Multi-swarm optimization

About: Multi-swarm optimization is a research topic. Over the lifetime, 19162 publications have been published within this topic receiving 549725 citations.

Regrouping particle swarm optimization: A new global optimization algorithm with improved performance consistency across benchmarks

Abstract: Particle swarm optimization (PSO) is known to suffer from stagnation once particles have prematurely converged to any particular region of the search space. The proposed regrouping PSO (RegPSO) avoids the stagnation problem by automatically triggering swarm regrouping when premature convergence is detected. This mechanism liberates particles from sub-optimal solutions and enables continued progress toward the true global minimum. Particles are regrouped within a range on each dimension proportional to the degree of uncertainty implied by the maximum deviation of any particle from the globally best position. This is a computationally simple yet effective addition to the computationally simple PSO algorithm. Experimental results show that the proposed RegPSO successfully reduces each popular benchmark tested to its approximate global minimum.

A Collective Neurodynamic Approach to Constrained Global Optimization

Abstract: Global optimization is a long-lasting research topic in the field of optimization, posting many challenging theoretic and computational issues. This paper presents a novel collective neurodynamic method for solving constrained global optimization problems. At first, a one-layer recurrent neural network (RNN) is presented for searching the Karush–Kuhn–Tucker points of the optimization problem under study. Next, a collective neuroydnamic optimization approach is developed by emulating the paradigm of brainstorming. Multiple RNNs are exploited cooperatively to search for the global optimal solutions in a framework of particle swarm optimization. Each RNN carries out a precise local search and converges to a candidate solution according to its own neurodynamics. The neuronal state of each neural network is repetitively reset by exchanging historical information of each individual network and the entire group. Wavelet mutation is performed to avoid prematurity, add diversity, and promote global convergence. It is proved in the framework of stochastic optimization that the proposed collective neurodynamic approach is capable of computing the global optimal solutions with probability one provided that a sufficiently large number of neural networks are utilized. The essence of the collective neurodynamic optimization approach lies in its potential to solve constrained global optimization problems in real time. The effectiveness and characteristics of the proposed approach are illustrated by using benchmark optimization problems.

Particle Swarm Optimization-Based Multivariable Generalized Predictive Control for an Overhead Crane

Abstract: The transient and residual vibrations in flexible underactuated mechatronic systems adversely affect the effectiveness and accuracy of performed tasks and movements. Moreover, in the case of crane operation the transient underactuated payload swing may present a safety hazard. In this paper, a novel control approach based on a multivariable model predictive control and a particle swarm optimizer is proposed for limiting the transient and residual swing of a payload transferred by an overhead crane. A control scheme is developed based on a discrete-time model approximating the decoupled dynamic of an actuated cart and an underactuated pendulum identified on-line using a recursive least-squares technique with parameters projection. A particle swarm optimizer is applied to determine the optimal sequence of control increments in the presence of constraints on input and output variables. The control scheme was successfully tested on a laboratory scaled overhead crane for different constraints and operating conditions. The experiments proved the feasibility and robustness of the proposed method.

The oracle penalty method

Abstract: A new and universal penalty method is introduced in this contribution. It is especially intended to be applied in stochastic metaheuristics like genetic algorithms, particle swarm optimization or ant colony optimization. The novelty of this method is, that it is an advanced approach that only requires one parameter to be tuned. Moreover this parameter, named oracle, is easy and intuitive to handle. A pseudo-code implementation of the method is presented together with numerical results on a set of 60 constrained benchmark problems from the open literature. The results are compared with those obtained by common penalty methods, revealing the strength of the proposed approach. Further results on three real-world applications are briefly discussed and fortify the practical usefulness and capability of the method.