The deployment of commercial-off-the-shelf (COTS) GPUs in space has emerged as a promising approach for supporting inorbit deep neural network (DNN) inference. However, unlike terrestrial environments, understanding the impact of space radiation on COTS GPU-enabled DNNs is critical. This is challenging because existing methods, such as real-world radiation testing and software emulation, fail to link radiation-induced memory errors to runtime DNN behaviors. In this paper, we propose REMU, a memory-aware Radiation EMUlator to fill this gap. REMU introduces a dual addressing mechanism across virtual, physical, and DRAM memory spaces, enabling precise mapping and efficient injection of radiation-induced errors from DRAM to runtime DNN inference. Extensive evaluations across 10 well-known DNN models and 2 typical in-orbit computing tasks demonstrate the effectiveness of REMU, providing valuable insights for understanding the resilience of runtime DNN inferences on space radiations.

Low-earth-orbit (LEO) satellite mega-constellations enable universal Internet access from space. To ensure mission safety, LEO satellites conduct orbital maneuvers to prevent physical collisions with other space objects. These maneuvers challenge the performance of predictive TCP congestion control, which mitigates unnecessary throughput reductions caused by handover-induced data loss/delay. Our empirical study shows that these maneuvers can downgrade predictive TCP congestion control’s throughput by 17.63% due to the maneuvering satellite’s cumulative position deviations. The root cause is that end users rely on coarse-grained Two-Line Elements (TLEs) to predict satellites’ orbits, thus suffering from inaccurate predictions. Although these negative impacts seem unsolvable, fine-grained ephemeris can help end users enhance the accuracy of predicting handover events and effectively manage the durations of freezing congestion windows to a more affordable level. We then propose MATCP, a Maneuver-Aware TCP congestion control scheme to enhance the performance of TCP transport in maneuverable satellite networks. Compared to existing predictive congestion control, MATCP leverages ephemeris to achieve more accurate predictions of satellite handovers, and freezes the congestion window at predicted handover timing with a shorter freezing duration, thus improving the throughput of predictive congestion control. Our evaluations, driven by Starlink’s space situational awareness (SSA) dataset, validate that MATCP can safely prevent 94.21% of maneuver-induced throughput reductions in predictive TCP congestion control and increase throughput by 3.83× compared to TCP CUBIC and 20.07% compared to existing predictive satellite congestion control (SATCP).

As a promising paradigm, Satellite Edge Computing (SEC) enables new opportunities for facilitating intelligent processing onboard, crucial for the timely execution of mission-critical tasks. These tasks typically involve high data capture rates and rely on compute-intensive Deep Neural Network (DNN) models. However, a single satellite struggles to handle these tasks promptly due to its limited computational capabilities. Thus, effective collaboration within the SEC network is urgently needed to adapt to diverse capture rates, optimize resource utilization, and ensure real-time responses. Motivated by the fact that partitioning a DNN model can accelerate task inference and make better use of idle resources by simultaneous sub-task execution and reduced transmitted data, we propose HiO2, a hierarchical task offloading framework that maximizes system throughput by effective collaboration among satellites and ground stations to process the partitioned sub-tasks. This highlights the challenge of designing effective task partitioning and offloading strategies in dynamic, resource-constrained networks. HiO2 addresses this challenge with two key methods. First, it adopts a distributed swarm-level task offloading strategy that assigns tasks to swarms based on their optimal quantity. Second, HiO2 introduces a distributed node-level partitioning and offloading scheme, which dynamically identifies efficient cut-points according to workload and network dynamics, then offloads sub-tasks by collaboration among nodes in each swarm. Extensive data-driven evaluations demonstrate that, compared to the state-of-the-art baselines, HiO2 improves throughput to 1.19×, reduces average task completion time to 69.7%, and consistently meets task deadlines.

Direct-to-cell satellites enable global network services for our regular phones/IoTs via 4G, 5G, and beyond. To enforce highly available, trustworthy, and roaming policy-compliant network services, they heavily rely on user geolocation and timing information from external global navigation satellite systems (GNSS) to assist with their radio access, authentication, and authorization. Our analysis and field tests reveal that, this cross-technology over-reliance propagates satellite navigation's defects to direct-to-cell satellite networks, leading to diverse issues such as intermittent connectivity, over/under-billing, unauthorized services, and service denials even when direct-to-cell satellites are accessible. Our solution, SN2, adopts the "fate-sharing" principle to reuse direct-to-cell satellites themselves for self-navigating networks. By exploiting the flexible tradeoffs between satellite network availability and navigation accuracy, it enables "good enough" built-in navigation for highly available and functionally correct network services at a negligible cost of hardware or communication resources. Our evaluations with commodity satellite phones and 3GPP NTN protocol stacks demonstrate SN2's 4.4–23.5× network availability boost and 1.9–12.3× access latency reduction over legacy solutions.

The recent renaissance of low Earth orbit (LEO) satellite networks expands the boundaries of global Internet access, but also introduces substantial new challenges for existing end-to-end congestion control algorithms (CCAs). The rapid and continuous movement of LEO satellites leads to infrastructure-level dynamics, resulting in frequent, LEO-dynamics-induced changes in link capacity, delay, and packet loss rate, which can further mislead the rate control in existing CCAs and cause self-limited performance.

