Deep Learning Methods for Space Situational Awareness in Mega-Constellations Satellite-Based Internet of Things Networks (original) (raw)

Deep Reinforcement Learning-Based Long Short-Term Memory for Satellite IoT Channel Allocation

Intelligent Automation & Soft Computing

In recent years, the demand for smart wireless communication technology has increased tremendously, and it urges to extend internet services globally with high reliability, less cost and minimal delay. In this connection, low earth orbit (LEO) satellites have played prominent role by reducing the terrestrial infrastructure facilities and providing global coverage all over the earth with the help of satellite internet of things (SIoT). LEO satellites provide wide coverage area to dynamically accessing network with limited resources. Presently, most resource allocation schemes are designed only for geostationary earth orbit (GEO) satellites. For LEO satellites, resource allocation is challenging due to limited availability of resources. Moreover, due to uneven distribution of users on the ground, the satellite remains unaware of the users in each beam and therefore cannot adapt to changing state of users among the beams. In this paper, long short-term memory (LSTM) neural network has been implemented for efficient allocation of channels with the help of deep reinforcement learning (DRL) model. We name this model as DRL-LSTM scheme. Depending on the pool of resources available to the satellite, a channel allocation method based on the user density in each beam is designed. To make the satellite aware of the number of users in each beam, previous information related to the user density is provided to LSTM. It stores the information and allocates channels depending upon the requirement. Extensive simulations have been carried out which have shown that the DRL-LSTM scheme performs better as compared to the traditional and recently proposed schemes.

SmartSat Constellation - A Deep Reinforcement Learning Approach for Decentralized Coordination

2021

With rapid advancements in satellite technology, the amount of low earth orbit satellites has grown significantly which are primarily deployed for weather monitoring, earth observation or military purposes. Due to this reason, there has been an increased interest in enhancing the level of autonomy and cognition, onboard satellites to achieve optimal data collection. Optimal data is said to be collected when the satellites in a small sat constellation work together to collect information. This means that even if one of the satellites has missed out on some important information, the others can still collect them. A satellite constellation can be considered as a multi-agent reinforcement learning system. Having these agents coordinate with one another, can reduce the amount of time required to perform a task. The state-of-the-art satellite constellations follow a centralized coordination mechanism in which one primary satellite controls the rest of the satellites. This process is computationally more expensive and requires substantial communication between the satellites. It has a single point of failure and communication might be affected if the primary satellite fails. On the other hand, decentralized coordination allows agents to control their behavior themselves without the command of a supervised master. In this case, there is less inter-satellite communication which reduces the requirement for specialized onboard computational hardware. The proposal constitutes leveraging the Multi-Agent Deep Deterministic Policy Gradient [2] (MADDPG) algorithm to train the agents (satellites) to achieve optimal data collection. There are multiple use cases for the proposed solution such as illegal maritime activity tracking, natural disaster detection and assessing building damage after a natural disaster. The proposed solution focuses on tracking of ships in an extensively simulated environment for which a custom ship environment was created by leveraging OpenAI Gym [12]. By providing on-board autonomy, we aim to reduce frequent Earth Station (ES) communication significantly and enhance data collection capability.

Artificial intelligence for satellite communication: A review

Intelligent and Converged Networks, 2021

Satellite communication offers the prospect of service continuity over uncovered and under-covered areas, service ubiquity, and service scalability. However, several challenges must first be addressed to realize these benefits, as the resource management, network control, network security, spectrum management, and energy usage of satellite networks are more challenging than that of terrestrial networks. Meanwhile, artificial intelligence (AI), including machine learning, deep learning, and reinforcement learning, has been steadily growing as a research field and has shown successful results in diverse applications, including wireless communication. In particular, the application of AI to a wide variety of satellite communication aspects has demonstrated excellent potential, including beam-hopping, anti-jamming, network traffic forecasting, channel modeling, telemetry mining, ionospheric scintillation detecting, interference managing, remote sensing, behavior modeling, space-air-ground integrating, and energy managing. This work thus provides a general overview of AI, its diverse sub-fields, and its state-of-the-art algorithms. Several challenges facing diverse aspects of satellite communication systems are then discussed, and their proposed and potential AI-based solutions are presented. Finally, an outlook of field is drawn, and future steps are suggested.

Deep learning approach for interruption attacks detection in LEO satellite networks

arXiv (Cornell University), 2022

The developments of satellite communication in network systems require strong and effective security plans. Attacks such as denial of service (DoS) can be detected through the use of machine learning techniques, especially under normal operational conditions. This work aims to provide an interruption detection strategy for Low Earth Orbit (LEO) satellite networks using deep learning algorithms. Both the training, and the testing of the proposed models are carried out with our own communication datasets, created by utilizing a satellite traffic (benign and malicious) that was generated using satellite networks simulation platforms, Omnet++ and Inet. We test different deep learning algorithms including Multi Layer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Gated Recurrent Units (GRU), and Long Short-term Memory (LSTM). Followed by a full analysis and investigation of detection rate in both binary classification, and multi-classes classification that includes different interruption categories such as Distributed DoS (DDoS), Network Jamming, and meteorological disturbances. Simulation results for both classification types surpassed 99.33 % in terms of detection rate in scenarios of full network surveillance. However, in more realistic scenarios, the best-recorded performance was 96.12 % for the detection of binary traffic and 94.35 % for the detection of multi-class traffic with a false positive rate of 3.72 %, using a hybrid model that combines MLP and GRU. This Deep Learning approach efficiency calls for the necessity of using machine learning methods to improve security and to give more awareness to search for solutions that facilitate data collection in LEO satellite networks.

Deep Learning in IoT systems: A Review

The expansion of the internet, along with its interconnection of devices has made it possible to increase the world's interconnectedness in these days, with the growth in internet connectivity capabilities and quality, a lot of items are interconnected, which means they communicate with each other using new and powerful techniques. Innovative sensor systems are spreading their consumers are strongly connected to the internet. The growth of linked sensors and systems has an incremental impact on the quantity of data. Regardless of its purpose, it is accumulating whole data. The Internet of Things (IoT) has a practical use for industries such as obtaining field data, tracking it and keeping them, all connected. To imitate the human intelligence level, the machine or software is made smarter by using advanced deep learning. In the paper, several diverse types of IoT technologies will be referenced, including intelligent cities, smart health care, mobility networks, and educational systems, among others. In addition, a range of novel deep learning algorithms that were implemented to simplify the intelligent usage of the machines without involving human control has been reviewed and good results of each algorithm in different categories are demonstrated as a table of comparison. This paper gives an overview of the applications that need to combine deep learning to serve IoT applications in an efficient and automated manner. IJSB Literature review

Game Theoretic Training Enabled Deep Learning Solutions for Rapid Discovery of Satellite Behaviors

Satellite Systems - Design, Modeling, Simulation and Analysis [Working Title]

The chapter presents a game theoretic training model enabling a deep learning solution for rapid discovery of satellite behaviors from collected sensor data. The solution has two parts, namely, Part 1 and Part 2. Part 1 is a PE game model that enables data augmentation method, and Part 2 uses convolutional neural networks (CNNs) for satellite behavior classification. The sensor data are propagated with the various maneuver strategies from the proposed space game models. Under the PE game theoretic framework, various satellite behaviors are simulated to generate synthetic datasets with labels for the training to detect space object behaviors. To evaluate the performance of the proposed PE model, a CNN model is designed and implemented for satellite behavior classification. Python 3 and TensorFlow are used in this implementation. The simulation results show that the trained machine learning model can efficiently and correctly classify the satellite behaviors up to 99.8%.