Resource allocation of fog radio access network based on deep reinforcement learning

Tan, Jingru; Guan, Wenbo

doi:10.1002/eng2.12497

Cited by 17 publications

(7 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…𝑄-learning is a renowned reinforcement learning algorithms 33 . During the interaction with the environment, the agent receives rewards 𝑅 corresponding to executed action 𝑎.…”

Section: The Designed Q-learning Algorithmmentioning

confidence: 99%

A Q-learning Algorithm for Two-Stage Hybrid Flow Shop Scheduling

Lu,

Liu,

Zhang

2024

Preprint

View full text Add to dashboard Cite

With the increasing demand for customization, flow shop scheduling tends to process multi-variety small batch products. Thus, there are frequent switches between batches. Frequent switchovers between different sets are required during batch changeover, where machine setups may be necessary. This paper investigates scheduling optimization and work-in-process inventory optimization problems in a hybrid flow shop with rolling processing requirements. Developing continuous processing conditions to meet rolling processing requirements presents a significant challenge. In this work, continuous processing conditions are derived. Subsequently, a linear programming model is designed to find an optimal solution for this scheduling problem. Formulas for calculating work-in-process inventory are presented. To enhance work-in-process storage, a greedy algorithm with bubble sort and a Q-learning algorithm with a modified ε-policy are proposed to find an optimized product sequence and reduce work-in-process inventory, respectively. Numerical experiments evaluate the effectiveness and efficiency of the proposed methods.

show abstract

“…𝑄-learning is a renowned reinforcement learning algorithms 33 . During the interaction with the environment, the agent receives rewards 𝑅 corresponding to executed action 𝑎.…”

Section: The Designed Q-learning Algorithmmentioning

confidence: 99%

A Q-learning Algorithm for Two-Stage Hybrid Flow Shop Scheduling

Lu,

Liu,

Zhang

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…For a fully connected network with J layers, the operation time of each update is given by J−1 j=0 u j u j+1 , where u j denotes the number of neurons in layer j. Therefore, the time complexity for deep Q-learning is expressed by O(mt J−1 j=0 u j u j+1 ) [34]. Training time for Q-learning is relatively shorter due to the more straightforward structure of updating the Qtable, which does not require the extensive computational resources that deep neural networks demand.…”

Section: Complexity Analysismentioning

confidence: 99%

Radio Resource Management for Intelligent Neutral Host (INH) in Multi-Operator Environments

Navidan,

Naseri,

Moerman

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

This work was executed within the imec.ICON 5GECO project, a research project bringing together academic research partners and industry partners. The 5GECO project was co-financed by imec and received support from Flanders Innovation Entrepreneurship (project nr. HBC.2021.0673). This work is also funded by the Horizon Europe program under the MCSA Staff Exchanges 2021 grant agreement 101086218 (EVOLVE project).

show abstract

“…AI has been proven effective for network optimization and management of satellite and terrestrial networks in previous studies [101]- [105]. However, previous applications of AI in networking rely on external simulation tools, e.g., TensorFlow and PyTorch.…”

Section: Ai Integration With Stin Simulationmentioning

confidence: 99%

Network Simulators for Satellite-Terrestrial Integrated Networks: A Survey

Jiang,

Zhan,

Xiao

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Satellite-terrestrial integrated networks have been proposed as a promising solution to provide global seamless coverage in next-generation communication networks. To enable the integration of satellite and terrestrial networks, network simulation is a fundamental and economically efficient step compared to the high cost of field trial and real-world system deployment. Simulation challenges arise with the fast growth of LEO mega-constellations, including frequent re-connection and handover, long satellite transmission delay, high dynamics of satellite network topologies, and the integration of heterogeneous infrastructures. More requirements emerge for satellite-terrestrial integrated simulation, including fidelity, scalability, extensibility, agility, and real-time. However, there is a lack of a state-of-the-art review for relevant simulators. To the best of our knowledge, this paper is the most comprehensive and latest survey that covers network simulators for satellite-terrestrial integrated networks, with all or partial simulation functionalities for satellite orbit simulation, physical layer modeling, and network protocols and algorithms. Compared with existing surveys, this survey contributes from three aspects: (1) an up-to-date collection and a comprehensive taxonomy of simulation tools in the past decade; (2) a summary of the main requirements and challenges; and (3) an inspiring summary for new research opportunities and publicly available simulation tools for follow-up research.

show abstract

Resource allocation of fog radio access network based on deep reinforcement learning

Cited by 17 publications

References 45 publications

A Q-learning Algorithm for Two-Stage Hybrid Flow Shop Scheduling

A Q-learning Algorithm for Two-Stage Hybrid Flow Shop Scheduling

Radio Resource Management for Intelligent Neutral Host (INH) in Multi-Operator Environments

Network Simulators for Satellite-Terrestrial Integrated Networks: A Survey

Contact Info

Product

Resources

About