Evolutionary Computation for Energy Applications: An Overview and Future Perspectives

Joao Soares, Polvtechnic of Porto ABSTRACT: In this talk, João Soares will go through some of the complex issues with the current paradigm of power systems. In reality, standard mathematical methods often simplify the formulations to make optimization problems easier to handle, but this is often at the expense of accuracy and better solutions. When models are close to how things work in the real world, it’s hard to use traditional tools because of problems with scalability, execution time, memory needs, or even uncertainty. Computational intelligence (CI) is a set of problem-solving methods that try to imitate the intelligence found in nature. It has been used to solve complex problems in the energy sector. This talk will look at how some CI methods, like Evolutionary Computation (EC), can be used to solve challenging problems and the potential of these strategies for the energy industry. There will be a quick look at some of the tools our group has been working on for the last decade at the Polytechnic of Porto (GECAD) and some insights that may motivate future research avenues. EC optimization algorithms for energy applications are available on our platform. Indeed, some of these algorithms and platforms are accessible to the public and have been released at global algorithm competitions, repositories and websites, which can be visited at http://www.gecad.isep.ipp.pt/smartgridcompetitions and http://www.gecad.isep.ipp.pt/Meta-ERM for more information.