A genetic algorithm for solving a production and delivery scheduling problem with time windows

This paper deals with the problem of selecting and scheduling a set of orders to be processed by a manufacturing plant and immediately delivered to the customer site. Constraints to be considered are the limited production capacity, the available number of vehicles and the time windows within which orders must be served. We describe the problem relating it to similar problems studied in the literature. A genetic algorithm to solve the problem is developed and tested empirically with randomly generated problems. Comparisons with an exact procedure and a tabu search procedure show that the method finds very good-quality solutions.