Multi-Agent Deep Reinforcement Learning for Resource Allocation in the Multi-Objective HetNet

Nie, Hongrui; Li, Shaosheng; Liu, Yong

doi:10.1109/iwcmc51323.2021.9498647

Cited by 5 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [33,34], the CTDE approach is followed, where in [33] spectrum and energy efficiency are optimized concurrently, while in [34] user association and power allocation are optimized. Benchmarks show that CTDE converges faster than a fully centralized algorithm.…”

Section: Radio Resources and Power Allocationmentioning

confidence: 99%

Distributed Machine Learning and Native AI Enablers for End-to-End Resources Management in 6G

Karachalios,

Zafeiropoulos,

Kontovasilis

et al. 2023

Electronics

View full text Add to dashboard Cite

6G targets a broad and ambitious range of networking scenarios with stringent and diverse requirements. Such challenging demands require a multitude of computational and communication resources and means for their efficient and coordinated management in an end-to-end fashion across various domains. Conventional approaches cannot handle the complexity, dynamicity, and end-to-end scope of the problem, and solutions based on artificial intelligence (AI) become necessary. However, current applications of AI to resource management (RM) tasks provide partial ad hoc solutions that largely lack compatibility with notions of native AI enablers, as foreseen in 6G, and either have a narrow focus, without regard for an end-to-end scope, or employ non-scalable representations/learning. This survey article contributes a systematic demonstration that the 6G vision promotes the employment of appropriate distributed machine learning (ML) frameworks that interact through native AI enablers in a composable fashion towards a versatile and effective end-to-end RM framework. We start with an account of 6G challenges that yields three criteria for benchmarking the suitability of candidate ML-powered RM methodologies for 6G, also in connection with an end-to-end scope. We then proceed with a focused survey of appropriate methodologies in light of these criteria. All considered methodologies are classified in accordance with six distinct methodological frameworks, and this approach invites broader insight into the potential and limitations of the more general frameworks, beyond individual methodologies. The landscape is complemented by considering important AI enablers, discussing their functionality and interplay, and exploring their potential for supporting each of the six methodological frameworks. The article culminates with lessons learned, open issues, and directions for future research.

show abstract

Section: Radio Resources and Power Allocationmentioning

confidence: 99%

Distributed Machine Learning and Native AI Enablers for End-to-End Resources Management in 6G

Karachalios,

Zafeiropoulos,

Kontovasilis

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Yet, DeepRAT does not handle the multi-RAT Het-Net's joint optimization of both PA and RA. To maximize SE and EE, the authors of [124] presented a distributed multi-agent deep reinforcement learning (MADRL) for joint RA. The suggested distributed MADRL-Multi Optimization Problem (MOP) framework can deliver an optimal solution in few iterations.…”

Section: Deep Reinforcement Learningmentioning

confidence: 99%

A Comprehensive Survey on Radio Resource Management in 5G HetNets: Current Solutions, Future Trends and Open Issues

Agarwal

Togou

Ruffini

et al. 2022

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

The 5G network technologies are intended to accommodate innovative services with a large influx of data traffic with lower energy consumption and increased quality of service and user quality of experience levels. In order to meet 5G expectations, heterogeneous networks (HetNets) have been introduced. They involve deployment of additional low power nodes within the coverage area of conventional high power nodes and their placement closer to user underlay HetNets. Due to the increased density of small-cell networks and radio access technologies, radio resource management (RRM) for potential 5G HetNets has emerged as a critical avenue. It plays a pivotal role in enhancing spectrum utilization, load balancing, and network energy efficiency. In this paper, we summarize the key challenges i.e., cross-tier interference, co-tier interference, and user association-resource-power allocation (UA-RA-PA) emerging in 5G HetNets and highlight their significance. In addition, we present a comprehensive survey of RRM schemes based on interference management (IM), UA-RA-PA and combined approaches (UA-RA-PA + IM). We introduce a taxonomy for individual (IM, UA-RA-PA) and combined approaches as a framework for systematically studying the existing schemes. These schemes are also qualitatively analyzed and compared to each other. Finally, challenges and opportunities for RRM in 5G are outlined, and design guidelines along with possible solutions for advanced mechanisms are presented.

show abstract

“…The most promising solution is to enhance the abilities of existing cellular networks by using picocells and femtocells with different transmission power and coverage. These heterogeneous networks (HetNets) can offload data transmission of user equipments (UEs) from MBSs to picocell and femtocell base stations (PBSs/FBSs) with different transmission power and coverage [2]. In HetNet, users associate with MBSs, PBSs or FBSs, resulting in different user experiences.…”

Section: Introductionmentioning

confidence: 99%

Joint Optimization of User Association and Resource Allocation in HetNets: A parameterized-DRL Approach

Fu,

Li,

Tao

et al. 2024

Preprint

View full text Add to dashboard Cite

Facing the problem of resources utilization in of multiple wireless communication systems with multiple coverage, convergence of heterogeneous network (HetNets) can reduce the burden and decrease deployment costs of a single communication network. Due to the non-convexity of joint optimization and the difficulty to obtain the feasible solution of the mixed operation space (i.e. discrete operation versus continuous operation) of HetNets, so it is a formidable challenge to achieve global optimization of energy efficiency (EE) and spectral efficiency (SE) simultaneously when facing user association (discrete) together with power allocation (continuous). Unlike the method of deep reinforcement learning (DRL) by discretizing continuous space directly, we proposed a novel parameterized-DRL that maximizes the performance of joint EE-SE while ensuring the quality of service (QoS) of downlink user devices (UEs) in HetNets. In addition, to solve the computationally intensive problem in the state-action space, an algorithm of parameterized-experience-replay dueling double DQN with multi-agent priority (P-MAPD3QN) is introduced to obtain an almost optimal QoS. Simulation results show that this algorithm improves the effectiveness of the system by 4.9% over traditional D3QN algorithm in terms of system capacity and 13.1% in terms of joint EE-SE performance.

show abstract

Multi-Agent Deep Reinforcement Learning for Resource Allocation in the Multi-Objective HetNet

Cited by 5 publications

References 16 publications

Distributed Machine Learning and Native AI Enablers for End-to-End Resources Management in 6G

Distributed Machine Learning and Native AI Enablers for End-to-End Resources Management in 6G

A Comprehensive Survey on Radio Resource Management in 5G HetNets: Current Solutions, Future Trends and Open Issues

Joint Optimization of User Association and Resource Allocation in HetNets: A parameterized-DRL Approach

Contact Info

Product

Resources

About