tahanakabi/DRL-for-microgrid-energy-management tahanakabi/DRL-for-microgrid-energy-management

  • Stars
    star
    152
  • Rank 244,685 (Top 5 %)
  • Language
    HTML
  • License
    MIT License
  • Created almost 5 years ago
  • Updated about 1 year ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
tahanakabi/DRL-for-microgrid-energy-management
github

tahanakabi

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

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.

Deep Reinforcement Learning for Microgrid Energy Management

This repository contains an implementation of a Deep Reinforcement Learning (DRL) algorithm for managing the energy demand and supply of a microgrid. The implementation is built using Python and is based on the OpenAI Gym environment.

Installation

Clone the repository and navigate to the directory
Create a conda environment
conda env create -f conda.yaml
Activate the environment
conda activate tf2-gpu

Usage

To train the DRL agent, you can use the A3C_plusplus.py file.
python A3C_plusplus.py --train

To evaluate the performance of a trained model, you can use the same file with the option --test.

python A3C_plusplus.py --test

Contributing

Contributions to this repository are welcome! If you find a bug or have an idea for an improvement, please submit a pull request.

License

This code is released under the MIT License. More information about this project can be found at: https://doi.org/10.1016/j.segan.2020.100413

More Repositories

1

Optimal-Price-Based-control-of-heterogeneous-thermostatically-controlled-loads-under-uncertainty-usi

we consider the problem of thermostatically controlled load (TCL) control through dynamic electricity prices, under partial observability of the environment and uncertainty of the control response. The problem is formulated as a Markov decision process where an agent must find a near-optimal pricing scheme using partial observations of the state and action. We propose a long-short-term memory (LSTM) network to learn the individual behaviors of TCL units. We use the aggregated information to predict the response of the TCL cluster to a pricing policy. We use this prediction model in a genetic algorithm to find the best prices in terms of profit maximization in an energy arbitrage operation. The simulation results show that the proposed method offers a profit equal to 96% of the theoretical optimal solution.
Python
16
star
2

Deep-Reinforcenment-learning-for-TCL-control

This is an attempt to implement the RL control method used in https://arxiv.org/pdf/1604.08382.pdf
Python
9
star
3

microgrid_demo

Python
8
star
4

An-ANN-LSTM-based-Model-for-Learning-Individual-Customer-Behavior-in-Response-to-Electricity-Prices

An ANN-LSTM based Model for Learning Individual Customer Behavior in Response to Electricity Prices
Python
8
star
5

GHSOM-clustering

A GHSOM algorithm for electricity users classification
Python
3
star
6

RNN_predict_robot_positions

The aim of this project is to predict the next 60 positions of a moving robot given training data and the previous positions. We used a RNN with long short term memory to predict the next positions as a time series.
Python
2
star
7

binary_classification

Python
1
star
8

recommender_system_KNN

Python
1
star