Current congestion control algorithms (CCAs) are inefficient in wireless networks due to the lack of distinction of congestion and wireless packet losses. In this work, we propose a simple yet effective learning-based wireless loss diagnosis (WiLD) solution for enhancing wireless congestion control. WiLD uses a neural network (NN) to accurately distinguish between wireless packet loss and congestion packet loss. To seamlessly cooperate with rule-based CCAs and make real-time decisions, we further implement WiLD in Linux kernel to avoid the frequent kernel-space communication. Specifically, we use a lightweight NN for inference and propose an integer quantization for WiLD deployment in various Linux versions. Real-world experiments and simulations demonstrate that WiLD can accurately differentiate the wireless and congestion packet loss with negligible CPU overhead (around 1% of WiLD vs. around 100% of learning-based algorithms such as Vivace and Aurora) and fast inference time (45% less compared to TensorFlow Lite). When combined with Cubic, WiLD-Cubic can achieve around 792%, 536%, 412%, 231%, 218%, 108%, 85% and 291% throughput improvement compared with BBRv2, Cubic, Westwood, Copa, Copa+, Vivace, Aurora and Indigo in the real network environment.

The widespread integration of the Internet of Things with sensors like depth-of-field cameras, LiDAR scanners, and eye-tracking infrared sensors, in head-mounted devices, has ushered in a new era of immersive digital experiences. Full-scene volumetric video (VV), a key innovation in this integration, provides a deeply immersive experience by capturing the richness and detail of the 3D world. However, its massive data volume presents significant streaming challenges. While 3D tile-based viewport approaches have been proposed, they struggle to full-scene VV given the small video buffer limitation, high tile segmentation overhead, and lack of full-scene consideration. In this work, inspired by the advancements of implicit neural radiance field (NeRF), we present \({\mathsf{V}^{2}\mathsf{NeRF}}\) , a novel full-scene VV streaming system featured by layered representation. It harmonizes the NeRF with explicit point clouds to represent the static background and dynamic foreground, thereby avoiding large data transfers and achieving photorealistic content representation. To tackle the issues of intensive computation requirements and multiscale adaptation scheduling within \({\mathsf{V}^{2}\mathsf{NeRF}}\) system, we propose a lightweight non-visible background removal method and a two-stage decoupled architecture. In addition, an efficient buffer-aware simulated annealing algorithm is developed, alongside the utilization of a perceptually learned metric, to enhance user experience. We further discuss the concerns about practical development and deployment. Extensive prototype evaluations demonstrate \({\mathsf{V}^{2}\mathsf{NeRF}}\) ’s superior streaming and viewing performance on a wide variety of networks, viewing motions, and scenes. For instance, compared to state-of-the-art approaches, it achieves a 24% increment in perceptual quality, an 83% reduction in rebuffering time, and a 54% enhancement in user experience on average.

Emerging low-latency video (LLV) services, such as cloud gaming, video conferencing, and virtual reality, demand ultra-low latency for smooth interaction. However, existing methods often overlook the misalignment between frame-level perception and packet-level scheduling in ubiquitous Wi-Fi networks, causing high tail latency and degraded user experience. To this end, we propose Flick, a frame-perceptive packet scheduling framework at Wi-Fi access points (APs). It leverages the periodic per-frame transmission behavior and the LLV traffic distribution characteristics to infer the end-to-end frame latency at APs. Flick consists of three components: a Frame Boundary Identifier that detects video frame boundaries using only packet size, an End-to-End Frame Latency Estimator that estimates the end-to-end latency without sender or receiver timestamps, and a Fast-Send, Slow-Recovery Scheduler that dynamically adjusts scheduling priority based on inferred latency. We implement Flick on a commercial Wi-Fi AP. Testbed results show that Flick reduces P99 latency and stall rate by 57% and 81%, respectively, while preserving 95% throughput and maintaining high fairness.

Deploying artificial intelligence (AI) models on the programmable data plane is a key direction toward realizing intelligent data planes. However, this vision faces significant challenges: existing approaches often incur excessive consumption of scarce switch hardware resources or introduce packet recirculation, leading to performance bottlenecks. To address these issues, we propose SwitchLGN, a novel Deep Differentiable Logic Gate Network (DDLGN) architecture deployable on programmable switches. The core of SwitchLGN lies in its hardware-aligned design, which decomposes the model into multiple independent sub-layers and maps each to distinct pipeline processing units. This design enables the entire inference process to be executed solely with the switch's native bit-level logic operations, thereby eliminating the challenges of cross-cluster computation and complex arithmetic in the data plane. In addition, we develop a compilation toolchain to support the automated mapping of SwitchLGN models to P4 code. Experimental evaluations show that SwitchLGN achieves accuracies of 99.42% for network anomaly detection and 95.59% for flow size classification, while reducing SRAM usage to below 3% and making TCAM consumption negligible. Notably, it delivers line-rate inference without packet recirculation, achieving a per-packet latency of only 283 ns.

