Green Deep Reinforcement Learning for Radio Resource Management: Architecture, Algorithm Compression, and Challenges

  title={Green Deep Reinforcement Learning for Radio Resource Management: Architecture, Algorithm Compression, and Challenges},
  author={Zhiyong Du and Yansha Deng and Weisi Guo and Arumugam Nallanathan and Qi-hui Wu},
  journal={IEEE Vehicular Technology Magazine},
Artificial intelligence (AI) heralds a step-change in wireless networks but may also cause irreversible environmental damage due to its high energy consumption. Here, we address this challenge in the context of 5G and beyond, where there is a complexity explosion in radio resource management (RRM). For high-dimensional RRM problems in a dynamic environment, deep reinforcement learning (DRL) provides a powerful tool for scalable optimization, but it consumes a large amount of energy over time… 

Figures and Tables from this paper

Multi-Objective Optimization of Energy Saving and Throughput in Heterogeneous Networks Using Deep Reinforcement Learning

A proximal policy (PPO)-based multi-objective algorithm using the actor-critic model that is realized as an optimistic linear support framework in which the PPO algorithm searches for feasible solutions iteratively and can achieve throughput and energy savings comparable to the CPLEX.

Partially Explainable Big Data Driven Deep Reinforcement Learning for Green 5G UAV

  • Weisi Guo
  • Computer Science
    ICC 2020 - 2020 IEEE International Conference on Communications (ICC)
  • 2020
This work designs a Double Dueling Deep Q-learning Neural Network (DDDQN) with Prioritised Experience Replay (PER) and fixed Q-targets to achieve stable performance and avoid over-fitting, offering performance gains over naive DQN algorithms.

Machine Learning for Physical Layer in 5G and beyond Wireless Networks: A Survey

A comprehensive survey on 5G technologies that emphasize machine learning-based solutions to cope with existing and future challenges and signaling techniques for 5G massive multiple-input and multiple-output and beam-forming techniques to enhance data rates with efficient spectrum sharing are provided.

Trustworthy Deep Learning in 6G-Enabled Mass Autonomy: From Concept to Quality-of-Trust Key Performance Indicators

The concept of trustworthy autonomy for 6G is outlined, including essential elements such as how explainable AI (XAI) can generate the qualitative and quantitative modalities of trust.

A Survey on Requirements of Future Intelligent Networks: Solutions and Future Research Directions

The core objectives of this study are to provide a taxonomy of requirements envisioned for end-to-end FIN, relevant ML techniques, and their analysis to find research gaps, open issues, and future research directions and recommend an ML pipeline based architecture for FIN.

Deep Reinforcement Learning for Radio Resource Allocation and Management in Next Generation Heterogeneous Wireless Networks: A Survey

A systematic in-depth, and comprehensive survey of the applications of DRL techniques in RRAM for next generation wireless networks to guide and stimulate more research endeavors towards building efficient and fine-grained DRL-based RRAM schemes for future wireless networks.



A deep reinforcement learning based framework for power-efficient resource allocation in cloud RANs

A novel DRL-based framework for power-efficient resource allocation in cloud RANs is presented, which can achieve significant power savings while meeting user demands, and it can well handle highly dynamic cases.

Learning Deterministic Policy with Target for Power Control in Wireless Networks

A Deep Reinforcement Learning with Deterministic Policy and Target (DRL-DPT) framework for ICIC in wireless networks improves up to 15% of energy efficiency with faster convergence rate.

Power Control Based on Deep Reinforcement Learning for Spectrum Sharing

An asynchronous advantage actor critic (A3C)-based power control of SU that is a parallel actor-learners framework with root mean square prop (RMSProp) optimization is proposed that enables the network to converge quickly.

Applications of Deep Reinforcement Learning in Communications and Networking: A Survey

This paper presents a comprehensive literature review on applications of deep reinforcement learning (DRL) in communications and networking, and presents applications of DRL for traffic routing, resource sharing, and data collection.

Artificial Intelligence-Based Resource Allocation in Ultradense Networks: Applying Event-Triggered Q-Learning Algorithms

This article discusses resource allocation schemes based on AI algorithms in UDNs and proposes an event-triggered, reinforcement-learning-based subchannel and power allocation algorithm that can be applied to UDN scenarios.

Deep-Reinforcement Learning Multiple Access for Heterogeneous Wireless Networks

The use of neural networks in DRL allows for fast convergence to optimal solutions and robustness against perturbation in hyper- parameter settings, two essential properties for practical deployment of DLMA in real wireless networks.

Reinforcement Learning for Real-Time Optimization in NB-IoT Networks

The results show that the proposed reinforcement learning-based approaches considerably outperform the conventional heuristic approaches based on load estimation (LE-URC) in terms of the number of served IoT devices and that LA-Q and DQN can be good alternatives for tabular-Q to achieve almost the same performance with much less training time.

Deep Reinforcement Learning for Resource Management in Network Slicing

This paper investigates the application of deep reinforcement learning in solving some typical resource management for network slicing scenarios, which include radio resource slicing and priority-based core network slicing, and demonstrates the advantage of DRL over several competing schemes through extensive simulations.

Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks

This work considers a dynamic multichannel access problem, where multiple correlated channels follow an unknown joint Markov model and users select the channel to transmit data, and proposes an adaptive DQN approach with the capability to adapt its learning in time-varying scenarios.

Optimal and Fast Real-Time Resource Slicing With Deep Dueling Neural Networks

This paper develops an optimal and fast real-time resource slicing framework that maximizes the long-term return of the network provider while taking into account the uncertainty of resource demands from tenants.