Flexible Mixed decomposition Method for Large Scale Linear Programs: -Integration of a Network of Process Models-

Abstract

In combining dispersed optimization models, either primal or dual(or both) decomposition method widely used as an organizing device. Interpreting the methods economically, the concepts of price and resource-directive coordination are generally well accepted. Most of deomposition/ integration methods utilize either primal information of dual information, not both, from subsystems, while some authors have developed mixed decomposition approaches employing two master problems dealing primal and dual proposals separately. In this paper a hybrid decomposition method is introduced, where one hybrid master problem utilizes the underlying relationships between primal and dual information from each subsystem. The suggested method is well justified with respect to the flexibility in information flow pattern choice (some prices and other quantities) and to the compatibility of subdivisions optimum to the systemwide optimum, that is often lacking in conventional decomposition methods such as Dantzig-Wolfes. A numerical example is also presented to illustrate the suggested approach.