The LLM serving systems are increasingly growing in popularity, as they provide various capabilities ranging from realtime translation to AI-driven chatbots. Recently, significant effort has been made to optimize server-side metrics such as token generation throughput, while the optimization of token streaming is simply overlooked, resulting in excessive network traffic and poor network utilization. In this paper, we introduce user regions to relieve the network issues, since users from the same region (e.g., universities and business zones) are likely to share similar behaviors to access LLM serving systems (e.g., they are active in a period of time). In this context, we propose Libra, a proxy-cloud collaborative serving system, where the cloud generates and bundles the tokens in terms of user regions and region-based proxy extracts and repacks the received token bundle to their corresponding users. At its core, we design an online region-based task scheduling algorithm with a provable performance to optimize user QoE and system overhead over time. Our evaluations show that Libra outperforms the state-of-the-art LLM serving systems (without user regions), such as vLLM, VTC and Andes, by up to$2.1 \times$in the Time-Between-Tokens (TBT) metric and$78.4 \times$in the number of packets. In addition, it achieves a 32.6 % reduction in TBT compared to other alternative algorithms (with user regions).

3D immersive telepresence systems have dramatically transformed the way users communicate, yet existing point cloud and mesh-based approaches require large amounts of data transmission. Although recent 3D facial semantic-driven techniques can be used to reduce the network burden, they face the critical problem of the high computational cost of facial semantic extraction. To solve the problem, we design and implement an innovative bimodal semantic-driven real-time 3D telepresence system which leverages the low-cost audio-driven semantics for facial expression extraction and head movement semantics for 3D interaction. To improve the efficiency and accuracy of semantic information processing, we propose a speech separation module and optimize the data reception strategy. To optimize the quality of video content reconstruction, we employ frame interpolation and super-resolution techniques, and further propose an online resource scheduling algorithm to balance the rendering, interpolation, and super-resolution processes with limited terminal resources. Experimental results demonstrate that our system can achieve 1K rendering resolution and ~46FPS frame rate with ultra-low network bandwidth (375kbps, approximately 0.32% compared to the point cloud-based approach) and low latency (about 78% semantic feature extraction latency compared to the 3D facial semantic-driven approach) in the campus network.

3D Gaussian Splatting (3DGS), as the cutting-edge static three-dimensional (3D) content generation technology, revolutionizes the speed and fidelity of 3D model construction and provides immense potential for various applications, including e-commerce, 3D exhibitions, and virtual tourism. However, our pioneering analysis of firsthand user experiments uncovers a critical challenge: the unique user behavior patterns of static 3D scenarios render existing immersive video streaming solutions inadequate. To be concrete, the frequent switches between active and inactive states impair viewport prediction accuracy, while the fast glance and slow view pattern provides an opportunity for further quality of experience (QoE) improvement. To tackle these problems, this paper introduces innovative designs for static 3D video streaming. Specifically, we devise a viewport prediction and error correction mechanism on the client side to restore the user viewport with a low cost. Furthermore, we design a dynamic frame rate and bitrate control algorithm to improve user QoE under various network conditions. We implement the first 3DGS-enabled immersive static 3D video streaming system based on an edge-rendered architecture, ensuring efficient rendering and encoding on the edge server while providing broad accessibility for various client-side devices through a web browser. Extensive testing under real-world network conditions and with various kinds of devices demonstrates that the proposed approach exhibits robust and rapid adaptability to fluctuating network conditions, improving user QoE by over 20%, reducing interactive latency by 89%, and minimizing the stall duration by 26% compared to existing low-latency streaming solutions.

Networked 360$^\circ$video has become increasingly popular. Despite the immersive experience for users, its sheer data volume, even with the latest H.266 coding and viewport adaptation, remains a significant challenge to today's networks. Recent studies have shown that integrating deep learning into video coding can significantly enhance compression efficiency, providing new opportunities for high-quality video streaming. In this work, we conduct a comprehensive analysis of the potential and issues in applying neural codecs to 360$^\circ$video streaming. We accordingly present$\mathsf {NETA}$, a synergistic streaming scheme that merges neural compression with traditional coding techniques, seamlessly implemented within an edge intelligence framework. To address the non-trivial challenges in the short viewport prediction window and time-varying viewing directions, we propose implicit-explicit buffer-based prefetching grounded in content visual saliency and bitrate adaptation with smart model switching around viewports. A novel Lyapunov-guided deep reinforcement learning algorithm is developed to maximize user experience and ensure long-term system stability. We further discuss the concerns towards practical development and deployment and have built a working prototype that verifies$\mathsf {NETA}$’s excellent performance. For instance, it achieves a 27% increment in viewing quality, a 90% reduction in rebuffering time, and a 64% decrease in quality variation on average, compared to state-of-the-art approaches.

Latency is one of the most significant issues in cloud gaming, among which tail latency, mainly attributed to dynamic network environments (i.e., transmission) and limited device computing capacity (e.g., decoding), has attracted increasing attention. To mitigate the tail latency, different from existing researches considering resource adaptation such as bitrate adaptation, we propose TailClip, whose novel idea is to enable video frame generation at the client if the tail latency is about to happen. TailClip consists of two innovative components: a Deep Reinforcement Learning (DRL) driven tail latency trigger that jointly decides a series of subsequent frame generation regarding multidimensional features of historical tail latency; a lightweight frame generation model derived by adaptive pruning in terms of device computing capacity at runtime. Extensive evaluations indicate the superior performance of TailClip. For example, it can remove the high-latency frames (i.e., over 100 ms) by 77% with an acceptable video quality (i.e., 0.45 dB reduction on average).

