Jia Chen

As an important support of next-generation network technologies, edge computing provides crucial support for holographic communication services (HCSs) by offering low latency and high computing power. However, in resource-constrained environments, the deployment of HCSs is significantly affected by the coordinated scheduling of computational and transmission resources, as well as the selection of multi-task processing ratios, which in turn curtails service latency and user experience. For this purpose, this paper proposes an efficient edge network offloading and orchestration framework that jointly optimizes adaptive video processing, multi-task offloading, and resource allocation strategies. Specifically, we model computation offloading and video processing as a stochastic optimization problem to maximize system utility, which is defined as a weighted difference between network satisfaction and user utility. Based on Lyapunov optimization theory, the original long-term optimization problem is decomposed into single time slot subproblem, and further reformulated as a Markov Decision Process (MDP). To effectively solve this problem, we design a Graph attention-driven Computing and Networking Coordination based policy optimization Orchestration algorithm (GCNCO). The multi-dimensional policy joint optimization is achieved by fully sensing the contextual relationship of services and network state distribution. Finally, we compare the proposed algorithm with several benchmark algorithms and validate it using a prototype system. Experimental results demonstrate that GCNCO outperforms existing approaches in terms of convergence speed and performance stability, significantly enhancing system utility and improving the success performance of HCS orchestration.

Immersive media applications often create an immersive experience for users through head‐mounted displays. However, the computing power and storage capacity of terminal devices are limited, and the local computing architecture cannot meet the high resolution and low latency requirements of panoramic video frames. As a new computing paradigm, cloud, edge and end collaborative computing architecture selectively schedules computing tasks to cloud servers and edge servers with higher computing power, which can effectively improve computing efficiency. However, for dependent computational tasks, the scheduling of each task needs to consider its previous tasks, network state, and computational resources of different servers. Therefore, how to make computational offloading decisions and resource allocation for dependent tasks is a key issue for collaborative computing architectures. This paper investigates and analyzes the immersive media scenarios and the basic computation offloading strategies, and construct a dependent task model graph and optimization problem model. Based on threshold strategy, greedy strategy of heuristic algorithm and deep reinforcement learning model, a scheduling strategy under collaborative computing architecture is designed to maximize the reward related to delay and cost. Finally, the basic performance of the computational task scheduling strategy based on deep reinforcement learning and greedy policy is verified through simulation experiments. The experimental results show that the algorithm reduces the latency by more than 1.8 ms and increases the timely completion rate by more than relative to several basic scheduling schemes, which can effectively improve the service quality and user experience.

Natural disasters pose a significant threat to human life. In these extreme conditions, terrestrial networks frequently become incapacitated, hindering the provision of essential communication and computing services required for emergency response efforts. In recent years, the rapid advancement of drone technology, coupled with the maturation of lightweight communication and computing equipment, has led to the emergence of unmanned aerial vehicle (UAV) networks as a crucial asset in disaster rescue missions. These networks provide significant advantages, including rapid response times, flexible deployment capabilities, and heightened resilience to complex terrains, showcasing considerable potential for further development. UAV networks exemplify resource-constrained systems where efficient scheduling of computing resources is vital. Especially in emergency rescue scenarios, this complexity is exacerbated by the diverse range of tasks, varying demands, and stringent real-time requirements. Effectively managing and allocating the computational resources of drones is essential for maximizing their operational efficiency in response to the intricate dynamics of disaster situations. To improve the computational service efficiency of the network, this paper proposes an emergency rescue UAVs network architecture. Additionally, we investigate a joint optimization approach for task planning and SFC scheduling. Current research on SFC scheduling primarily focuses on ground data center networks, with comparatively limited investigation into UAV networks. Fully considering the mobility of computing nodes, as well as the wireless transmission modes within the aerial environment, we establish a joint optimization model for task planning and SFC scheduling aiming at minimizing the total weighted end-to-end delay. Then we design the A3C based algorithm to learn the optimization strategy. Simulation results are presented to demonstrate the superiority of the proposed approach in the aspect of total weighted end to end delay and training time against other benchmark algorithms.