Do we really need 10,000s of Low Earth Orbit (LEO) satellites to meet huge global Internet demands? While proven feasible and valuable, such LEO mega-constellation networks have raised concerns about their prohibitive capital expenditures, market monopoly, and unsustainable use of space. Instead, our analysis reveals that most of their satellites can be wasted due to their mismatch with physically uneven demands. We thus propose TinyLEO, a software-defined solution to shrink LEO network size for enormous global demands via dynamic spatiotemporal supply-demand matching. TinyLEO sparsifies satellite supplies on demand by combining diverse yet sparse orbits, hides complexities of this sparse LEO network via orbital model predictive control, and shifts the responsibility for handling these complexities to its geographic segment anycast for higher network usability, lower resource wastes, faster failovers, simpler satellites, and more flexible network orchestration. We have prototyped TinyLEO as a community toolkit for open research. Our evaluation using this toolkit shows that TinyLEO can compress the existing LEO mega-constellation network size by 2.0–7.9×, cut control plane costs by 1–3 orders of magnitude, and maintain the same demands and comparable data plane performance.

Leveraging direct-to-cell (DTC) satellites in low-earth orbits (LEO) to directly provide communication services for terrestrial cellphones is gaining popularity in recent years. However, the unique characteristics of the wireless medium in space-ground communication, combined with the dynamic behavior of LEO satellites, raise a new privacy leakage risk that an adversary eavesdropping on DTC broadcasts could steal the physical locations of active users. In this paper, we investigate new techniques to analyze the location leakage risks in emerging LEO direct-to-cell satellite networks (DCSN). We present DCATOR1DCATOR indicates the abbreviation of DCSN terminal locator. , a novel location leakage analyzer which continuously monitors DTC signaling messages in broadcast channels, extracts various location clues and combines them with the time-varying satellite trajectories to infer the physical locations of active users. We use DCATOR to analyze the consequences if an adversary is able to continuously monitor and process broadcast DTC signaling to deduce the locations of other users within the same satellite coverage area, in three representative DCSNs: (i) the operational Iridium; (ii) the developing Starlink DTC; and (iii) a DCSN based on the latest 3GPP NTN standards. Our extensive experiments demonstrate the existence of location leakages in real DCSNs, and in the worst case an adversary can precisely track the locations of other users within hundreds of meters. Finally, we propose privacy-enhancing countermeasures for DCSNs.

In this paper, we perform a systematic study to explore a pivotal problem facing the web community: is current distributed web cache ready for future satellite Internet? First, through a worldwide performance measurement based on the RIPE Atlas platform and Starlink, the largest low-earth orbit (LEO) satellite network (LSN) today, we identify that the uneven deployment of current distributed cache servers, inter-ISP meandering routes and the last-mile congestion on LEO links jointly prevent existing terrestrial web cache from providing low-latency web access for users in emerging LSNs. Second, we propose Spache, a novel web caching system which addresses the limitations of existing ground-only cache by exploiting a bold idea: integrating web cache into LEO satellites to achieve ubiquitous and low-latency web services. Specifically, Spache leverages a key feature of LSNs called communication schedule to efficiently prefetch web contents on satellites, and adopts a schedule-driven partitioning strategy to avoid cache pollution involved by LEO mobility. Finally, we implement a prototype of Spache, and evaluate it based on real-world HTTP traces and data-driven LSN simulation. Extensive evaluations demonstrate that as compared to existing distributed caching solutions, Spache can improve cache hit ratio by 19.8% on average, reduce latency by up to 17.7%, and maintains consistently low web browsing latency for global LSN users.

User-perceived latency is important for the quality of experience (QoE) of wide-area real-time communications (RTC). With the rapid development of low Earth orbit (LEO) mega-constellations, this paper explores a futuristic yet important problem facing the RTC community:can we exploit emerging mega-constellations to facilitate low-latency RTC globally?We carry out our quest in three steps. First, through a measurement study associated with a large number of geo-distributed RTC users, we quantitatively expose that themeandering routesin theclient-to-cloudandinter-cloud-sitesegment of existing cloud-based RTC architecture are critical culprits for the high latency issue suffered by wide-area RTC sessions. Second, we proposeSpaceRTC, a satellite-cloud cooperative framework that dynamically selectsrelay serversupon satellites and cloud sites to build an overlay network which enables diverse close-to-optimal paths.SpaceRTCjudiciously allocates RTC flows of different sessions upon the network to facilitate low-latency interactions and adaptively selects bitrates to offer high user-perceived QoE in energy-limited space circumstance. Finally, we implement a testbed based on public constellation information and real-world RTC traces. Extensive experiments demonstrate thatSpaceRTCcan deliver near-optimal interactive latency, with up to 53.3% average latency reduction and 103.6% average bitrate improvement as compared to other state-of-the-art cloud-based solutions.

Low Earth Orbit (LEO) satellite network is undergoing an explosive expansion to enable high-speed Internet for numerous users anywhere on Earth. However, as a cyber-physical network, the LEO network's sustainable expansion is constrained by its harsh, crowded, and imbalanced physical environment. This position paper dives into two physical constraints for the LEO network scalability: the scale-out limit by satellite safety distances in crowded outer space, and the scale-up limit by the mismatch between the uniform LEO network capacity supply and geographically non-uniform global distribution of user demands. Traditional networking research pays less attention to these physical scaling limits, which may imply a call for a cyber-physical co-design to help the LEO network grow in the challenged space environment.

