Baidu Encyclopedia version

Particle Swarm Optimization, also known as Particle Swarm Optimization or Particle Swarm Optimization, abbreviated as PSO, is a new evolutionary algorithm (Evolutionary Algorithm-EA) developed by J. Kennedy and RC Eberhart.

The PSO algorithm is a kind of evolutionary algorithm. It is similar to the simulated annealing algorithm. It also starts from the random solution and finds the optimal solution through iteration. It also evaluates the quality of the solution by fitness, but it is simpler than the rules of genetic algorithm. It does not have the "crossover" and "mutation" operations of the genetic algorithm, which seeks global optimality by following the current searched optimal values. This kind of algorithm has attracted the attention of the academic community because of its advantages of easy implementation, high precision and fast convergence, and it has demonstrated its superiority in solving practical problems.

Particle swarm optimization is a parallel algorithm.

Read More


Wikipedia version

In computational science, Particle Swarm Optimization (PSO) is a computational approach that optimizes problems by iteratively trying to improve candidate solutions for a given quality metric. It solves the problem by proposing a set of candidate solutions (herein referred to as particles) based on simple mathematical formulas on the position and velocity of the particles and moving them in the search space. The motion of each particle is affected by its locally best known position, but is also directed to the most famous locations in the search space, which are updated as other particles find a better position. This is expected to push the group to the best solution.

Originally attributed to Kennedy, Eberhart and Shi, PSO was originally used to simulate social behavior as a stylized representation of the movement of organisms in flocks or fish schools. The algorithm is simplified and execution optimization is observed. The work of Kennedy and Eberhart describes many of the philosophical aspects of PSO and group intelligence. Poli conducted an extensive survey of PSO applications. Recently, Bonyadi and Michalewicz published a comprehensive review of PSO theory and experimental work, and reviewed the history and recent developments of Sengupta, Basak and Peters, and the hybrid perspective.

PSO is a meta-heuristic algorithm because it makes little or no assumptions about the problem being optimised and can search for very large spaces in the candidate solution. However, metaheuristics such as PSO are not guaranteed to find the best solution. Furthermore, the PSO does not use the gradient of the problem being optimized, which means that the PSO does not require that the optimization problem can be differentiated as required by classical optimization methods such as gradient descent and quasi-Newton methods.

Read More