☆ 4.2 Article

On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement

JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT (2022)

Related references

Note: Only part of the references are listed.

Article Telecommunications

Combining Deep Reinforcement Learning With Graph Neural Networks for Optimal VNF Placement

Penghao Sun et al.

Summary: NFV technology uses software to implement virtual instances of network functions, reducing costs on middlebox hardware. VNF instances require multiple resource types and considering both resource utilization and QoS is NP-hard. DeepOpt, combining DRL and GNN, outperforms existing VNF placement schemes.

IEEE COMMUNICATIONS LETTERS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Robustness and performance of Deep Reinforcement Learning

Raid Rafi Omar Al-Nima et al.

Summary: The paper introduces a novel approach called GANC to improve the robustness and performance of a DRL network by maximizing neuron coverage through augmented inputs. The method is applied in self-driving car applications, achieving very promising outcomes.

APPLIED SOFT COMPUTING (2021)

Add to Collection

Proceedings Paper Telecommunications

Controlled Deep Reinforcement Learning for Optimized Slice Placement

Jose Jurandir Alves Esteves et al.

Summary: The paper introduces a hybrid ML-heuristic approach named Heuristically Assisted Deep Reinforcement Learning (HA-DRL) for solving Network Slice Placement Optimization. This approach leverages recent works on Deep Reinforcement Learning (DRL) and Virtual Network Embedding (VNE), using a heuristic function to optimize exploration of the action space, prioritizing reliable actions indicated by an efficient heuristic algorithm. Evaluation results demonstrate that the proposed HA-DRL algorithm can accelerate learning of an efficient slice placement policy, improving slice acceptance ratio compared to state-of-the-art approaches based solely on reinforcement learning.

2021 IEEE INTERNATIONAL MEDITERRANEAN CONFERENCE ON COMMUNICATIONS AND NETWORKING (IEEE MEDITCOM 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Learn to improve: A novel deep reinforcement learning approach for beyond 5G network slicing

Anouar Rkhami et al.

Summary: Network slicing is a key technology in 5G and B5G networks, allowing multiple virtual networks to coexist on the same physical infrastructure. However, resource allocation, known as VNEP, is a major challenge. Heuristics, meta-heuristics, and DRL-based solutions have been proposed, but they may result in suboptimal solutions and increased costs.

2021 IEEE 18TH ANNUAL CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE (CCNC) (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Optimal VNF Placement via Deep Reinforcement Learning in SDN/NFV-Enabled Networks

Jianing Pei et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2020)

Add to Collection

Article Computer Science, Hardware & Architecture

Robust Machine Learning Systems: Challenges,Current Trends, Perspectives, and the Road Ahead

Muhammad Shafique et al.

IEEE DESIGN & TEST (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Automatic Virtual Network Embedding: A Deep Reinforcement Learning Approach With Graph Convolutional Networks

Zhongxia Yan et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2020)

Add to Collection

Article Computer Science, Information Systems

Data-driven dynamic resource scheduling for network slicing: A Deep reinforcement learning approach

Haozhe Wang et al.

INFORMATION SCIENCES (2019)

Add to Collection

Article Computer Science, Information Systems

A Deep Reinforcement Learning Approach for VNF Forwarding Graph Embedding

Pham Tran Anh Quang et al.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2019)

Add to Collection

Article Computer Science, Information Systems

A Survey on the Placement of Virtual Resources and Virtual Network Functions

Abdelquoddouss Laghrissi et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2019)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

DeepViNE: Virtual Network Embedding with Deep Reinforcement Learning

Mahdi Dolati et al.

IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM 2019 WKSHPS) (2019)

Add to Collection

Proceedings Paper Engineering, Electrical & Electronic

Multi-domain non-cooperative VNF-FG embedding: A deep reinforcement learning approach

Pham Tran Anh Quang et al.

IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM 2019 WKSHPS) (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

A novel reinforcement learning algorithm for virtual network embedding

Haipeng Yao et al.

NEUROCOMPUTING (2018)

Add to Collection

Article Computer Science, Hardware & Architecture

A fast robust optimization-based heuristic for the deployment of green virtual network functions

Antonio Marotta et al.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2017)

Add to Collection

Article Computer Science, Hardware & Architecture

On the energy cost of robustness for green virtual network function placement in 5G virtualized infrastructures

Antonio Marotta et al.

COMPUTER NETWORKS (2017)

Add to Collection

Article Computer Science, Information Systems

Resource Allocation in NFV: A Comprehensive Survey

Juliver Gil Herrera et al.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2016)

Add to Collection

Article Computer Science, Information Systems

Resource Allocation in NFV: A Comprehensive Survey

Juliver Gil Herrera et al.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2016)

Add to Collection

Article Computer Science, Theory & Methods

The power of two choices in randomized load balancing

M Mitzenmacher

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.