Immersive full-scene volumetric video (VV) showcases the richness and detail of the 3D world, yet poses significant streaming challenges given its massive data volume. Existing 3D tile-based viewport approaches struggle to effectively adapt to full-scene VV owing to their small video buffer limitation, high tile segmentation overhead, and lack of full-scene consideration.

Apart from the promising potential, federated learning (FL) faces challenges, such as high communication costs and client heterogeneity. Although numerous works have been proposed to address these issues, they lack a holistic perspective to balance all requirements. Moreover, these solutions have not fully utilized the underlying computation capability and network resources, resulting in suboptimal tradeoffs between communication efficiency and inference accuracy. To overcome these challenges, we propose FDL: a federated distillation (FD) learning framework that combines FD and FL to fully utilize computation and network resources. We theoretically prove the convergence bound of the proposed FDL framework. Furthermore, to minimize the training time while maintaining inference accuracy, we design HAD: a heterogeneity-aware FL/FD selection algorithm that determines the total communication rounds and selects the set of FL and FD nodes in each communication round. The optimality of HAD is also theoretically proved. The FDL framework and HAD algorithm together minimize the training time while satisfying the inference accuracy in a heterogeneous and dynamic environment. Extensive experiments on various learning algorithms and data sets show that the proposed FDL-HAD solution can obtain the optimal selection decision in overwhelmingly less selection time compared with the Gurobi solver and can reduce the overall training time by at least 44.8% compared with FL solutions with the same inference accuracy.

Ultra-High-Definition (UHD) videos have been getting increasing attention. However, existing video streaming solutions fail to deliver them due to the extremely high bandwidth requirement. The emerging cloud native 5G networks have opened up the possibility of enhancing UHD video quality by leveraging in-network video streaming. Unfortunately, the restricted storage and bandwidth of in-network servers could become the main bottleneck. To this end, we present${\sf EMS}$, a novel UHD video streaming framework, by integratingErasure-coded storage withMulti-sourceStreaming. We respectively introduce a deadline-aware and a latency-sensitive metric to indicate the service quality of video servers and advocate a federated learning paradigm for the adaptive service quality update, including a reinforcement learning based multi-server selection (i.e., user local training) and a global service quality aggregation. To facilitate user local training without sacrificing streaming Quality-of-Experience (QoE), we cast the multi-server selection associated with the restriction on the average number of selected servers per video chunk into two kinds of Multi-Armed Bandit (MAB) models in terms of the proposed service quality metrics. We design lightweight Upper Confidence Bound (UCB) based algorithms with a theoretical performance guarantee. We implement a prototype of${\sf EMS}$, and extensive experiments confirm the superiority of the proposed algorithms.

In this paper, we advocate${\sf NetDPI}$, a novel and efficient Deep Packet Inspection (DPI) solution built-in 5G Data Plane for multi-access edge computing, leveraging the unique forwarding while computing capability of emerging programmable switches. As the cornerstone, we propose${\sf FIVE}$, the firstFiltering-plus-Verification algorithm tailored to programmable switches to achieve efficient multiple pattern matching (i.e., the core of DPI). Briefly, the filtering phase introduces a multi-window parallel shift-or algorithm to rapidly screen out all the “suspicious” packet payloads. Meanwhile, the verification phase innovates a level-based state encoding scheme for the Aho–Corasick (AC) algorithm, which substantially increases the number of supported patterns and consequently figures out more “guilty” payloads. We implement the prototype of${\sf NetDPI}$in both software and hardware programmable switches (i.e., BMv2 and Barefoot Tofino2) and make them publicly available. Extensive evaluations indicate that${\sf NetDPI}$provides orders of magnitude improvement in throughput compared to the typical cloud-delivered DPI solutions, and besides${\sf FIVE}$greatly reduces the memory consumption compared to the alternative in-network exact match algorithms under a variety of system settings including different DPI pattern sets and malware-packet percentages.

In this paper, we advocate CPN-FedSL, a novel and flexible Federated Split Learning (FedSL) framework over Computing Power Network (CPN). We build a dedicated model to capture the basic settings and learning characteristics (e.g., training flow, latency and convergence). Based on this model, we introduce Resource Usage Effectiveness (RUE), a novel performance metric integrating training utility with system cost, and formulate a multivariate scheduling problem that maximizes RUE by comprehensively taking client admission, model partition, server selection, routing and bandwidth allocation into account (i.e., mixed-integer fractional programming). We design Refinery, an efficient approach that first linearizes the fractional objective and non-convex constraints, and then solves the transformed problem via a greedy based rounding algorithm in multiple iterations. Extensive evaluations corroborate that CPN-FedSL is superior to the standard and state-of-the-art learning frameworks (e.g., FedAvg and SplitFed), and besides Refinery is lightweight and significantly outperforms its variants and de facto heuristic methods under a variety of settings.