End-to-end congestion control algorithms (CCAs) are expected to perform well in any Internet path, including those paths with low-earth orbit (LEO) satellite links. In this paper, we conduct a performance study on various CCAs in an operational LEO satellite network. We find that existing CCAs struggle to deal with the drastic network variations caused by the mobility of LEO satellites, resulting in poor link utilization or high latency. Further, through an in-depth analysis, we identify the fundamental challenge is that existing end-to-end CCAs detect network congestion based on performance changes observed on the sender, but the unique LEO mobility can involve massive non-congestion performance changes which seriously mislead CCA behaviors. Finally, we explore and discuss possible solutions to mitigate the misleading effects of LEO mobility.

Emerging satellite Internet constellations such as SpaceX's Starlink will deploy thousands of broadband satellites and construct Low-Earth Orbit (LEO) satellite networks (LSNs) in space, significantly expanding the boundaries of today's terrestrial Internet. However, due to the unique global LEO dynamics, satellite routers will inevitably pass through uncontrolled areas, suffering from security threats. It should be important for satellite network operators (SNOs) to enable verifiable riskavoidance routing to identify path anomalies. In this paper, we present STARVERI, a novel network path verification framework tailored for emerging LSNs. STARVERI addresses the limitations of existing crypto-based and delay-based verification approaches and accomplishes efficient and accurate path verification by: (i) adopting a dynamic relay selection mechanism deployed in SNO's operation center to judiciously select verifiable relays for each communication pair over LSNs; and (ii) incorporating a lightweight path verification algorithm to dynamically verify each segment path split by distributed relays. We build an LSN simulator based on real constellation information and the results demonstrate that STARVERI can significantly improve the path verification accuracy and achieve lower router overhead compared with existing approaches.

Recently we have witnessed the active deployment of mega-constellations with hundreds to thousands of low-earth orbit (LEO) satellites, targeting at constructing LEO satellite networks (LSN) to provide ubiquitous Internet services globally. However, while the massive deployment of LEO satellites can improve the network survivability and performance of an LSN, it also involves additional sustainable challenges such as higher deployment cost, risk of satellite conjunction and space debris.In this paper, we investigate an important research problem facing the upcoming satellite Internet: from a network perspective, how many satellites exactly do we need to construct a survivable and performant LSN? To answer this question, we first formulate the survivable and performant LSN design (SPLD) problem, which aims to find the minimum number of needed satellites to construct an LSN that can provide sufficient amount of redundant paths, required link capacity and acceptable latency for traffic carried by the LSN. Second, to efficiently solve the tricky SPLD problem, we propose MegaReduce, a requirement-driven constellation optimization mechanism, which can calculate feasible solutions for SPLD in polynomial time. Finally, we conduct extensive trace-driven simulations to verify MegaReduce’s cost-effectiveness in constructing survivable and performant LSNs on demand, and showcase how MegaReduce can help optimize the incremental deployment and long-term maintenance of future satellite Internet.

Emerging integrated space and terrestrial networks (ISTN) built upon low earth orbit (LEO) satellite constellations aim at providing planet-wide Internet services, not only for residential users, but also for mobile users (e.g., in airplane and cruise scenarios). Efficiently managing global mobility and keeping connections active for mobile users is critical for ISTN operators. However, our quantitative analysis identifies that existing mobility management (MM) schemes suffer from frequent connection interruptions and long latency in ISTN scenarios. The fundamental challenge stems from a unique characteristic of ISTNs: not only users are mobile, but also core network infrastructures (i.e., LEO satellites) are frequently changing their locations in the network.To facilitate seamless and low-latency satellite Internet services, this paper presents SkyCastle, a novel network-based global mobility management mechanism. SkyCastle incorporates two key techniques to address frequent connection interruptions in ISTNs. First, to reduce the interruption time, SkyCastle adopts distributed satellite anchors to track the location changes of mobile nodes, manage handovers and avoid routing convergence. Second, SkyCastle leverages an anchor manager to schedule MM functionalities at satellites to reduce deployment costs while guaranteeing low latency. Extensive evaluations combining real constellation information and mobile user trajectories show that: SkyCastle can improve up to 55.8% uninterrupted time and reduce 47.8% latency as compared to other existing MM solutions.

With the rapid evolution of space-borne capabilities, space edge computing (SEC) is becoming a new computation paradigm for future integrated space and terrestrial networks. Satellite edges adopt advanced on-board hardware, which not only enables new opportunities to perform complex intelligent tasks in orbit, but also involves new challenges due to the additional energy consumption in power-constrained space environment.In this paper, we present Phoenix, an energy-efficient task scheduling framework for emerging SEC networks. Phoenix exploits a key insight that in the SEC network, there always exist a number of sunlit edges which are illuminated during the entire orbital period and have sufficient energy supplement from the sun. Phoenix accomplishes energy-efficient in-orbit computing by judiciously offloading space tasks to "sunlight-sufficient" edges or to the ground. Specifically, Phoenix first formulates the SEC battery energy optimizing (SBEO) problem which aims at minimizing the average battery energy consumption while satisfying various task completion constraints. Then Phoenix incorporates a sunlight-aware scheduling mechanism to solve the SBEO problem and schedule SEC tasks efficiently. Finally, we implement a Phoenix prototype and build an SEC testbed. Extensive data-driven evaluations demonstrate that as compared to other state-of-the-art solutions, Phoenix can effectively reduce up to 54.8% SEC battery energy consumption and prolong battery lifetime to 2.9× while still completing tasks on time.

