China
Africa
Explore chapters and articles related to this topic
Advancements in Quantum-PSO and Its Application in Sustainable Development
Published in Sam Goundar, Archana Purwar, Ajmer Singh, Applications of Artificial Intelligence, Big Data and Internet of Things in Sustainable Development, 2023
In Wei and Wang (2020) Annealing Krill QPSO (AKQPSO) is used to solve the 100-Digit Challenge launched in IEEE Congress on Evolutionary Computation (CEC, 2019). QPSO performs better exploitation, and the Annealing Krill Herd (AKH) algorithm performs better in exploration of the solution. AKQPSO proposed here improves the diversity of the population and demonstrates better than other algorithms as stated in this chapter due to better performance in both properties of exploitation and exploration.
Optimization of the p-xylene oxidation process by a multi-objective differential evolution algorithm with adaptive parameters co-derived with the population-based incremental learning algorithm
Published in Engineering Optimization, 2018
This section presents the experimental results and the performance estimation. The ZDT benchmark functions (Zitzler, Deb, and Thiele 2000), DTLZ benchmark functions (Deb et al.2002b) and 2009 IEEE Congress on Evolutionary Computation (CEC 2009) benchmark functions (Zhang et al.2008) are used. There are 12 bi-objective problems (ZDT families and UF1–UF7) and eight tri-objective problems (DTLZ families and UF8–UF10). The results of the PBMODE algorithm were compared with those of generalized differential evolution-3 (GDE3) (Kukkonen and Lampinen 2005), Pareto-archived evolution strategy (PAES) (Knowles and Corne 1999), NSGA-II (Deb et al.2002a), multi-objective evolutionary algorithm based on decomposition/differential evolution (MOEA/D-DE) (Li and Zhang 2009), SPEA2 (Zitzler, Laumanns, and Thiele 2001), S-metric selection based on evolutionary multi-objective optimization algorithm (SMS-EMOA) (Beume, Naujoks, and Emmerich 2007) and MODE, through the performance metrics inverted generational distance (IGD) (Li and Zhang 2009) and Epsilon (Akay 2013). The contrast experiments (PAES, GDE3, SMS-EMOA) are realized using the jMetal software package (Durillo and Nebro 2011), the source code for which is available at http://jmetal.sourceforge.net/.
A new hybrid matheuristic optimization algorithm for solving design and network engineering problems
Published in International Journal of Management Science and Engineering Management, 2018
G. Chagwiza, B. C. Jones, S. D. Hove-Musekwa, S. Mtisi
A total of six problems are taken from the IEEE Congress on Evolutionary Computation 2006 introduced by Liang et al. (2006). Two have linear, two polynomial and two quadratic objective functions. The details of these problems are shown in Table 6. The information includes the estimated ratio between the feasible region and the search space, the number of linear inequality constraints (Li), the number of nonlinear inequality constraints (NI), the number of linear equality constraints (LE), the number of nonlinear equality constraints (NE) and the number of active constraints (α).
Improved genetic algorithm based on particle swarm optimization-inspired reference point placement
Published in Engineering Optimization, 2019
Ima O. Essiet, Yanxia Sun, Zenghui Wang
PSO and NSGA are both population-based metaheurisitic algorithms. PSO has performed particularly well in the optimization of large solution spaces involving many objectives (Hu, Yen, and Luo 2017; Zhang, Zhou, and Cui 2017; Lin et al.2018). Therefore, its topology has inspired the algorithm that is proposed in this article. The performance of the proposed algorithm on many-objective optimization problems is evaluated on the IEEE Congress on Evolutionary Computation (CEC) 2017 benchmark test suite (Cheng et al.2017).