DEVELOPING IMPROVED INVENTORY AND TRANSPORTATION POLICIES FOR DISTRIBUTION SYSTEMS USING GENETIC ALGORITHM AND NEURAL NETWORK METHODS

摘要

A common problem in business is deciding on inventory and transportation policies for a physical distribution system within a changing business environment. Most prior studies have concentrated on inventory (economic order quantity), or on transportation (solid transportation problem) allocations. This work addresses both: selection of an optimal set of policies for a multi-product, multi-echelon, multi-modal physical distribution system, in a non-stationary environment. The problem is highly multi-dimensional, even with a small system, and the fitness surface is quite often discontinuous, with low penalty and high penalty regions separated by no more than a single transport unit. The approach used was to perform a global search for a good initial policy set using a genetic algorithm (GA) in a static environment, followed by local optimization and fitness-terrain-following in a changing environment using a multiple artificial neural network-based adaptive critic controller (NN). Preliminary findings are that: (1) under the experimental conditions imposed, the GA is capable of finding a good set of policies, but not the best ones; (2) the NN controller, designed using dual heuristic programming techniques, can improve on the solution found by the GA; (3) the NN cannot find a good solution without the assistance of the GA. A unique feature of this study is the use of off-optimal data from the GA to train the plant-model NN subsystem used in the DHP controller design process.