With the rise of the Metaverse, Real-time Holographic-type Communication (HTC) has emerged as a promising approach to creating immersive experiences. In HTC, Motion-to-Photon (MTP) latency, which is composed of computing, network and storage latency, must be ultra-low and bounded to avoid vertigo syndrome. Time Sensitive Networks (TSN) and Deterministic Networks (DetNet) are generally adopted to ensure deterministic transmission with ultra-low bounded latency. However, the transmission of HTC streaming faces computing latency fluctuation and requires high bandwidth, which exceeds the capabilities of TSN and DetNet. Therefore, to address these limitations, this paper proposes Deterministic Transmission based on Computing-Network-Storage Resources Tradeoff (DT-CNST). In DT-CNST, a Computing-based Traffic Shaper is proposed to eliminate computing latency fluctuation. A Cyclic Buffering, Queuing and Forwarding mechanism is also designed to ensure deterministic transmission of large frames. Moreover, a Computing-Network-Storage (CNS) model is established, incorporating constraints and a resource tradeoff optimization. Based on the CNS model, the Hybrid PPO-Greedy Resource Tradeoff (HPG-RT) algorithm is developed to maximize the number of scheduled streams. Simulation results show that HPG-RT achieves a schedulability rate of 90.7%, outperforming benchmarks with a maximum improvement of 35.5%. Prototype results confirm that DT-CNST provides an immersive experience with at least 25 frames per second.

The current Internet struggles to meet the deterministic transmission requirements in terms of end-to-end delay. Time-sensitive networking (TSN) provides a solution by offering deterministic forwarding services for critical flows, ensuring strict latency requirements. However, the costs and complexity of hardware associated with TSN increases the barriers for researchers to build prototype for validating newly proposed queue scheduling algorithms. To address this dilemma, software-based simulation platforms are widely used for reduction of simulation expenses. However, these platforms cannot flexibly simulate various queue scheduling algorithms. Although existing programmable packet scheduling methods can adapt to TSN queue scheduling algorithms for common hardware base, they cannot be directly applied to software-based TSN simulation platforms. In response, we propose a novel lightweight software-defined packet scheduling primitive—first-in-pick-out (FIPO), based on the programmable switch behavior-model-version-2 (BMV2). FIPO is capable of expressing customized queue scheduling algorithms to support current TSN algorithms and can be flexibly extended to future algorithms. Particularly, FIPO consists only of multipriority queues and eligible time comparator to implement TSN queue scheduling with minimal computational and management overhead. We also propose a fine-grained logical queue-based flow queue mechanism to enhance FIPO. Finally, a lightweight prototype system for the FIPO is established, incorporating four customized deterministic scheduling algorithms. Extensive experimental results show that FIPO can quickly implement customized queue scheduling algorithms and simulate network conditions that closely resemble real environments. It also demonstrates increased implementation flexibility, achieving millisecond-level configuration times with only a moderate increase in CPU utilization (less than 10%).

Emerging applications such as holographic communications and smart medical care are driving the rapid evolution of future networks. In the network architecture enabled by software defined networking and network function virtualization, service function chaining (SFC), which orderly schedules various virtual network functions (VNFs), is one of the primary methods to provide flexible, agile, and diversified network services. However, these emerging applications face dual challenges of resource allocation and low latency requirements. To address this issue, in this paper, we propose a joint resource and latency-aware based SFC optimization orchestration approach for emerging applications that are delay-sensitive and computation-intensive, establishing a resource-aware scheduling model based on discrete time. The problem is described as an integer linear programming problem with QoS as the optimization objective. Furthermore, we present a deep reinforcement learning based optimal orchestration algorithm for simultaneous VNF embedding and flow routing, the core idea of “joint resource and latency awareness” is applied to realize the scheduling of delay-sensitive services. Finally, the proposed approach is compared with four benchmark algorithms. Experimental results indicate that the proposed approach can enhance QoS, achieve a greater acceptance rate, and complete the scheduling of more delay-sensitive services.