I was invited to present two of our recent works on learning to solve optimization, with applications in network flow and optimal power flow problems. More details about the two virtual talks, “Learning Generalizable Network Flow Solvers via Neural Networks” and “Learning To Solve Optimal Power Flow Via Robust Neural Decoding” can be viewed here!
I am also serving as a FacilitatORs in two sessions with topics on Robust Optimization and Machine Learning respectively. Look forward to virtual INFORMS this year!
Two of our papers are on Arxiv trying to use machine learning for efficiently solving Optimal power flow (OPF) problem.
In our first paper, we proposed a novel approach for learning the “codewords” associated with binding constraints in the OPF problem. Such learned properties can help accelerate OPF solving process.
In the second paper, we theoretically analyze the generalization properties of the learning algorithm to unseen patterns, while deriving novel learning procedures to make the solutions feasible.
We recently posted a preprint Using Mobility for Load Forecasting During the COVID-19 Pandemic on Arxiv. We proposed a novel load forecasting method to use the mobility data and transfer learning to help forecast the volatile load during the pandemic. We hope such method would ease the burden for utilities and system operators during the difficult times. Check out the open-source code and dataset here!
Also featured in VentureBeat.
Started an internship at Microsoft Research this summer! Working in machine learning for sustainable energy systems.
I took a virtual, online general exam on March 10th due to our continuous fight with COVID-19 at this special time. Special thanks to my committee Baosen Zhang, Daniel Kirschen, Radha Poovendran and Cynthia Chen who provided a lot of help throughout this process! Here is the link to my thesis proposal: Bridging Machine Learning to Power System Operation and Control
We got a paper accepted at Power Systems Computation Conference (PSCC) 2020, with the title “Data-Driven Optimal Voltage Regulation Using Input Convex Neural Networks”. Extended version including distributed algorithms is available at Arxiv: Link.
After some long-time efforts and revision starting from my undergraduate, our work on automatically discovering the underlying dynamics for ecosystem is finally featured on the cover of BioEssays! Take a peek at the cover. Kudos to my previous mentors and collaborators Yang-Yu and Marco!
Felt great to attend a local INFORMS annual meeting in Seattle last week! Got to know some very interesting and new research in optimization, energy systems and learning, and got to meet with some old friends.
I attended Machine Learning Summer School (MLSS) held at London, July 15th – July 26th. Glad to know so many interesting minds working in general areas of machine learning. England summer is great!
Great honor to get the 2nd Best Paper award at this year’s E-Energy Conference in Phoenix! Trying to advocate more rigorous analysis when applying machine learning/forecasting techniques in power systems. See our paper here!
Also great to attend FCRC 2019! Learned a lot from other venues other than e-Energy such as Sigmetrics, EC and COLT.