Decentralized federated learning across edge networks can leverage blockchain with consensus mechanisms for training information exchange among participants over costly and distrustful wide-area networks. However, it is non-trivial to optimally operate the blockchain to support decentralized federated learning due to the complex cost structure of blockchain operations, the balance between blockchain overhead and model convergence, and the dynamics and uncertainties of edge network environments. To overcome these challenges, we formulate a non-linear time-varying integer program that jointly places blockchain nodes and determines the number of training iterations to minimize the long-term blockchain computation and communication cost. We then design an online polynomial-time approximation algorithm that decomposes the problem and solves the subproblems alternately on the fly using only estimated inputs. We rigorously prove the sublinear regret of our approach. We further implement our approach with a prototype system, and conduct extensive trace-driven experiments to validate the superiority of our approach over other alternatives.

360° videos generally require a large amount of bandwidth between video servers and users, which puts much burden on the current CDN-based single-source video streaming solutions. The emerging cloud native 5G networks can bridge the distance between video servers and users by leveraging in-network single-source video streaming to enhance 360° video quality. Unfortunately, the restricted bandwidth of in-network servers becomes the main bottleneck. Although tile-based video streaming is promising to reduce video transmission size while keeping user QoE, it highly depends on the accuracy of user FoV prediction, which existing prediction methods cannot guarantee. Recently, some researchers advocate the idea of “super FoV” (i.e., an extended range of predicted FoV) to cope with the inaccurate FoV prediction, which however could lower the effect of tile-based video streaming. Alternatively, we present Muster, a multi-source streaming for tile-based 360° videos within cloud native 5G networks. We detail the system components, provide a comprehensive model, formulate joint server selection and tile requesting problems, and correspondingly propose efficient online algorithms with a performance guarantee. Small-scale testbed and large-scale simulation based evaluation confirm the superiority of the proposed algorithms.

Mobile edge computing is a promising framework for mobile virtual reality (VR) game. Although there are several existing studies on the edge assisted mobile VR game system, they lack the consideration of provisioning services with satisfactory QoE to a large number of users. In this paper, we consider the problem of providing QoE-oriented edge assisted mobile VR game as a service to multiple users, with a comprehensive QoE concern of both visual and delay aspects. Due to the unique features of mobile VR game, the problem is formulated into a Mixed Integer Quadratically Constrained Quadratic Programming (MIQCQP) problem. We show that the problem is NP-hard with object placement decision and rendering level selection decision quadratically coupling together. To solve this problem, we propose the Alternating Directions Method of Multipliers (ADMM) algorithm which can iteratively decouple the quadratic terms and reform the problem into the efficiently solvable MIQCQP-1 (i.e., MIQCQP with one constraint) problem. Trace driven simulation shows that our algorithm fits the edge assisted mobile VR game scenario well with fast computation time (at least 4 orders of magnitude less computation time compared to Gurobi solver) and good performance (at least 18% of user visual QoE improvement compared to other mobile VR scheme).

360° video streaming requires ultra-high bandwidth to provide an excellent immersive experience. Traditional viewport-aware streaming methods are theoretically effective but unreliable in practice due to the adverse effects of time-varying available bandwidth on the small playback buffer. To this end, we ponder the complementarity between the large buffer-based approach and the viewport-aware strategy for 360°video streaming. In this work, we present Sophon, a buffer-based and neural-enhanced streaming framework, which exploits the double buffer design, super-resolution technique, and viewport-aware strategy to improve user experience. Furthermore, we propose two well-suited ideas: visual saliency-aware prefetch and super-resolution model selection scheme to address the challenges of insufficient computing resources and dynamic user preferences. Correspondingly, we respectively introduce the prefetch and model selection metric, and develop a lightweight buffer occupancy-based prefetch algorithm and a deep reinforcement learning method to trade off bandwidth consumption, computing resource utilization, and content quality enhancement. We implement a prototype of Sophon and extensive evaluations corroborate its superior performance over state-of-the-art works.

Recent advances in deep learning models have pushed Super-Resolution (SR) techniques to an unprecedented altitude, enabling high-quality image rendering with variable scaling size and natural fidelity. To deploy them on resource-constrained mobile devices, however, confronts significant chal-lenges of excessively long latency and poor user experience. To this end, we propose Apie, an edge-assisted adaptive image rendering system that allows low-latency, progressive image enhancement for a smooth user experience. Apie adopts a data parallel strategy across the end device and the edge server, along with a residual learning mechanism to judiciously retrieve information for SR models. Besides, a novel progressive image reconstruction is developed by exploiting content-aware image blocking and incremental image rendering, towards improved quality of user experience. Furthermore, Apie can dynamically adjust the choice of employed SR models with respect to the networking conditions, striking a good balance upon the latency-quality trade-off. Extensive evaluations show that Apie performs 7.33x faster than on-device GPU execution and 1.42x faster compared to the partial offloading method, while achieves 2.84dB higher PSNR compared to the interpolation method using conventional JPEG image compression and 0.74dB higher PSNR compared to the partial offloading method.

