Tomorrow, August 23rd Prashant Kumar will give a talk at the Ray Summit conference in San Francisco. The two day long summit in San Francisco covers topics around ML in production, MLOps, deep & reinforcement learning, cloud computing, server-less, data processing and other uses of the Ray libraries.
Prashant will present how our DeepSim platform uses Ray and the RLlib library to develop a wake steering solution that improves the power production of wind turbines. The talk includes an overview of the DeepSim platform and how it takes advantage of the Ray toolkit and a detailed description of how we used the platform to develop the wake steering solution.
The solution, which came forth from a collaboration with Microsoft and Vestas, enables the development of wind farm controllers that boost annual energy production by 1-2% on publicly available data. The full abstract can be found below.
For more information and registration to the conference see the official website.
If you want to meet with Prashant or Rajiv Pratap, our CBO, then drop us a note via email@example.com . Both will be attending both days of the conference and are happy to provide more info on DeepSim, the wake steering solution or any other projects you want to discuss.
Title: Wind farm optimization using RL and large-scale simulation
In collaboration with Microsoft and Vestas, we developed wind farm controllers that boost annual energy production by 1-2% on publicly available data. The controller achieves this by adjusting the yaw of upstream wind turbines in the farm to minimize wake losses at downstream turbines. The training of such deep reinforcement learning-based controllers for wind farms required large-scale and time-consuming computational fluid dynamics simulations. During the training of the controllers we used up to 15,000 CPU cores in parallel, using our platform DeepSim. DeepSim is minds.ai’s end-to-end machine learning platform that uses Ray for distributed computing, model serving, and data processing. In this talk, we will discuss the project and how the controllers were efficiently trained in the cloud.
Ray Summit 2022
Ray Summit is an event for software engineers, machine learning practitioners, data scientists, developers, MLOps professionals, and architects — and anyone else who wants to learn about building and deploying large-scale applications, especially in AI and machine learning. The summit brings the global Ray community together to learn the fundamentals, explore new use cases, share best practices, and discuss the future of AI.
Ray Summit will take place at the Hyatt Regency Embarcadero Hotel (5 Embarcadero Ctr, San Francisco, CA 94111) on August 23 and 24, 2022.