Deep Learning based User Slice Allocation in 5G Radio Access Networks

Matoussi, Salma; Fajjari, Ilhem; Aitsaadi, Nadjib; Langar, Rami

doi:10.1109/lcn48667.2020.9314857

Cited by 14 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the authors in [9]- [11] have shown the non-triviality of vRAN performance and the importance of learning based-framework to manage the vRAN resources, they still did not discuss how to design a framework that learns to optimize the functional splits. Recent work in [23] has studied user-centric slicing and split optimization problems using a deep learning method. The authors modelled their problem as supervised learning, which relies on highquality labelled datasets (e.g., optimal labels) to assess the quality of the decisions.…”

Section: A Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Constrained Deep Reinforcement Based Functional Split Optimization in Virtualized RANs

Murti

Ali

2022

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

In virtualized radio access network (vRAN), the base station (BS) functions are decomposed into virtualized components that can be hosted at the centralized unit or distributed units through functional splits. Such flexibility has many benefits; however, it also requires solving the problem of finding the optimal splits of functions of the BSs in such a way that minimizes the total network cost. The underlying vRAN system is complex and precise modelling of it is not trivial. Formulating the functional split problem to minimize the cost results in a combinatorial problem that is provably NP-hard, and solving it is computationally expensive. In this paper, a constrained deep reinforcement learning (RL) approach is proposed to solve the problem with minimal assumptions about the underlying system. Since in deep RL, the action selection is the outcome of inference of a neural network, it can be done in real-time while training to update the neural networks can be done in the background. However, since the problem is combinatorial, even for a small number of functions, the action space of the RL problem becomes large. Therefore, to deal with such a large action space, a chain rule-based stochastic policy is exploited in which a long short-term memory (LSTM) network-based sequence-to-sequence model is applied to estimate the policy that is selecting the functional split actions. However, the utilized policy is still limited to an unconstrained problem, and each split decision is bounded by vRAN's constraint requirements. Hence, a constrained policy gradient method is leveraged to train and guide the policy toward constraint satisfaction. Further, a search strategy by greedy decoding or temperature sampling is utilized to improve the optimality performance at the test time. Simulations are performed to evaluate the performance of the proposed solution using synthetic and real network datasets. Our numerical results show that the proposed RL solution architecture successfully learns to make optimal functional split decisions with the accuracy of the solution is up to 0.05% of the optimality gap. Moreover, our solution can achieve considerable cost savings compared to C-RAN or D-RAN systems and a faster computational time than the optimal baseline.

show abstract

Section: A Related Workmentioning

confidence: 99%

“…We argue that every split decision in vRANs is interdependent as the BSs share the same network links and computing nodes with limited capacity. Besides, [23] focused on the split assignment for the users, and [24] studied the effectiveness of energy sources, but we aim for a different goal.…”

Section: A Related Workmentioning

confidence: 99%

Constrained Deep Reinforcement Based Functional Split Optimization in Virtualized RANs

Murti

Ali

2022

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

show abstract

“…180kHz) per RB in 1-ms Transmission Time Interval (TTI). It is commonly assumed in papers that RBs are shared through the Orthogonal Frequency-Division Multiple-Access (OFDMA) method for downlink (DL) transmission to address the interference issues among UEs [151]. Notably, traffic variations at slice-level can be observed over time intervals in the order of hours/days.…”

Section: ) Resource Allocation In Ranmentioning

confidence: 99%

“…Similarly, the authors of [151] study the RB allocation and RAN functional split to slices, while considering users' throughput, latency, and CQI. They formalize the problem as ILP and solve it using the Branch and Cut (B&C) algorithm as well as an LSTM-based approach.…”

Section: Fine-grainedmentioning

confidence: 99%

Machine Learning in Network Slicing - A Survey

Phyu¹,

Naboulsi²,

Stanica³

2022

Preprint

View full text Add to dashboard Cite

<p>5G and beyond networks are expected to support a wide range of services, with highly diverse requirements. Yet, the traditional “one-size-fits-all” network architecture lacks the flexibility to accommodate these services. In this respect, network slicing has been introduced as a promising paradigm for 5G and beyond networks, supporting not only traditional mobile services, but also vertical industries services, with very heterogeneous<br> requirements. Along with its benefits, the practical implementation of network slicing brings a lot of challenges. Thanks to the recent advances on Machine Learning (ML), some of these challenges have been addressed. In particular, the application of ML approaches is enabling the autonomous management of resources, in the network slicing paradigm. Accordingly, this paper presents a comprehensive survey on contributions on<br> ML in network slicing, identifying major categories and sub-categories in the literature. Key takeaways are also presented and open research challenges are discussed, together with potential solutions.</p>

show abstract

“…It is worth noting that our approach requires minimal handcrafted engineering. It does not need to know the vRAN split problem mathematically, e.g., mathematical optimization-based approaches [8]- [11], or direct access to the optimal labeled data, e.g., supervised learning [21]. Instead, it learns from interaction with the environment that expects to receive the reward (total network cost) signal and Penalization (constraints violation).…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Based Optimization of Function Splitting in Virtualized Radio Access Networks

Murti

Ali

2021

2021 IEEE International Conference on Communications Workshops (ICC Workshops)

View full text Add to dashboard Cite

Virtualized Radio Access Network (vRAN) is one of the key enablers of future wireless networks as it brings the agility to the radio access network (RAN) architecture and offers degrees of design freedom. Yet, it also creates a challenging problem on how to design the functional split configuration. In this paper, a deep reinforcement learning approach is proposed to optimize function splitting in vRAN. A learning paradigm is developed that optimizes the location of functions in the RAN. These functions can be placed either at a central/cloud unit (CU) or a distributed unit (DU). This problem is formulated as constrained neural combinatorial reinforcement learning to minimize the total network cost. In this solution, a policy gradient method with Lagrangian relaxation is applied that uses a stacked long short-term memory (LSTM) neural network architecture to approximate the policy. Then, a sampling technique with a temperature hyperparameter is applied for the inference process. The results show that our proposed solution can learn the optimal function split decision and solve the problem with a 0.4% optimality gap. Moreover, our method can reduce the cost by up to 320% compared to a distributed-RAN (D-RAN). We also conclude that altering the traffic load and routing cost does not significantly degrade the optimality performance.

show abstract

Deep Learning based User Slice Allocation in 5G Radio Access Networks

Cited by 14 publications

References 19 publications

Constrained Deep Reinforcement Based Functional Split Optimization in Virtualized RANs

Constrained Deep Reinforcement Based Functional Split Optimization in Virtualized RANs

Machine Learning in Network Slicing - A Survey

Deep Reinforcement Based Optimization of Function Splitting in Virtualized Radio Access Networks

Contact Info

Product

Resources

About