Deep Reinforcement Learning Based Dynamic Resource Allocation in 5G Ultra-Dense Networks

2019 ◽  
Author(s):  
Zhiyong Liu ◽  
Xin Chen ◽  
Ying Chen ◽  
Zhuo Li
Keyword(s):  
Resource Allocation ◽  
Reinforcement Learning ◽  
Dynamic Resource Allocation ◽  
Dense Networks ◽  
Dynamic Resource

scholarly journals Dynamic Resource Allocation with Integrated Reinforcement Learning for a D2D-Enabled LTE-A Network with Access to Unlicensed Band

2016 ◽  
Vol 2016 ◽  
pp. 1-18 ◽  
Author(s):  
Alia Asheralieva ◽  
Yoshikazu Miyanaga
Keyword(s):  
Resource Allocation ◽  
Reinforcement Learning ◽  
Channel Allocation ◽  
Dynamic Resource Allocation ◽  
Throughput Maximization ◽  
Cellular Radio ◽  
Resource Allocation Algorithm ◽  
Stochastic Optimization Problem ◽  
Player Game ◽  
Dynamic Resource

We propose a dynamic resource allocation algorithm for device-to-device (D2D) communication underlying a Long Term Evolution Advanced (LTE-A) network with reinforcement learning (RL) applied for unlicensed channel allocation. In a considered system, the inband and outband resources are assigned by the LTE evolved NodeB (eNB) to different device pairs to maximize the network utility subject to the target signal-to-interference-and-noise ratio (SINR) constraints. Because of the absence of an established control link between the unlicensed and cellular radio interfaces, the eNB cannot acquire any information about the quality and availability of unlicensed channels. As a result, a considered problem becomes a stochastic optimization problem that can be dealt with by deploying a learning theory (to estimate the random unlicensed channel environment). Consequently, we formulate the outband D2D access as a dynamic single-player game in which the player (eNB) estimates its possible strategy and expected utility for all of its actions based only on its own local observations using a joint utility and strategy estimation based reinforcement learning (JUSTE-RL) with regret algorithm. A proposed approach for resource allocation demonstrates near-optimal performance after a small number of RL iterations and surpasses the other comparable methods in terms of energy efficiency and throughput maximization.

scholarly journals Interference Management with Dynamic Resource Allocation Method on Ultra-Dense Networks in Femto-Macrocellular Network

2021 ◽  
Vol 17 (4) ◽  
Author(s):  
Misfa Susanto ◽  
Sitronella Nurfitriani Hasim ◽  
Helmy Fitriawan
Keyword(s):  
Resource Allocation ◽  
Cellular Networks ◽  
Interference Management ◽  
Dynamic Resource Allocation ◽  
Performance Parameters ◽  
Cell Edge ◽  
Dense Networks ◽  
Allocation Method ◽  
Dynamic Resource

Ultra-Dense Network (UDN) which is formed from femtocells densely deployed is known as one of key technologies for 5th generation (5G) cellular networks. UDN promises for increased capacity and quality of cellular networks. However, UDN faces more complex interference problems than rarely deployed femtocells, worse on femtocells that are located on cell edge area of macrocell. Therefore, mitigating or reducing effects of interferences is an important issue in UDN. This paper focuses on interference management using dynamic resource allocation for UDN. Types of interference considered in this study are cross-tier (macrocell-to-femtocell) and co-tier (femtocellto-femtocell) interferences for uplink transmission. We consider several scenarios to examine the dynamic resource allocation method for UDN in case of femtocells deployed in the whole area of microcell and in the cell edge area of macrocell. Simulation experiment using MATLAB program has been carried out. The performance parameters that are collected from the simulation are Signal to Interference and Noise Ratio (SINR), throughput, and Bit Error Rate (BER). The obtained simulation results show that system using dynamic resource allocation method outperforms conventional system and the results were consistent for the collected performance parameters. The dynamic resource allocation promises to reduce the effects of interference in UDN.

Sign in / Sign up

Export Citation Format

Share Document