ACC24 Gekko Tutorial Session

Special Session: Tackling Control Problems with Open-Source Software in Julia and Python
Open-source control and optimization packages are gaining maturity and industrial acceptance. This accelerates developments from university research groups to industrial practice with a common framework for development and deployment. Recent developments for control include classical analysis to new developments such as transformer-based Model Predictive Control (MPC). This presentation reviews Python open-source packages at the intersection of advanced control, optimization, and machine learning. Gekko is highlighted as an open-source algebraic modeling language built in Python that is used to formulate mixed-integer, nonlinear, and differential equations for optimization and advanced control with object-oriented programming. Gekko has been used to optimize grid energy, maximize production, combine control and design optimization, optimize solar-powered aircraft, control the Temperature Control Lab (TCLab), and maximize waste loading for nuclear waste vitrification. Machine learning models like gaussian process regression, support vector regression, and neural networks are integrated into Gekko for gray-box modeling and optimization. Future developments are critical to sustain community momentum and near-term priorities are discussed.
#acc24 #gekko #machinelearning #python #engineering #automation

[@aaronsarinana1654]

Great session! Thanks professor!

[@darkside3ng]

Amazing!!!

Well done.

[@lakshminarayanansamavedham3770]

Thank you!

[@zemanntill]

Hey, I am building a game with a friend where you can fly an aircraft and other aircraft are controlled by AI center controllers. We really want to spend some time learning and trying different optimization algorithms to find their optimal routes (to ensure safety and minimize fuel). The game also has weather which we want to take into account. Now comes my question: does anyone know which algorithms would fit the problem? It would be cool to have some simple ones but you can also suggest more time-intensive algorithms that we can try out! Thanks a lot :)

[@apm]

Optimization algorithms for aircraft routing are essential for ensuring efficient flight operations, minimizing costs, and maximizing safety. Mixed Integer Linear Programming is a popular method for scheduling optimization. Nonlinear Programming is used for trajectory optimization. Here is a recent review paper: academic.oup.com/iti/article/doi/10.1093/iti/liad026/7459776

[@zemanntill]

​@@apmthanks for the answer? Do you think more complex approaches like Reinforcement Learning or Model Predictive Control could work? I'm not sure what to do when they don't give a solution.. e.g. you could plan ahead using RL but if there would be a crash in the future what would I do?

[@zemanntill]

​@@apmAnd is nonlinear optimization fast enough if I have many agents?

[@apm]

@@zemanntill MPC uses linear or nonlinear programming to calculate the new trajectory. The speed depends on the number of equations and degree of nonlinearity. RL can be useful if you have a simulated environment where it can learn from the trials. RL is typically slow, but iteratively improves.