Code of Paper: Smart Economic and Mobility Aware Cooperation for Resource Sharing in Multi-Tier Edge Slicing
- Citation Author(s):
- Submitted by:
- ali nouruzi
- Last updated:
- Fri, 05/13/2022 - 14:05
- Data Format:
In this paper, we propose a novel cooperative resource sharing in a multi-tier edge slicing networks which is
robust to imperfect channel state information (CSI) caused by user equipments’ (UEs) mobility. Due to the mobility
of UEs, the dynamic requirements of their tasks, and the limited resources of the network, we propose a smart joint
dynamic pricing and resources sharing (SJDPRS) scenario that can incentivize the infrastructure provider (InP) and
mobile network operators (MNOs). Aiming to maximize the profits of UEs, MNOs and the InP under the task
fulfillment constraints, we formulate an optimization problem by deploying the multi-objective optimization method
where in addition to the resource allocation variables, the price values are also the optimization variables. To solve
the problem, we adopt a new deep reinforcement learning (DRL) method based on a carefully designed reward
function. The simulation results indicate that the proposed resource sharing scenario can increase total profits for
the UEs, MNOs, and InP in comparison to non-cooperative case, while also providing almost complete fairness
among the players. In specific, the obtained results show that the average fulfilled tasks, minimum profit of MNOs,
and average profit for the InP enhanced by 78%, 75%, and 79%, respectively.
The main source code of this paper is provided in this data set. For the main parameters such as delay, data size and number of users, please check the "data_file.py" and "main.py".
In addition, to evaluate the dynamic pricing process please check " profit_cal_file.py".
The network resources are defined in "resources_file".
The state of the network is calculated in "state_cal_file".
- codes.zip (103.54 kB)