1 January 2025 in Electronics Letters
One of the most significant technologies for ensuring deterministic low‐latency transmission for time‐sensitive applications in the integrated TSN‐5G network is the traffic scheduling method. In this paper, we propose a channel‐aware and queue‐aware deficit round Robin (CQDRR) scheduling method for different hybrid flows in an integrated TSN‐5G network. The proposed asynchronous CQDRR scheduling algorithm achieves a computational complexity of O ( m ), making it effective and particularly suitable for scalable TSN‐5G network environments. Its design eliminates the need for time synchronization between 5G and TSN networks, further enhancing its applicability in heterogeneous network scenarios. The CQDRR scheduling method considers both queue load and channel information in its quantum allocation decisions, achieving a good delay performance by distributing suitable quantities of quantum to various TSN flows. The simulation results show that the CQDRR scheduling algorithm significantly outperforms the deterministic quality‐of‐service (DQOS) and deficit round Robin (DRR) in terms of end‐to‐end delay performance, especially at high network loads and/or bad channel conditions.
25 May 2026 in IEEE Internet of Things Journal
Integrating Fifth Generation Communication Network (5G) with Time-Sensitive Networking (TSN) is essential for deterministic Industrial Internet of Things (IIoT). It is a challenge to provide ultra-reliable and deterministic services for time-triggered (TT) flow in the integrated TSN-5G network. In this paper, we propose PTFRS, a Proximal Policy Optimization (PPO)-based time–frequency resource scheduling approach that provides ultra-reliable and deterministic services for TT flow in 5G channel quality fluctuations. PTFRS applies a residual neural network (ResNet)-based convolutional neural network (CNN) (ResNet-based CNN) as a shared state encoder to extract high-dimensional features from the environment state. Then, based on these embeddings, the model jointly optimizes the allocation of sending time offsets, queue shifts, and resource blocks (RBs) using PPO. The auction expert algorithm serves as a guide in the PTFRS, helping the agent develop a more effective resource block allocation strategy for the UEs. The experimental results show that PTFRS reduces end-to-end delay by 26.16%, 14.17% over PPO-RB and DetTsch DRL algorithms and improves TT scheduling success by 20.3%, 53.4%, and 20.9% over PPO-Sym, PPO-RB, and DetTsch DRL algorithms, respectively. The PTFRS algorithm significantly reduces end-to-end delay and significantly enhances the scheduling success ratio and reliability performance. Our proposed PTFRS stabilizes and accelerates the model learning compared to the other existing deep reinforcement learning (DRL) algorithms. Consequently, the proposed PTFRS can provide ultra-reliable, low-latency, and deterministic services for TT flows in the integrated TSN-5G network.
25 February 2026 in IEEE Transactions on Network and Service Management
With the rapid evolution of 5G/6G networks, deterministic services such as the Industrial Internet, vehicular communications, and immersive applications impose stringent end-to-end (E2E) latency guarantees. Efficient resource allocation for E2E network slicing (NS) is therefore required to simultaneously satisfy strict latency constraints and improve overall resource efficiency. However, orchestrating cross-domain and multidimensional resources across the radio access network (RAN) and core network (CN) remains challenging due to strong coupling and scalability issues. To address this problem, this paper develops a profit-driven optimization framework for static E2E NS, which jointly accounts for deterministic service guarantees and system profitability. On the RAN side, a hybrid genetic algorithm (HGA) is developed to preserve the global exploration capability of genetic algorithms, while incorporating a gradient-guided resource scaling (GGRS) operator to refine elite solutions and improve solution quality. On the CN side, we design a capacity-aware workload balancing algorithm (CA-WLB). For each candidate path, CA-WLB couples capacity adaptive virtual network function (VNF) placement with demand responsive CPU allocation to jointly optimize latency and resource consumption, and then selects the path that yields the maximum profit. Extensive simulations across a wide range of scenarios demonstrate that the proposed framework consistently outperforms conventional heuristic and meta-heuristic approaches, while achieving performance close to high-complexity optimization benchmarks with significantly reduced computational overhead.