Cooperative Downloading for LEO Satellite Networks: A DRL-Based Approach

Article Telecommunications

Collaborative Data Offloading for Earth Observation Satellite Networks

Lijun He et al.

Summary: This paper studies the problem of collaborative data offloading in satellite networks and proposes an algorithm based on task flow graph. Simulation results demonstrate the effectiveness of collaborative data offloading.

IEEE COMMUNICATIONS LETTERS (2022)

添加到收藏夹

Article Geochemistry & Geophysics

Satellite Image Compression and Denoising With Neural Networks

Vinicius Alves de Oliveira et al.

Summary: Satellite image compression and denoising are crucial for earth observation. This letter proposes two neural network-based approaches, one for joint onboard compression and denoising, and the other for sequential onboard compression and on-ground denoising. The experiments show that both approaches outperform the current satellite imaging system, and their pros and cons are discussed.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Integrated Satellite-Terrestrial Networks Toward 6G: Architectures, Applications, and Challenges

Xiangming Zhu et al.

Summary: This article presents a comprehensive survey of the state-of-the-art integrated satellite-terrestrial networks towards 6G, including classification and summary of the integration architecture, discussion of typical applications, identification of challenges, and exploration of promising future techniques. The importance of a detailed survey of potential integration architectures for flexible network design and construction in future 6G networks is emphasized.

IEEE INTERNET OF THINGS JOURNAL (2022)

添加到收藏夹

Article Chemistry, Analytical

Deep Reinforcement Learning-Based Resource Allocation for Satellite Internet of Things with Diverse QoS Guarantee

Siqi Tang et al.

Summary: This paper proposes a deep reinforcement learning-based online channel allocation and power control algorithm to balance success rate and power efficiency while ensuring QoS requirements. Through simulation experiments, the method can improve resource efficiency and guarantee QoS requirements, and can be transferred to a space environment.

SENSORS (2022)

添加到收藏夹

Article Computer Science, Information Systems

RL/DRL Meets Vehicular Task Offloading Using Edge and Vehicular Cloudlet: A Survey

Jinshi Liu et al.

Summary: In the past two decades, there has been a clear trend towards intelligent vehicles that provide safer, stress-free, and more enjoyable driving experiences. However, current intelligent vehicles have limited computing capabilities, making it challenging to meet the demands of delay-sensitive and computation-intensive applications. Vehicular task/computation offloading to edge cloud and vehicular cloudlet is considered a promising solution to improve network performance and application quality of service.

IEEE INTERNET OF THINGS JOURNAL (2022)

添加到收藏夹

Article Computer Science, Information Systems

Joint Observation and Transmission Scheduling in Agile Satellite Networks

Lijun He et al.

Summary: This paper investigates joint observation and transmission scheduling in agile satellite networks (ASNs) to accommodate more imaging data. The problem is formulated as an integer linear programming (ILP) and solved efficiently using semidefinite relaxation (SDR).

IEEE TRANSACTIONS ON MOBILE COMPUTING (2022)

添加到收藏夹

Article Chemistry, Analytical

Dual Stream Transmission and Downlink Power Control for Multiple LEO Satellites-Assisted IoT Networks

Bingyu Xu et al.

Summary: This paper investigates the dual-stream transmission and downlink power control for multiple LEO satellites-assisted IoT networks, and proposes a multi-satellites synchronization scheme to mitigate the effects of frequency offset. Different power control schemes are given to maintain the stability of data rate.

SENSORS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Deep Reinforcement Learning-Based Power Allocation for Rate-Splitting Multiple Access in 6G LEO Satellite Communication System

Jingfei Huang et al.

Summary: This letter investigates the power allocation problem in LEO satellite networks with rate-splitting multiple access (RSMA) mechanism based on deep reinforcement learning. A highly-effective proximal policy optimization (PPO) scheme is proposed to tackle the challenge of uncertain and limited channel distribution information. Simulation results demonstrate the superiority of the proposed scheme in terms of the sum rate metric with low computation complexity.

IEEE WIRELESS COMMUNICATIONS LETTERS (2022)

添加到收藏夹

Article Chemistry, Analytical

Federated Reinforcement Learning Based AANs with LEO Satellites and UAVs

Seungho Yoo et al.

Summary: Advances in rocket technology have allowed companies like SpaceX and Amazon to enter the satellite internet business competitively. However, the limited resources of satellites make it challenging to provide sufficient internet service in densely populated areas. To address this issue, an adaptable aerial access network (AAN) composed of low-Earth orbit satellites and federated reinforcement learning (FRL)-enabled unmanned aerial vehicles (UAVs) has been proposed.

SENSORS (2021)

添加到收藏夹

Review Computer Science, Information Systems

Drone Deep Reinforcement Learning: A Review

Ahmad Taher Azar et al.

Summary: Unmanned Aerial Vehicles (UAVs) are increasingly used in various applications, requiring a high level of autonomy for accomplishing planned missions without human intervention. Artificial intelligence algorithms like deep reinforcement learning (DRL) are designed for UAVs' guidance, navigation, and control, but further research efforts are needed to address challenges in deployment in real-life scenarios.

ELECTRONICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

5G Embraces Satellites for 6G Ubiquitous IoT: Basic Models for Integrated Satellite Terrestrial Networks

Xinran Fang et al.

Summary: Current terrestrial communication networks mainly cover urban areas, while satellites have limitations in terms of latency and data rate. To overcome these issues, researchers have extensively studied the integration of terrestrial and satellite components for seamless broadband coverage. However, establishing an efficient hybrid satellite-terrestrial network still faces challenges due to the significant differences between satellite and terrestrial communications.

IEEE INTERNET OF THINGS JOURNAL (2021)

添加到收藏夹

Article Computer Science, Information Systems

Integrating Edge Computing into Low Earth Orbit Satellite Networks: Architecture and Prototype

Chengcheng Li et al.

Summary: Integrating edge computing into Low Earth Orbit satellite networks can enhance the performance of satellite IoT networks and support delay-sensitive and resource-intensive wide-area IoT applications.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications