Using Machine Learning and Deep Learning for Energy Forecasting with MATLAB
29th September 2020 from 14:00-15:00 CEST
AI, or Artificial Intelligence, is powering a massive shift in technical organizations that expect to gain or strengthen their competitive advantage. AI workflows such as deep learning and machine learning are transforming industries with high impact; the power and utilities industries are not exceptional in this regard. The legacy power grid is adopting the concept of smart grid technology, where the role of AI is crucial in multiple aspects. Grid analytics is one of the key focus areas of smart grid infrastructure, where load forecasting is highly pronounced. Forecasting the load on grid helps power and utility companies to plan their resources and effectively service consumer demands in a profitable way. Medium-term forecasting and long-term forecasting are a key focus of the energy production and utilities industry, as this helps to decide on multiple strategies such as generation planning and demand side management services.
The load on the grid depends on multiple external factors, making the data highly complex in nature. AI can be thought of as a tool to develop the forecast models for this complex data. At present, domain experts spend valuable efforts in cleaning data, searching for the right choice of predictive algorithms and fixing syntax of the code. Manual deployment of developed models is also a cumbersome process and additionally requires IT expertise.
In this webinar, you will learn:
- How to handle large data
- How to leverage domain expertise in the AI workflow using MATLAB
- How to deploy algorithms seamlessly to enterprise scale solutions and integrating with a dashboard
About the Presenter
As an application engineer at MathWorks, Sebastian Bomberg supports customers in implementing artificial intelligence projects. For instance, he develops applications for energy forecasting, predictive maintenance and IoT in general. To this end, he uses techniques from machine learning and deep learning as well as big data algorithms and cloud computing. Sebastian Bomberg holds a Dipl.-Ing. degree in mechanical engineering from Technische Universität München, where he also worked as a researcher at the Thermo-Fluid Dynamics Group.
- Curve Fitting Toolbox
- Deep Learning Toolbox
- MATLAB Production Server
- Parallel Computing Toolbox
- Statistics and Machine Learning Toobox
For more information, please click this link.