As an integral component of the space-air-ground integrated network (SAGIN), the low Earth orbit (LEO) satellite network has displayed immense potential in providing ubiquitous connectivity and broadband mobile communication. However, the intrinsic dynamics of LEO satellites pose unprecedented challenges in network management and service delivery. In this paper, we investigate the service function chain (SFC) orchestration in dynamic LEO satellite networks to achieve flexible and efficient service provision. Considering the service requirements and the limitations of network resources, we formulate the SFC orchestration problem as the integer nonlinear programming (INLP) problem for maximizing the service acceptance and the load fairness of satellites. Then, an efficient heuristic algorithm is proposed to solve this problem. Addressing the situation with frequent service requests, a graph attention network (GAT)-based approach with low complexity is also presented. Simulation results demonstrate that our proposed approaches outperform the benchmarks by a substantial margin in terms of load fairness and service acceptance. Besides, the proposed GAT-based approach shows its advantage in computation complexity, and exhibits robustness in unstable network scenarios with intermittent link interruptions.

This paper proposes a novel knowledge-driven approach for resource allocation in wireless networks using the graph neural network (GNN) architecture. To meet the millisecond-level timeliness and scalability required for the dynamic network environment, our proposed approach, named UWGNN, incorporates the deep unrolling of the weighted minimum mean square error (WMMSE) algorithm, referred to as domain knowledge, into GNN, thereby reducing computational delay and sample complexity while adapting to various data distributions. Specifically, by unrolling WMMSE algorithm into a series of interconnected submodules, UWGNN aligns closely with the optimization steps of the algorithm. Our analysis reveals the effectiveness of the deep unrolling method within UWGNN, which decomposes complicated end-to-end mappings, leading to a reduction in model complexity and parameter count. Experimental results demonstrate that UWGNN maintains optimal performance with computation latency 3 to 4 orders of magnitude lower than the WMMSE algorithm and exhibits strong performance and generalization across diverse data distributions and communication topologies without the need for retraining. Our findings contribute to the development of efficient and scalable wireless resource management solutions for distributed and dynamic networks with strict latency requirements.

Due to the wireless broadcasting and broad coverage in satellite-supported Internet of things (IoT) networks, the IoT nodes are susceptible to eavesdropping threats. Considering the distance difference between satellite and nearby destinations is negligible, the main and wiretapping channels between satellite and IoT node are similar, it poses great challenges to reach physical layer security in satellite-assisted IoT networks. In this paper, to guarantee secure transmissions for satellite-assisted IoT downlink communications, the multi-domain resource multiplexing based secure approach is proposed. Particularly, the self-induced co-channel interference between adjacent nodes is leveraged to increase the difference of signal transmission quality over both main and wiretapping channels. By comprehensively optimizing multi-domain resources, i.e., frequency, power, and spatial domains, secure transmissions from satellite to IoT nodes are reached. Specifically, the problem to maximize the sum secrecy rate of IoT nodes is formulated with a constraint of common communication rate of IoT nodes. To solve this non-convex problem, an alternating optimization (AO) algorithm with two inner successive convex approximation (SCA) algorithms are executed to solve the power allocation, spectral multiplexing, and precoding. In addition, simulation results are carried out to evaluate the secrecy rate performance and verify the efficiency of our proposed approach.

Due to the dense deployment of a small base station (SBS), wired backhauling is not always available, nor it is efficient. Therefore mmWaves are introduced to serve as backhauling links that offer high backhauling throughput and low CAPEX. However, mmWaves suffer from a high attenuation rate as the distance between SBSs and a macro base station (MBS) increases, which can severely degrade the system performance. Therefore, it is more efficient to use some SBSs to aggregate from different SBSs to MBS. On the other hand, densely deployed SBSs with wireless backhauling can cause high energy consumption in the system. In this work, we present a new network model in which SBSs are able to harvest energy from a renewable source and utilize it for backhauling and their associate UEs. A mathematical Optimization problem is formulated to solve UEs association, dynamic sleeping, backhauling, and transmission power. Moreover, due to the complexity of the formulated problem, a heuristic algorithm is introduced. Namely, a heuristic backhauling and dynamic sleeping (HBDS) algorithm is introduced to decomposes the formulated problem into two parts and solve it iteratively. Finally, computer simulation results that demonstrate the model’s performance are presented for comparison between optimal solution and HBDS, which shows that HBDS has better computation efficiency with minimum performance difference.

In this paper an optimization problem to minimize the energy drawn from the network grid by utilizing the harvested energy and dynamic sleeping of the Small Base Stations (SBSs) is presented. Due to the complexity of the optimization problem, a new UEs' movement prediction method is introduced to provide future information for the model to apply an accurate optimization problem. This method is based on a combined approach of Non-linear Autoregressive with External input (NARX) and probabilistic Latent Semantic Analysis (pLSA) to provide accurate prediction for multiple steps. Furthermore, extensive simulation results are presented to show the effectiveness of our approaches in comparison to the optimal results.

Data forwarding from a source to a sink node when they are not within the communication range is a challenging problem in wireless networking. With the increasing demand of wireless networks, several applications have emerged where a group of users are disconnected from their targeted destinations. Therefore, we consider in this paper a multi-Unmanned Aerial Vehicles (UAVs) system to convey collected data from isolated fields to the base station. In each field, a group of sensors or Internet of Things devices are distributed and send their data to one UAV. The UAVs collaborate in forwarding the collected data to the base station in order to maximize the minimum battery level for all UAVs by the end of the service time. Hence, a group of UAVs can meet at a waypoint along their path to the base station such that one UAV collects the data from all other UAVs and moves forward to another meeting point or the base station. All other UAVs that relayed their messages return back to their initial locations. All collected data from all fields reach to the base station within a certain maximum time to guarantee a certain quality of service. We formulate the problem as a Mixed Integer Nonlinear Program (MINLP), then we reformulated the problem as Mixed Integer Linear Program (MILP) after we linearize the mathematical model. Simulations results show the advantages of adopting the proposed model in using the UAVs' energy more efficiently.

This paper considers a heterogenous network HetNet where a macro base station (MBS) coexists with many small base stations (SBSs). SBSs can be deactivated and put to sleep to save energy and are equipped with two power sources, harvested energy (HE) source and a power grid source, where first the SBS will use its available HE to serve the associated users. Then, the SBS will request any shortage of its energy from other active or deactivated SBSs which have surplus of HE. Finally, if there is still shortage in energy, the SBS will use the power drawn from the grid. This transfer of energy is facilitated through the use of the promising technology of the smart grid (SG). We investigate the grid energy minimization problem by optimizing both the transmission power and activation/deactivation (Dynamic Sleeping) of the SBSs. Moreover, a decomposition of the problem into a convex optimization problem and users association according to the best SINR is proposed. Then, we derived a closed form of the optimal transmission power and use the IPOPT algorithm to find the Lagrangian variables. The results clearly show the advantages of our model operational strategy.