| الوصف: |
Inventory control typically considers controlling the price and the production rate. However, such systems have rigidity towards altering the physical storage capacity -- one can not easily alter the physical size after the initial design. The paper focuses on this critical aspect, consideration of which leads to a non-standard control problem. Here, the objective is a weighted combination of the classical integral term (formed by usual inventory costs) and an $L^{\infty}$ term (the maximum inventory level in the entire planning horizon). Our approach is to consider an additional state component to capture the `instantaneous' $L^{\infty}$ term (maximum inventory level till that instant) by virtue of which, we could convert the problem to the classical framework. For the direct ($L^{\infty}$) problem, we first identify a relation between the optimal price and the production rate policy, thereby reducing the dimensionality of the problem. By numerically solving a smooth variant of the converted problem, we obtain an optimal policy that illustrates a significant reduction in the storage capacity requirement. Interestingly, the loss in the revenue is negligible (less than $6\%$). As the importance of the $L^{\infty}$ component increases, the variations in the corresponding optimal inventory-level trajectory reduce. In the scenarios with partial/zero information about future demand curves, the above observation provides a guidance -- one should continually tune the policies to maintain instantaneous inventory-levels as close to zero as possible. With such a policy, the reduction in revenue is negligible, while having significant improvements for storage capacity. We theoretically establish certain interesting properties of the optimal policy, which also support the above guidance. |
