Automated Conversion of Static to Dynamic Scheduler via Natural Language
This work addresses the need for optimization experts to manually update scheduling models, offering an incremental improvement by automating constraint implementation for dynamic scheduling.
The paper tackles the problem of manually updating static scheduling models by proposing a Retrieval-Augmented Generation (RAG) based LLM model called RAGDyS to automatically convert static to dynamic schedulers using natural language constraints, allowing end-users to quickly generate new schedules without expert intervention.
In this paper, we explore the potential application of Large Language Models (LLMs) that will automatically model constraints and generate code for dynamic scheduling problems given an existing static model. Static scheduling problems are modelled and coded by optimization experts. These models may be easily obsoleted as the underlying constraints may need to be fine-tuned in order to reflect changes in the scheduling rules. Furthermore, it may be necessary to turn a static model into a dynamic one in order to cope with disturbances in the environment. In this paper, we propose a Retrieval-Augmented Generation (RAG) based LLM model to automate the process of implementing constraints for Dynamic Scheduling (RAGDyS), without seeking help from an optimization modeling expert. Our framework aims to minimize technical complexities related to mathematical modelling and computational workload for end-users, thereby allowing end-users to quickly obtain a new schedule close to the original schedule with changes reflected by natural language constraint descriptions.