The existing intelligent optimization algorithms are designed based on the finest granularity, i.e., a point. This leads to weak global search ability and inefficiency. To address this problem, we proposed a novel multi-granularity optimization algorithm, namely granular-ball optimization algorithm (GBO), by introducing granular-ball computing. GBO uses many granular-balls to cover the solution space. Quite a lot of small and fine-grained granular-balls are used to depict the important parts, and a little number of large and coarse-grained granular-balls are used to depict the inessential parts. Fine multi-granularity data description ability results in a higher global search capability and faster convergence speed. In comparison with the most popular and state-of-the-art algorithms, the experiments on twenty benchmark functions demonstrate its better performance. The faster speed, higher approximation ability of optimal solution, no hyper-parameters, and simpler design of GBO make it an all-around replacement of most of the existing popular intelligent optimization algorithms.
翻译:现有的智能优化算法都是基于最细粒度——点的设计,这导致了全局搜索能力弱和效率低下的问题。为了解决这个问题,我们提出了一种新颖的多粒度优化算法——颗粒球优化算法(GBO),通过引入颗粒球计算。GBO使用许多颗粒球来覆盖解决方案空间。许多小的和细粒度的颗粒球用于描述重要部分,少量大而粗粒度的颗粒球用于描述不重要的部分。细致的多粒度数据描述能力导致更高的全局搜索能力和更快的收敛速度。与最受欢迎和最先进的算法相比,对二十个基准函数的实验表明了其更好的性能。GBO的更快速度、更高的最优解逼近能力、无超参数和更简单的设计使其成为大多数现有流行智能优化算法的全面替代品。