基于混沌进化算法的梯级水电系统短期发电计划

提出一种求解梯级水电系统短期发电计划问题的新方法－混沌杂交进化算法（CHEA）。该算法将混沌序列与进化算法有机结合在一起，同时采用浮点数编码并构造一种新的自适应误差反向传播变异算子，从而有效抑制了进化算法的“早熟”现象和收敛速度慢等缺陷，仿真计算结果表明，该方法可以求解具有复杂约束条件的非线性优化问题，算法求解精度高，收敛速度快，从而为水电系统的短期发电计划问题提供了一种有效的方法。

HYBRID CHAOTIC/EVOLUTIONARY ALGORITHM TO SHORT-TERM CASCADED HYDROELECTRIC SCHEDULING

This paper proposes a new hybrid approach of chaos and evolutionary algorithm to solve the short-term schedulingon cascaded hydro system. The integration of chaotic sequence and evolutionary algorithm with a new self-adaptive errorback--propagation mutation operator and float-point encoding are developed. which can overcome premature and increaseconvergence speed in the process of evolution. Simulation results show that it can improve the precision of solutions andincrease the speed of convergence for complex constrained nonlinear optimization problem, therefore an efficient method isprovided for short--term cascaded hydro system scheduling.