Low Earth Orbit (LEO) satellite mega-constellations promise ubiquitous network services to "unconnected" users. But their upcoming global routing for Earth will be unstable due to exhaustive topology updates between satellites and Earth, inside an orbital shell, and across heterogeneous orbital shells. In real LEO networks, these multi-dimensional dynamics are interleaved and complicated by chaotic orbital maneuvers and random failures. They are less predictable than most satellite routing proposals expect and threaten these proposals' availability, efficiency, or resiliency at scale.

With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmission limits of satellite-to-ground links. Although existing learned image compression solutions achieve remarkable performance by using a sophisticated encoder to extract fruitful features as compression and using a decoder to reconstruct. It is still hard to directly deploy those complex encoders on current satellites' embedded GPUs with limited computing capability and power supply to compress images in orbit. In this paper, we propose COSMIC, a simple yet effective learned compression solution to transmit satellite images. We first design a lightweight encoder (i.e. reducing FLOPs by 2.5~5X) on satellite to achieve a high image compression ratio to save satellite-to-ground links. Then, for reconstructions on the ground, to deal with the feature extraction ability degradation due to simplifying encoders, we propose a diffusion-based model to compensate image details when decoding. Our insight is that satellite's earth observation photos are not just images but indeed multi-modal data with a nature of Text-to-Image pairing since they are collected with rich sensor data (e.g. coordinates, timestep, etc.) that can be used as the condition for diffusion generation. Extensive experiments show that COSMIC outperforms state-of-the-art baselines on both perceptual and distortion metrics.

The emergent direct-to-cell Low-Earth Orbit (LEO) satellite mega-constellations promise ubiquitous LTE/5G access for our commodity phones and IoTs without terrestrial base stations. While their extreme scale and mobility help tolerate diverse attacks, we show that both new features are exploitable to amplify signaling protocol vulnerabilities inherited from LTE/5G and obfuscate attacks to threaten satellite services. We showcase this with SatOver, a control-plane cross-layer attack that lets a greedy terrestrial operator or a man-in-the-middle attacker block all direct-to-cell satellites in urban areas. SatOver can reuse terrestrial LTE/5G base stations or deploy commodity software-defined radios as false satellites, stealthily hijack victim devices, delay their satellite access, stop them from probing other satellites, and block the entire mega-constellation. Our real-world satellite tests, lab tests with commodity 3GPP NR/IoT-NTN stacks, and operational trace-driven emulation validate SatOver’s viability for attacking COTS and upcoming NTN phones/IoTs. We discuss potential defenses against SatOver’s attack amplification/obfuscation.

The integration of Mobile Edge Computing (MEC) and Low Earth Orbit (LEO) satellite networks holds the potential to offer ubiquitous computing services for ground users and has garnered significant attention recently. While there has been extensive research conducted in the field of Satellite Mobile Edge Computing (SMEC), research on edge server deployment in mega-constellation is overlooked. Edge servers require an appropriate quantification and placement before the implementation of computation offloading. The improper deployment strategy can result in high access latency and imbalance workload. In this paper, we propose a two-stage approach, called cluster-based small-scale server deloyment (CSSD), for small-scale placing and dynamic allocating edge servers that enable low access latency and workload balancing. Specifically, the offline stage is employed to determine the optimal placement of edge servers and the initial offloading mapping from access satellites to service satellites. The online stage, building dynamically adjusts the offloading mapping based on the spatiotemporal positions and workload of the satellites to balance system workload. Evaluation results show that CSSD outperforms other approaches with up to 16.37% and 35.38% enhancements in terms of workload standard deviation and user service rate while maintaining low access latency.

Delay-sensitive Web services are crucial applications in emerging low-earth orbit (LEO) satellite networks (LSNs). However, our real-world measurement study based on SpaceX's Starlink, the most widely used commercial LSN today, reveals that the endless and bursty packet losses over unstable LEO satellite links impose significant challenges on guaranteeing the quality of experience (QoE) of Web applications. We propose SatGuard, a distributed in-orbit loss recovery mechanism that can reduce user-perceived delay by completely concealing packet losses in the unstable and lossy LSN environment from endpoints. Specifically, SatGuard adopts a series of techniques to: (i) correctly migrate on-board packet buffer to support link-local retransmission under LEO dynamics; (ii) efficiently detect packet losses on satellite links; and (iii) ensure packet ordering for endpoints. We implement a SatGuard prototype, and conduct extensive trace-driven evaluations guided by public constellation information and real-world measurements. Our experiments demonstrate that, in comparison with other state-of-the-art approaches, SatGuard can significantly improve Web-based QoE, by reducing: (i) up to 48.3% of page load time for Web browsing; and (ii) up to 57.4% end-to-end communication delay for WebRTC.

