Tidal mobile traffic patterns offer opportunities for efficient Cloud Radio Access Network (CRAN) scheduling by leveraging its disaggregated and virtualized baseband processing, where baseband functions form a virtualized network function service chain (VNF-SC, or RAN slice) deployed across metro access, aggregation, and core networks. By dynamically reconfiguring and migrating RAN slices, processing pools can be powered down during low-demand periods to save energy. However, RAN slice migration causes service disruptions and degrades Quality of Service (QoS), making the tradeoff between energy efficiency and QoS a key challenge in CRAN scheduling. Existing approaches, such as heuristic and Deep Reinforcement Learning (DRL)-based methods, have achieved certain optimizations but rely on fixed scheduling intervals, which require provisioning for peak demand within the interval, leading to resource overprovisioning and inefficiency. To enable flexible and adaptive scheduling, we propose threshold-triggered heuristic-assisted DRL (TT-HA-DRL), which employs a threshold-triggered mechanism based on varying service demands and a heuristic-assisted DRL framework for adaptive RAN slice migration. Heuristic algorithms are used for action pruning to optimize the action space, enhancing scheduling performance. Baseline heuristics are incorporated to construct the Normalized Performance Loss as the reward function, enabling a tradeoff among the multiple optimization objectives. Extensive simulations validate the effectiveness and scalability of the proposed TT-HA-DRL. Compared to fixed-interval HA-DRL, our approach achieves reductions of up to 10.8% in power consumption, 12.3% in migration time, and 23.9% in Maximum Frequency Slot Index (MFSI) in a 30-node network. These results confirm TT-HA-DRL's ability for elastic and QoS-guaranteed RAN slice scheduling.

Network slicing has emerged as a promising solution for end-to-end (E2E) resource management and orchestration, enabled by software-defined networking (SDN) and network function virtualization (NFV) technologies. In this paper, we investigate the dynamic E2E optical-wireless network slicing mapping problem in converged optical-wireless access networks. To address user data rate requirements in wireless networks and radio access network (RAN) slicing scheduling in optical networks, we first formulate an E2E optical-wireless network slicing mapping model with its associated constraints. Subsequently, to provide feasible solutions for real-world applications, we propose a dynamic E2E optical-wireless network slicing mapping (D-E2E-OW-NSM) algorithm based on deep reinforcement learning (DRL). To facilitate the decision-making process of the DRL agent, we decompose the intricate E2E optical-wireless network slicing request into several sub-requests, solving them one by one in turn. Simulation results demonstrate that our proposed method reduces the request blocking probability by up to 18.2% in a small-scale network and 11.3% in a large-scale network compared to baseline methods. Our analyses provide valuable insights into the modeling and design of efficient converged optical-wireless access networks for 5G and beyond.

With the advancement of network function virtualization, 5G RAN slice’s baseband processing functions, such as distributed unit and centralized unit, can be implemented via virtual machines in processing pools (PPs). When traffic demand decreases, we can sleep the low-utilized PPs and migrate the slice requests they serve to other PPs for energy savings. However, migrations of RAN slice can cause service interruptions, leading to degraded Quality of Service (QoS). Existing works have addressed the energy-efficient and QoS-guaranteed RAN slice migrations problems effectively. However, their scheduling schemes are based on fixed-time intervals, which inevitably leads to the over-provisioning issue. To ensure service quality, fixed-time interval scheduling requires resource allocation based on the maximum demand within a time interval, leading to resource wastage. To address this issue, we propose an Adaptive Threshold-Triggered Heuristic-assisted Deep Reinforcement Learning (ATT-HADRL) algorithm that schedules RAN slice migrations in response to tidal traffic demands. Simulation results confirm that the proposed ATT-HA-DRL algorithm not only reduces power consumption and minimizes resource wastage but also decreases the number of scheduling events and shortens the total migration time, thereby maintaining high service quality and outperforming fixed-interval scheduling approaches.

In this article, we address the key problem of sensing and communication integrated resource allocation for 6G-empowered distribution grid hierarchical coordinated control. First, we construct a novel information timeliness metric for electric semantic communication, namely, Peak Age of Semantics (PAoS), which covers the entire lifecycle of information sensing, semantic compression, semantic transmission, and semantic decoding. Second, we propose a sensing and semantic communication integrated resource allocation algorithm based on Top-$\text {N}^{2}$and hybrid knowledge–statistic-driven fuzzy reinforcement learning. A deep fuzzy neural network is utilized to build a knowledge model between the grid operating state and decision making. The knowledge is embedded into statistic-driven model of reinforcement learning to enhance accuracy of upper confidence bound (UCB) utility evaluation. Finally, simulations based on realistic application scenarios indicate that compared with two comparison algorithms, the proposed algorithm reduces average PAoS by 4.72% and 9.49%, and the maximum PAoS by 5.76% and 13.57%. Additionally, its end-to-end delay trend and semantic packet decoding success rate align more closely with semantic importance.

