Deep Reinforcement Learning-Based Joint Scheduling of eMBB and URLLC in 5G Networks

Li, Jing; Zhang, Xing

doi:10.1109/lwc.2020.2997036

Cited by 67 publications

(51 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li and Zhang [52] applied DRL which is used in the 5G network to optimize the tradeoff between the quality of service and enhanced broadband and low latency communications. It is found that the quality of the service is achieved with the tradeoff between the enhanced mobile broadband and ultrareliable low latency communications.…”

Section: E Applications Of the Deep Reinforcement Learning In 5g Wire...mentioning

confidence: 99%

“…Xu et al [38] proposed RGB stream and spatial rich model noise stream for differentiating between adversarial and clean examples. e CNN is used to detect adversarial image, and Caching scheme Dong et al [41] Hybrid 5G service Gante et al [27]; Yu et al [104]; Cheng et al [36]; Kaya and Viswanathan [73]; Zhang et al [74] mmWave Huang et al [68] Traffic loads Huang et al [28] Channel information Kim et al [92] Massive MIMO Kim et al [62] Sparse code multiple access Klautau et al [15] Beam Lei et al [61]; Yu et al [53] Cache Luo et al [67] Channel state information Luo et al [69] Power transmission Maimó et al [76]; Doan and Zhang [34]; Chen et al [83]; Maimó et al [78] Traffic flow Ning et al [42]; Ahmed et al [35] Spectrum Ozturk et al [81]; Klus et al [32] Handover Pang et al [12] Intelligent cache scheme Razaak et al [89] 5G fixed wireless Sadeghi et al [43] Scalable cache Shahriari et al [39] Load balancing Sundqvist et al [79]; Abbas et al [90]; Ali et al [100] Random access network He et al [29] MU-MIMO Li et al [44] Chaining Xia et al [45] Multicell MEC Saetan et al [93] Nonorthogonal multiple access Pradhan and Das [48]; Li and Zhang [52] Ultrareliable low-latency Ho et al [50] 5G-V2X Tang et al [47...…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

“…erefore, we have this research question for researchers: What is the systematic deep learning approach to conceal data confidentiality before, during, and after modeling? [44] User group DQN Effective chaining Xia et al [45] User group DQN Reduces energy cost and delay experience by users Saetan et al [93] Outdoor DDNN Predicts power factor Pradhan and Das [48] Individual RL Provides packet drop probability and better resource utilization Zhao et al [49] Outdoor RL Fast response to network demand Ho et al [50] Outdoor DQN Solves the problem of base station allocation Yu et al [46] Outdoor DQN Searches for optimal deployment location with high speed Tang et al [47] Outdoor DQN Improved network performance based on throughput and packet drop rate Chergui and Verikoukis [99] Outdoor DDNN Estimates slices resources El Boudani et al [97] Outdoor DDNN Predicts 3D position of mobile station Xie et al [51] Outdoor DQN Improves efficiency of initial window decision Hussain et al [30] Outdoor CNN Detects denial of service with high accuracy Butt et al [95] Outdoor DDN Estimating user equipment positioning Godala et al [31] Outdoor CNN Estimates channel state information Li and Zhang [52] Outdoor DRL Improves quality of service Yu et al [53] Outdoor DRL Improves energy efficiency Yu et al [9] Outdoor LSTM Resource allocation in TV broadband services Liu et al [82] Outdoor LSTM Predicts hotspot for small virtual cell Mismar et al [54] Outdoor DQN Signal to interference plus noise ratio improvement Sim et al [96] Outdoor DDNN Selection of beam Doan and Zhang [34] Outdoor CNN Detects anomaly in 5G network Memon et al [84] Outdoor LSTM Improves power savings and predicts discontinue reception Klus et al [32] Localization CNN Predicts user localization and reduces unnecessary handover Saeidian et al [55] Outdoor DQN Improves data rate at the edge and reduces power transmitted antharate et al [98] Outdoor DDNN Detects security thread 5.10. Complexity.…”

Section: G Ecosystemmentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning-Based Solutions for 5G Network and 5G-Enabled Internet of Vehicles: Advances, Meta-Data Analysis, and Future Direction

