I passed my qualifying exam by the end of Spring quarter 2018 with works on generative models for renewables [slides]. Special thanks to my committee Radha Poovendran, Sreeram Kannan and Lillian Ratliff!
I will be working as a research intern in Los Alamos National Laboratory from June to September, mainly working with Dr. Misha Chertkov and Dr. Deepjyoti Deka in Center for Nonlinear Studies.
A work working with my mates from Materials Science and Engineering on wind power forecasts using recurrent neural nets and demand response with design of Q learning system is shown in Data Intensive Research Enabling Clean Technologies (DIRECT) program. Take a look at our poster here!
Our paper, which addresses the scenario forecasts problem in renewables generation has been accepted to Power Systems Computation Conference 2018! Take a look at our pre-print paper here: https://arxiv.org/abs/1711.02247
02/12 CEI Travel Award awarded for the conference.
I was invited to 2nd Physics Informed Machine Learning Conference hosted by Los Alamos National Laboratory in Santa Fe. Here is our poster on generative models for renewables.
My lab mate, Yuanyuan Shi, presented our joint work at INFORMS Annual Meeting 2017 for Learning, optimization and control for resilient power grids. The work is focused on building energy control and optimization via deep learning. It’s quite a unique, general optimal control approach which utilizes deep learning tools for system modeling and optimization. Take a look at our slides: Informs_talk.
Thanks to the Clean Energy Institute (CEI), I was awarded a CEI graduate fellowship to support my research on learning and optimization for cyber-physical systems for clean energy!
For more info, please take a look at: http://www.cei.washington.edu/persons/yize-chen/
Paper entitles “Model-Free Renewable Scenario Generation Using Generative Adversarial Networks”
A work with Yishen Wang, Daniel Kirschen and Baosen Zhang on renewables scenarios generation has been submitted to IEEE Transactions on Power Systems Special Section on
Enabling very high penetration renewable energy integration into future power systems. Take a loot at our Arxiv version: https://arxiv.org/pdf/1707.09676.pdf
Update: Jan.17th 2017 Paper accepted to IEEE Transactions on Power Systems. Preprint: http://ieeexplore.ieee.org/document/8260947/
Paper on building energy management and control based on deep learning: Modeling and Optimization of Complex Building Energy Systems with Deep Neural Networks by Yize Chen, Yuanyuan Shi and Baosen Zhang accpeted by Asilomar Conference on Signals, Systems, and Computers 2017.
Take a look at our work! https://arxiv.org/pdf/1703.04318.pdf