Distributed Robust Power Minimization for the Downlink of Multi-Cloud Radio Access Networks

Dhifallah, Oussama; Dahrouj, Hayssam; Al-Naffouri, Tareq Y.; Alouini, Mohamed‐Slim

doi:10.1109/tgcn.2017.2780449

Cited by 14 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Like any other optimization problems, optimization problems in a CRAN can be single objective addressing issues such as energy minimization, capacity maximization, etc. Many single objective optimization problems have been considered in literature [44]- [52], [54], [55], [57], [67]- [75], [77]- [79], [81]- [86], [88], [89]. Similarly, optimization problems can be multi-objective which can address multiple conflicting or nonconflicting objectives simultaneously.…”

Section: B Resource Allocation Parametersmentioning

confidence: 99%

A comprehensive survey on resource allocation for CRAN in 5G and beyond networks

Ejaz

Sharma

Saadat

et al. 2020

Journal of Network and Computer Applications

View full text Add to dashboard Cite

The diverse service requirements coming with the advent of sophisticated applications as well as a large number of connected devices demand for revolutionary changes in the traditional distributed radio access network (RAN). To this end, Cloud-RAN (CRAN) is considered as an important paradigm to enhance the performance of the upcoming fifth generation (5G) and beyond wireless networks in terms of capacity, latency, and connectivity to a large number of devices. Out of several potential enablers, efficient resource allocation can mitigate various challenges related to user assignment, power allocation, and spectrum management in a CRAN, and is the focus of this paper. Herein, we provide a comprehensive review of resource allocation schemes in a CRAN along with a detailed optimization taxonomy on various aspects of resource allocation. More importantly, we identity and discuss the key elements for efficient resource allocation and management in CRAN, namely: user assignment, remote radio heads (RRH) selection, throughput maximization, spectrum management, network utility, and power allocation. Furthermore, we present emerging use-cases including heterogeneous CRAN, millimeter-wave CRAN, virtualized CRAN, Non-Orthogonal Multiple Access (NoMA)-based CRAN and fullduplex enabled CRAN to illustrate how their performance can be enhanced by adopting CRAN technology. We then classify and discuss objectives and constraints involved in CRAN-based 5G and beyond networks. Moreover, a detailed taxonomy of optimization methods and solution approaches with different objectives is presented and discussed. Finally, we conclude the paper with several open research issues and future directions.

show abstract

Section: B Resource Allocation Parametersmentioning

confidence: 99%

A comprehensive survey on resource allocation for CRAN in 5G and beyond networks

Ejaz

Sharma

Saadat

et al. 2020

Journal of Network and Computer Applications

View full text Add to dashboard Cite

show abstract

“…There are many works that focused on enhancing energy efficiency in C-RAN. In [4], a network power minimisation problem is considered for C-RAN under per-user quality of service (QoS) and per-RRH transmit power constraints, as well as fronthaul capacity and channel state information (CSI) error constraints. This work proposes an alternating direction method of multipliers based algorithm to obtain the beamforming vectors and the quantisation noise covariance matrix.…”

Section: Related Workmentioning

confidence: 99%

Energy‐efficient BBU pool virtualisation for C‐RAN with quality of service guarantees

et al. 2020

View full text Add to dashboard Cite

“…Inspired by the above advantages of CRAN, resource allocation (RA) for CRAN has been extensively studied. Total throughput [8], transmission power [9], and EE [10] are the prevalent RA objective functions which quantify the CRAN system efficiency. These RA works, however, do not consider the energy switching cost of RRHs during optimization.…”

Section: Introductionmentioning

confidence: 99%

Double Deep Q-Network-Based Energy-Efficient Resource Allocation in Cloud Radio Access Network

2021

View full text Add to dashboard Cite

Cloud radio access network (CRAN) has been shown as an effective means to boost network performance. Such gain stems from the intelligent management of remote radio heads (RRHs) in terms of on/off operation mode and power consumption. Most conventional resource allocation (RA) methods, however, optimize the network utility without considering the switching overhead of RRHs in adjacent time intervals. When the network environment becomes time-correlated, mathematical optimization is not directly applicable. In this paper, we aim to optimize the energy efficiency (EE) subject to the constraints on per-RRH transmission power and user data rates. To this end, we formulate the EE problem as a Markov decision process (MDP) and subsequently adopt deep reinforcement learning (DRL) technique to reap the cumulative EE rewards. Our starting point is the deep Q network (DQN), which is a combination of deep learning and Q-learning. In each time slot, DQN configures the status of RRHs yielding the largest Q-value (known as state-action value) prior to solving a power minimization problem for active RRHs. To overcome the Q-value overestimation issue of DQN, we propose a Double DQN (DDQN) framework that obtains optimal reward better than DQN by separating the selected action from the target Q-value generator. Simulation results validate that the DDQN-based RA method is more energy-efficient than the DQN-based RA algorithm and a baseline solution.

show abstract

Distributed Robust Power Minimization for the Downlink of Multi-Cloud Radio Access Networks

Cited by 14 publications

References 15 publications

A comprehensive survey on resource allocation for CRAN in 5G and beyond networks

A comprehensive survey on resource allocation for CRAN in 5G and beyond networks

Energy‐efficient BBU pool virtualisation for C‐RAN with quality of service guarantees

Double Deep Q-Network-Based Energy-Efficient Resource Allocation in Cloud Radio Access Network

Contact Info

Product

Resources

About