To facilitate the emerging applications in 5G networks, mobile network operators will provide many network functions in terms of control and prediction. Recently, they have recognized the power of machine learning (ML) and started to explore its potential to facilitate those network functions. Nevertheless, the current ML models for network functions are often derived in an offline manner, which is inefficient due to the excessive overhead for transmitting a huge volume of dataset to remote ML training clouds and failing to provide the incremental learning capability for the continuous model updating. As an alternative solution, we proposeCocktail, an incremental learning framework within a reference 5G network architecture. To achieve cost efficiency while increasing trained model accuracy, an efficient online data scheduling policy is essential. To this end, we formulate an online data scheduling problem to optimize the framework cost while alleviating the data skew issue caused by the capacity heterogeneity of training workers from the long-term perspective. We exploit the stochastic gradient descent to devise an online asymptotically optimal algorithm, including two optimal policies based on novel graph constructions for skew-aware data collection and data training. Small-scale testbed and large-scale simulations validate the superior performance of our proposed framework.

Cloud gaming has been very popular in recent years, but issues relating to maintaining low interaction delay to guarantee satisfactory user experience are still prevalent. We observe that the server-side processing delay in cloud gaming system could be heavily influenced by how the resources are partitioned among processes. However, finding the optimal partitioning policy that minimizes the response delay faces several critical challenges. First, fine-grained resource partitioning is non-trivial due to the limitations of hardwre-based resource isolation techniques. Second, game wokload is highly dynamic and unpredictable, making the design of efficient resource partitioning policy more challenging. In this article, we propose an online resource partitioning framework for reducing response delay in cloud gaming, which has several promising properties. First, we divide the processes into disjoint groups and partition resources among process groups, which greatly simplifies the resource partitioning problem while ensuring high partitioning effectiveness. Second, to tackle dynamic workload changes, we classify game workloads into several clusters and maintain separate process grouping plan for each cluster. Third, we leverage reinforcement learning to adaptively choose the best actions for minimizing response delay in real time. We evaluate the proposed framework in a real cloud gaming environment using several real games. The experimental results show that our approach can reduce the response delay by 22 to 41 percent compared to a system without resource partitioning, and outperforms other resource partitioning policies significantly.

Image-based three-dimensional (3D) reconstruction utilizes a set of photos to build 3D model and can be widely used in many emerging applications such as augmented reality (AR) and disaster recovery. Most of existing 3D reconstruction methods require a mobile user to walk around the target area and reconstruct objectives with a hand-held camera, which is inefficient and time-consuming. To meet the requirements of delay intensive and resource hungry applications in 5G, we propose an edge computing-based photo crowdsourcing (EC-PCS) framework in this paper. The main objective is to collect a set of representative photos from ubiquitous mobile and Internet of Things (IoT) devices at the network edge for real-time 3D model reconstruction, with network resource and monetary cost considerations. Specifically, we first propose a photo pricing mechanism by jointly considering their freshness, resolution and data size. Then, we design a novel photo selection scheme to dynamically select a set of photos with the required target coverage and the minimum monetary cost. We prove the NP-hardness of such problem, and develop an efficient greedy-based approximation algorithm to obtain a near-optimal solution. Moreover, an optimal network resource allocation scheme is presented, in order to minimize the maximum uploading delay of the selected photos to the edge server. Finally, a 3D reconstruction algorithm and a 3D model caching scheme are performed by the edge server in real time. Extensive experimental results based on real-world datasets demonstrate the superior performance of our EC-PCS system over the existing mechanisms.

360° video services require extremely high bitrate and frame rate videos for a good immersive experience. Traditional solutions for adaptive bitrate streaming are still limited by currently insufficient and fluctuating bandwidth. Besides, viewpoint-aware or tile-based solutions would lead more rebuffering due to the short viewpoint prediction window. In this paper, we present EC-360, a novel video streaming framework to speed up 360° video streaming. Specifically, it creatively integrates tilebased online erasure coding into multi-source content delivery to mitigate “cask effect” or impact of straggler node, which oftentimes leads to failure to improve delivery speed in multisource streaming. We formulate the critical tile-based request scheduling problem in EC-360 based on the Combinatorial Multiarmed Bandit (CMAB) model and develop a low complexity online algorithm. We further theoretically verify the efficiency of the CMAB-based algorithm by deriving its regret upper bound. Extensive experiments based on prototype implementation and real network traces corroborate the efficiency, flexibility, and lightweight of proposed solution. EC-360 achieves superior performance improvement compared to state-of-the-art works in various network scenes and system settings.

The incoming 5G cellular network is stepping into a densification era, where various kinds of base stations are densely deployed to provide fruitful mobile services such as video streaming. In order to improve the performance of these mobile services, the way to optimally allocate cellular resources for the network-wide users is a crucial problem. In this paper, we consider the mobile Ultra-High-Definition (UHD) video streaming service, envision a 5G ultra dense network (UDN) consisting of a series of Video Base Stations (VBSs) dedicated to video streaming services for multiple users, and mainly explore the impact of cellular resource allocation on video streaming. We incorporate two important video streaming states into cellular resource allocation and formulate a streaming-aware and fairness-aware cellular resource allocation problem. To deal with the formulated problem, we provide a novel graph transformation and design an optimal matching algorithm which can be solved in polynomial time. Extensive trace-driven simulations validate the superior performance of the proposed algorithm under different user mobility patterns and network scales.

