yyystg

AlwaysSafe

Code for the paper "AlwaysSafe: Reinforcement Learning Without Safety Constraint Violations During Training"

CityLearn

Official reinforcement learning environment for demand response and load shaping

DRL-code-pytorch

Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.

DRL-for-Energy-Systems-Optimal-Scheduling

The source code for Performance comparision of Deep RL algorithms for Energy Systems Optimal Scheduling

DRL-for-microgrid-energy-management

We study the performance of various deep reinforcement learning algorithms for the problem of microgrid’s energy management system. We propose a novel microgrid model that consists of a wind turbine generator, an energy storage system, a population of thermostatically controlled loads, a population of price-responsive loads, and a connection to the main grid. The proposed energy management system is designed to coordinate between the different sources of flexibility by defining the priority resources, the direct demand control signals and the electricity prices. Seven deep reinforcement learning algorithms are implemented and empirically compared in this paper. The numerical results show a significant difference between the different deep reinforcement learning algorithms in their ability to converge to optimal policies. By adding an experience replay and a second semi-deterministic training phase to the well-known Asynchronous advantage actor critic algorithm, we achieved considerably better performance and converged to superior policies in terms of energy efficiency and economic value.

DRLforPowerSystemRecovery

Master Thesis Project for DRL in power system restoration using renewables

ElegantRL

Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥

gym-opendss

An implementation of an OpenAI gym environment for EPRI OpenDSS, using OpenDSS's native Python COM interface.

HEM-DeepRL-v2-1

Home Energy Management based on Deep Reinforcement Learning Approach.

HEMS_CNN

Deep Learning : Home energy usage prediction using HEMS_CNN

yyystg/gym-opendss

An implementation of an OpenAI gym environment for EPRI OpenDSS, using OpenDSS's native Python COM interface.

yyystg/HEM-DeepRL-v2-1

Home Energy Management based on Deep Reinforcement Learning Approach.

yyystg/AlwaysSafe

Code for the paper "AlwaysSafe: Reinforcement Learning Without Safety Constraint Violations During Training"

yyystg/CityLearn

Official reinforcement learning environment for demand response and load shaping

yyystg/DRL-code-pytorch

Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.

yyystg/DRL-for-Energy-Systems-Optimal-Scheduling

The source code for Performance comparision of Deep RL algorithms for Energy Systems Optimal Scheduling

yyystg/DRL-for-microgrid-energy-management

We study the performance of various deep reinforcement learning algorithms for the problem of microgrid’s energy management system. We propose a novel microgrid model that consists of a wind turbine generator, an energy storage system, a population of thermostatically controlled loads, a population of price-responsive loads, and a connection to the main grid. The proposed energy management system is designed to coordinate between the different sources of flexibility by defining the priority resources, the direct demand control signals and the electricity prices. Seven deep reinforcement learning algorithms are implemented and empirically compared in this paper. The numerical results show a significant difference between the different deep reinforcement learning algorithms in their ability to converge to optimal policies. By adding an experience replay and a second semi-deterministic training phase to the well-known Asynchronous advantage actor critic algorithm, we achieved considerably better performance and converged to superior policies in terms of energy efficiency and economic value.

yyystg/ElegantRL

Scalable and Elastic Deep Reinforcement Learning Using PyTorch. Please star. 🔥

yyystg/EVDPEP

Probabilistic Deep Learningfor Electric-Vehicle Energy-Use Prediction

yyystg/federated-double-deep-Q_network-

A framework that exploits the potentials of distributed federated learning and double deep Q-networks to minimize joint energy and delay in IoT networks

yyystg/fry_course_materials

范仁义录播课资料，会依次推出各种完全免费的前端、后端、大数据、人工智能等课程，课程网站： https://fanrenyi.com ； b站课程地址： https://space.bilibili.com/45664489 ；

yyystg/gen_pandapower_pv

Network generation for paper Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks.

yyystg/grid

simple pytorch baseline for L2RPN

yyystg/heating-RL-agent

A Pytorch DQN and DDPG implementation for a smart home energy management system under varying electricity price.

yyystg/HEM-DeepRL-v2

Home Energy Management based on Deep Reinforcement Learning Approach.

yyystg/hybrid-action-RL

Hybrid action space reinforcement learning algorithms.

yyystg/L2RPN_WCCI_a_Solution

Repository for L2RPN WCCI 2020 competition. One possible solution.

yyystg/microgrid_demo

yyystg/MIMO_DRL_Building_control

Deep reinforcement learning-based control of room temperature and bidirectional EV charging

yyystg/openmodelica-microgrid-gym

OpenModelica Microgrid Gym (OMG): An OpenAI Gym Environment for Microgrids

yyystg/powergym

A Gym-like environment for Volt-Var control in power distribution systems.

yyystg/pymgrid

pymgrid is a python library to generate and simulate a large number of microgrids.

yyystg/pypownet

A power network simulator with a Reinforcement Learning-focused usage.

yyystg/rl4uc

Reinforcement learning for unit commitment

yyystg/RL_VPP_Thesis

Thesis based on the development of a RL agent that manages a VPP through EVs charging stations. Main optimization objectives of the VPP are: Valley filling and peak shaving. Main action performed to reach objectives are: storage of Renewable energy resources and power push in the grid at high demand times. Assumptions of high number of vehicles connected for minimum time of 3-4 hours in the grid.

yyystg/RLGC

An open-source platform for applying Reinforcement Learning for Grid Control (RLGC)

yyystg/smart-rl-mg

Reinforcement Learning + Microgrids for OpenDSS with the Stanford Microgrid Analysis and Research Training internship

yyystg/Vanilla-DQN-for-Bat

Deep Reinforcement Learning Techniques for Energy Management of Networked Microgrids

yyystg/WCSAC

yyystg/yyystg

Config files for my GitHub profile.