A BP Neural Network Based Punctured Scheduling Scheme Within Mini-slots for Joint URLLC and eMBB Traffic

Shang, Qingqing; Liu, Fangfang; Feng, Chunyan; Zhang, Ruiyi; Zhao, Shulun

doi:10.1109/globalsip45357.2019.8969539

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing works on designing resource allocation strategies mostly focuses on two goals, either to maximize the utility of eMBB traffic or to reduce the loss of URLLC puncturing on eMBB utility. [22][23][24][25][26] The authors in Reference 22 adopted a back propagation neural network to reduce the eMBB throughput loss caused by URLLC puncturing. The authors in Reference 23 proposed a model-free deep reinforcement learning method DEMUX to reduce the adverse effects of URLLC preemption on eMBB utility.…”

Section: Related Workmentioning

confidence: 99%

“…Existing works on designing resource allocation strategies mostly focuses on two goals, either to maximize the utility of eMBB traffic or to reduce the loss of URLLC puncturing on eMBB utility 22–26 . The authors in Reference 22 adopted a back propagation neural network to reduce the eMBB throughput loss caused by URLLC puncturing. The authors in Reference 23 proposed a model‐free deep reinforcement learning method DEMUX to reduce the adverse effects of URLLC preemption on eMBB utility.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fairness‐aware eMBB/URLLC spectrum resource multiplexing to ensure reliability in vehicular networks

Li,

Wang,

Wang

et al. 2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Spectrum resource multiplexing of enhanced Mobile BroadBand (eMBB) and Ultra‐Reliable and Low Latency Communications (URLLC) via puncturing in vehicular networks has become an important research direction. The main issue in this direction is how to minimize the adverse impact of preemptive puncturing on eMBB traffic. However, the available eMBB/URLLC coexisting schemes lack considerations on the quality of service of a single eMBB user and fairness between users. In view of this, we formulate the eMBB/URLLC multiplexing problem to maximize eMBB reliability and fairness under the premise of meeting the requirements of URLLC as a nonlinear integer programming (NIP) in this article. To balance the performance and computational complexity, we decompose this NIP into two subproblems that be solved efficiently. For the eMBB spectrum resource allocation subproblem of maximizing the reliability and fairness under resource constraints, we prove that this problem is NP‐hard, and design a Deep Q‐Network (DQN)‐based spectrum resource allocation algorithm and a two‐stage heuristic spectrum resource allocation algorithm, respectively. For the URLLC preemption subproblem, we further propose bandwidth‐sensitive URLLC spectrum resource preemption algorithm and time‐sensitive URLLC spectrum resource preemption algorithm, respectively. Simulation results show that the proposed scheme can guarantee better fairness and reliability for eMBB users compared with the comparison schemes. Besides, for the eMBB resource allocation problem, the proposed scheme can achieve near‐optimal performance with low complexity.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Existing works on designing resource allocation strategies mostly focuses on two goals, either to maximize the utility of eMBB traffic or to reduce the loss of URLLC puncturing on eMBB utility 22–26 . The authors in Reference 22 adopted a back propagation neural network to reduce the eMBB throughput loss caused by URLLC puncturing. The authors in Reference 23 proposed a model‐free deep reinforcement learning method DEMUX to reduce the adverse effects of URLLC preemption on eMBB utility.…”

Section: Introductionmentioning

confidence: 99%

Fairness‐aware eMBB/URLLC spectrum resource multiplexing to ensure reliability in vehicular networks

Li,

Wang,

Wang

et al. 2024

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…Therefore, eMBB transmissions are supposed to schedule in the slot, and URLLC transmissions are supposed to schedule in the mini-slot to achieve latency requirements. [5][6][7][8][9][10][11][12] Alsenwi et al 5 maximized the average data rate of eMBB users while URLLC constraints were satisfied, and the variance of eMBB data rates was minimized to protect low-rate eMBB users. However, it did not consider the data rate requirements of eMBB transmissions.…”

Section: Coexistence Of Embb Urllc Servicesmentioning

confidence: 99%

“…To address the URLLC placement problem, the work by Shang et al 11 presented a backpropagation neural network and selected the eMBB user who would suffer the least throughput loss if punctured. Bairagi et al 12 used a heuristic approach to address the resource allocation problem of eMBB transmissions, whereas a one-sided matching approach was used to handle the resource allocation problem of URLLC traffic.…”

Section: Coexistence Of Embb Urllc Servicesmentioning

confidence: 99%

Digital twin‐enabled deep reinforcement learning for joint scheduling of ultra‐reliable low latency communication and enhanced mobile broad band: A reliability‐guaranteed approach

Zhang

Liu

et al. 2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In the coexistence of ultra‐reliable low latency communication (URLLC) and enhanced mobile broad band (eMBB) in 5G networks, the arriving URLLC traffic with strict latency requirements will be scheduled by puncturing ongoing eMBB transmissions, negatively impacting eMBB data rate. In this article, we add reliability measurement for eMBB users with high data rate requirements. The scheduling problem is formulated as an optimization problem with the goal of maximizing the data rate of eMBB users while meeting the requirements of URLLC latency and eMBB data rate. To jointly optimize resource allocation policy and puncturing policy, an algorithm based on deep reinforcement learning (DRL) is introduced. Considering that the utilization of DRL in the resource scheduling problem is limited due to the nonstationary communication environment, a digital twin‐enabled DRL architecture is presented to fine‐tune the DRL model according to feedback from the real‐world network. The DRL agent can explore in the digital twin model, avoiding the loss of quality of service caused by exploration in the real‐world environment. According to simulation results, the approach proposed in this article can improve the reliability of eMBB users with data rate requirements.

show abstract

Joint Resource Scheduling for Coexistence of URLLC and eMBB in 5G Wireless Networks

Sun

Yang

et al. 2021

2021 Computing, Communications and IoT Applications (ComComAp)

View full text Add to dashboard Cite

A BP Neural Network Based Punctured Scheduling Scheme Within Mini-slots for Joint URLLC and eMBB Traffic

Cited by 7 publications

References 16 publications

Fairness‐aware eMBB/URLLC spectrum resource multiplexing to ensure reliability in vehicular networks

Fairness‐aware eMBB/URLLC spectrum resource multiplexing to ensure reliability in vehicular networks

Digital twin‐enabled deep reinforcement learning for joint scheduling of ultra‐reliable low latency communication and enhanced mobile broad band: A reliability‐guaranteed approach

Joint Resource Scheduling for Coexistence of URLLC and eMBB in 5G Wireless Networks

Contact Info

Product

Resources

About