Datasets
Standard Dataset
AI-Based Secure NOMA and Cognitive Radio enabled Green Communications: Channel State Information and Battery Value Uncertainties
- Citation Author(s):
-
MohsenPourghasemian
- Submitted by:
- Mohsen Pourghasemian
- Last updated:
- Tue, 05/17/2022 - 22:18
- DOI:
- 10.21227/d95p-qz45
- Research Article Link:
- License:
512 Views- Categories:
Abstract
In this paper, the security-aware robust resource allocation in energy harvesting cognitive radio networks is considered with cooperation between two transmitters while there are uncertainties in channel gains and battery energy value. To be specific, the primary access point harvests energy from the green resource and uses time switching protocol to send the energy and data towards the secondary access point (SAP). Using power-domain non-orthogonal multiple access technique, the SAP helps the primary network to improve the security of data transmission by using the frequency band of the primary network. In this regard, we introduce the problem of maximizing the proportional-fair energy efficiency (PFEE) considering uncertainty in the channel gains and battery energy value subject to the practical constraints. Moreover, the channel gain of the eavesdropper is assumed to be unknown. Employing the decentralized partially observable Markov decision process, we investigate the solution of the corresponding resource allocation problem. We exploit multi-agent with single reward deep deterministic policy gradient (MASRDDPG) and recurrent deterministic policy gradient (RDPG) methods. These methods are compared with the state-of-the-art ones like multi-agent and single-agent DDPG. Simulation results show that both MASRDDPG and RDPG methods, outperform the state-of-the-art methods by providing more PFEE to the network.
This repository includes the DDPG, MADDPG, MASRDDPG, and RDPG deep reinforcement learning based on the paper "AI-Based Secure NOMA and Cognitive Radio enabled Green Communications: Channel State Information and Battery Value Uncertainties".
Instructions:
## Special thanks to Dr. Phil Winder ##
## Dependencies
- Python 3.6+ (tested with 3.6 and 3.7)
- tensorflow 1.15+
- gym
- numpy
- networkx
- matplotlib
# System minimum requirements
-CPU: Intel Corei3 at 2.0 GHz.
-RAM: 4 GB.
# Preparing
All environments written on top of gym environment. There are 12 different environment for MASRDDPG, MADDPG, RDPG, and DDPG with three uncertainty approaches as:
"AI_GreenComm_TS_NOMA_W.py" (Worst case)
"AI_GreenComm_TS_NOMA_S.py", (Stochastic)
"AI_GreenComm_TS_NOMA_B.py", (Bernstein)
in the repository.
You need to add these environments into gym environment and register them. For creating and registering gym environment, please visit the URL below:
https://towardsdatascience.com/creating-a-custom-openai-gym-environment-...
After adding those environments, the code is prepared for execution.
#################### Example Usage######################
For running each method, go to the relevant directory for each method, i.e., MASRDDPG or RDPG, and change the ‘env_name’ in gym.make(‘env_name’) in main.py file based on the name that you registered in gym. Then, simply type the following command:
$ python main.py
The code for each method generates some text files related to instantaneous and cumulative secrecy rate, energy consumption, reward, and other values in the "instant" and "cumulative" directories, respectively. You need to create these directories.
Finally, you can easily plot the results by importing the text files in to excel or MATLAB.
