用遗传算法解算机组组合的研究

UNIT COMMITMENT BASED ON GENETIC ALGORITHMS

用遗传算法解决电力系统机组组合及机组间的负荷分配问题。在机组数目增加时,二进制编码的遗传算法的计算量及存储量会增加很多,并且经典的遗传算法不具有渐近收敛性。针对这些问题,作者采用二进制与浮点数混合的编码方案,并根据这一特点设计了遗传算子;对经典的遗传算法在计算中出现的随机性问题,则采用压缩映射遗传算法使计算过程渐近收敛。计算表明,该算法的具有渐近收敛性,与二进制编码的算法相比,计算所需时间及内存少,而且更易引入问题的相关信息。

How to solve unit commitment (UC) and load dispatch of power system by genetic algorithms (GAs) is researched. Using binary coding GAs to solve UC the amount of calculation and employed ram will be greatly increased and the classical GAs does not possess the ability of asymptotic convergence. For these problems a coding scheme is used in which the binary encoding and floating numbers are combined and according to this feature the corresponding genetic operators are designed. For the randomness of classical GA which appears in calculation process, the contraction mapping GA is applied to make the calculation asymptotically convergent. The results of calculation examples show that the proposed GAs is symptotically convergent, comparing with the algorithm of binary coding this algorithm needs less calculation time and less ram to be employed and the relevant information of UC can be led into more easily.