基于伪动态的混沌人工鱼群算法在多阶段输电网络规划中的应用

Multistage transmission network planning based on pseudo-dynamic chaotic artificial fish school algorithm

与传统输电网络规划不同,多阶段输电网络规划需要考虑时段因素,在何阶段搭建何种路线使全局规划方案最优。多阶段规划的难点是阶段之间的过渡,后面阶段的决策要根据前面阶段的决策来定,对于大规模输电网规划经典的动态规划方法无法解决。利用伪动态规划的思想处理多阶段问题,这样减少了算法的迭代次数和运算时间。将混沌优化算法和人工鱼群算法相结合,摆脱了混沌搜索的盲目性和人工鱼搜索的局限性,使该混合算法效率高、收敛速度快。对巴西南部46节点系统的计算结果表明,该混合算法具有可行性和高效性。

The traditional transmission network planning is confined to a single-level construction,while the actual transmission network planning needs to take into account the time factor,namely how to build the best route to network planning.The difficulty of the multi-stage planning is the transition between stages,with the later stages of the decision-making depending on earlier stages of decision-making.Classic dynamic programming can not solve large-scale transmission network planning program.In this paper,pseudo-dynamic programming deals with the multi-stage problem,whose objective is to reduce the number of iterations.The combination of Chaotic Optimization Algorithm and Artificial Fish School Algorithm is free from blindness and limitations of the hybrid algorithm search.The hybrid algorithm is efficient and quick in computation.The calculation results of the 46-bus system reveal that applying hybrid algorithm into transmission network planning is not only feasible,but also has a very high computational efficiency.