Abstract
The Shuttle-Based Storage and Retrieval System (SBS/RS) has been widely studied because it is currently the most efficient automated warehousing system. Most of the related existing studies are focused on the prediction and improvement of the efficiency of such a system at the design stage. Hence, the control of existing SBS/RSs has been rarely investigated. In existing SBS/RSs, some empirical rules, such as storing loads column by column, are used to control or schedule the storage process. The question is whether or not the control of the storage process in an existing system can be improved further by using a different approach. The storage process is controlled to minimize the makespan of storing a series of loads into racks. Empirical storage rules are easy to control, but they do not reach the minimum makespan. In this study, the performance of a control system that uses reinforcement learning to schedule the storage process of an SBS/RS with fixed configurations is evaluated. Specifically, a reinforcement learning algorithm called the actor-critic algorithm is used. This algorithm is made up of two neural networks and is effective in making decisions and updating itself. It can also reduce the makespan relative to the existing empirical rules used to improve system performance. Experiment results show that in an SBS/RS comprising six columns and six tiers and featuring a storage capacity of 72 loads, the actor-critic algorithm can reduce the makespan by 6.67% relative to the column-by-column storage rule. The proposed algorithm also reduces the makespan by more than 30% when the number of loads being stored is in the range of 7-45, which is equal to 9.7%-62.5% of the systems' storage capacity.
Highlights
1.1 BackgroundDuring the COVID-19 pandemic, online shopping has Different layout configurations and control proceduresC The author(s) 2021
The experiment results show that the configuration of the Shuttle-Based Storage and Retrieval System (SBS/RS) do not affect the superiority of the AC algorithm over the empirical storage rules, but the degree of superiority is different
The result of the first experiment (SBS/RS model with six tiers and six columns) shows that when the number of stored loads is in the range of 6 – 56, which equates to 8.33%–77.78% of the systems’ storage capacity, the AC algorithm reduces the makespan by more than 20% relative to the ColByCol rule (Table 4)
Summary
1.1 BackgroundDuring the COVID-19 pandemic, online shopping has Different layout configurations and control proceduresC The author(s) 2021. The length of a rack can be expected to affect the average time needed to store a load in it. The height of the rack affects the time needed by a lift to vertically move a load. Controlling these moves simultaneously is a challenging task, and predicting and improving the performance of the systems are difficult because of their complexity. Malmborg[2] (2002) was the first to investigate Autonomous Vehicle Storage and Retrieval Systems (AVS/RSs), which use the same technology as SBS/RSs. A continuous Markov chain that models horizontal and vertical material flows was used to calculate the expected storage-retrieval cycle time and throughput
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have