Search

Loss of selection pressure in the presence of many objectives is one of the pertinent problems in evolutionary optimization. Therefore, it is difficult for evolutionary algorithms to find the best-fitting candidate solutions for the final Pareto optimal front representing a multi-objective optimization problem, particularly when the solution space changes with time. In this study, we propose a multi-objective algorithm called enhanced dynamic non-dominated sorting genetic algorithm III (E-dyNSGA-III). This evolutionary algorithm is an improvement of the earlier proposed dyNSGA-III, which used principal component analysis and Euclidean distance to maintain selection pressure and integrity of the final Pareto optimal front. E-dyNSGA-III proposes a strategy to select a group of super-performing mutated candidates to improve the selection pressure at high dimensions and with changing time. This strategy is based on an earlier proposed approach on the use of mutated candidates, which are randomly chosen from the mutation and crossover stages of the original NSGA-II algorithm. In our proposed approach, these mutated candidates are used to improve the diversity of the solution space when the rate of change in the objective function space increases with respect to time. The improved algorithm is tested on RPOOT problems and a real-world hydrothermal model, and the results show that the approach is promising. [ABSTRACT FROM AUTHOR]

Multiobjective evolutionary algorithm based on decomposition (MOEA/D) has attracted a lot of attention since it can handle multiobjective problems (MOP) with a complicated Pareto front. The procedure involves decomposing a MOP into single subproblems, which are eventually optimized simultaneously based on the MOP neighborhood information. However, the MOEA/D strategy tends to produce a distributed optimization that is not of good quality in some problems with complex Pareto optimal front, such as problems with a long tail and sharp peak, common in real-world situations. This paper proposes an improved MOEA/D to enhance the distributed optimization quality and minimize its complexity while accelerating the optimization to get a better solution. The improved method is achieved by incorporating a Hybrid Differential Evolution/Particle Swarm Optimization algorithm and a hybrid operator based on nondominated sorting and crowding distance algorithm. This incorporation takes place in the mutation generator and initial population part of the original MOEA/D algorithm. Simulations and comparisons are carried out based on some MOP benchmark functions to verify the proposed method's performance. The experimental results show that the proposed method achieves better performance compared to other algorithms. Furthermore, the proposed method is also applied to optimize the multiobjective wave energy converter model to maximize power per year and minimize cost per unit power. [ABSTRACT FROM AUTHOR]

Success-History-Based Parameter Adaptation Multi-Objective Differential Evolution (SHAMODE) has shown excellent performance recently compared to other multi-objective evolutionary algorithms (MOEAs) and therefore caught the interest of researchers lately. The SHAMODE framework employs historical memory of control parameters, which stores set values of control parameters that have performed well in the past generation and produces new set values of the parameter by directly sampling the parameter space close to one of these stored pairs. Since the algorithm's performance depends on the problem to be optimized, this paper proposes an enhanced version of SHAMODE that is compatible with optimizing the multi-objective wave energy converter problem. The improved version of SHAMODE is achieved by incorporating competing machine learning algorithms, Particle Swarm Optimization, and a modified bubble-net attacking method formula of the Whale optimization algorithm from its original form. Simulations and comparisons are used to verify the proposed method's performance based on some famous multi-objective problem (MOP) benchmark functions. The results reveal that the proposed algorithm performs better than other algorithms that have been recently developed. In addition, the suggested technique is used to optimize the multi-objective wave energy converter model in order to maximize the annual production of electric energy while minimizing the per-unit energy cost. • Machine Learning and PSO based Success-History Based Parameter Adaptation Multi-Objective Differential Evolution algorithm was proposed. • The Improved version of SHAMODE optimized the WEC system to maximize the annual power generated at a minimum Levelized cost of energy. • The Improved version of SHAMODE was applied to optimize the multi-objective wave energy converter model to maximize the annual generated power and minimize the per unit energy cost. [ABSTRACT FROM AUTHOR]

This article investigates the use of optimal reference point placement to improve performance of non-dominated sorting genetic algorithm (NSGA). Placement of reference points for many-objective optimization is inspired by wheel and Von Neumann topologies of Particle Swarm Optimization (PSO). Results obtained show that the pattern of reference point placement determines performance efficiency of NSGA. The better-performing wheel topology (called wheel reference point genetic algorithm (wRPGA), is compared to three other many-objective evolutionary algorithms: knee-driven evolutionary algorithm (KnEA), non-dominated sorting genetic algorithm III (NSGAIII) and multi-objective evolutionary algorithm based on dominance and decomposition (MOEAD/D). The selected many-objective benchmark problems are Walking Fish Group 2 (WFG2) and Deb-Thiele-Laumanns-Zitzler 2 (DTLZ2). It is also tested on a 3-objective cost function for a hypothetical model of a stand-alone microgrid. Through the simulations, the wheel configuration performed 88.9% better than the Von Neumann configuration. The wheel topology also achieved better performance with respect to inverted generational distance (IGD) compared to KnEA, NSGAIII and MOEAD/D for 7 out of 15 IEEE Congress on Evolutionary Computation (CEC) 2017 benchmark problems. wRPGA gave a good approximation of the Pareto front for the 3-objective model representing the hypothetical microgrid. [ABSTRACT FROM AUTHOR]

Abstract This paper proposes an improved enhanced differential evolution algorithm for implementing demand response between aggregator and consumer. The proposed algorithm utilizes a secondary population archive, which contains unfit solutions that are discarded by the primary archive of the earlier proposed enhanced differential evolution algorithm. The secondary archive initializes, mutates and recombines candidates in order to improve their fitness and then passes them back to the primary archive for possible selection. The capability of this proposed algorithm is confirmed by comparing its performance with three other well-performing evolutionary algorithms: enhanced differential evolution, multiobjective evolutionary algorithm based on dominance and decomposition, and non-dominated sorting genetic algorithm III. This is achieved by testing the algorithms' ability to optimize a multi-objective optimization problem representing a smart home with demand response aggregator. Shiftable and non-shiftable loads are considered for the smart home which model energy usage profile for a typical household in Johannesburg, South Africa. In this study, renewable sources include battery bank and rooftop photovoltaic panels. Simulation results show that the proposed algorithm is able to optimize energy usage by balancing load scheduling and contribution of renewable sources, while maximizing user comfort and minimizing peak-to-average ratio. Highlights • Evolutionary algorithms play significant role in demand response implementation. • Aggregator-consumer matching via evolutionary algorithms improves mutual benefits. • Two-archive strategy improves mutation and crossover speed in differential evolution. [ABSTRACT FROM AUTHOR]