Ultra-High-Definition (UHD) videos have absorbed great attention in recent years. However, as they are of significant size, streaming them require an extremely high bandwidth to achieve a good quality of experience, which poses a great challenge on the current cellular networks. Realizing the great potentials of coordinated multi-point joint transmission (JT-CoMP) in 5G Ultra Dense Network, we propose a novel Tuner framework for the UHD video streaming service. In this framework, we strive to design an efficient algorithm for VBS sleeping and VBS grouping to maximize the data rates of overall video users while reducing the overhead of cellular networks. To this end, we provide a comprehensive framework model and formulate a single-timescale VBS sleeping & grouping problem. We design a novel master-slave based algorithm to solve the formulated mixed-integer programming problem optimally with low complexity. In addition, we extend it to facilitate the more practical setting, i.e., two-timescale VBS sleeping & grouping. Extensive simulations validate the superior performance of our framework in various system settings.

360° or panoramic video applications have seen booming development and absorbed great attention in recent years. However, as they are of significant size and usually watched from a close distance, they require an extremely higher bandwidth and frame rate for a good immersible experience, which poses a great challenge on mobile networks. Realizing the great potentials of tile-based transcoding, viewport adaptive streaming, and edge caching, we propose Allies, a tile-based joint transcoding, delivery, and caching framework for 360° video services in edge cloud networks. Meanwhile, an innovative idea about 360° video caching way is proposed and applied to improve the cache utilization of edge clouds. In this framework, we formulate the joint optimization problem as an integer nonlinear program and propose a greedy suboptimal algorithm with polynomial running time to minimize video service costs. Finally, extensive simulations with real user's head movement traces and corresponding 360° video datasets corroborate the efficiency, flexibility, and lightweight of our proposed algorithm; for instance, it achieves over 25% performance improvement compared to state-of-the-art works in various system settings.

360° UHD videos have absorbed great attention in recent years. However, as they are of significant size and usually watched from a close range, they require extremely high bandwidth for a good immersive experience, which poses a great challenge on the current single-source adaptive streaming strategies. Realizing the great potentials of tile-based video streaming and pervasive edge services, we advocate a tile-based multi-source adaptive streaming strategy for 360° UHD videos over edge networks. In order to reap its benefits, we consider a comprehensive model which captures the key components of tile-based multi-source adaptive streaming. Then we formulate a joint bitrate selection and request scheduling problem, aiming at maximizing the system utility (i.e., user QoE minus service overhead) while satisfying the service integrity and latency constraints. To solve the formulated non-linear integer programming problem efficiently, we decouple the control variables and resort to matroid theory to design an optimal master-slave algorithm. In addition, we improve our proposed algorithm with a deep learning-based bitrate selection algorithm, which can achieve a rationalization result in a short running time. Extensive datadriven simulations validate the superior performance of our proposed algorithm.

Deep Neural Networks (DNNs) have been extensively applied in a variety of tasks, including image classification, object detection, etc. However, DNNs are computationally expensive, making on-device inference impractical due to limited hardware capabilities and high energy consumption. This paper first incorporates downside risk into characteristics of per-request processing latency for DNN serving systems. Then, considering applications' diverse preferences of latency and accuracy, we introduce a scheme for assigning applications to different DNN models in an edge site, in order to maximize QoS of all applications while reducing the risk of having large processing latency and to meet requirements of minimum accuracy at the same time. Empirical results show that our approach improves system performance and takes an acceptable amount of time for computation.

With the proliferation of Internet of Things (IoT), zillions of bytes of data are generated at the network edge, incurring an urgent need to push the frontiers of artificial intelligence (AI) to network edge so as to fully unleash the potential of the IoT big data. To materialize such a vision which is known as edge intelligence, federated learning is emerging as a promising solution to enable edge nodes to collaboratively learn a shared model in a privacy-preserving and communication-efficient manner, by keeping the data at the edge nodes. While pilot efforts on federated learning have mostly focused on reducing the communication overhead, the computation efficiency of those resource-constrained edge nodes has been largely overlooked. To bridge this gap, in this article, we investigate how to coordinate the edge and the cloud to optimize the system-wide cost efficiency of federated learning. Leveraging the Lyapunov optimization theory, we design and analyze a cost-efficient optimization framework CEFL to make online yet near-optimal control decisions on admission control, load balancing, data scheduling, and accuracy tuning for the dynamically arrived training data samples, reducing both computation and communication cost. In particular, our control framework CEFL can be flexibly extended to incorporate various design choices and practical requirements of federated learning, such as exploiting the cheaper cloud resource for model training with better cost efficiency yet still facilitating on-demand privacy preservation. Via both rigorous theoretical analysis and extensive trace-driven evaluations, we verify the cost efficiency of our proposed CEFL framework.

