SDSongshi Dou

Songshi Dou

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Songshi Dou has a total of 41 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Beyond Space Routers: Revisiting the Role of LEO Satellite Constellations in Future Global Internet Architecture

    by Songshi Dou, Shengyu Zhang, Xianhao Chen, Zehua Guo, Tony Q. S. Quek, Kwan L. Yeung

    Low Earth Orbit (LEO) satellite constellations are redefining global Internet infrastructure with transformative potential. This article first reviews the evolution of LEO satellite networks from early bent-pipe models to sophisticated space routers with inter-satellite links, which enable data to hop across satellites in space. Beyond providing wide-area coverage and low-latency connectivity, modern LEO satellite constellations are taking on multi-faceted functions traditionally associated with terrestrial networks. Specifically, we discuss emerging paradigms in which satellites perform in-network content caching to bring data closer to users. We also highlight the use of LEO satellite networks for enhancing Internet resilience during disasters and outages, as well as initiatives for cross-constellation interoperability that envision an integrated “Internet of satellites” spanning the globe. We aim to provide a synthesis of LEO satellites’ expanding capabilities (beyond space routers) and an analysis of the architectural shift towards a space-based multi-role infrastructure. Finally, several future research directions and opportunities are outlined to highlight the broader significance of LEO satellite constellations in the design of future Internet architectures and their potential to extend services beyond traditional terrestrial networks.


  • Quest: Quality of Service-Centric Resilient Routing for Software-Defined Wide Area Networks

    by Songshi Dou, Zehua Guo

    Emerging network applications pose diverse Quality of Service (QoS) demands, prompting the adoption of Software-Defined Networking (SDN) in Wide Area Networks (WANs), known as Software-Defined Wide Area Networks (SD-WANs). SDN introduces path programmability, allowing controllers to dynamically adjust flow forwarding paths at their switches to accommodate varying traffic conditions and differentiated QoS requirements. However, controller failures can lead to the offline state of controlled switches, causing flows traversing these switches to lose path programmability and degrade QoS. Existing solutions typically focus on indirect metrics such as path programmability or coarse-grained load balancing, which often neglect the individual QoS demands of each flow and the control plane performance. To fill this research gap, we propose Quest, a QoS-aware resilient routing framework designed to preserve QoS in both data and control planes during controller failures. Compared to existing solutions, Quest explicitly addresses the critical limitations by jointly optimizing fine-grained QoS-aware flow routing and control plane latency. We formulate an optimization problem that jointly ensures QoS-aware flow routing and minimizes control plane delays. Due to the complexity of this problem, we utilize a linearization approach and further develop a heuristic QoS-centric resilient routing algorithm. Extensive simulations using real-world topologies and traffic traces demon-strate that Quest substantially improves network performance, achieving a 1.71% increase in average throughput ratio, a 46.65% reduction in average latency, and a 62.74% decrease in average control latency compared to baseline approaches.


  • Maintaining Predictable QoS for Online Service Provisioning in Non-Terrestrial Networks via Safe Transfer Learning

    by Shengyu Zhang, Songshi Dou, Zhenglong Li, Kwan L. Yeung, Tony Q. S. Quek

    Emerging mega-constellations with numerous Low Earth Orbit (LEO) satellites actively provide pervasive Internet services worldwide, which are usually considered crucial components of Non-Terrestrial Networks (NTNs). However, the high mobility and limited coverage of LEO satellites introduce frequent handovers, causing network interruptions and degrading Quality of Service (QoS). While many efforts have been made to alleviate the impact of handovers on service provisioning from NTNs, they usually assume channel conditions are pre-determined and remain unchanged as satellites move, which is different from real situations and thus may experience significant performance degradation compared to theoretical analysis. In this paper, we propose Oracle to promise QoS-aware service provisioning in NTNs under dynamic channel conditions. Specifically, we mathematically formulate a channel model to characterize dynamic channel conditions in NTNs and develop a QoS maximization problem considering handover frequency and transmission capacity. To accommodate the dynamic nature of NTNs, we introduce a Model Predictive Control (MPC)-based controller to predict future network status and generate control strategies correspondingly, and leverage Digital Twin (DT) for real-time network status consideration. For higher efficiency, we further employ Generative Artificial Intelligence (GAI) with a safe transfer learning-based framework to enhance model adaptivity to environmental uncertainties and ensure feasible control decisions in real-world NTNs. Extensive simulation results under the real-world constellation demonstrate that Oracle can enhance up to $3\times $ QoS during online service provisioning.


  • Matchmaker: Maintaining QoS-Aware and Predictable Load Balancing Performance for LEO Mega-Constellations

    by Songshi Dou, Jinxian Wu, Shengyu Zhang, Xianhao Chen, Tony Q. S. Quek, Kwan L. Yeung

    With millions of users introducing significant traffic loads, maintaining effective load balancing in Low Earth Orbit (LEO) mega-constellations is challenging due to satellites’ limited processing capabilities. While existing studies primarily focus on constellations fully equipped with inter-satellite links, this paper addresses the less-explored yet critical issue of achieving QoS-aware load balancing in existing bent pipe architectures. We identify user-satellite assignment as a key determinant of satellite load and propose MATCHMAKER, a strategy that balances satellite load by optimizing user-satellite assignment while simultaneously minimizing disruptive handovers. Specifically, we formulate the QoS-aware User-Satellite Assignment problem to jointly minimize maximum satellite utilization and user-satellite handovers. Given the NP-hardness of this problem, we propose a heuristic algorithm with a performance guarantee. Evaluation results demonstrate that MATCHMAKER improves load balancing performance by up to 130.22% and reduces handovers by up to 46.88% compared to state-of-the-art methods.


