云理论在配电网络变电站选址定容中的应用

发布时间：2018-05-14 12:57

本文选题：变电站选址定容 + 云理论　；参考：《中国电机工程学报》2014年04期

【摘要】：变电站选址与定容优化规划属于大规模组合优化问题,基于云在定性概念描述与定量数值表示之间转换过程中的优良特性,借鉴遗传算法"优胜劣汰,适者生存"的进化思想,提出一种基于云理论的优化算法(cloud theory optimization algorithm,CTOA),并将其应用于电力系统配电网络变电站站址、站容的优化规划研究中。在该算法中,用云的期望代表父代个体的优良特征,用云的熵和超熵控制遗传和变异的程度,用正态云算子完成概念空间到数值空间的转换,产生种群,实现遗传操作。CTOA在定性知识的指导下能实现空间范围的自适应控制搜索,可以有效改善智能优化算法易陷入局部最优解和早熟收敛等问题。最后结合某装备制造基地变电站选址定容实例,分别采用改进自适应遗传算法(improved adaptive genetic algorithm,IAGA)、改进多组织粒子群优化算法(refined multi-team particle swarm optimization algorithm,RMPSO)和CTOA算法对其进行了优化规划研究。结果表明,CTOA在收敛时间,搜索精度性能指标方面优于IAGA、RMPSO算法,且该算法无需编码,操作流程简单,易于实现,能更好的满足配电网络中大规模变电站规划的需求。
[Abstract]:Substation location and constant volume optimization are large-scale combinatorial optimization problems. Based on the excellent characteristics of cloud in the process of transformation between qualitative conceptual description and quantitative numerical representation, the evolutionary idea of genetic algorithm "survival of the fittest, survival of the fittest" is used for reference. A cloud theory optimization algorithm based on cloud theory is proposed and applied to the optimal planning of substation site and capacity in power distribution network. In this algorithm, the expectation of cloud is used to represent the fine characteristics of parent, entropy and hyperentropy of cloud are used to control the degree of heredity and mutation, and normal cloud operator is used to complete the transformation from concept space to numerical space to produce population. Under the guidance of qualitative knowledge, genetic operation. CTOA can realize adaptive control search in space range, which can effectively improve the problem that intelligent optimization algorithm is easy to fall into local optimal solution and premature convergence. Finally, combined with an example of substation location and volume determination in a certain equipment manufacturing base, the improved adaptive genetic algorithm (AGA), the improved multi-organization particle swarm optimization (MPSO) algorithm and the CTOA algorithm are used to study the optimization planning. The results show that CTOA is better than IAGA RMPSO algorithm in convergence time and searching precision performance index, and the algorithm does not need coding, the operation flow is simple and easy to realize, and it can better meet the needs of large-scale substation planning in distribution network.
【作者单位】：华北电力大学电气与电子工程学院;中国水电顾问集团昆明勘测设计研究院;
【基金】：国家高技术研究发展计划(863计划)(2011AA05A121) 河北省自然科学基金(E2010001703)~~
【分类号】：TM715

【参考文献】