Simultaneous production planning and scheduling in a production line of I.V. (intravenous) fluids and irrigation solutions

The pharmaceutical supply chain should provide medicines in the right quantity, with the acceptable quality, to the right place and customers, at the right time and with optimum cost. Pharmaceutical companies, the most important player in the pharmaceutical supply chain, have a crucial role. An integrated approach in production planning and scheduling in pharmaceutical companies typically optimizes several consecutive stages in the pharmaceutical supply chain because these companies, are both linked to suppliers and distributors/end users. Hospitals are the most crucial end-user among the end-users because of the necessity of a massive amount of drugs to render service to a large number of patients in hospitals. Intravenous fluids and irrigation solutions help patients maintain the optimal internal temperature and increase comfort in hospitals during procedures like surgery or recovery. In this work, simultaneous production planning and scheduling in a real-world application, a production line of intravenous fluids and irrigation solutions at Darou Pakhsh Pharmaceutical Manufacturing Company is addressed.

A novel mixed-integer linear programming model is formulated for multi-period simultaneous production planning and scheduling. Since the problem is NP-hard in the strong sense, a memetic algorithm is proposed that reduces the computational effort of the problem. The chromosome representation is based on a permutation matrix, and a new algorithm is developed to construct a complete schedule from the permutation matrix through the planning horizon.

40 problems were investigated, containing 36 randomly generated instances and four real problems according to the data within the last two years. The generated instances were divided into small-sized, medium-sized, and large-sized instances. Among the 36 instances, 22 instances were optimally solved by both the exact method and the proposed memetic algorithm. The average gap for small-sized, medium-sized, and large-sized instances are respectively 0.00%, -1.15%, and -51.38%, indicating as the size of instances grows, the gap becomes considerable. The exact method could not reach an optimal solution for four real instances. The running time for real instances is expanded to 8 hours. The results revealed that the proposed memetic algorithm significantly outperformed the exact method in obtaining better solutions for real instances.

The computational results showed that the proposed memetic algorithm obtained optimal solutions on all the instances solved optimally by the exact method. It outperformed the exact method in other problems. This outperformance becomes more evident as the size of instances grows.