In this paper, we propose a novel resource management scheme that jointly allocates the transmitpower and computational resources in a centralized radio access network architecture. The networkcomprises a set of computing nodes to which the requested tasks of different users are offloaded. Theoptimization problem minimizes the energy consumption of task offloading while takes the end-to-end latency, i.e., the transmission, execution, and propagation latencies of each task, into account.

Instructions: 

Notes on the simulation files:

DTO.m simulates the disjoint task offloading (DTO) method in the manuscript. This file receives the following parameters as its inputs:

1.   Number of single-antenna users, which is equal to the number of tasks

2.   Maximum acceptable latency of tasks

3.   Ratio of RAN latency to the maximum acceptable latency

4.   Computational load of each task

5.   Data size of each task

After receiving the parameters, DTO.m executes the disjoint method and returns the outputs as in the following:

1.      Acceptance Ratio

2.   Radio Transmission latency of all tasks

3.   Propagation latency of all tasks

4.   Execution latency of all tasks

 

JTO.m simulates the joint task offloading (JTO) method in the manuscript. This file receives the following parameters as its inputs:

1.      Number of single-antenna users, which is equal to the number of tasks.

2.   Maximum acceptable latency of tasks

3.   Computational load of each task

4.   Data size of each task.

After receiving the parameters, JTO.m executes the disjoint method and returns the outputs as in the following:

1.      Acceptance Ratio

2.   Radio Transmission latency of all tasks

3.   Propagation latency of all tasks

4.   Execution latency of all tasks.

Categories:
197 Views

The simulation code for the paper:

"AoI-Aware Resource Allocation for Platoon-Based C-V2X Networks via Multi-Agent Multi-Task Reinforcement Learning"

 

The overall architecture of the proposed MARL framework is shown in the figure.

 

Modified MADDPG: This algorithm trains two critics (different from legacy MADDPG) with the following functionalities:

Categories:
402 Views

# -*- coding: utf-8 -*-

"""

Created on Wed Feb 26 11:19:38 2020

 

@author: ali nouruzi

"""

 

import numpy as np

import random

Categories:
221 Views

This dataset contains the database of the transport block (TB) configurations .

Categories:
170 Views

Smart Grids (SG) are a novel paradigm introduced for optimizing the management of the power generation, transmission, distribution and consumption. A SG system can efficiently work only if all the components are connected through a communication network able to satisfy the SG applications requirements. Wireless communications are the most appropriate candidates for handling SG requirements due to their flexibility.

Categories:
83 Views

Smart Grids (SG) are a novel paradigm introduced for optimizing the management of the power generation, transmission, distribution and consumption. A SG system can efficiently work only if all the components are connected through a communication network able to satisfy the SG applications requirements. Wireless communications are the most appropriate candidates for handling SG requirements due to their flexibility.

Categories:
294 Views