On the Optimization of Multi-Cloud Virtualized Radio Access Networks

Murti, Fahri Wisnu; García‐Saavedra, Andrés; Costa‐Pérez, Xavier; Iosifidis, George

doi:10.1109/icc40277.2020.9149318

Cited by 13 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This evaluation is conducted using pretrained models as results of DRLT-vRAN training and search strategy for the inference process. Firstly, we consider traffic loads within a range λ n = [10,150] Mbps and use the original routing cost of R1. Then, we change the scale of routing cost, i.e., increasing or decreasing the leasing agreement's price, maintenance, etc., within a range [0.1, 1] and using default traffic load λ n = 150 Mbps.…”

Section: Impact Of Load and Routing Costmentioning

confidence: 99%

“…Follow up works, [8] and [9] offered optimal solution of minimizing total cost for integration vRAN with Mobile Edge Computing (MEC). Then, [10] proposed an optimized multi-cloud vRAN framework with balancing its centralization [11]. However, the mentioned works above rely on mathematical optimization techniques that often have a slow convergence rate and exponential complexity for finding the optimal solution, particularly in large networks.…”

Section: Introductionmentioning

confidence: 99%

“…We evaluate our approach in a synthetic network generated by the Waxman algorithm that highly represents a backhaul network [26]. The used system parameters are from a measurement-based 3GPP-compliant system model [10], [11]. To assess our approach's effectiveness, we compare it to the optimal value obtained from a Phyton-MIP solver 1 .…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Murti

Ali

2021

2021 IEEE International Conference on Communications Workshops (ICC Workshops)

Self Cite

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

Section: Impact Of Load and Routing Costmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Murti

Ali

2021

2021 IEEE International Conference on Communications Workshops (ICC Workshops)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this context, the BS operation is essentially a chain of functions, each one performing specific tasks after the wireless radio signal is sampled. 1 This technological advancement has allowed pooling the BS functions in cloud servers within the RAN, known also as Cloud Units (CUs), aiming to reduce their execution cost (using more efficient servers) but also to improve the network performance through its centralized control. For instance, the co-location of functions of different BSs enables Coordinated Multi-Point transmissions, supports dynamic multi-cell spectrum management and also cross-cell interference control [3], [4].…”

Section: Introduction a Backgroundmentioning

confidence: 99%

An Optimal Deployment Framework for Multi-Cloud Virtualized Radio Access Networks

Murti

Ayala‐Romero

García‐Saavedra³

et al. 2021

IEEE Trans. Wireless Commun.

Self Cite

View full text Add to dashboard Cite

Virtualized radio access networks (vRAN) are emerging as a key component of wireless cellular networks, and it is therefore imperative to optimize their architecture. vRANs are decentralized systems where the Base Station (BS) functions can be split between the edge Distributed Units (DUs) and Cloud computing Units (CUs); hence they have many degrees of design freedom. We propose a framework for optimizing the number and location of CUs, the function split for each BS, and the association and routing for each DU-CU pair. We combine a linearization technique with a cutting-planes method to expedite the exact problem solution. The goal is to minimize the network costs and balance them with the criterion of centralization, i.e., the number of functions placed at CUs. Using data-driven simulations we find that multi-CU vRANs achieve cost savings up to 28% and improve centralization by 77%, compared to single-CU vRANs. Interestingly, we see non-trivial trade-offs among centralization and cost, which can be aligned or conflicting based on the traffic and network parameters. Our work sheds light on the vRAN design problem from a new angle, highlights the importance of deploying multiple CUs, and offers a rigorous optimization tool for balancing costs and performance.

show abstract

“…Formulac ¸ão do MPP-RANO MPP-RAN leva em considerac ¸ão dois pontos importantes no planejamento de RAN, o primeiro deles é relacionado à centralizac ¸ão de NFVs. A partir da centralizac ¸ão em camadas mais próximas ao núcleo da rede, ganhos de desempenho são alcanc ¸ados para controle e comunicac ¸ão entre as RUs[Murti et al 2020]. Entretanto, o MPP-RAN leva em considerac ¸ão casos específicos de centralizac ¸ão chamados agregac ¸ão, que ocorrem quando há centralizac ¸ão de NFVs iguais em um mesmo CR.…”

unclassified

MPP-RAN: Posicionamento de funções de rede virtualizadas em redes de acesso de nova geração com divisão de ﬂuxos

Almeida

Lopes²,

Both

et al. 2021

Anais Do I Workshop De Redes 6G (W6G 2021)

View full text Add to dashboard Cite

Redes de Acesso por Rádio de Próxima Geração (NG-RAN) devem suportar oito opções de divisões funcionais combinando o posicionamento em três nós, i.e., Unidade Central, Unidade Distribuída e Unidade de Rádio. Além disso, esses nós devem trabalhar de forma virtualizada, resultando em uma solução vNG-RAN. Neste artigo, é proposto um modelo de otimização exato que tem como objetivo o posicionamento de VNFs para o planejamento de vNGRAN com possibilidade de divisão do ﬂuxo de roteamento em múltiplos caminhos. Entretanto, nossos testes apresentam que esta abordagem é complexa para vNG-RAN de tamanho real. Desta forma, esse artigo apresenta uma discussão sobre a utilização de aprendizagem por reforço profundo para resolver este problema.

show abstract

On the Optimization of Multi-Cloud Virtualized Radio Access Networks

Cited by 13 publications

References 18 publications

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

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

An Optimal Deployment Framework for Multi-Cloud Virtualized Radio Access Networks

MPP-RAN: Posicionamento de funções de rede virtualizadas em redes de acesso de nova geração com divisão de ﬂuxos

Contact Info

Product

Resources

About