With increasing demands for ultra-reliable, low-latency applications and next-generation network services, integrating artificial intelligence and machine learning (AI/ML) into Open Radio Access Network (O-RAN) components has become a critical research focus. However, realizing the full potential of AI/ML in O-RAN presents unresolved challenges due to the absence of system-level mechanisms for dynamic resource allocation and limited coordination among the functionally separated components. The paper addresses some of these challenges by proposing a bottleneck-based deep learning-driven resource allocation approach that employs a Gated Recurrent Unit (GRU)-based forecasting model to proactively identify and mitigate bottleneck resources, enabling the system to adapt to fluctuating user demands and varying network conditions, and guiding task reallocation through policy-driven decisions. Our approach combines the capabilities of the Non-Real-Time (Non-RT) and Near-Real-Time (Near-RT) RAN Intelligent Controllers (RICs) across the cloud-edge continuum. Since edge computing nodes often have limited resources and are more expensive compared to cloud infrastructure, components of the Near-RT RIC are deployed at the edge, while Non-RT RIC components are placed in the cloud. We implement this framework in both xApp and rApp forms, fully compliant with O-RAN specifications, and conduct extensive performance evaluations using real-world network data in an extended Kubernetes environment, demonstrating the integration of Near-RT RIC at the edge and Non-RT RIC in the cloud. Comprehensive performance evaluations conducted on the O-RAN Software Community (OSC) testbed demonstrate significant improvements in network efficiency, scalability, and latency, as the proposed approach significantly outperforms existing methods by reducing resource utilization by 14%–40%, reducing task delay by 21.6%–44.0%, and achieving an admittance ratio improvement ranging from 6.48% to 16.6% compared to other approaches.

With the rapid development of artificial intelligence and the dramatic growth of communication services, the sixth-generation (6G) wireless network needs to handle communication tasks more flexibly and efficiently, significantly exacerbating the challenge of resource allocation. For the access network scenarios in 6G networks, the existing single-layer reinforcement learning resource allocation algorithms are hard to satisfy the diverse demands of users due to the complex and variable state space. Therefore, we propose a reinforcement learning-based two-timescale resource allocation scheme, aiming to jointly enhance the quality of service and system resource utilization. The proposed method comprises an upper-layer controller that allocates network resources to lower-layer controllers on a large time scale. Then, lower-layer controllers refine the resources based on user service types on a smaller time scale. To implement the proposed two-timescale allocation scheme, we propose a two-layer reinforcement learning framework consisting of a deep deterministic policy gradient (DDPG) and a dueling deep Q network (Dueling-DQN). Furthermore, recognizing that coupling multiple reinforcement learning processes may slow down algorithm convergence, we employ asynchronous training, transfer learning, and prediction-based action space simplification to expedite the model’s convergence speed. Finally, we build a prototyping network to verify the performance of the proposed small-timescale and the large-timescale allocation algorithms. Our proposed scheme demonstrates significant improvements in both resource utilization and quality of service compared to existing schemes.

Network slicing promotes the development of different industries by dividing multiple logical networks on the same physical network to provide the customized services. However, the complex environment of network slicing deployment makes it difficult to obtain the accurate mathematical models, so that the traditional rule-based heuristic algorithms are difficult to process them efficiently. Therefore, we combine the Graph Convolutional Networks (GCN) and the Deep Deterministic Policy Gradient (DDPG) algorithms and propose the GCN-DDPG (G-DDPG) algorithm in this paper to solve the end-to-end network slicing deployment problem, while taking into account the constraints of Virtual Network Function (VNF) placement, VNF sharing, tolerable latency, and node and link resources limitations. First, the end-to-end network slicing deployment optimization is formulated as a problem of maximizing the weighted sum of system resource utilization and acceptance rate. Second, the physical network features extracted by GCN are combined with the state information of end-to-end network slicing requests as the state space of the optimization problem, and a G-DDPG algorithm is proposed to solve it. Finally, the simulation results demonstrate that our proposed method superior to benchmark solutions in terms of the resource utilization of the system, acceptance rate of end-to-end network slicing.

