Projects

1. InventOpt   Simulation models, code, and research results for optimizing supply chain and inventory networks using discrete-event simulation.
   
   

   This project demonstrates how to optimize inventory levels across a five-node supply chain network to maximize overall net profit. It explores metamodel-based simulation optimization using Gaussian Process Regression and Neural Network metamodels with local optimizers. The repository is organized into four sequential modules:

   1. Model: Constructs a simulation model for supply chain networks using SimPy
   2. Cost Accuracy Tradeoff: Estimates computation budgets for running the model
   3. Design Experimentation: Manages experiment setup and data collection
   4. Metamodel-based Optimization: Applies optimization approaches to collected data
   
   

   This work is based on the paper "An Open Tool-set for Simulation, Design-space Exploration and Optimization of Supply Chains and Inventory Problems" presented at SIMULTECH 2023, Rome.
   Visit the GitHub repo to learn more.

---



2. SupplyNetPy   A Python library specifically designed to model and simulate different supply chain problems with ease.
   
   

   SupplyNetPy provides configurable, modular components — such as suppliers, manufacturers, distributors, and demand points — to build custom supply chain network architectures. It includes configurable policies for inventory management and replenishment strategies, enabling flexible approaches to stock control. Users can quickly assemble a supply chain, define demand and supply behaviors, then run simulations to evaluate key performance metrics such as throughput and profit.
   
   The library is built on Python’s SimPy discrete-event simulation framework and is flexible and extensible, allowing users to customize and extend its functionality as needed.
   
   For more details, visit the GitHub repo or the documentation.

---