Xpso Jun 2026

comparing XPSO against other meta-heuristic algorithms Code examples for implementing XPSO in Python

In standard PSO, parameters like inertia weight ($w$) and acceleration coefficients ($c_1, c_2$) are often static or linearly decreasing. XPSO often utilizes where these parameters change dynamically based on the swarm's convergence state. For example, if the swarm is stagnating, the inertia weight might increase to encourage exploration. To prevent the entire swarm from rushing towards

To prevent the entire swarm from rushing towards a premature, suboptimal "local" best, XPSO assigns a "forgetting ability" to particles. This encourages particles to break away from outdated, ineffective information, maintaining diversity within the population and preventing the algorithm from getting stuck. 3. Multiple Sub-swarms Multiple Sub-swarms Starting the search in a more

Starting the search in a more intelligent way to cover the search space more efficiently. Core Components of the XPSO Algorithm suboptimal "local" best

(eXtended Particle Swarm Optimization) enhances standard PSO by addressing two key limitations: premature convergence and poor diversity in high-dimensional or multimodal problems.