Network Resource Allocation Strategy Based on Deep Reinforcement Learning

Zhang, Shidong; Wang, Chao; Zhang, Junsan; Duan, Youxiang; You, Xinhong; Zhang, Peiying

doi:10.1109/ojcs.2020.3000330

Cited by 16 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature [16,31], virtual networks acquire specific node and link resources, and the strategies based on the RL algorithm aim at selecting substrate nodes and links with abundant resources to embed VNRs. However, it is different in wireless network, where the requirement is transmission rate and the substrate network resources allocation strategy is indeterminate.…”

Section: Reinforcement Learning Environmentmentioning

confidence: 99%

Wireless Virtual Network Embedding Algorithm Based on Deep Reinforcement Learning

et al. 2022

View full text Add to dashboard Cite

Wireless network virtualization is widely used to solve the ossification problem of networks, such as 5G and the Internet of Things. The most crucial method of wireless network virtualization is virtual network embedding, which allows virtual networks to share the substrate network resources. However, in wireless networks, link interference is an inherent problem while mapping virtual networks because of the characteristics of wireless channels. To distribute resources efficiently and address the problem of interference, a dynamic embedding algorithm with deep reinforcement learning is proposed. During the training stage, we take resource use and interference from substrate networks as observations to train the agent, and then the agent generates a resource allocation strategy. Aiming at realizing load balance, we reshape the reward function considering the execution ratio and residual ratio of substrate network resources as well as the cost consumed by current virtual network request. Numerical tests show that our embedding approach increases the acceptance ratio and maintains better robustness. Moreover, the results also illustrate that our algorithm maintains a high acceptance ratio while producing less interference and lower cost.

show abstract

Section: Reinforcement Learning Environmentmentioning

confidence: 99%

Wireless Virtual Network Embedding Algorithm Based on Deep Reinforcement Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Experiment results have proved that FAM-DRL-VNE algorithm has obvious advantages. The authors of [21] propose a VNE framework (VNE2) based on equivalent bandwidth and guaranteed delay based on current 5G network. Experiments have proved that the proposal of this framework increases the profit of InP in bandwidth allocation.…”

Section: A the Distributed Embedding Algorithmmentioning

confidence: 99%

VNE-HPSO: Virtual Network Embedding Algorithm Based on Hybrid Particle Swarm Optimization

et al. 2020

Self Cite

View full text Add to dashboard Cite

Today, the 5G Internet era has arrived, and network virtualization technology has captured the attention of people. However, traditional single-domain virtual embedding technology generated huge overhead in embedding and caused a certain waste of resources. Therefore, for cutting virtual embedding overhead and improving the embedding efficiency, this paper proposes a new multi-domain embedding programme. For this scheme, firstly, to rationalize the use of physical resources to a higher degree, we set up a model for the embedding problem. Secondly, in order to obtain the optimal global solution, we introduce simulated annealing into the PSO algorithm, and distribute the particles through the particle initialization distribution strategy. In addition, for the parameter of inertia weight in the algorithm, we use the linear differential decline strategy to calculate. The experimental results show that compared with VNE-PSO algorithm, this scheme reduces the cost of virtual network mapping by 32.82%, increases the acceptance rate of virtual requests by 7%, and reduces the running time by 18.7%. This scheme maximizes the benefits.

show abstract

“…Thus, the design philosophy to resource allocation needs to change to overcome these challenges and complexities. Today, the use of machine learning methods to overcome the problems of the next generation has been the subject of much research 13‐15 …”

Section: Introductionmentioning

confidence: 99%

“…Today, the use of machine learning methods to overcome the problems of the next generation has been the subject of much research. [13][14][15] In wireless technology, radio resources are dynamically distributed based on real-time data of the user, namely their CSI and QoS needs. Inexpensive cloud storage saves the information as data on historical scenarios in the cloud space.…”

Section: Introductionmentioning

confidence: 99%

Optimizing resources allocation in a heterogeneous cloud radio access network using machine learning

Shirmohamadi

Bakhshi

Dosaranian‐Moghadam

2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In this article, we propose an iterative algorithm based on lazy learning. The proposed scheme considers two consecutive algorithms for optimal resource allocation in heterogeneous cloud radio access networks (H-CRAN). In the conventional approach, resources allocation is usually presented as a mathematical optimization problem and solved online using a real-time scenario. Due to the non-convex nature of resource allocation problems, finding optimal solutions in real-time is a difficult challenge and has high computational complexity. To overcome these challenges in this paper, the problem is first formulated as a mixed-integer nonlinear programming (MINLP) to optimize the system capacity and assign the underlay users to the subchannels, which is NP-hard. To obtain the solution, in the first algorithm, the proposed problem is first reformulated as a convex problem using a matching theory and coalition formation method. Then, in the second algorithm, the lazy learning method is employed to find the optimal solution to the resources allocation problem. The lazy algorithm uses the output results of the first algorithm as training data, which are known as historical data. Similarities between current scenario data and historical scenario data, as well as the solution of resources allocation in historical scenarios, can be exploited to improve the resource allocation of the current scenario. Simulation results confirm that compared with the conventional approach, the suggested technique can significantly improve the system performance in terms of the total users assigned, overall throughput, the pace of resource allocation, and user fairness.

show abstract

Network Resource Allocation Strategy Based on Deep Reinforcement Learning

Cited by 16 publications

References 41 publications

Wireless Virtual Network Embedding Algorithm Based on Deep Reinforcement Learning

Wireless Virtual Network Embedding Algorithm Based on Deep Reinforcement Learning

VNE-HPSO: Virtual Network Embedding Algorithm Based on Hybrid Particle Swarm Optimization

Optimizing resources allocation in a heterogeneous cloud radio access network using machine learning

Contact Info

Product

Resources

About