The virtualization and distribution of 5G Radio Access Network (RAN) functions across radio unit (RU), distributed unit (DU), and centralized unit (CU) in conjunction with multi-access edge computing (MEC) enable the creation of network slices tailored for various applications with distinct quality of service (QoS) demands. Nonetheless, given the dynamic nature of slice requests and limited network resources, optimizing long-term revenue for infrastructure providers (InPs) through real-time admission and embedding of slice requests poses a significant challenge. Prior works have employed Deep Reinforcement Learning (DRL) to address this issue, but these approaches require re-training with the slightest topology changes due to node/link failure or overlook the joint consideration of slice admission and embedding problems. This paper proposes a novel method, utilizing multi-agent DRL and Graph Attention Networks (GATs), to overcome these limitations. Specifically, we develop topology-independent admission and slicing agents that are scalable and generalizable across diverse metropolitan networks. Results demonstrate substantial revenue gains-up to 35.2% compared to heuristics and 19.5% when compared to other DRL-based methods. Moreover, our approach showcases robust performance in different network failure scenarios and substrate networks not seen during training without the need for re-training or re-tuning. Additionally, we bring interpretability by analyzing attention maps, which enables InPs to identify network bottlenecks, increase capacity at critical nodes, and gain a clear understanding of the model decision-making process.

The 5G RAN functions can be virtualized and distributed across the radio unit (RU), distributed unit (DU), and centralized unit (CU) to facilitate flexible resource management. Complemented by multi-access edge computing (MEC), these components create network slices tailored for applications with diverse quality of service (QoS) requirements. However, as the requests for various slices arrive dynamically over time and the network resources are limited, it is non-trivial for an infrastructure provider (InP) to optimize its long-term revenue from real-time admission and embedding of slice requests. Prior works have leveraged Deep Reinforcement Learning (DRL) to address this problem, however, these solutions either require re-training when facing topology changes or do not consider the slice admission and embedding problems jointly. In this paper, we use multi-agent DRL and Graph Attention Networks (GATs) to address these limitations. Specifically, we propose novel topology-independent admission and slicing agents that are scalable and generalizable to large and different metropolitan networks. Results show that the proposed approach converges faster and achieves up to 35.2% and 20% gain in revenue compared to heuristics and other DRL-based approaches, respectively. Additionally, we demonstrate that our approach is generalizable to scenarios and substrate networks previously unseen during training, as it maintains superior performance without re-training or re-tuning.

5G Cloud Radio Access Networks (C-RANs) facilitate new forms of flexible resource management as dynamic RAN function splitting and placement. Virtualized RAN functions can be placed at different sites in the substrate network based on resource availability and slice constraints. Due to limited resources in the substrate network and variability in revenue of slices, the Infrastructure Provider (InP) must perform network slicing in a strategic manner, and accept or reject slice-requests to maximize long-term revenue. In this paper, we propose to use multi-agent Deep Reinforcement Learning (DRL) to jointly solve the problems of network slicing and slice Admission Control (AC). Multi-agent DRL along with reward shaping is a promising choice, which is well-suited to problems where multiple distinct tasks have to be performed optimally. The proposed DRL approach can learn the dynamics of slice-request traffic and effectively address these joint problems. We compare multi-agent DRL to approaches that use: (i) simple heuristics to address the problems, and (ii) DRL to address either slicing or AC. Our results show that the proposed approach achieves up to 30% and 5.18% gain in long-term InP revenue when compared to approaches (i) and (ii), respectively. Additionally, we show that multi-agent DRL is preferable to a single-agent DRL approach for the joint problems in terms of convergence time and InP revenue. Finally, we evaluate the robustness of the trained agents in scenarios that differ from training, such as different arrival rates and real dynamic traffic patterns.

5G Cloud Radio Access Networks (C-RANs) facilitate new forms of flexible resource management as dynamic RAN function splitting and placement. Virtualized RAN functions can be placed at different sites in the substrate network according to resource availability and slice constraints. Due to limited resource availability in the substrate network, the Infrastructure Provider (InP) must perform network slicing in a strategic manner, and accept or reject slice-requests in order to maximize long-term revenue. In this paper, we propose to use multi-agent Deep Reinforcement Learning (DRL) to jointly solve the problems of network slicing and slice Admission Control (AC). Multi-agent DRL is a promising choice since it is well-suited to problems where multiple distinct tasks have to be performed optimally. The proposed DRL approach can learn the dynamics of slice-request traffic and effectively address these joint problems. We compare multi-agent DRL to approaches that use: (i) simple heuristics to address the problems, and (ii) DRL to address either slicing or AC. Our results show that the proposed approach achieves up to 18% and 3.8% gain in long-term InP revenue when compared to approaches (i) and (ii), respectively. Additionally, we show that multi-agent DRL is preferable to a single-agent DRL approach that addresses the problems jointly. Finally, we evaluate the robustness of the trained model in terms of its ability to generalize to scenarios that deviate from training.

Network traffic prediction is a fundamental prerequisite for dynamic resource provisioning in wireline and wireless networks, but is known to be challenging due to non-stationarity and due to its burstiness and self-similar nature. The prediction of network traffic at the user level is particularly challenging, because the traffic characteristics emerge from a complex interaction of user level and application protocol behavior. In this work we address the problem of predicting the network traffic at the user level over a short horizon, motivated by its applications in cellular scheduling. Motivated by recent works on robust adversarial learning, we treat the prediction problem for non-stationary traffic in an adversarial context, and propose a meta-learning scheme that consists of a set of predictors, each optimized to predict a particular kind of traffic, and of a master policy that is trained for choosing the best fit predictor dynamically based on recent prediction performance, using deep reinforcement learning. We evaluate the proposed meta-learning scheme on a variety of traffic traces consisting of video and non-video traffic. Our results show that it consistently outperforms state-of-the-art predictors, and can adapt to before unseen traffic without the need for retraining the individual predictors.