Exploiting a constellation of small satellites to realize continuous earth observations (EO) is gaining popularity. Large-volume EO data acquired from space needs to be transferred to the ground. However, existing EO delivery approaches are either: (a) efficiency-limited, suffering from long delivery completion time due to the intermittent ground-space communication, or (b) scalability-limited since they fail to support concurrent delivery for multiple satellites in an EO constellation.To make big data delivery for emerging EO constellations fast and scalable, we propose Falcon, a multi-path EO delivery framework that wisely exploits diverse paths in broadband constellations to collaboratively deliver EO data effectively. In particular, we formulate the constellation-wide EO data multi-path download (CEOMD) problem, which aims at minimizing the delivery completion time of requested data for all EO sources. We prove the hardness of solving CEOMD, and further present a heuristic multipath routing and bandwidth allocation mechanism to tackle the technical challenges caused by time-varying satellite dynamics and flow contention, and solve the CEOMD problem efficiently. Evaluation results based on public orbital data of real EO constellations show that as compared to other state-of-the-art approaches, Falcon can reduce at least 51% delivery completion time for various data requests in large EO constellations.

The emerging satellite internet constellation aims to deploy hundreds of low-orbit satellites to provide high-speed broadband internet services to global ground terminals. However, this poses a significant challenge for large-scale and highly dynamic satellite networking due to the traditional satellite constellations’ uniform structure. This structure is limited by four laser links per low-orbit satellite, using default connections of two intra-orbit links and two inter-orbit links, and is difficult to match with the uneven population distribution and user traffic on the ground, resulting in unnecessary overheads in propagation delay and transmission hops. In recent years, researchers have developed methods for matching structure and traffic distribution that overcome the limitations of traditional connection methods, reducing transmission delay and hops. Despite this progress, these methods still maintain the characteristics of uniform configuration. To address this issue, a new link connection design for large-scale low-orbit satellite network driven by user distribution has been proposed. This mechanism enables the dynamic matching of satellite structure and users, facilitating elastic networking under dynamic topology conditions, improving the overall capacity and utilization of satellite networks. Through simulation, this user-driven link connection design has been verified to reduce the average hop count by at least 41% in many scenarios, demonstrating its effectiveness for a variety of new large-scale low-orbit satellite networks.

Entering the “NewSpace” era, satellite Internet constellation (SIC) is expanding rapidly. However, while operating a large number of broadband satellites in free space enables great opportunities for ubiquitous and low-latency Internet services, it also involves new threats that were previously ignored to the energy-limited satellite systems. In this paper, we investigate the feasibility and impact of a new class of real risk in emerging SICs: energy drain attack. To this end, we play the role of an attacker and propose Starmelt,an energy drain attack mechanism that persistently injects malicious traffic that goes through the victim satellite from various geo-distributed locations, preventing the victim from hibernating and overusing the satellite battery to cut its lifetime. Further, we design a series of techniques to: (i) handle the path ambiguity challenge caused by various access selection and routing schemes to guarantee that the deliberately crafted traffic can precisely pass through the victim; (ii) leverage the tail energy consumption characteristics to reduce the detectability as well as the traffic cost of an attack. Extensive simulations based on real constellation knowledge demonstrate that Starmeltcan substantially increase on-board energy consumption, reducing up to 76% lifetime of the victim satellite under various power models and traffic patterns.

Low-earth-orbit (LEO) satellite mega-constellations, such as SpaceX Starlink, are under rocket-fast deployments and promise broadband Internet to remote areas that terrestrial networks cannot reach. For mission safety and sustainable uses of space, Starlink has adopted a proprietary onboard autonomous driving system for its extremely mobile LEO satellites. This paper demystifies and diagnoses its impacts on the LEO mega-constellation and satellite networks. We design a domain-specific method to characterize key components in Starlink's autonomous driving from various public space situational awareness datasets, including continuous orbit maintenance, collision avoidance, and maneuvers between orbital shells. Our analysis shows that, these operations have mixed impacts on the stability and performance of the entire mega-constellation, inter-satellite links, topology, and upper-layer network functions. To this end, we investigate and empirically assess the potential of networking-autonomous driving co-designs for the upcoming satellite networks.

The communication channels in millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems possess some unique fine-grained angle domain features such as channel gain, azimuth angle of arrival (AAoA), and elevation angle of arrival (EAoA). This paper combines AAoA, EAoA, channel gain as well as phase noise features to propose a novel physical layer authentication scheme for mmWave MIMO communication systems. Based on the limit posterior Bayesian Cramér-Rao bound (LPBCRB) and maximum-likelihood (ML) estimation theories, we first develop an efficient approach for the evaluation of hardware phase noise and mmWave channel features. To depict the authentication performance of the new scheme, we then apply the statistical signal processing and hypothesis testing theories to derive the closed-form expressions for false alarm and detection probabilities under the scheme. Finally, extensive numerical results are provided to validate our theoretical models and to demonstrate the capability of the proposed authentication scheme against impersonation attacks.

