Kian Sheng Lim

Improving Vector Evaluated Particle Swarm Optimisation by Incorporating Nondominated Solutions

The Vector Evaluated Particle Swarm Optimisation algorithm is widely used to solve multiobjective optimisation problems. This algorithm optimises one objective using a swarm of particles where their movements are guided by the best solution found by another swarm. However, the best solution of a swarm is only updated when a newly generated solution has better fitness than the best solution at the objective function optimised by that swarm, yielding poor solutions for the multiobjective optimisation problems. Thus, an improved Vector Evaluated Particle Swarm Optimisation algorithm is introduced by incorporating the nondominated solutions as the guidance for a swarm rather than using the best solution from another swarm. In this paper, the performance of improved Vector Evaluated Particle Swarm Optimisation algorithm is investigated using performance measures such as the number of nondominated solutions found, the generational distance, the spread, and the hypervolume. The results suggest that the improved Vector Evaluated Particle Swarm Optimisation algorithm has impressive performance compared with the conventional Vector Evaluated Particle Swarm Optimisation algorithm.

Performance evaluation of vector evaluated gravitational search algorithm II

This paper presents a performance evaluation of a novel Vector Evaluated Gravitational Search Algorithm II (VEGSAII) for multi-objective optimization problems. The VEGSAII algorithm uses a number of populations of particles. In particular, a population of particles corresponds to one objective function to be minimized or maximized. Simultaneous minimization or maximization of every objective function is realized by exchanging a variable between populations. The results shows that the VEGSA is outperformed by other multi-objective optimization algorithms and further enhancements are needed before it can be employed in any application.

Improving Vector Evaluated Particle Swarm Optimisation Using Multiple Nondominated Leaders

The vector evaluated particle swarm optimisation (VEPSO) algorithm was previously improved by incorporating nondominated solutions for solving multiobjective optimisation problems. However, the obtained solutions did not converge close to the Pareto front and also did not distribute evenly over the Pareto front. Therefore, in this study, the concept of multiple nondominated leaders is incorporated to further improve the VEPSO algorithm. Hence, multiple nondominated solutions that are best at a respective objective function are used to guide particles in finding optimal solutions. The improved VEPSO is measured by the number of nondominated solutions found, generational distance, spread, and hypervolume. The results from the conducted experiments show that the proposed VEPSO significantly improved the existing VEPSO algorithms.

Convergence and Diversity Measurement for Vector Evaluated Particle Swarm Optimization Based on ZDT Test Problems

Vector Evaluated Particle Swarm Optimization (VEPSO) has been successfully applied to various applications. However, the VEPSO actual performance is still uncertain. Hence, this paper will evaluate the VEPSO performance in term of convergence and diversity ability using Generalized Distance and Spread measurement respectively. Simulation with ZDT benchmark test problems show VEPSO is weak in solving non-convex, non-uniformity search space and low solution density near Pareto optimal front problems. Besides, VEPSO is very weak in multi modality problems because PSO weakness in facing multiple local Pareto optimal fronts problems. Lastly, VEPSO has weak diversity ability due to no diversity control mechanism in searching the solutions.

An Improved VEPSO Algorithm for Multi-objective Optimisation Problems

Multi-objective optimisation problem is the problem which contains more than one objective that needs to be solved simultaneously. The vector evaluated particle swarm optimisation algorithm is widely used for such purpose, where this algorithm optimised one objective using one swarm of particles by the guidance from the best solution found by another swarm. However, this best solution is only updated when a solution is better with respect to the optimised objective and results in poor performance. Therefore, the vector evaluated particle swarm optimisation algorithm is improved by incorporating the non-dominated solutions for guiding the particle movement during optimisation. The performance of the improved algorithm is analysed with several performance measures and simulated on various test functions. The results suggest that the improved algorithm outperformed the performance of the original algorithm.

Evaluation of Vector Evaluated Particle Swarm Optimisation Enhanced with Non-dominated Solutions and Multiple Nondominated Leaders Based on WFG Test Functions

Multi Objective Optimisation (MOO) problem involves simultaneous minimization or maximization of many objective functions. One of MOO algorithms is Vector Evaluated Particle Swarm Optimization (VEPSO) algorithm. In VEPSO, each objective function is optimised by a swarm of particles under guidance of the best solution, known as leader, from another swarm. Recently, an improved VEPSO algorithm, namely VEPSO incorporated non-dominated solution (VEPSOnds), has been introduced by the use of non-dominated solution as leader. Then, the VEPSOnds algorithm is further modified with multi leaders, namely VEPSO with multi leaders (VEPSOml). The improved VEPSO algorithms have been subjected to a series of numerical experiments based on ZDT benchmark datasets. In this study, a more complex benchmark datasets called WFG, is considered for the evaluation of VEPSO, VEPSOnds, and VEPSOml algorithms.

DNA words based on an enhanced algorithm of multi-objective particle swarm optimization in a continuous search space

In this paper, particle swarm optimization algorithm in a continuous search space is implemented to generate a set of DNA words. A single swarm with 20 particles is used to find the best solution (gbest). Here, each particle has a number of sub-particles which is referred as the number of sequences to be designed. Overall, the particle which has the optimum fitness value is considered as the best solution. Fitness value of a particle is computed from the average value of all the applied objective functions. The solution obtained from this algorithm is found to be better as compared with other approaches. Furthermore, it has a fast convergence towards the optimum fitness value.