activity
20152022
most citedCombining Model-Based and Model-Free Methods for Nonlinear Control: A Provably Convergent Policy Gradient Approach

11 citations · 35 across the 16 of their papers we have counts for

collaborators
Showing 2020Show all

12 papers · 1 filter

eess.SY20202 cited

Adaptive Charging Networks: A Framework for Smart Electric Vehicle Charging

Zachary J. Lee, George Lee, Ted Lee +6

We describe the architecture and algorithms of the Adaptive Charging Network (ACN), which was first deployed on the Caltech campus in early 2016 and is currently operating at over…

eess.SY20208 cited

DeepOPF+: A Deep Neural Network Approach for DC Optimal Power Flow for Ensuring Feasibility

Tianyu Zhao, Xiang Pan, Minghua Chen +2

Deep Neural Networks (DNNs) approaches for the Optimal Power Flow (OPF) problem received considerable attention recently. A key challenge of these approaches lies in ensuring the f…

eess.SY2020

Real-time Flexibility Feedback for Closed-loop Aggregator and System Operator Coordination

Tongxin Li, Steven H. Low, Adam Wierman

Aggregators have emerged as crucial tools for the coordination of distributed, controllable loads. However, to be used effectively, aggregators must be able to communicate the avai…

cs.AI2020

Learning Optimal Power Flow: Worst-Case Guarantees for Neural Networks

Andreas Venzke, Guannan Qu, Steven Low +1

This paper introduces for the first time a framework to obtain provable worst-case guarantees for neural network performance, using learning for optimal power flow (OPF) problems a…

math.OC202011 cited

Combining Model-Based and Model-Free Methods for Nonlinear Control: A Provably Convergent Policy Gradient Approach

Guannan Qu, Chenkai Yu, Steven Low +1

Model-free learning-based control methods have seen great success recently. However, such methods typically suffer from poor sample complexity and limited convergence guarantees. T…

math.OC2020

Approaching Prosumer Social Optimum via Energy Sharing with Proof of Convergence

Yue Chen, Changhong Zhao, Steven H. Low +1

With the advent of prosumers, the traditional centralized operation may become impracticable due to computational burden, privacy concerns, and conflicting interests. In this paper…