Emerging low earth orbit (LEO) satellites and geo-distributed ground station networks can assist pervasive and efficient Internet data delivery on a global scale. However, while promising, the improper integration of ingress satellite selection (ISS) and inter-satellite routing (ISR) can result in significantly high propagation latency and low network utilization. In this paper, we propose AeroPath, a ground-station-driven data delivery architecture that enables high-throughput data transmission while maintaining low latency. Specifically, to accomplish transmission efficiency, geo-distributed ground stations independently schedule flows over ground-satellite links in collaboration with ISR and cooperatively select inter-satellite paths to avoid bandwidth competition between different ground stations. Finally, we evaluate the effectiveness of AeroPath via extensive simulations driven by realistic constellation information. Evaluation results show that AeroPath can outperform other approaches with up to 24.1% and 18.5% improvement in terms of average system throughput and ground station utilization respectively under state-of-the-art constellation patterns.

The emergence of mega-constellations is the most promising satellite network trend in recent years, which brings new security challenges to the network layer and higher layers, such as DDoS, worm, and DNS pollution. Source address validation is one of the effective solutions in terrestrial networks, by filtering the invalid address and resisting the source address spoofing. Because of the time-vary topology in mega-constellations, the source address validation mechanism faces the severe problem of the anchor mobility, which leads to a sharp decline in SAVI (Source Address Validation Improvements) performance and increases the cost to maintain the user status. In this paper, we develop a source address spoofing avoidance mechanism under high movement (SASA) for mega-constellations. Specifically, we propose that the user and the satellite both maintain the user status. After the satellite signed the binding information by the private key, it forms the mapping between the authenticity of the user address and the initial access satellite on the user side. Moreover, when the handover occurs, the user safely transmits the authentication information to the new access satellite through asymmetric encryption to complete rebinding. Simulation results show that SASA can greatly reduce the rebinding cost of mega-constellations by 95.04% in Starlink and 81.84% in Kuiper.

The low-earth-orbit (LEO) satellite networks promise low-latency broadband network services to remote areas. LEO networks require deploying many satellites to serve numerous users in crowded terrestrial areas, thus forming a satellite mega-constellation. It is well known that this practice would lower network utilization, which may be exacerbated with recent LEO satellite mega-constellations. For LEO satellite mega-constellation networks with complex and dynamic structures, multiple functions, and diversified user demands, this paper presents a methodology for systematically analyzing utilization. Our study shows that operational mega-constellations today suffer from < 10% low network utilization. The root cause is twofold. First, today's evenly distributed satellites do not match the unevenly distributed terrestrial users, and the law of satellite movement keeps a satellite above sparsely populated areas most of the time. Second, a uniform LEO mega-constellation cannot simultaneously meet the heterogeneous demands from local satellite access (requiring more satellites to serve the enormous population in hotspots) and global satellite routing (requiring fewer satellites for shorter paths). Based on these findings, we analyze how to improve utilization from angles of constellation structure and network architecture design. We showcase it can increase the utilization with fewer and divergent satellites while retaining comparable performance to state-of-the-art.

Is it worth and feasible to push mobile core network functions to low-earth-orbit (LEO) satellite mega-constellations? While this paradigm is being tested in space and promises new values, it also raises scalability, performance, and security concerns based on our study with datasets from operational satellites and 5G. A major challenge is today's stateful mobile core, which suffers from signaling storms in satellites' extreme mobility, intermittent failures in outer space, and attacks when unavoidably exposed to untrusted foreign locations. To this end, we make a case for a stateless mobile core in space. Our solution, SpaceCore, decouples states from orbital core functions, simplifies location states via geospatial addressing, eliminates unnecessary state migrations in satellite mobility by shifting to geospatial service areas, and localizes state retrievals with device-as-the-repository. Our evaluation with datasets from operational satellites and 5G shows SpaceCore's 17.5× over existing solutions signaling reductions and resiliency to failures/attacks.

In this paper, we study the self-healing problem of unmanned aerial vehicle (UAV) swarm network (USNET) that is required to quickly rebuild the communication connectivity under unpredictable external destructions (UEDs). Firstly, to cope with theone-off UEDs, we propose a graph convolutional neural network (GCN) that can find the recovery topology of the USNET in an on-line manner. Secondly, to cope withgeneral UEDs, we develop a GCN based trajectory planning algorithm that can make UAVs rebuild the communication connectivity during the self-healing process. We also design a meta learning scheme to facilitate the on-line executions of the GCN. Numerical results show that the proposed algorithms can rebuild the communication connectivity of the USNET more quickly than the existing algorithms under both one-off UEDs and general UEDs. The simulation results also show that the meta learning scheme can not only enhance the performance of the GCN but also reduce the time complexity of the on-line executions.

We study a new design objective for "Internet in space" for terrestrial users: To align logical network topology, address, and route in the virtual cyberspace with movements of satellite mega-constellations and earth's rotations in the real physical world. We explain why this is particularly desirable by the recent low-earth-orbit (LEO) mega-constellations, and how it welcomes mobility to streamline the network design for stability, efficiency, and scalability in an unstable space-ground environment. We showcase its feasibility with the common fixed satellite sub-point trajectory in mega-constellations. We describe how it permits stable recursive topology, unifies cyber-physical locations in the address, and naturally embeds the geographical routing into the topological routing.

