ABS算法在求解MPEC问题中的应用  

Application of the ABS Algorithm to MPEC

作　　者：徐菲[1] 夏尊铨[1] 

机构地区：[1]大连理工大学应用数学系,辽宁大连116024

出　　处：《运筹与管理》2004年第4期45-49,共5页Operations Research and Management Science

摘　　要：应用ABS—隐式LU算法,简化MPEC问题的约束条件,将简化后的MPEC问题转化为目标函数带有罚函数子项的非线性无约束优化问题,给出收敛性定理,证明当罚因子足够大时,此非线性无约束问题的极小点就是简化后的MPEC问题的极小点,将此极小点代入本文中给出的一个转换公式可得原MPEC问题的极小点,文末给出一算例。By using the implicit LU algorithm, which is a class of ABS algorithm, we simplify the constraint conditions of a mathematical program with equilibrium constraints(MPEC), then turn the simplified MPEC into a non-linear unconstrained optimication problem. A convergence theorem is given, which proves that when the penalty parameter is big enough, the mimimun point, of this unconstrained optimization problem converges to that of the simplified MPEC. Finally, we obtain the minimun point of the original problem by taking it into a conversion formula. At last, an example is given to illustrate this method.

关 键 词：MPEC问题 ABS算法 罚函数 

分 类 号：O224[理学—运筹学与控制论]