The development of 6G networks is driving the need for innovative resource orchestration solutions to meet the diverse and dynamic demands of next-generation applications. As the number of connected devices increases, traditional network management approaches are insufficient to handle the complex and multi-resource requirements of 6G, which include communication, computation, and storage capabilities across multi-domain environments. To address these challenges, we introduce HyOrch, a novel approach for 6G-driven resource orchestration that employs hypergraph theory to model the intricate interactions and dependencies among network elements across multiple domains. HyOrch enables a comprehensive representation of these complexities, facilitating efficient resource orchestration across End Devices (EDs), Edge Servers (ESs), and Cloud Servers (CSs). It employs a hierarchical distributed resource allocation mechanism that dynamically allocates resources based on real-time availability and application-specific requirements, ensuring optimal performance across the entire network. To validate the effectiveness of HyOrch, we conducted evaluations on a real-world testbed with both virtual and physical devices. The results show that HyOrch significantly outperforms existing approaches, improving resource efficiency by 31.54%-42.13% and reducing delay by 9.77%-39.12%, demonstrating its capability to address the evolving challenges of 6G network orchestration.

To support the explosive growth of wireless traffic, the emerging control-and user-plane separation (CUPS) paradigm allows control base stations (CBS) to provide control plane (CP) coverage, while traffic base stations (TBSs) catering to varying mobile traffic and diverse quality of service (QoS) requirements. However, learning-based traffic prediction has yet to utilize the potential advantages provided by CUPS to facilitate energy saving. In this paper, we introduce a novel base station (BS) sleep scheme for CUPS that employs a learning-based approach to determine the TBS’s active/deactive states. First, traffic demands of TBSs are predicted by a novel data-driven learning approach. This approach leverages the receptive fields to explore the spatial characteristics of mobile traffic, and then employs Bidirectional Long Short-Term Memory (Bi-LSTM) networks to extract context feature of mobile traffic. Based on the traffic forecasting, we formulate a long-term network energy efficiency maximization problem that optimizes the active/deactive states of TBSs. Moreover, we introduce a service penalty term into CP to mitigate potential network coverage vulnerabilities of TBS. Then, an improved twin delayed deep deterministic policy gradient (TD3)-based algorithm is employed to solve the above non-deterministic polynomial-time hard (NP-hard) problem. Extensive experiments using a real-world dataset demonstrate that the proposed scheme significantly outperforms the existing methods in terms of traffic forecasting accuracy. Additionally, the proposed energy efficiency maximization algorithm achieves superior performance than other benchmark schemes.

Cloud-edge-terminal collaborative network (CETCN) has become a key enabler of the next generation wireless network. However, due to the privacy concern, terminals and the edge server may not will to leakage individual data to the cloud server. At the same time, limited computing capability of the edge server and terminals leads to long latency. Therefore, in this paper, we utilize a federated deep reinforce learning (DRL) algorithm named federated learning-based Double Deep Q Network (FL-DDQN) algorithm to solve the task offloading problem in CETCN. To be specific, firstly, we model the task offloading issue as the minimization problem of weighted energy consumption and latency of the CETCN with the constraints of subcarriers and maximum task processing latency. Secondly, we propose a DRL algorithm to obtain the suboptimal solution of the optimization problem. Thirdly, aiming to improve data security and reduce the working pressure of the terminals and the edge server, the FL-DDQN algorithm is further utilized, where the DDQN model is trained cooperatively in the terminals and the edge server. Finally the simulation result demonstrate that our proposed method superior to benchmark solutions in terms of total energy consumption and latency.

