3 October 2024 in IEEE Internet of Things Journal
The ultradense low-Earth orbit (UD-LEO) satellite network has attracted significant attention recently due to its great potential in providing global Internet coverage and services. For the sake of improving performance and reliability, multiple network paths can be utilized for coordinated transmission. However, state-of-the-art multipath routing algorithms face the challenge when dealing with highly dynamic network characteristics (i.e., high-speed node movement, frequent topology changes) in such emerging networks. In this article, we propose a deep-reinforcement-learning-based multipath cooperative routing (DRL-MPCR) scheme for UD-LEO satellite networks, with the aim of enhancing routing discovery capability and improving multipath transmission performance. Two main building blocks of multipath transport protocol are considered: 1) routing discovery and 2) multipath scheduling. On the one hand, in order to cope with the highly dynamic satellite network, a DRL-based multipath routing discovery algorithm is proposed, where satellite agents independently make routing decisions according to the perceived local network state, so that multiple available paths can be obtained. On the other hand, to promptly make traffic scheduling according to the varying path conditions, a water filling algorithm-based multipath scheduling policy is designed, which aims to optimize the maximum path cost when multiple paths are utilized for cooperative transmission. Extensive simulation results demonstrate that the proposed DRL-MPCR scheme achieves more efficient routing discovery and better multipath transmission performance than existing ones.
28 February 2023 in IEEE Transactions on Wireless Communications
In this paper, we propose a meta-learning based cell-level network traffic prediction framework (ML-TP), which can provide the proper initial weight vector for the learning model of a new prediction task based on the prediction task’s meta-features. In the ML-TP, each prediction task forms a base-task, and a multi-layer long short-term memory (LSTM) network is constructed as its base-learner. Through fast Fourier transform (FFT) analyses of real-world network traffic data, we find that the five most dominating frequency components can capture the cell-level traffic variations, and hence can be used as a base-task’s meta-features. We prove that the well-trained weight vector of a previous base-task’s base-learner is likely to be a proper initial weight vector of a new base-task’s base-learner if the meta-features of the two base-tasks are close to each other in the Euclidean space. Accordingly, we propose a K-nearest neighbours (KNN) algorithm based meta-learner to deal with the meta-task in the ML-TP. Numerical tests show that the ML-TP can significantly increase the base-learners’ after-training prediction accuracy and learning efficiency in terms of the number of base-samples and the number of epochs needed in each base-learner’s fine-tuning progress.
20 April 2023 in IEEE Transactions on Vehicular Technology
Deploying the 5 G new radio network on the unlicensed mmWave band (NR-U) is a promising solution to meet the constantly increasing traffic demand of the cellular network. However, the coexistence issue on the unlicensed mmWave spectrum between NR-U and Wireless Gigabit (WiGig) networks becomes a significant concern. The coexistence schemes between LTE and Wi-Fi networks cannot be readily applied to support the coexistence between NR-U and WiGig networks due to the directional beamforming and propagation characteristic of the mmWave band. The directional transmission complicates the coexistence problem but opens up possibilities for increased system capacity via concurrent multi-user MIMO (MU-MIMO) transmission at the expense of interference management. To this end, we consider an NR-U and WiGig coexisting scenario and aim to maximize the total NR-U throughput on the unlicensed spectrum via resource allocation and inter-beam interference mitigation. The optimization problem is formulated into an integer nonlinear programming (INLP) problem and is further transformed into a many-to-one matching game for tractability. We propose a matching-based concurrent algorithm (MBCA) to solve it and the inter-beam interference is mitigated via the forbidden pairs (FPs). In comparison to the exhaustive search-based algorithm (ESA), simulation results show that FP effectively mitigates inter-beam interference and achieves near-optimal performance. The proposed algorithm also outperforms the state-of-art algorithms in existing research.
21 January 2025 in IEEE Internet of Things Journal
Ultra-dense Low earth orbit (LEO) satellite-terrestrial network (ULSN) has evolved as a new paradigm to provide ubiquitous and high-capacity communications in next generation wireless networks. However, the direct LEO satellite broadband connectivity faces significant challenges in urban environments due to the masking effect, which limits the reliability and availability of communication links in ULSNs. To address this, reconfigurable intelligent surface (RIS) is emerging as a promising solution in ULSNs. In this paper, we investigate RIS-aided downlink data transmission in urban environments of multi-users in ULSNs. We set up a mixed-integer programming (MIP) model for maximizing the sum rate of terrestrial users in ULSNs. To solve the complex MIP problem, we propose a two-phase joint optimization (TPJO) algorithm with a deep learning phase and an alternative optimization (AO) phase. In the deep learning phase, a deep neural network (DNN) algorithm is employed to obtain the optimal user association matrix based on the positions of terrestrial users and LEO satellites. Then in the AO phase, successive convex approximation (SCA) is utilized to transform the nonconvex subproblems of beamforming and RIS phase design into convex formulations and iteratively solve them. Simulation results demonstrate that the proposed algorithm outperforms other baseline algorithms.
24 January 2019 in IEEE Access
Device-to-device (D2D) communications as an underlay to cellular networks can potentially improve the system throughput and reduce transmission delays between users, which however are largely limited by the battery lifetime of user equipment (UE). In this paper, we define the overall system survival time of a mobile cell and maximize it by jointly optimizing the resource allocation and power control (RAPC) for D2D and conventional cellular (CC) links. Considering that UEs may have different levels of residual battery energy, we define the overall system survival time as the minimal expected battery lifetime among all transmitting UEs in a cell. Subject to the transmission rate requirement of each link, we formulate the joint optimization of RAPC as a non-linear programming (NLP) problem, which is NP-hard. To solve it, we devise a game theory based distributed approach, where the links are considered as noncooperative players with the overall system survival time as their utility function. We prove the existence of Nash equilibrium in our RAPC game and propose a low complexity algorithm to calculate each individual player’s best response given the strategies of other players. Numerical results show that our game theory based approach can significantly prolong the overall system survival time as compared with existing RAPC schemes.
24 February 2020 in IEEE Wireless Communications Letters
Device-to-device (D2D) communication underlaying cellular networks is seen as a promising technology for future communication systems, especially when relays are employed to extend the range of D2D links. However, the mutual interference between the spectrum-sharing D2D links and conventional cellular (CC) links is still the dominating performance limiting factor, which enforces those links to adopt higher transmission power. As energy saving is always one of the key concerns, we propose to minimize the total transmission energy consumption of a relay-assisted D2D link and a CC link sharing radio resources by jointly optimizing their transmission rate selection and power control (TRSPC). We formulate the optimization problem as a non-convex non-linear programming (NLP) problem and then develop a game theory based distributed approach to solve it. Simulation results demonstrate that our game theory based TRSPC approach can enormously decrease the total transmission energy consumption compared with existing works.