Almutairi

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The advent of the 5G mobile network has brought a lot of benefits. However, it prompted new challenges on the 5G network cybersecurity defense system, resource management, energy, cache, and mobile network, therefore making the existing approaches obsolete to tackle the new challenges. As a result of that, research studies were conducted to investigate deep learning approaches in solving problems in 5G network and 5G powered Internet of Vehicles (IoVs). In this article, we present a survey on the applications of deep learning algorithms for solving problems in 5G mobile network and 5G powered IoV. The survey pointed out the recent advances on the adoption of deep learning variants in solving the challenges of 5G mobile network and 5G powered IoV. The deep learning algorithm solutions for security, energy, resource management, 5G-enabled IoV, and mobile network in 5G communication systems were presented including several other applications. New comprehensive taxonomies were created, and new comprehensive taxonomies were suggested, analysed, and presented. The challenges of the approaches are already discussed in the literature, and new perspective for solving the challenges was outlined and discussed. We believed that this article can stimulate new interest in practical applications of deep learning in 5G network and provide clear direction for novel approaches to expert researchers.

show abstract

Section: E Applications Of the Deep Reinforcement Learning In 5g Wire...mentioning

confidence: 99%

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

Section: G Ecosystemmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Solutions for 5G Network and 5G-Enabled Internet of Vehicles: Advances, Meta-Data Analysis, and Future Direction

Almutairi

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Another line of work that has recently been emerging relies on utilizing machine learning to address the coexistence and scheduling of URLL and eMBB traffic, especially for cases with unscheduled URLLC traffic. [12]- [14] propose machine learning aided approaches that proactively allocate resources and facilitate URLL communications. More specifically, [12] proposes a risk-aware online learning approach for the allocation of resources, and [13] proposes Q-learning for the allocation of power and time-frequency resources.…”

Section: A Prior Workmentioning

confidence: 99%

Computer Vision Aided URLL Communications: Proactive Service Identification and Coexistence

Alrabeiah,

Demirhan,

Hredzak

et al. 2021

Preprint

View full text Add to dashboard Cite

The support of coexisting ultra-reliable and lowlatency (URLL) and enhanced Mobile BroadBand (eMBB) services is a key challenge for the current and future wireless communication networks. Those two types of services introduce strict, and in some time conflicting, resource allocation requirements that may result in a power-struggle between reliability, latency, and resource utilization in wireless networks. The difficulty in addressing that challenge could be traced back to the predominant reactive approach in allocating the wireless resources. This allocation operation is carried out based on received service requests and global network statistics, which may not incorporate a sense of proaction. Therefore, this paper proposes a novel framework termed service identification to develop novel proactive resource allocation algorithms. The developed framework is based on visual data (captured for example by RGB cameras) and deep learning (e.g., deep neural networks). The ultimate objective of this framework is to equip future wireless networks with the ability to analyze user behavior, anticipate incoming services, and perform proactive resource allocation. To demonstrate the potential of the proposed framework, a wireless network scenario with two coexisting URLL and eMBB services is considered, and two deep learning algorithms are designed to utilize RGB video frames and predict incoming service type and its request time. An evaluation dataset based on the considered scenario is developed and used to evaluate the performance of the two algorithms. The results confirm the anticipated value of proaction to wireless networks; the proposed models enable efficient network performance ensuring more than 85% utilization of the network resources at ∼ 98% reliability. This highlights a promising direction for the future vision-aided wireless communication networks.

show abstract

“…Another approach is proposed in [175], where a risk-sensitive model was introduced in order to ensure URLLC allocation but also to minimize the loss of eMBB users. However, these strategies can result in significant losses in terms of data rates for eMBB services [176] and may impact eMBB transmission reliability [177].…”

Section: Resource Allocation In Heterogeneous Servicesmentioning

confidence: 99%

Real-time detection and optimization algorithms for flexible resource allocation in 5G networks and beyond