Internet-of-Things (IoT) big data streaming applications, such as video surveillance and automatic driving, tend to use mobile-edge computing (MEC) infrastructure to enhance their performance and augment their functionalities. Although extensive previous studies have worked on offloading requests to MEC servers, none of them has comprehensively and thoroughly considered the important features of IoT data streaming applications (i.e., component dependency and dynamic arrival) and the infrastructure provisioning (i.e., capacity constraint and colocation interference). In this article, we consider the offloading problem for dynamically arrived IoT data streaming requests on MEC servers in real time. We model it as a delay-sensitive multiuser multiresource online offloading problem respecting component dependency and capacity constraint. The problem is NP-hard with offloading decisions coupling together. To solve it, we decouple the problem into component placement problem and request scheduling problem and propose a two-stage DPGPD algorithm with polynomial time complexity. We show the first stage dynamic programming (DP) algorithm is the optimal solution and the second-stage greedy primal-dual (GPD) algorithm is asymptotic optimal. The simulation results show that our solution is effective yet efficient compared to benchmark solutions. (DP provides the optimal placement layout with 12× less decision time of Gurobi; and GPD provides the asymptotic optimal scheduling with 5× less average waiting time compared to least work left (LWL) in heavy workload.) We implement a dedicated prototype and exploit several representative big data streaming applications to evaluate it. Lab-scale experiment shows that our solution can provide over 3× less total completion time compared to local execution.

In this paper, we consider MEC in NGFI-based C-RAN, a novel and practical MEC framework to facilitate the emerging mobile applications such as AR/VR and video surveillance. However, it is challenging to implement it in a cost-efficient manner (i.e., optimized operational expenditures and service performance), due to the coupled resource provision, service deployment and workload distribution. To solve this joint resource scheduling problem, we resort to rounding and decomposition to devise Matryoshka, a novel approximation algorithm with polynomial running time. Extensive data-driven simulations corroborate that Matryoshka achieves superior performance (e.g., 43% and 52% performance gain compared with two state-of-the-art works, CSPP and Octopus) and scales well to support a variety of system settings.

Cloud gaming has been increasing in popularity recently, but issues relating to maintaining low interaction delay for users to guarantee satisfactory gaming experience is still prevalent. Interaction delays caused by server-side processing are heavily influenced by how the processes partition the resources. However, finding the optimal partitioning policy that minimizes the response delay is complicated by several critical challenges. In this paper, we propose Themis, a system that enables efficient and adaptive online resource partitioning for reducing response delay in cloud gaming. Briefly, Themis employs machine learning technology to build a performance model which is able to capture the complex relationships between resource partition and system performance. With this model, Themis divides the processes into disjoint groups and partitions resources among process groups, which greatly simplifies the resource partition problem while ensuring high partitioning effectiveness. To tackle dynamic workload changes, Themis leverages reinforcement learning to learn how different partitioning actions affect system performance in an online manner, and adaptively choose the best actions for minimizing response delay in real time. We evaluate Themis in a real cloud gaming environment using several real games. The experimental results show that Themis can reduce the response delay by 17% to 36% compared to a system without resource partitioning, and outperforms other resource partitioning policies significantly. To the best of our knowledge, this is the first work to optimize response delay in cloud gaming through resource partitioning.

In this paper, we propose Chimera, a novel hybrid edge computing framework, integrated with the emerging edge cloud radio access network, to augment network-wide vehicle resources for future large-scale vehicular crowdsensing applications, by leveraging a multitude of cooperative vehicles and the virtual machine (VM) pool in the edge cloud via the control of the application manager deployed in the edge cloud. We present a comprehensive framework model and formulate a novel multivehicle and multitask offloading problem, aiming at minimizing the energy consumption of network-wide recruited vehicles serving heterogeneous crowdsensing applications, and meanwhile reconciling both application deadline and vehicle incentive. We invoke Lyapunov optimization framework to design TaskSche, an online task scheduling algorithm, which only utilizes the current system information. As the core components of the algorithm, we propose a task workload assignment policy based on graph transformation and a knapsack-based VM pool resource allocation policy. Rigorous theoretical analyses and extensive trace-driven simulations indicate that our framework achieves superior performance (e.g., 20%-68% energy saving without overstepping application deadlines for network-wide vehicles compared with vehicle local processing) and scales well for a large number of vehicles and applications.

Operating distributed cloudlets at optimal cost is nontrivial when facing not only the dynamic and unpredictable resource prices and user requests, but also the low efficiency of today's immature cloudlet infrastructures. We propose to control cloudlet networks at multiple granularities: fine-grained control of servers inside cloudlets and coarse-grained control of cloudlets themselves. We model this problem as a mixed-integer nonlinear program with the switching cost over time. To solve this problem online, we firstly linearize, "regularize", and decouple it into a series of one-shot subproblems that we solve at each corresponding time slot, and afterwards we design an iterative, dependent rounding framework using our proposed randomized pairwise rounding algorithm to convert the fractional control decisions into the integral ones at each time slot. Via rigorous theoretical analysis, we exhibit our approach's performance guarantee in terms of the competitive ratio and the multiplicative integrality gap towards the offline optimal integral decisions. Extensive evaluations with real-world data confirm the empirical superiority of our approach over the single granularity server control and the state-of-the-art algorithms.

