New research paper: Integrating Real-Time Dynamic Electricity Price Forecast into Job Shop Production Scheduling Model with Multiple Machine Environments

The variability in electricity prices, driven by the intermittent nature of green energy sources, presents a unique challenge. These prices are determined using machine learning forecasting techniques based on weather and grid data. So, how can manufacturing companies enhance their sustainable production efforts by optimizing their utilization of green electricity on the shop floor?

In our latest research, featured in the ACM International Conference on Industrial Engineering and Applications 2023, we propose a mixed integer linear programming model designed for the efficient scheduling of multiple machines. This model seamlessly incorporates dynamic price forecasts, allowing manufacturers to make the most of green electricity resources.

Our research builds upon the Bachelor Thesis of Stefan Krstevski, an esteemed alumnus of Constructor University. Stefan’s dedication to mathematical modeling and data analytics for production planning and control paved the way for his academic journey, eventually leading him to the esteemed halls of the University of Cambridge. His work forms the foundation of this paper.

I also appreciate of the supports of my colleague Omid Fatahi Valilai in the publication.

#latepost #sustainableproduction #productionplanning #operationsresearch #machinelearning

The paper can be accessed here