珊瑚礁算法的改进研究

Improved Coral Reef Algorithm

珊瑚礁算法易于陷入局部最优且寻优精度低,因此提出一种改进的珊瑚礁算法.此算法借鉴粒子群算法、高斯变异和模拟退火算法的思想改进珊瑚礁算法的内部有性繁殖、无性繁殖和更替机制,提高了算法的寻优精度并可跳出局部最优.在仿真实验中,将改进珊瑚礁算法与基本珊瑚礁算法和粒子群算法等10种算法分别在高维和低维测试函数下进行比较.实验结果表明,改进的珊瑚礁算法不仅较其他算法具有更好的收敛速度和精度,而且在高维测试函数中,仍然可以保持良好的性能.

The coral reef algorithm has the disadvantages of being easy to fall into local optimum and low precision.In view of the shortcomings of coral reef algorithm,this paper proposes an improved coral reef algorithm.By referring to particle swarm optimization,Gaussian mutation and simulated annealing algorithm,this algorithm improves the broadcast spawning,asexual reproduction and setting(replacement)mechanisms of coral reef algorithm,which greatly improves the optimization precision of the algorithm and can jump out of the local optimum.In the simulation experiment,the improved coral reef algorithm is respectively compared with ten algorithms such as basic coral reef algorithm and particle swarm algorithm in high-dimensional and low-dimensional test functions.The experimental results show that the improved coral reef algorithm has better convergence rate and accuracy than other algorithms,which can still be maintained in the high-dimensional test functions.