Skaperas¹,

Σκαπέρας²

View full text Add to dashboard Cite

Η ανάπτυξη των δικτύων κινητής τηλεφωνίας πέμπτης γενιάς (5G) καθώς και η επικείμενη έκτη γενιά (6G) θα επιφέρουν θεμελιώδεις αλλαγές στον τρόπο επικοινωνίας και πρόσβασης σε υπηρεσίες και ψυχαγωγία. Σχετικά με τα παραπάνω, η ραγδαία αύξηση του ρυθμού δεδομένων των βελτιωμένων υπηρεσιών ευρυζωνικής κινητής τηλεφωνίας (eMBB) θα παρέχει στους χρήστες εξαιρετικά υψηλή ανάλυση στη ροή βίντεο, και σε εφαρμογές πολυμέσων και εικονικής πραγματικότητας, προσφέροντας συναρπαστικές εμπειρίες.Για το σκοπό αυτό, είναι σημαντικό για τις υποδομές παράδοσης περιεχομένου να εντοπίζουν και να ανταποκρίνονται γρήγορα σε αλλαγές στη δυναμική της δημοτικότητας του περιεχομένου. Επικεντρώνοντας στην απαίτηση για ευέλικτες και εξαιρετικά προσαρμοστικές λύσεις, η ικανότητα για γρήγορη και εκ νέου κατανομή πόρων, θα πρέπει να καθοδηγείται από αλγορίθμους γρήγορης ανίχνευσης της δημοτικότητας του περιεχομένου και ταυτόχρονα χαμηλής πολυπλοκότητας. Στην παρούσα διατριβή, μελετάμε πτυχές που σχετίζονται με την ανάπτυξη αλγορίθμων, πραγματικού χρόνου και χαμηλής πολυπλοκότητας, για την ανίχνευση αλλαγών στη δημοτικότητα περιεχομένου βίντεο. Αντιμετωπίζουμε το τελευταίο ως στατιστικό πρόβλημα ανίχνευσης σημείου αλλαγής (CP), ανοίγοντας εντελώς νέο έδαφος σε σύγκριση με προηγούμενες εργασίες σχετικές με την έρευνα του περιεχομένου ιστού. Επιπλέον, στο πλαίσιο των εξαιρετικά αξιόπιστων επικοινωνιών χαμηλού λανθάνοντος χρόνου (URLLC) και των μαζικών επικοινωνιών τύπου μηχανής (mMTC), νέες συναρπαστικές περιπτώσεις χρήσης παρουσιάστηκαν στα 5G. Η νέα βιομηχανική επανάσταση, που ονομάζεται Βιομηχανία 4.0, μαζί με τους αναδυόμενους κλάδους της τηλεϊατρικής, της έξυπνης γεωργίας κ.λπ., θα προσφέρει πρωτόγνωρα επίπεδα αυτοματισμού και ευφυΐας. Καθώς το 5G απαιτεί την υποστήριξη ενός μεγάλου εύρους υπηρεσιών, αναζητούνται νέες λύσεις που επιτρέπουν υψηλότερη απόδοση πόρων. Σε αυτό το πλαίσιο, σε αυτή τη διατριβή μελετάμε τον χρονοπρογραμματισμό ετερογενών υπηρεσιών στο επίπεδο δικτύου 2, εστιάζοντας στην περίπτωση συνύπαρξης URLLC και eMBB. Προτείνουμε νέους ευρετικούς αλγόριθμους και διερευνούμε περαιτέρω λύσεις που αξιοποιούν τη μη ορθογώνια πολλαπλή πρόσβαση (NOMA), λόγω των πλεονεκτημάτων της σε σχέση με τα συμβατικά σχήματα πολλαπλής πρόσβασης (OMA) από την άποψη της φασματικής και ενεργειακής απόδοσης. Όλες οι προτεινόμενες λύσεις στοχεύουν και καταλήγουν σε ευέλικτα σχήματα κατανομής πόρων, ακρογωνιαίο λίθο τόσο των δικτύων 5G όσο και μελλοντικών δικτύων 6G.

show abstract

Deep Reinforcement Learning-Based Joint Scheduling of eMBB and URLLC in 5G Networks

Cited by 67 publications

References 6 publications

Deep Learning-Based Solutions for 5G Network and 5G-Enabled Internet of Vehicles: Advances, Meta-Data Analysis, and Future Direction

Deep Learning-Based Solutions for 5G Network and 5G-Enabled Internet of Vehicles: Advances, Meta-Data Analysis, and Future Direction

Computer Vision Aided URLL Communications: Proactive Service Identification and Coexistence

Real-time detection and optimization algorithms for flexible resource allocation in 5G networks and beyond

Contact Info

Product

Resources

About