  • SpaceCache+: Towards Pervasive Content Delivery via Low-Earth Orbit Mega-Constellations

    by Songshi Dou, Shengyu Zhang, Zhenglong Li, Jinxian Wu, Xianhao Chen, Kwan L. Yeung

    Emerging Low-Earth Orbit (LEO) mega-constellations face challenges such as limited bandwidth and highly variable user demand, which can degrade network performance and lead to inefficient satellite resource utilization. One promising solution is to enable Content Delivery Networks (CDNs) within LEO satellites by deploying cache-equipped satellites. However, many existing approaches rely on inter-satellite links, which are not widely used in practice and are typically activated only when terrestrial ground station coverage is insufficient. Furthermore, the dynamic coverage patterns of satellites and diverse regional content preferences add to the complexity of efficient CDN deployment in space. To address these challenges, we propose SpaceCache+, a satellite-based CDN framework. We introduce a new metric, user benefit, that jointly captures user coverage and latency reduction to assess the effectiveness of cache satellite deployment. Recognizing that deployment typically occurs incrementally, we formulate the User Benefit-centric Cache Satellite Deployment problem and design an efficient heuristic solution. To enhance content placement, we also propose a cache replacement policy based on zero-shot meta-learning, which adapts to both regional content popularity and satellite mobility. We evaluate the performance of SpaceCache+ using real-world constellation settings with CDN traces. Compared with benchmark strategies, SpaceCache+ improves user benefit and cache hit ratio by up to 66.29% and 77.12%, respectively.


  • Toward Improved Performance of Inner Convex Approximation for Suboptimal Nonlinear MPC

    by Jinxian Wu, Li Dai, Songshi Dou, Yunshan Deng, Yuanqing Xia

    Inner convex approximation is a compelling method that enables the real-time implementation of suboptimal nonlinear model predictive controls (MPCs). However, it suffers from a slow convergence rate, which prevents suboptimal MPC from achieving better performance within a specific sample time. To address this issue, we first reformulate the conventional inner convex approximation procedure as a root-finding problem for a nonlinear equation. Then, under mild assumptions, a comprehensive functional analysis is performed on the derived nonlinear equation, focusing on its continuity, differentiability, and the invertibility of the Jacobian matrix. Building on this analysis, we propose an improved algorithm that applies Broyden’s method to accelerate the root-finding procedure of this derived nonlinear equation, thereby enhancing the convergence rate of the conventional inner convex approximation method. We also provide a detailed analysis of the proposed algorithm’s convergence properties and computational complexity, showing that it achieves a locally superlinear convergence rate without devoting much additional computational effort. Simulation experiments are performed in an obstacle avoidance scenario, and the results are compared to the conventional inner convex approximation method to assess the effectiveness and advantages of the proposed approach.


  • Unleashing the Potential of LEO Constellations in Building Resilient and Low-Latency Control Plane for SD-WANs

    by Songshi Dou, Zehua Guo, Kwan L. Yeung

    Delivering seamless network services (e.g., video streaming, AR/VR, and cloud gaming) in Wide Area Networks (WANs) relies on flexible traffic management, which is facilitated by Software-Defined Wide Area Networks (SD-WANs), or SDN in WANs. In SD-WANs, control and data traffic usually share the same links for cost savings, a practice known as in-band control. The SDN controller can periodically send control messages to switches via control channels for routing policy updates to maintain satisfactory network performance. However, when a link failure occurs, control channels become disconnected. Since the controller can no longer communicate with the switches, the desired flexible traffic management cannot be promised. Although backup paths can be preconfigured to reconnect some control channels, high control latency may be introduced due to the meandering routes. Fortunately, commercial Low-Earth Orbit (LEO) mega-constellations, which provide pervasive and low-latency Internet services, present a promising solution to this control resiliency issue. Inspired by the rapid deployment of these LEO constellations, we propose a novel control plane design called SpaceHelper to leverage the LEO satellite network for improving SD-WANs’ control resiliency. SpaceHelper smartly integrates the LEO satellite network with terrestrial SD-WAN to reconnect control channels during link failure, which is formulated as an optimization problem to minimize overall control latency. A heuristic algorithm is proposed to solve the problem efficiently and guarantee prompt control channel reconnection. Performance evaluations are conducted using the Starlink constellation and real-world WAN topologies. Compared to the state-of-the-art in-band solution, we show that SpaceHelper can not only provide 100% resiliency, but also significantly reduce average control latency by up to 72.6% and 70.2% under GÉANT and Abilene topologies, respectively.