基于E占优的多目标二进制粒子群算法求解配电网故障恢复

Distribution network service restoration using a multi-objective binary particle swarm optimization based on E-dominance

针对基于Pareto占优机制和拥挤距离的经典多目标智能算法在迭代过程中没有考虑决策者的偏好知识,从而影响了算法收敛性的问题,提出了一种基于E占优的多目标二进制粒子群算法求解配电网故障恢复。通过采用改进原点距离的E占优机制,可以将决策者的偏好知识有效地融入到故障恢复方案的评价过程中。在算法迭代过程中,采用轮盘赌策略更新群体极值,采用方案的综合值对外部档案进行维护,使得决策者的偏好知识可以有效地指导下一代种群的产生。最后,通过算例验证了所提算法的可行性和有效性,并且该方法比基于Pareto占优机制和拥挤距离的多目标智能算法拥有更好的收敛性能,得到的最优前沿数量更少,质量更高。

The classic multi-objective evolutionary algorithm based on Pareto dominance criteria and crowding distance sorting method does not consider the preference of decision maker in the iterative process, which leads to the decline of convergence performance. For the problem, this paper proposes a multi-objective binary particle swarm optimization based on E-dominance to solve distribution network service restoration. By adopting E-dominance strategy of improving the origin distance, it can integrate the preference of decision makers into the evaluation process. This paper adopts roulette strategy to update the global best solution and integrated value to maintenance the external files, which can effectively guide the next generation of particle with preference of decision makers during iterative process. Finally, an example shows that the approach has better convergence performance, less quantity and better quality on solution than the classic multi-objective algorithm based on Pareto dominance criteria and crowding distance.