Tài liệu update hàng ngày

Arcgis sử dụng cho ảnh satellite

Link1 SR for satellite

Link2 SR for satellite

Link 3

Link 4

Link 5

Link 6

Một số ví dụ sử dụng opensand

Link1 opensand

Link2 opensand

Phần nén dữ liệu dựa vào GNN methods (ý tưởng thú vị)

link data compression

Các hướng và keywork có thể tiếp cận

1. AI for Reducing Latency in Satellite Communication:
   • https://g.co/bard/share/17d812024ab1
2. Reinforcement learning for routing in satellite network:
   • https://g.co/bard/share/9ba625337f22
3. AI for securiry in satellite network:
   • https://g.co/bard/share/f48d9cfced7f
4. AI with quantum computing:
   • https://g.co/bard/share/241770bdb9f4
5. Edge computing with satellite network:
   • https://g.co/bard/share/f3ae4208a836
6. Federated learning in satellite network:
   • https://g.co/bard/share/204d84c70757
7. Predict model

GT-LSTM: A spatio-temporal ensemble network for traffic flow prediction

Federated split learning for sequential data in satellite–terrestrial integrated networks

Traffic-Predictive Routing Strategy for Satellite Networks

Code mẫu về GA, PSO và DRL for RA

Code mẫu

Learn the concepts, characteristics and differences

• fog computing
• edge computing
• distribution computing
• federated learning

Certainly! Let’s go through each concept:

1. Fog Computing:
   • Concepts: Fog computing extends cloud computing by bringing computing resources closer to the edge of the network, typically at or near the source of data generation. It aims to reduce latency, bandwidth usage, and dependency on centralized cloud services. Fog computing involves distributing computing resources across various devices and infrastructure within the proximity of data sources.
   • Characteristics:
     • Proximity to edge devices.
     • Low-latency data processing.
     • Distributed computing infrastructure.
     • Improved efficiency for real-time applications.
   • Differences:
     • Unlike cloud computing, which relies on centralized data centers, fog computing pushes computing resources closer to the edge devices.
     • Fog computing addresses the challenges of latency and bandwidth by processing data locally.
     • It complements cloud computing by providing additional processing capabilities at the edge.
2. Edge Computing:
   • Concepts: Edge computing involves processing data closer to the data source, reducing the need to send all data to centralized data centers or cloud. It aims to improve response time, bandwidth usage, and overall system efficiency by distributing computation and storage capabilities.
   • Characteristics:
     • Decentralized processing.
     • Low-latency data processing.
     • Reducing reliance on centralized cloud services.
     • Enhanced performance for IoT (Internet of Things) devices.
   • Differences:
     • Edge computing is a broader concept that includes fog computing as a subset.
     • Edge computing focuses on bringing computation closer to the source of data, often at the network’s edge.
     • It is applicable in various domains, including IoT, manufacturing, healthcare, and more.
3. Distributed Computing:
   • Concepts: Distributed computing involves the use of multiple interconnected computers to solve a complex problem or perform a task. It aims to improve performance, fault tolerance, and scalability by distributing tasks across a network.
   • Characteristics:
     • Parallel processing.
     • Fault tolerance.
     • Scalability.
     • Collaboration among distributed nodes.
   • Differences:
     • Distributed computing is a general concept that can include fog and edge computing.
     • It focuses on the overall approach of distributing tasks across multiple nodes.
     • Applications can be diverse, ranging from scientific simulations to large-scale data processing.
4. Federated Learning:
   • Concepts: Federated learning is a machine learning approach where a model is trained across decentralized devices (edge devices) holding local data samples. Instead of sending raw data to a central server, only model updates (gradients) are transmitted, preserving privacy and reducing the need for massive data transfers.
   • Characteristics:
     • Privacy-preserving.
     • Decentralized training.
     • Collaborative learning without raw data sharing.
     • Iterative model updates.
   • Differences:
     • Federated learning is a specific application within the broader field of machine learning.
     • It focuses on training models collaboratively while keeping data localized.
     • It addresses privacy concerns associated with centralized model training approaches.

In summary, while fog computing and edge computing focus on distributing computing resources for processing data closer to the edge, distributed computing is a general concept involving the use of multiple interconnected computers. Federated learning, on the other hand, is a specific approach in machine learning that leverages decentralized model training to address privacy concerns.

Tài liệu tham khảo

Nên tham khảo các nguồn sau: scholar, fb gr, medium, github

Hết.