JADS: PhD AI power grid balancing using recommendation-enhanced Demand Response

Jheronimus Academy of Data Science (JADS) Den Bosch, isproud to start with three large Robust AI labs together with:

JADS is seeking enthusiastic colleagues for the position of PhD students. We operationalize the huge ambition around AI by explicitly aligning our research agenda on Robust AI with the United Nation's sustainable development goals.

The project is funded in a public private partnership by NWO/NLAIC and the private partners. This position is part of the LaNubia project.

Short Description

Are you fascinated in how we can align human behavior with smart AI technologies to achieve a sustainable energy transition? In this project we aim to develop novel recommendation technology that helps energy consumers in managing their energy consumption (and production). Current methods assume users passively follow the demand-response (pricing) schemes. AI technology such as recommender algorithms could play an active role in recommending consumers how and when to distribute their energy usage and return.

JobDescription

As part of the Ilustre lab, you will develop recommendation technologies to tailor advice on energy usage decisions in the smart grid. Demand-Response methods motivates energy consumers in some way (e.g. pricing-based) to adjust their energy usage to the available energy resources and demand. Smart grid technology allows DR to be more data-driven and a multitude of AI technologies have already been applied to DR but the consumer side of has not been developed much. However, modeling and supporting the energy decisions of users is crucial, as a smart grid will only be successful if the users of the systems behave predictable and in the most energy efficient way. For example, charging your electric car when the solar PV generated in the neighborhood is highest will put the smallest load on the grid and will be cheapest, but can only be achieved if it fits in the users' calendar and daily habits.

In this project you will extend current AI energy consumption forecasting and DR methods with tailored and explainable recommendations that will provide both household and industry consumers with tailored advice how to adjust for Demand Response. As many stakeholders are involved, and dynamic changes in energy usage will affect other consumers in the network, a multi-stakeholder perspective on recommendations should be employed. You will work together with other PhD students in the lab that will work on forecasting and on identifying the stakeholders.

In the project you will review existing methods for AI in DR, work on recommender model and approaches, test several of these models in prototypes and in a pilot project within the Ilustre lab.