水库发电优化调度约束处理方法性能差异

Study on the performance difference of constraint processing methods for hydropower reservoir optimal operation

针对水库发电优化调度复杂约束问题,采用搜索空间限定法、强制修复法和惩罚函数法三种约束条件处理方法,结合粒子群优化(particle swarm optimization,PSO)算法求解水库发电调度过程,分析不同约束处理方法对水库发电优化调度运行结果的影响,比较不同处理方法下种群适应度和寻优能力等方面的性能差异.结果表明:当水库水位可行域逐月控制时,三种约束条件处理方法均可使种群较快趋于最优解;当水库水位全年以同一可行域控制时,搜索空间限定法、强制修复法比惩罚函数法优化效果更好,可有效减少种群数目和迭代次数.

Aiming at the complex constraint problem of hydropower reservoir optimal operation,three constraint treatment methods are designed:search space limitation method,forced repair method and penalty function method.Using the particle swarm optimization algorithm to solve the reservoir power generation operation process,the effects of different constraint treatment methods on reservoir optimal operation are analyzed.The performance differences of population adaptability and optimization ability under different treatment methods are compared.The results show that when the feasible region of reservoir water level is controlled month by month,all the three constraint treatment methods can make the population approach to the optimal solution quickly.When the reservoir water level is controlled by the same feasible region throughout the year,the search space limiting method and forced repair method have better optimization effect than that of penalty function method,which can effectively reduce the number of population and iteration times.