In some application scenarios, strong spatio-temporal correlations exist between remote sensing data streams. For instance, during earthquake relief efforts, users in nearby locations may simultaneously request remote sensing data from an area of interest within the same time period. This leads to large data volumes transmitted in a limited spatio-temporal range, causing network traffic imbalance and reduced transmission efficiency. To address this issue, this paper proposes the Aggregated Transmission Strategy for Remote Sensing Data based on Spatio-Temporal Association (AFRST). According to the spatio-temporal attributes of remote sensing data and the location of users, AFRST utilizes the mapping relationship between naming and demand in Named Data Networking(NDN) and generates a demand association set when the demand between users in the same area reaches the association threshold, and the data in the overlapping area in the set is transmitted only once. We also uniformly assign transmission paths to the association set to improve the data transmission efficiency. Furthermore, AFRST takes into account the network state and user demand, constructing a Transmission-Load Balancing Control Model (TLBCM) based on the network utility maximization framework. This model maximizes the data transmission rate and balances the network load under constraints such as link capacity and other factors in each time slot, optimizing network service performance. The performance of AFRST is evaluated using ndnSIM, and the experimental results demonstrate the effectiveness of AFRST in terms of transmission latency, throughput, and number of completions. Compared to DCT and DPCCP, the average completion time per demand is increased by 29.9% and 18.1%, the overall transmission rate is increased by 43.5% and 22.8%, the overall average increase in the number of completions is about 42.4% and 22.9%, and the throughput is about 16.1% and 15.7% higher.

Satellite remote sensing cooperation is essential for ensuring efficient data transmission in real-time applications. Network traffic prediction plays a crucial role in optimizing data transmission strategies, managing congestion, and reducing network latency. However, current research work on network traffic prediction frequently fails to fully exploit the complex spatial-temporal dependencies inherent in satellite network traffic. To address this limitation and improve the accuracy of long-term network traffic prediction, we propose an Efficient Spatiotemporal Prediction Transformer (ESPformer) for dynamic data transmission in cooperative satellite remote sensing. The proposed scheme not only considers propagation delays but also captures the temporal and spatial relationships among the network traffic. In particular, we design a spatial-temporal multi-head attention mechanism within an encoder-decoder transformer to capture the dynamic spatial dependencies and predict the network topology and its parameters, including traffic flow and bandwidth. By leveraging historical traffic data and the network traffic conditions, the model estimates expected queuing delays. Finally, based on the volume of traffic predicted and the changes in network conditions, we dynamically adjust the transmission strategies to maintain an efficient relaying mechanism. Therefore, our model enables an adaptive transmission strategy and offers an optimal delay reduction in real-time satellite data transmission. Extensive experiments conducted on four well-known traffic datasets demonstrate that the ESPformer significantly outperforms state-of-the-art baselines across all key performance metrics.

With the development of in-orbit processing technology of remote sensing satellites, the intelligent processing units carried on the satellites realize the real-time acquisition and intelligent processing of remote sensing images, thus satisfying users’ individual needs and enhancing the response speed of tasks. However, a large amount of observation data cannot be transmitted back to the ground in time due to the limitation of the transmission capability of remote sensing satellites to the ground and the visible time window between satellites and ground stations in the process of satellite-terrestrial transmission. To solve this problem, a community division-based content distribution strategy (CDCD) is proposed. Firstly, the time slot model is designed to capture the time-varying topological information of the satellite network. Also, a content naming method that fits the characteristics of remote sensing data is presented. Then, a caching scheme based on community division is proposed by analyzing the regional characteristics of user requests. Taking advantage of the community structure characteristics of satellite networks, a novel cache node selection algorithm is designed to meet the user’s demand for fast access to target files. Meanwhile, a cached content prioritization model is constructed to further optimize the utilization of caching resources. Finally, the community structure-based routing algorithm (CSR) is proposed to effectively reduce the redundant transmission during content access through the mutual collaboration of intra-community and inter-community routing schemes. Simulation experiments show that the CDCD strategy effectively exploits the limited caching resources in the satellite network compared with other strategies, which promotes the stable and efficient distribution of remote sensing data.

