Junbo Zhao's Projects
Model reduction library with an emphasis on large scale parallelism and linear subspace methods
The code repo for building reliable load forecasting model during the COVID-19 pandemic
These are the set of python codes for Locally Adaptive Activation Function (LAAF) used in deep neural networks. The paper is available on arxiv https://arxiv.org/abs/1909.12228 Please cite this work as "A D Jagtap, K Kawaguchi, G E Karniadakis, Locally adaptive activation functions with slope recovery term for deep and physics-informed neural networks, arXiv preprint arXiv:1909.12228, 2019
This set of codes implements our TPWRS paper "Security-Constrained Unit Commitment Considering Locational Frequency Stability in Low-Inertia Power Grids". This work is under the open license: CC BY 4.0.
Code for "Actor-Attention-Critic for Multi-Agent Reinforcement Learning" ICML 2019
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Paper list of multi-agent reinforcement learning (MARL)
Code for paper 'Learning transferable cooperative behaviors in multi-agent teams' (ICML 2019)
Here, we would like to share the Matlab code of the GM-estimator to all researchers. We also invite each of you to test the method and give us your feedback if you have any. The code attached is to implement the GM-estimator proposed by Mili in [R1]. The test systems include IEEE 14-bus, 30-bus and 118-bus systems. Only SCADA measurements are included. We have included detailed comments of the code.
Machine Learning for HPC Workflows
Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient - 7th ICML AutoML workshop 2020
multifidelity global sensitivity analysis
Multi Fidelity Monte Carlo
Code samples for my book "Neural Networks and Deep Learning"
Pytorch-based framework for solving parametric constrained optimization problems.
《神经网络与深度学习》 邱锡鹏著 Neural Network and Deep Learning
This repository contain a modified version of NS-3 where the users can create attacks such as TCP SYN flood , ARP spoofing, ICMP redirection and MITM attacks. The intention is for the user to carry out cybersecurity simulations for power systems. Up to date the users can modify general TCP/UDP socket data and DNP3 protocol data. We will be adding support for the other protocols like MODBUS, IEC104, PMU and IEC61850 in the future. Have a look at the folder ns-allinone-3.29/ns-3.29/examples/RTDS-DoS-Simulation for the examples related to running cyber-physical simulations with an RTDS simulator.
Numerical Gaussian Processes for Time-dependent and Non-linear Partial Differential Equations
An Open-Source Optimal Power Flow Formulation: Integrating Pyomo & OpenDSS in Python
Open-source Distributed Energy Resources (DER) Model that represents IEEE Standard 1547-2018 requirements for steady-state and dynamic analyses
Distributed Optimal Power Flow for Radial Networks via Message Passing Interface (MPI)
OptNet: Differentiable Optimization as a Layer in Neural Networks
Parametric Gaussian Process Regression for Big Data
Code associated with the paper "Leveraging Passivity Enforcement for Locating the Sources of Forced Oscillations"
Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data