Our work Exploiting Vulnerabilities of Load Forecasting Through Adversarial Attacks was accepted at this year’s ACM e-Energy conference. We looked into the overlooked security issues on load forecasting, which is an essential step in power system operations. With only small attack efforts, severe damages could be made upon normal system operations.
Code is available here.
I attended the 3rd Grid Science Winter School & Conference held in Santa Fe by Los Alamos National Laboratory. It was a super interesting venue! Great to hear from a lot of inspiring works, gather with old friends during my summer internship, and showed our work on Optimal Control via Neural Networks as a contributed student talk. Also showed one poster on our ongoing work Data-Driven Vulnerabilities of Power Systems Algorithms.
Our work on control via neural network (preprint on Arxiv available): Optimal Control Via Neural Networks: A Convex Approach was accepted to ICLR 2019. Very exciting theoretical results on showing a class of neural networks being input-convex, which are able to achieve excellent learning plus control performances on tasks such as Mujoco locomotion and building energy management.
Also nominated as an oral paper for the conference, along with a travel award. Featured in media coverage such as Sohu, 机器之心.
We presented our work on generative models for renewable generations at this year’s Informs annual meeting conference held in Phoenix on November 4-7. Take a look at our slides and special thanks to Yuanyuan!
I attended the SmartGridComm this year held in Aalborg, Denmark on Oct. 29-31, 2018, and presented our work Is Machine Learning in Power Systems Vulnerable? We are interested in the general security issues of applied ML in power networks and smart grids, and call for more rigorous analysis of algorithmic security threatens. Take a look at our Arxiv preprint!
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.