stvsd1314 Goto Github PK

ppgn-physics-preserved-graph-networks

The increasing number of variable renewable energy (solar and wind power) causes power grids to have more abnormal conditions or faults. Faults may further trigger power blackouts or wildfires without timely monitoring and control strategy. Machine learning is a promising technology to accelerate the automation and intelligence of power grid monitoring systems. Unfortunately, the black-box machine learning methods are weak to the realistic challenges in power grids: low observation, insufficient labels, and stochastic environments. To overcome the vulnerability of black-box machine learning, we preserve the physics of power grids through graph networks to efficiently and accurately locate the faults even with limited observability and low label rates. We first calculate the graph embedding of power grid infrastructure by establishing a reduced graph network with the observed nodes, then efficiently locate the fault on the node level using the low-dimensional graph embedding. To augment the location accuracy at low label rates, we build another graph network representing the physical similarity of labeled and unlabeled data samples. Importantly, we provide the physical interpretations of the benefits of the graph design through a random walk equivalence. We conduct comprehensive numerical experiments in the IEEE 123-node. Our proposed method shows superior performance than three baseline classifiers for different fault types, label rates, and robustness to out-of-distribution (OOD) data. Additionally, we extend the proposed method to the IEEE 37-node benchmark system and validate the effectiveness of the proposed training strategy.

project

project_ee394v_spr2021

code & report files for Project of EE394V SPR 2021

propeller

Ship propeller selection usign Kt and KQ

pss-ml2

Machine learning for power system transient stability assessment

publications

pumpkin-book

《机器学习》（西瓜书）公式推导解析，在线阅读地址：https://datawhalechina.github.io/pumpkin-book

pytorch_classification

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

pytorch_geometric_temporal

A Temporal Extension Library for PyTorch Geometric

q-learning

A model free reinforcement learning algorithm for detect and defense task in a smart power system

reflection_summary

算法理论基础知识应知应会

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

reinforcementlearning

reinforcement learning

reinforcementlearning-1

Focuses on Reinforcement Learning related concepts, use cases, and learning approaches

resnet-lstm-gcn

Code for Deep-learning Architecture for Short-term Passenger Flow Forecasting in Urban Rail Transit

resourceadequacy.jl

A framework and collection of implementations for power system reliability assessment - the core element of PRAS

riskawarelearning_voltageopt_distgrid

rl-based-event-triggered-mpc

rl_dispatch

The toy example of power dispatch using reinforcement learning

safe-policy-optimization

This is a benchmark repository for safe reinforcement learning algorithms

safe-reinforcement-learing-for-microgrid-control

ship

ship-simulator

Simulator of wave and ship dynamics in MATLAB.

ship_in_transit_simulator

single-period-two-critic-drl

code for paper "Single-Period Two-Critic Deep Reinforcement Learning for Inverter-based Volt-Var Control in Active Distribution Networks"

spatio-temporal-clustering

使用numpy实现的聚类算法（包括时空聚类算法）

spatio_temporal_missing_data_imputation

The project develop various neural networks for spatio-temporal missing data imputation.

spatiotemporal_prediction

This code is for the paper "A spatio-temporal deep learning approach for airspace complexity prediction" that is submitted to the TRB

sql

MySQL学习

st-mgcn

Pytorch Replication of AAAI'19 Paper: Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting