Optimization, AI, ML & Python Integration

[#1]

This article lists off application models of Optimization, AI, ML & Python Integration. Explore additional example models and topics in the FlexSim Application Models.

Machine Learning

• Using Reinforcement Learning for Job Sequencing
  Demonstrates reinforcement learning for optimizing job sequencing decisions.
• Reinforcement Learning Using Previous Versions
  Demonstrates reinforcement learning integration techniques compatible with earlier FlexSim versions.

Optimization Models

• Integrating FlexSim with Python to Solve the Knapsack Problem
  Uses Python (Pyomo) to solve optimization problems and return results to FlexSim.
  
• A Supply Chain Model that Uses Mixed Integer Programming with Python
  Proof-of-concept integrating FlexSim with MIP optimization models.

Experimentation & Distributed Computing

• Distributed Experiments or Optimizations
  Shows how to run distributed simulations or optimization experiments across multiple machines.
  
• Using Amazon Web Services for Distributed Experiments or Optimization
  Demonstrates how to run distributed experiments or optimizations using AWS cloud infrastructure.
• Experimenter/Optimizer Export to Database
  Shows how to export experimenter and optimizer results to an external database.

Data Integration & Messaging

• MQTT: Accessing Retained Messages in FlexSim using Python
  Uses Python and MQTT to retrieve retained messages from a broker for simulation input.
  

Python

• A Supply Chain Model that Uses Mixed Integer Programming with Python
  Integrates FlexSim with Python-based MIP optimization for supply chain decision-making.