As an attractive enabling technology for next-generation wireless communications, network slicing supports diverse customized services in the global space–air–ground-integrated network (SAGIN) with diverse resource constraints. In this article, we dynamically consider three typical classes of radio access network (RAN) slices, namely, high-throughput slices, low-delay slices and wide-coverage slices, under the same underlying physical SAGIN. The throughput, the service delay, and the coverage area of these three classes of RAN slices are jointly optimized in a nonscalar form by considering the distinct channel features and service advantages of the terrestrial, aerial, and satellite components of acrshortpl SAGIN. A joint central and distributed multiagent deep deterministic policy gradient (CDMADDPG) algorithm is proposed for solving the above problem to obtain the Pareto-optimal solutions. The algorithm first determines the optimal virtual unmanned aerial vehicle (vUAV) positions and the interslice subchannel and power sharing by relying on a centralized unit. Then, it optimizes the intraslice subchannel and power allocation, and the virtual base station (vBS)/vUAV/virtual low Earth orbit (vLEO) satellite deployment in support of three classes of slices by three separate distributed units. Simulation results verify that the proposed method approaches the Pareto-optimal exploitation of multiple RAN slices, and outperforms the benchmarkers.

With the continuous development of multi-access edge computing (MEC) and artificial intelligence (AI), a new paradigm for 6G, namely endogenous intelligence (EI)-based MEC is created. Hence, a novel EI-based MEC scheme is proposed in this paper. Firstly, we present an EI-based MEC architecture, which deepens EI into MEC architecture. Secondly, referring to service-based architecture (SBA) for 5G core network (5GC), we decouple the edge intelligent services into multiple network functions (NFs) to enhance the flexibility of EI-based MEC architecture. Thirdly, for specific service types, we design MEC templates and instantiation schemes to complete the reconfiguration of EI-based MEC. Finally, we establish a testbed, and experimental results demonstrate that our proposed EI-based MEC can provide users with more reliable and agile edge intelligent services and effectively improve the Quality of Service (QoS).

5G spawns plenty of application scenarios to meet the diverse requirements of vertical industries, which poses challenges to the management and orchestration (MANO) of the 5G core network (5GC). This paper provides a microservice-based MANO for 5GC, so as to realize the on-demand deployment. Firstly, we propose a microservice-based MANO plane of 5GC. Secondly, we design the network functions (NF) and the transfer processes among them in the MANO plane. Finally, an experimental platform is built and the experimental results show that the microservice-based MANO has better resource utilization and disaster tolerance capabilities compared with the monolithic architecture.

In this paper, we design a caching replacement algorithm for edge networks to enhance the cache hit ratio of the edge network and reduce the traffic usage in the backbone network. Firstly, we design a dynamic-game model to represent the caching behavior between edge servers where each server takes the cache content of other servers into account to make their own caching decisions. Secondly, we analyze the utility function of edge servers from the perspective of caching contents. Finally, we derive the Nash equilibrium solution of the dynamic-game model and design a caching replacement algorithm to obtain the Nash equilibrium solution. Numerical results prove that the proposed edge caching replacement algorithm based on dynamic-game model improves the edge hit ratio up to 80% and meanwhile reduces 40% backbone traffic compared to the baseline solution.

Edge caching has been widely recognized as a key technology for multimedia services. However, the storage resource of the edge servers are severely restricted compared to the cloud servers, therefore we aim to design and implement an efficient video caching scheme while considering the limited storage resource of edge servers. Firstly, we propose an edge caching scheme to cache videos at the edge servers based on Adaptive Bitrate (ABR) Streaming, where we cache the representations of the most popular video chunks and the metadata of the less popular video chunks. Secondly, we use Docker to deploy the proposed caching scheme as an application at the edge server, which can dynamically determine whether the video chunk is cached with its representations or metadata. Finally, experimental results show that the proposed scheme can effectively utilize the idle computing resource at the edge to respond to the most video requests of the most users.

Based on wireless network virtualization, radio access network (RAN) slicing is developed to provide services for the different users' requirements. Moreover, the users' sum data rate and delay are two significant metrics to guarantee quality of services. In this paper, we first establish an optimization problem to maximize the downlink sum rate while guaranteeing users' delay for RAN slices, where the base stations and user equipments are randomly distributed. Then we analyze the performance tradeoff between the sum rate maximization and delay tolerance. With the aid of Lyapunov optimization, the upper bounds of the achievable rate and delay are derived, through which the existence of tradeoff in performance is obvious and verified by numerical results.