The booming of satellite mega-constellations to provide Internet access around the Earth is attracting more attention recently. To provide broadband Internet globally, satellites will be responsible to undertake IP address management of ground terminals. However, the movement of the LEO (Low Earth Orbit) satellite will cause difficulties to IP address management, because every LEO satellite can just stay in sight of a ground terminal for several minutes. On one hand, stateful IP address management faces a short lifetime, signal storm, and unstable address space problems. On the other hand, stateless IP address management cannot avoid high overhead in DAD (Duplicate Address Detection). This paper proposes GAMS, Geographical Addressing Management for Satellite, an efficient IP address management mechanism for mega-constellations networks. By embedding both satellites' feature information and geographical location into IPv6 addresses, GAMS enables efficient DAD with assigned address tables ONLY on respective satellite routers. Theoretical proof and simulation results validate that GAMS could effectively provide unique and long-lifetime IPv6 addresses to ground terminals with negligible cost.

The rapid development of high-speed rails (HSRs) has brought great convenience to people's travel. But related scholars found that the network status on the train is very inefficient. In order to solve that, some scholars proposed to use multipath TCP (MPTCP). However, MPTCP suffers when different paths have heterogeneous quality. In HSR scenarios, frequent handover (less than 10 seconds) occurs when devices connect to cellular network base stations. If MPTCP is used, each sub-flow has to go through handover and packets will be heavily garbled. In turn, it occupies a large amount of the receiver's buffer, even up to 100%. The latency of data submission to application will also be higher (10ms or more). It will affect the overall transfer performance. The reason for the above problem is that MPTCP does not react quickly enough to link changes and cannot accurately schedule packets between sub-flows. After consulting the measurement data of relevant scholars, we found that the trains in HSR have some recurring phenomena. For example, base station handover always occurs in the same place for devices in HSR. Based on relevant recurring information, this paper proposes Hysteresis Optimized Multipath TCP Data Scheduling Algorithm (HoMPTCP) in Predictable Networks. Combined with the prediction information formed by using historical trajectories in HSR, HoMPTCP can more accurately schedule packets between sub-flows and control the congestion window of sub-flows. After the experiments of HSR scenario, HoMPTCP can improve throughput performance by 5%-15% while increasing sequential arrival rate by 10%-15%.

With low latency and wide coverage, Low Earth Orbit (LEO) satellite networks can provide network services for places that cannot be reached by the terrestrial network and become a critical supplement to the traditional network, playing an increasingly important role. While the wide coverage and broadcasting enable LEO satellite networks (LSNs) accessible to more devices, this also raises the risk of being attacked by potential adversaries. Previous research on secure routing is either mainly based on the design of encryption-based algorithms or is only suitable for the relative static topology of the traditional terrestrial networks. However, given limited computational resources and the highly dynamic changes of the LEO satellite, encryption-based algorithms can hardly meet the demands of LSNs. Unlike these works, this paper proposes a lightweight risk-avoidance routing algorithm (LRAR). It allows users' data packets to be forwarded by avoiding specified high-risk areas to reduce the risk of user data being attacked. As can be seen in extensive simulation experiments, the LRAR implements results close to the optimal path with little overhead. Also, it enhances security and flexible extensibility.

Due to the simplification of path selection in traditional IP routing schemes and the uneven distribution of traffic, problems such as congestion and low system performance are still unavoidable in satellite networks. Compared with terrestrial networks, satellite networks have much more equal-cost paths between any two points. So, this paper uses path diversity to solve the above problems. Researchers have proposed many traffic engineering algorithms to solve similar problems, but high-dynamics and high-latency of the satellite network make these algorithms ineffective. This paper proposed a Multi-routing-plane based Flow Scheduling Strategy (MFSS), using different routing schemes in different routing planes. It can make full use of path diversity to solve simplification of path selection and solve the high-dynamics problem through cooperation between satellites and the terrestrial networks. The simulation result on the topology of Starlink shows that, in our scenarios, MFSS can increase the system throughput by 60.9% while the delay growth does not exceed 3%.

With the rapid evolution of space communication technologies, satellite networks have entered a booming period. In recent years, Integrated Satellite and Terrestrial Network (ISTN) has been recognized as the trend of future networks. In order to adapt the existing routing technology to the network with high dynamic characteristics, a large number of research have tried to divide the timeslot in the satellite network and regard the network as static in a timeslot. However, The existing methods do not consider the existence of network convergence process in ISTN. With the massive increase in satellite handoff and the consensus of running distributed routing protocol, the network availability drops sharply in the timeslot divided by the existing methods. This paper proposes Handoff Synchronization to reduce the long convergence time. Moreover, STARSLOT is proposed to divide timeslots and improve the ISTN's availability. Extensive simulation show that for the typical ISTN architecture, STARSLOT can improve the network availability by 52.63% as compared to other existing methods. Moreover, STARSLOT is much less affected by the increase in network scale.

