Traditional terrestrial wireless communication networks cannot support the requirements for high-quality services for artificial intelligence applications such as smart cities. The space–air–ground-integrated network (SAGIN) could provide a solution to address this challenge. However, SAGIN is heterogeneous, time-varying, and multidimensional information sources, making it difficult for traditional network architectures to support resource allocation in large-scale complex network environments. This article proposes a service provision method based on service function chaining (SFC) to solve this problem. Network function virtualization (NFV) is essential for efficient resource allocation in SAGIN to meet the resource requirements of user service requests. We propose a federated learning (FL)-based algorithm to solve the embedding problem of SFCs in SAGIN. The algorithm considers different characteristics of nodes and resource load to balance resource consumption. Then, an SFC scheduling mechanism is proposed that allows SFC reconfiguration to reduce the service blocking rate. Simulation results show that our proposed FL-VNFE algorithm is more advantageous compared to other algorithms, with 12.9%, 2.52%, and 10.5% improvement in long-term average revenue, acceptance rate, and long-term average revenue–cost ratio, respectively.
24 January 2024 in IEEE Transactions on Services Computing
The space-air-ground-ocean integrated network (SAGOI-Net) has become the focus of research in recent years, which has the characteristics of wide coverage and strong adaptability. However, due to the influence of multiple heterogeneous network segments, this network is unable to provide excellent quality of service (QoS). Based on the software-defined network and virtual network architecture, we abstract SAGOI-Net as a three-layer heterogeneous physical network resource, and propose a multi-domain virtual network embedding solution to optimize QoS. Specifically, before virtual network embedding, we collected SAGOI-Net's resource information through software-defined network and modeled it. In the virtual network embedding process, we first classify the virtual network request through K-means, and dynamically adjust the reward function to use reinforcement learning to solve the optimal virtual network embedding strategy. Finally, simulation experiments verify the effectiveness of the scheme.
Virtual network embedding (VNE) refers to the process of mapping virtual networks onto physical networks, which can improve the utilization and flexibility of network resources. However, due to the complexity of VNE problems and the requirement for network security, how to efficiently complete virtual network embedding and ensure network security is important. In this paper, we analyze the characteristics of the cloud-edge-terminal collaborative vehicular network and design a resource allocation mechanism based on VNE, abbreviated as DRLS-VNE. Firstly, we establish a multi-dimensional heterogeneous network model and design a five-layer neural network as the DRL agent. The DRL agent can adaptively extract network feature attributes, thereby improving the performance of DRLS-VNE. Secondly, we introduce a dynamic trust evaluation mechanism, which can evaluate the trustworthiness of each node in the virtual network in real-time and set embedding constraints based on the evaluation results. At last, we conduct experiments to verify the practicality and effectiveness of DRLS-VNE. The experimental results show that our solution can significantly enhance the performance of the VNE solution.
The dramatic increase in the volume of users and services makes scheduling network resources for smart grids a key challenge. Network slicing is an important technology to solve this problem. We introduce edge computing networks into the smart grid to intelligently allocate resources based on users’ quality of service (QoS) and available resources. However, existing heuristic resource scheduling algorithms often lead to resource fragmentation and thus fall into local optima. To this end, we propose a deep reinforcement learning (DRL)-based virtual network embedding algorithm to optimize the resource allocation strategy of smart grids from a network virtualization perspective. We extract the network properties of the smart grid to construct a policy network as a training environment for DRL agents. Finally, DRL derives the probability of each node being embedded based on the extracted attributes of edge computing nodes and completes user request (UR) embedding based on this probability. The experimental results show that the algorithm proposed in this paper has excellent performance with guaranteed low latency, 21% improvement in long-term revenue and 5.6% improvement in UR success rate compared with the other two algorithms.
14 December 2022 in IEEE Internet of Things Journal
Due to geographical factors and resource constraints, the traditional Internet architecture cannot meet the needs of the space-air-ground integrated network (SAGIN) resource layout in the Industrial Internet of Things (IIoT) service. How to arrange network resources in SAGIN quickly and efficiently to meet the quality of service requirements of users has become a hot research topic in the industry. Based on the characteristics of SAGIN with multiple network segments, we convert the resource scheduling problem of SAGIN into a multi-domain virtual network embedding (VNE) problem. This paper proposes a latency-sensitive virtual network embedding algorithm based on deep reinforcement learning (DDRL-VNE) in the SAGIN environment. Unlike traditional latency optimization algorithms, we consider the effect of traffic size and hop count on latency when evaluating latency. We constructed a learning agent composed of a five-layer policy network and extracted a feature matrix as its training environment based on the network attributes of SAGIN. The node embedding is completed according to the probability that each node is embedded in the training, and then the breadth-first search strategy is used to complete the link embedding. The experimental results effectively illustrate the effectiveness of the algorithm in the SAGIN resource allocation problem.
16 May 2023 in IEEE Transactions on Mobile Computing
In the collaborative intelligent transportation system, providing precise positioning services is costly. Reducing resource consumption and improving revenue are crucial to the development of positioning services. Therefore, a practical algorithm that combines cloud and edge network environments is necessary to improve the positioning services. Integrating network function virtualization and edge computing can provide users with more flexible and efficient services. Based on the above issues, we use the service function chain (SFC) to improve the positioning services provided in cloud-edge-vehicle collaborative networks (CEVCN). We propose a deep reinforcement learning-assisted SFC embedding algorithm and improve its performance through training. We construct a five-layer policy network to sense the environment of CEVCN and derive the optimal node selection strategy. Finally, we use the breadth-first search algorithm to solve the embedding scheme for virtual links. The simulation results show that our proposed algorithm has excellent performance. The long-term average revenue is improved by 21%, the long-term average revenue-cost ratio is improved by 13%, and the embedding rate is improved by 8%.