Low-utilized antenna subarrays can be switched to sleep mode during traffic valleys to save energy. However, when an antenna subarray enters sleep mode, beam services connected with this subarray must be reassociated with another subarray, inevitably degrading the Quality of Service (QoS) for the beams. In this article, we investigate an energy-efficient and QoS guaranteed 3-D beam mapping problem for 2-D antenna subarray selection and radio resource block (RB) allocation in massive multiple input–multiple output (MIMO) systems under a tidal traffic load. The 3-D beam mapping problem is formulated as a mixed integer linear programming (ILP) model to find the optimal solution. To address the scalability issue of the ILP model, we propose a load adjustment (LA) with greedy searching (LA-GS) algorithm to optimize both the energy consumption (EC) of antenna subarrays and the traffic migration of beam services. Moreover, two benchmark algorithms, load reallocation (LR) and LA, are designed for performance comparison. Extensive numerical results demonstrate that the proposed LA-GS algorithm can guarantee both low EC and minimal traffic migration. Compared with the designed LR algorithm, our proposed LA-GS method can achieve up to a 28.3% cost reduction, primarily attributed to a 43.1% reduction in traffic migration with at most 1.9% higher EC.

To ensure reliable network services, the link protection method is widely employed for light-path provision. However, it inevitably increases propagation delay due to different transmission distances between active and backup light-paths, leading to a longer transport delay. Consequently, a crucial challenge is how to coordinate link protection and transport delay to maximize service availability while satisfying the delay requirements of each service. In this paper, we investigate the availability-aware and delay-sensitive (AADS) radio access network (RAN) slicing mapping problem with link protection in metro-access/aggregation elastic optical networks (EONs). We initially provide the mathematical model of availability and propagation delay for both unprotected and protected RAN slicing requests. Subsequently, we propose a mixed-integer linear programming (MILP) model and a deep reinforcement learning (DRL)-based algorithm to maximize the availability of RAN requests while satisfying the specified delay requirements of each slice. Finally, we analyze the availability under various 5G services (i.e., enhanced Mobile Broadband, ultra-Reliable Low-Latency Communication, and massive Machine Type Communication) from a delay perspective in both small-scale and large-scale networks. Simulation results demonstrate that our proposed DRL-based method can achieve up to a 14.1% increase in availability compared to the benchmarks.

The fine-grained functional split is an effective way to solve the baseband function processing centralization and optical bandwidth saving in radio access networks (RANs). In this paper, to improve computing resource utilization, we investigate how to realize the fine-grained function placement and routing of 5G RAN slice with function reuse scheme in elastic optical networks (EONs). We first formulate a mixed integer linear programming (MILP) model to solve the problem exactly. The main optimization goal in the MILP model is to jointly minimize the average cost of computing, bandwidth resources and end-to-end latency. Then, a heuristic-assisted deep reinforcement learning (HA-DRL) algorithm is proposed to obtain a near-optimal solution. In particular, the longest common subsequence-based path policy is utilized in the DRL to reduce the size of the action space and accelerate the training process. Finally, we evaluate the proposed MILP model and HA-DRL algorithm via extensive simulation. The results show that the proposed MILP model and HA-DRL algorithm outperform the benchmarks in terms of average cost, including the number of used processing pools (PPs), maximum frequency slot index (MFSI) on the lightpath and end-to-end latency of each slice request.

In today’s datacenters (DCs), IT resources virtualization is leveraged to realize Network Function Virtualization (NFV) over general-purpose servers. Meanwhile, most of the service providers (SPs) are planning to use Virtual Network Functions (VNFs) to provide agile and flexible network services. In service provisioning, the VNF selection and mapping greatly affect IT resource utilization in DCs and spectrum resource utilization in optical networks. This paper proposes a Deep Reinforce Learning (DRL)-based algorithm for VNF provisioning. By selecting appropriate VNFs for the service requests, the algorithm intelligently guarantees efficient reusing of deployed VNFs while consuming fewer spectrum resources in inter-DC elastic optical networks (EONs). To facilitate the decision-making of the DRL agent, we first decompose the complex VNF-based service chaining (VNF-SC) into several VNF components (VNFCs), which can be solved one-by-one in turn. Then, a feature matrix-based encoding scheme is designed to represent the set of the VNFCs, the available DCs for the VNFCs, and the VNFC being operated, i.e., the input of neural networks. In addition, considering the complexity and difficulty of the VNF-SC provisioning problem, Double Deep Q Network (DDQN) is introduced in the proposed algorithm. Finally, compared with the benchmark heuristics, the extensive simulation results in different network topologies show that the proposed algorithm can reduce the IT and spectrum resource consumption by at least 9.6% and 1.6%, which proves the effectiveness of the proposed DRL-based VNF provisioning algorithm.