☆ 4.1 Article

DRL-Based Slice Admission Using Overbooking in 5G Networks

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Information Systems

Probabilistic-Forecasting-Based Admission Control for Network Slicing in Software-Defined Networks

Weiwei Jiang et al.

Summary: This study proposes a DeepAR-based slice admission control mechanism for sequential decision making for network slice requests in SDN, with the support of the SDN controller. The effectiveness of the proposed mechanisms is validated through experiments based on real-world historical traffic data.

IEEE INTERNET OF THINGS JOURNAL (2022)

Add to Collection

Article Computer Science, Information Systems

Admission Control for 5G Core Network Slicing Based on Deep Reinforcement Learning

William F. Villota-Jacome et al.

Summary: This article proposes mechanisms based on reinforcement learning and deep reinforcement learning for admission control and resource allocation in network slicing. These mechanisms can meet the QoS requirements of 5G use-cases and improve the service provider's profit and resource utilization.

IEEE SYSTEMS JOURNAL (2022)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Slice admission control using overbooking for enhancing provider revenue in 5G Networks

Shivani Saxena et al.

Summary: Network Slicing introduces a new business model for Infrastructure Providers by allowing multiple tenants to request services, and utilizing overbooking to maximize revenue gain and resource utilization. The proposed approach significantly outperforms other mechanisms in terms of revenue gain and resource utilization.

PROCEEDINGS OF THE IEEE/IFIP NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM 2022 (2022)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Multi-Agent Deep Reinforcement Learning for Slicing and Admission Control in 5G C-RAN

Muhammad Sulaiman et al.

Summary: This paper proposes a method that uses multi-agent Deep Reinforcement Learning (DRL) to solve the problems of network slicing and slice Admission Control (AC). The proposed DRL approach can learn the dynamics of slice-request traffic and effectively address these joint problems.

PROCEEDINGS OF THE IEEE/IFIP NETWORK OPERATIONS AND MANAGEMENT SYMPOSIUM 2022 (2022)

Add to Collection

Proceedings Paper Computer Science, Information Systems

5G Network Slice Admission Control Using Optimization and Reinforcement Learning

Md Ariful Haque et al.

Summary: This study examines two complementary approaches to address the challenge of network slice admission control: dynamically evaluating and accepting slices that generate higher revenue using optimization algorithms, and automating admission decisions through reinforcement learning. Both approaches aim to maximize network operator revenue.

2022 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC) (2022)

Add to Collection

Article Computer Science, Information Systems

A Comprehensive Survey on the E2E 5G Network Slicing Model

Mohammed Chahbar et al.

Summary: This article addresses the lack of consideration for Network Slice (NS) modeling details from Standards Developing Organizations (SDOs) in End-to-End (E2E) NS implementations. It provides a general architecture for E2E network slicing functionality before delving into domain-specific visions and surveys the NS modeling works in Radio Access Networks (RAN), Core Networks (CN), and Transport Networks (TN). The goal is to clarify the E2E Network Slicing process and propose integrating data models developed by IETF working groups in the context of the ACTN architecture for managing Transport NSs.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2021)

Add to Collection

Proceedings Paper Computer Science, Information Systems

A Reinforcement Learning-Based Admission Control Strategy for Elastic Network Slices

Zhouxiang Wu et al.

Summary: This paper introduces a lightweight deep reinforcement learning model for intelligent admission control decisions for elastic and inelastic network slice requests. The model achieves higher revenue and acceptance rates compared to traditional heuristic methods, can be deployed without GPUs, and requires a relatively small amount of data for training while maintaining stable performance. Additionally, a Recurrent Neural Network is used to encode variable-size environments and train the encoder with the RL model.

2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) (2021)

Add to Collection

Proceedings Paper Computer Science, Information Systems

R-Learning-Based Admission Control for Service Federation in Multi-domain 5G Networks

Bahador Bakhshi et al.

Summary: This paper discusses the importance of network service federation in 5G/B5G networks and the role of smart admission control in expanding service offerings. Through theoretical analysis, the optimal AC policy is determined, and Q-Learning and R-Learning algorithms are used to approximate the optimal policy for practical deployment. Simulation results demonstrate that learning approaches outperform greedy policies and achieve good performance under various system configurations.

2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) (2021)

Add to Collection

Article Computer Science, Information Systems

A Machine Learning Approach to 5G Infrastructure Market Optimization

Dario Bega et al.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2020)

Add to Collection

Article Computer Science, Hardware & Architecture

On Provisioning Slices and Overbooking Resources in Service Tailored Networks of the Future

Conor Sexton et al.

IEEE-ACM TRANSACTIONS ON NETWORKING (2020)

Add to Collection

Article Engineering, Electrical & Electronic

A Slice Admission Policy Based on Big Data Analytics for Multi-Tenant 5G Networks

Muhammad Rehan Raza et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2019)

Add to Collection

Article Computer Science, Hardware & Architecture

AN OVERVIEW OF NETWORK SLICING FOR 5G

Shunliang Zhang

IEEE WIRELESS COMMUNICATIONS (2019)

Add to Collection

Article Computer Science, Hardware & Architecture

RL-NSB: Reinforcement Learning-Based 5G Network Slice Broker

Vincenzo Sciancalepore et al.

IEEE-ACM TRANSACTIONS ON NETWORKING (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Reinforcement Learning for Slicing in a 5G Flexible RAN

Muhammad Rehan Raza et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2019)

Add to Collection

Article Computer Science, Information Systems

Q-Learning Algorithms: A Comprehensive Classification and Applications

Beakcheol Jang et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

5G Wireless Network Slicing for eMBB, URLLC, and mMTC: A Communication-Theoretic View

Petar Popovski et al.

IEEE ACCESS (2018)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Overbooking Network Slices through Yield-driven End-to-End Orchestration

Josep Xavier Salvat et al.

CONEXT'18: PROCEEDINGS OF THE 14TH INTERNATIONAL CONFERENCE ON EMERGING NETWORKING EXPERIMENTS AND TECHNOLOGIES (2018)

Add to Collection

Proceedings Paper Energy & Fuels

Fundamental Q-learning Algorithm in Finding Optimal Policy

Canyu Sun

2017 INTERNATIONAL CONFERENCE ON SMART GRID AND ELECTRICAL AUTOMATION (ICSGEA) (2017)

Add to Collection

Article Computer Science, Information Systems

Markov Decision Processes With Applications in Wireless Sensor Networks: A Survey

Mohammad Abu Alsheikh et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2015)

Add to Collection

Article Engineering, Electrical & Electronic

Software-Defined Networking: A Comprehensive Survey

Diego Kreutz et al.

PROCEEDINGS OF THE IEEE (2015)

Add to Collection

Article Computer Science, Information Systems

A Survey of 5G Network: Architecture and Emerging Technologies

Akhil Gupta et al.

IEEE ACCESS (2015)

Add to Collection

Article Economics

Forecasting models and prediction intervals for the multiplicative Holt-Winters method

AB Koehler et al.

INTERNATIONAL JOURNAL OF FORECASTING (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.