求解约束优化问题的ε-骨干粒子群优化算法

ε-bare-bones Particle Swarm Optimization for Constrained Optimization Problems

为了提高复杂约束优化问题的收敛精度,提出了基于ε约束的骨干粒子群优化算法(Bare-bones Particle Swarm Optimization basedεconstrained简称ε-BPSO).首先,设计了时变的约束放松参数ε,使算法前期充分利用不可行解的有效信息;其次,为了避免早期收敛,提出动态学习BPSO算法,算法中粒子可以随机地向群体的优秀个体学习,并通过自适应学习权重使群体从全局勘探转向局部利用.最后,依概率采用梯度突变策略,将不可行域中的粒子引入可行域,加快搜索可行域的效率.在36个测试函数上测试并将本文算法与多种进化算法进行对比,实验结果和统计分析表明本文算法在求解约束优化问题上具有优越性.

A novel bare-bones particle swarm optimization based ε constrained （ ε-BPSO ） is proposed to improve the convergence ac- curacy in solving the complicated constrained optimization problems （ COPs ）. Firstly, a time-varying constraint parameter ε is intro- duced to make full use the effective information of infeasible solutions in early stage. Then, in order to avoid premature convergence, a BPSO with dynamic-learning strategy is presented in which particles can randomly learn from the excellent individual, and the adap- tive learning weight is used to achieve the abilities of the swarm from global search to local search over time. Finally, the gradient mu- tation strategy is probabilistically used to make the particles in infeasible region swarm into the feasible region. Simulation results on 36 benchmark test functions show ε-BPSO is competitive with other state-of-the-art optimization algorithms in solving constrained op- timization problems.