Information-centric satellite networks play a crucial role in remote sensing applications, particularly in the transmission of remote sensing images. However, the occurrence of burst traffic poses significant challenges in meeting the increased bandwidth demands. Traditional content delivery networks are ill-equipped to handle such bursts due to their pre-deployed content. In this paper, we propose an optimal replication strategy for mitigating burst traffic in information-centric satellite networks, specifically focusing on the transmission of remote sensing images. Our strategy involves selecting the most optimal replication delivery satellite node when multiple users subscribe to the same remote sensing content within a short time, effectively reducing network transmission data and preventing throughput degradation caused by burst traffic expansion. We formulate the content delivery process as a multi-objective optimization problem and apply Markov decision processes to determine the optimal value for burst traffic reduction. To address these challenges, we leverage federated reinforcement learning techniques. Additionally, we use bloom filters with subdivision and data identification methods to enable rapid retrieval and encoding of remote sensing images. Through software-based simulations using a low Earth orbit satellite constellation, we validate the effectiveness of our proposed strategy, achieving a significant 17% reduction in the average delivery delay. This paper offers valuable insights into efficient content delivery in satellite networks, specifically targeting the transmission of remote sensing images, and presents a promising approach to mitigate burst traffic challenges in information-centric environments.

The low earth orbit (LEO) remote sensing satellite has a short communication time with the earth station (ES), and a large amount of remote sensing data cannot be transmitted back to the ES in time using the LEO-ES link during the communication period. Using relay satellites can indirectly increase the amount of data transmitted back from LEO. In this paper, we combine LEO- ES link and relay satellite offloading to study the problem of maximizing the amount of data transmitted back from LEO remote sensing satellites. Most of the existing methods do not consider the effect of topology change on policy. In this paper, we consider a three-layer satellite network architecture of geostationary earth orbit (GEO), LEO remote sensing satellite , and ES. We studied the problem of maximizing the amount of LEO transmitted back data under dynamic topology between layers, and proposed a transmission strategy based on a combination of LEO-ES link and GEO offload under dynamic topology. First, in order to reduce the number of link interruptions in each time slot, a Non-Uniform Time Slot Division Method (NUTSDM) based on visible relationships between layers is proposed based on discrete-time points, which helps to accurately determine the number and identity of LEOs competing under each time slot. Second, the relationship among GEOs, LEOs, and network administrators is modeled as a Stackelberg game model, and a Two-way Bargaining Game Scheme under Dynamic Topology (TWBGS-DT) is proposed to maximize the amount of data transmitted back from space. Compared with the existing methods, the experimental results confirm the effectiveness of the proposed scheme in terms of algorithm convergence speed, terms of pricing, GEO cache space allocation, and increase the data volume of LEO transmissions back by 11.5% and 8.2 times relative to the ISL-Aided strategy and GAA-FARR strategy, respectively.

With the reduction in manufacturing and launch costs of low Earth orbit satellites and the advantages of large coverage and high data transmission rates, satellites have become an important part of data transmission in air-ground networks. However, due to the factors such as geographical location and people’s living habits, the differences in user’ demand for multimedia data will result in unbalanced network traffic, which may lead to network congestion and affect data transmission. In addition, in traditional satellite network transmission, the convergence of network information acquisition is slow and global network information cannot be collected in a fine-grained manner, which is not conducive to calculating optimal routes. The service quality requirements cannot be satisfied when multiple service requests are made. Based on the above, in this paper artificial intelligence technology is applied to the satellite network, and a software-defined network is used to obtain the global network information, perceive network traffic, develop comprehensive decisions online through reinforcement learning, and update the optimal routing strategy in real time. Simulation results show that the proposed reinforcement learning algorithm has good convergence performance and strong generalizability. Compared with traditional routing, the throughput is 8% higher, and the proposed method has load balancing characteristics.