This article focuses on the secure routing problem in the decentralized Internet of Things (IoT). We consider a typical decentralized IoT scenario composed of peer legitimate devices, unauthorized devices (eavesdroppers), and selfish helper jamming devices (jammers), and propose a novel incentive jamming-based secure routing scheme. For a pair of source and destination, we first provide theoretical modeling to reveal how the transmission security performance of a given route is related to the jamming power of jammers in the IoT. Then, we design an incentive mechanism with which the source pays some rewards to stimulate the artificial jamming among selfish jammers, and also develop a two-stage Stackelberg game framework to determine the optimal source rewards and jamming power. Finally, with the help of the theoretical modeling as well as the source rewards and jamming power setting results, we formulate a shortest weighted path-finding problem to identify the optimal route for secure data delivery between the source-destination pair, which can be solved by employing the Dijkstra's or Bellman-Ford algorithm. We prove that the proposed routing scheme is individually rational, stable, distributed, and computationally efficient. Simulation and numerical results are provided to demonstrate the performance of our routing scheme.

By exploiting two intrinsic physical (PHY)-layer features in terms of location-specific channel gain and transmitter-specific phase noise, this paper proposes a new PHY-layer authentication scheme for massive multiple-input multiple-output (MIMO) systems. In particular, we apply the linear minimum mean square error technique to estimate the time-varying channel gain and adopt extended Kalman filtering to track the time-varying phase noise. Based on the estimation error covariance matrices of channel gain and phase noise, we then formulate the PHY-layer authentication as a composite hypothesis testing problem. With the help of tools from statistical signal processing, matrix analysis, and composite hypothesis testing, we develop theoretical models to capture the false alarm and detection probability performances of the proposed scheme. Finally, we provide extensive numerical results to validate these theoretical models and to illustrate the efficiency of the proposed authentication scheme.

A trusted network path is a desired property of the Internet. Previous works introduced new protocol headers based on source routing for source authentication and path verification. It is obvious that any extra protocol headers will increase the network burden, and network path privacy deserves attention, especially when we use source routing. The emergence of IPv6 Segment Routing (SRv6) may bring the opportunity to assemble trusted network paths with a lightweight header. In this paper, we propose SR-TPP, a novel mechanism based on SRv6 to support network path verification meanwhile hides both-end and path information. Different from existing works, SR-TPP extends SRv6 function instead of introducing a new protocol header to meet the requirement of path compliance. Path information is sequentially encoded into the segment list in SR-TPP so that path information is partially visible to each intermediate router. The distributed verification of SR-TPP also makes it easier to locate faults. Finally, the security analysis and evaluation show that SR-TPP can assemble private and trusted network paths with acceptable performance.

This article proposes a general and lightweight PHY-layer authentication framework for the Internet of Things (IoT) devices in smart cities, based on tag embedding and tag verification. More specifically, a tag signal carefully designed to be independent of the message signal of a transmitter [i.e., an IoT device (IoTD)] is encrypted and embedded into the signal of the device, and the tag signal is then retrieved at a receiver based on signal detection techniques to verify if it is from the legitimate IoTD or from an illegitimate adversary. With the help of matrix analysis and composite hypothesis testing theories, analytical models are further developed to depict the authentication performance of the proposed authentication framework under various tag signal models. We then provide numerical results to validate these analytical models and to illustrate how authentication performance against the typical impersonation attack varies with system parameters. Finally, we include discussions to demonstrate the effectiveness of the proposed authentication solution in resisting against other various attacks like replay, unauthorized detection, tampering, and man-in-the-middle.

802.11 is a widely-used wireless communication standard today and is still under constant evolution. Two major enhancements of the standard, 802.11n and 802.11ac, boost the performance and quality of service, with the former getting support in nearly all commercial devices today and the latter gaining prevalence. However, there is currently no software-defined radio (SDR) system that is capable to support the whole 802.11ac protocol stack, especially the MAC layer, in real-time, limiting research and testing on these latest innovations. This paper presents GPLM, a Low-MAC architectural design for FPGA-based SDR systems that supports 802.11ac. We identify challenges imposed by new features in 802.11ac MAC layer, and make careful architectural choices to ensure both standard compliance and flexibility. The design and implementation of critical modules and the employment of software hardware co-design are detailed in this paper. Paired up with an existing work on the PHY layer implementation of 802.11ac, the implementation of GPLM is validated from various aspects.

Cognitive radio (CR) technology aims to provide real-time sensing and efficient dynamic spectrum access to improve the efficiency of spectrum resource usage. However, none of the existing SDR platforms is capable of supporting CR applications while maintaining high performance and programmability. In this paper, we propose CR-GRT, an SDR platform designed for cognitive radio applications. CR-GRT supports real-time sensing, analysis, decision-making and dynamic adjustment. It also provides interfaces for extensibility. Based on CR-GRT, we implement a comprehensive sensing strategy using both PHY and MAC information. The evaluation result shows that CR-GRT has advantages in high performance and programmability.

Tick is a new SDR system that provides programmability and ensures low latency at both PHY and MAC. It supports modular design and element-based programming, similar to the Click router framework [23]. It uses an accelerator-rich architecture, where an embedded processor executes control flows and handles various MAC events. User-defined accelerators offload those tasks, which are either computation-intensive or communication-heavy, or require fine-grained timing control, from the processor, and accelerate them in hardware. Tick applies a number of hardware and software co-design techniques to ensure low latency, including multi-clock-domain pipelining, field-based processing pipeline, separation of data and control flows, etc. We have implemented Tick and validated its effectiveness through extensive evaluations as well as two prototypes of 802.11ac SISO/MIMO and 802.11a/g full-duplex.