐based feature selection for DDoS attack detection in IoT networks

Contact Info

Product

Resources

About