Junbo Zhao's Projects
Real-time power system simulator (powerflow, dynamic phasors, EMT)
Distributed Resource AGGregation (DRAGG) implements centralized MPC for residential buildings using an aggregator and residential building owner (RBO) model
Physics informed, deep-learning-based state estimation for distribution electrical grids. The study proposes using physical properties of the grid connectivity as a regularizer of a deep neural network training.
Open-Source Poly-Phase Distribution load flow simulation tool
Efficient global sensitivity analysis using mechanistic or machine learning models
A Data-Driven Approach for Generating Synthetic Load Patterns and Usage Habits
Test cases for the simulation of electromagnetic transients
EnergyPlus™ is a whole building energy simulation program that engineers, architects, and researchers use to model both energy consumption and water use in buildings.
optimal power flow EPRI test feeder 5
Physics-informed learning of governing equations from scarce data
EV Profiles for sharing with DNSPs or any other interested party.
Step-by-step guide for building and running FNCS2, ns-3, GridLAB-D, and MATPOWER.
Source code of: "Manifold learning-based polynomial chaos expansions for high-dimensional surrogate models".
Code for the published paper: A Data-Driven Global Sensitivity Analysis Framework for Three-Phase Distribution System With PVs
A precocial reinforcement learning solution for HVAC control
Gaussian processes in TensorFlow
Matlab implementations of Gaussian processes and other machine learning tools.
Gaussian Process emulation for Uncertainty Quantification and Sensitivity Analysis
A curated list of adversarial attacks and defenses papers on graph-structured data.
GridCal, a cross-platform power systems solver written in Python with user interface and embedded python console
GridDyn is an open-source power transmission simulation software package
Gaussian Process CC-OPF framework
Book about interpretable machine learning
A data-driven framework for control of nonlinear flows with Koopman Model Predictive Control
CodaLab L2RPN: Learning to Run a Power Network