Solving and Interpreting Large-scale Harvest Scheduling Problems by Duality and Decomposition

This paper presents a solution to the forest planning problem that takes advantage of both the duality of linear programming formulations currently being used for harvest scheduling and the characteristics of decomposition inherent in the forest land class-relationship. The subproblems of decomposition, defined as the dual, can be solved in a simple, recursive fashion. In effect, such a technique reduces the computational burden in terms of time and computer storage as compared to the traditional primal solutions. In addition, utilization of this method allows the use of two simple procedures for creating an initial, basic, feasible solution. Forest management alternatives within one (or more) land class can be evaluated easily in this framework, and multiple-use considerations can be incorporated directly into the optimization as nonharvest values.