Improving the Performance of Particle Swarm Optimization with Diversive Curiosity

How to keep a balance between exploitation and exploration in Particle Swarm Optimization (PSO) for efficiently solving various optimization problems is an important issue. In order to handle premature convergence in PSO search, this paper proposes a novel algorithm, called Particle Swarm Optimization with Diversive Curiosity (PSO/DC), that introduces a mechanism of diversive curiosity into PSO for preventing premature convergence and ensuring exploration. A crucial idea here is to monitor the status of behaviors of swarm particles in PSO search by an interior indicator, and when swarm particles dropped into local minimum, they will be spontaneously reinitialized to start on finding other new solutions in search space. Applications of the proposal to a 2-dimensional optimization problem well demonstrate its effectiveness. Our experimental results indicate that the performance (90%) of the proposed method is superior in terms of success ratio to that (60%) of the PSO model optimized by EPSO.