The optimization and control group at Pacific Northwest National Lab seeks a post-doc to conduct research in the area of control and reinforcement learning with a focus on application to energy systems reliability. The research focus would be to develop and test combined control theory-based and reinforcement learning-based algorithms for emergency control operations in energy systems. In order to contribute to these research efforts, a successful candidate would have deep technical expertise in control of dynamic systems and good knowledge of reinforcement learning. In addition, the candidate should be proficient in programing languages and software tools and packages for grid simulation, control, and reinforcement learning. The candidate is expected to collaborate effectively with multi-disciplinary research and development teams including researchers within and outside PNNL.
Candidates must have received a PhD within the past five years (60 months) or within the next 8 months from an accredited college or university.
· The candidate must have a solid background in control of dynamic systems (preferably, with applications to energy systems) and reinforcement learning.
· Familiar with power system transient stability simulation software, such as PSS/E or other similar tools.
· Experience with tools, frameworks and algorithms used for reinforcement learning research such as Tensorflow, OpenAI Gym, OpenAI Baselines
· Good programming skills with Python, C++, Java, etc.
· Experience with power system emergency control is a plus.
Ph.D. degree in Control, Electrical Engineering, Mechanical Engineering or related field.