基于混合粒子群智能遗传算法的配电网络重构优化研究

Study of distribution network reconfiguration based on hybrid particle swarm intelligence genetic algorithm

将二进制粒子群优化算法的惯性因子进行了动态化自适应改进,设计了区别于标准遗传操作的高频交叉算子和随机自回馈变异算子,基于此提出了一种新算法——混合粒子群智能遗传算法(PGA)应用与配网的重构。在新型编码方案下,PGA应用两个遗传算子使种群保持多样性,避免陷入局部最优,同时结合PSO的快速群体智能寻优指导染色体的进化方向,能够使种群信息共享的同时提高算法的收敛速度,算例结果验证了新算法的可行性。

The inertia factor of the binary Particle Swarm Optimization （PSO） algorithm was improved for dynamic adaptability, and the high frequency crossover operator and the random feedback mutation operator were designed. Based on that, a new algorithm which is known as the Hybrid Particle Swarm Intelligence Genetic Algorithm （PGA） is proposed for distribution network reconfiguration. In the new coding scheme, the PGA uses the two novel genetic operators to maintain the population diversity to avoid falling into the local optimal solution. Meanwhile, the PSO was combined to guide the direction of the chromosome evolution. Consequently, information share among the population can be realized and the convergence speed can be improved. Calculation example proves the novel algorithm feasible.