In this paper, we propose MIU, a novel mobile edge computing framework for IoT applications in ultra dense networks, via the control of the macro base station. We present a comprehensive framework model, and formulate a joint task offloading, user association and small base station sleeping problem, aiming at minimizing the energy consumptions of network-wide IoT devices and total SBSs while respecting a series of practical constraints. We design an efficient algorithm by invoking dual-decomposition and subgradient method to solve the formulated mixed-integer quadratic programming problem. Extensive simulation results show that our proposed algorithm achieves better performance in energy consumption than several benchmark schemes.

In this paper, we advocate edge caching in cloud radio access networks (C-RAN) to facilitate the ever-increasing mobile multimedia services. In our framework, central offices will cooperatively allocate cloud resources to cache popular contents and satisfy user requests for those contents, so as to minimize the system costs in terms of storage, VM reconfiguration, content access latency, and content migration. However, this joint resource allocation, content placement and request routing, is nontrivial, since it needs to be continuously adjusted to accommodate system dynamics, such as user movement and content slashdot effect, while taking into account the time-correlated adjustment costs for VM reconfiguration and content migration. To this end, we build a comprehensive model to capture the key components of edge caching in C-RAN and formulate a joint optimization problem, aiming at minimizing the system costs over time and meanwhile satisfying the time-varying user requests and respecting various practical constraints (e.g., storage and bandwidth). Then, we propose a novel online approximation algorithm by resorting to the regularization, rounding, and decomposition technique, which can be proved to have a parameterized competitive ratio with a polynomial running time. Extensive trace-driven simulations corroborate the efficiency, flexibility, and lightweight of our proposed online algorithm; for instance, it achieves an empirical competitive ratio around 2 - 4 and gains over 30% improvement compared with many state-of-the-art algorithms in various system settings.

Recent years have witnessed the proliferation of mobile crowdsourcing that brings a new opportunity to leverage human intelligence and movement behaviors to wider application areas. In parallel with the development of online centralized platforms, we look into the realization of self-organized mobile crowdsourcing drawing on opportunistic networks, and propose the Crowd Foraging framework, in which a mobile task requester can proactively recruit a massive crowd of opportunistic encountered mobile workers in real time for quick and high-quality results. We present a comprehensive framework model that fully integrates human behavior factors for modeling task profile, worker arrival, and work ability, and then introduce a service quality concept to indicate the expected service gain that a requester can enjoy when she recruits an arrival worker by jointly considering the work ability of workers as well as timeliness and reward of tasks. Furthermore, we formulate a sequential worker recruitment problem as an online multiple stopping problem to maximize the expected sum of service quality, and accordingly derive an optimal worker recruitment policy through the dynamic programming principle, which exhibits a nice threshold-based structure. We provide data-driven case studies to validate the assumptions used in the policy design, and conduct extensive trace-driven numerical evaluations, which demonstrate that our policy can achieve superior performance (e.g., improve more than 30% performance over classic policies). Besides, our Android prototype shows that the Crowd Foraging framework is cost-efficient, such as requiring less than 7 s and 6 J in terms of time and energy consumption for the optimal threshold calculation in our policy in most cases.

In this paper, we advocate Crowdlet, a novel self-organized mobile crowdsourcing paradigm, in which a mobile task requester can proactively exploit a massive crowd of encountered mobile workers at real-time for quick and high-quality results. We present a comprehensive system model of Crowdlet that defines task, worker arrival and worker ability models. Further, we introduce a service quality concept to indicate the expected service gain that a requester can enjoy when he recruits an encountered worker, by jointly taking into account worker ability, real-timeness and task reward. Based on the models, we formulate an online worker recruitment problem to maximize the expected sum of service quality. We derive an optimal worker recruitment policy through the dynamic programming principle, and show that it exhibits a nice threshold based structure. We conduct extensive performance evaluation based on real traces, and numerical results demonstrate that our policy can achieve superior performance and improve more than 30% performance gain over classic policies. Besides, our Android prototype shows that Crowdlet is cost-efficient, requiring less than 7 seconds and 6 Joule in terms of time and energy cost for policy computation in most cases.

In this paper, we propose device-to-device (D2D) Fogging, a novel mobile task offloading framework based on network-assisted D2D collaboration, where mobile users can dynamically and beneficially share the computation and communication resources among each other via the control assistance by the network operators. The purpose of D2D Fogging is to achieve energy efficient task executions for network wide users. To this end, we propose an optimization problem formulation that aims at minimizing the time-average energy consumption for task executions of all users, meanwhile taking into account the incentive constraints of preventing the over-exploiting and free-riding behaviors which harm user's motivation for collaboration. To overcome the challenge that future system information such as user resource availability is difficult to predict, we develop an online task offloading algorithm, which leverages Lyapunov optimization methods and utilizes the current system information only. As the critical building block, we devise corresponding efficient task scheduling policies in terms of three kinds of system settings in a time frame. Extensive simulation results demonstrate that the proposed online algorithm not only achieves superior performance (e.g., it reduces approximately 30% ~ 40% energy consumption compared with user local execution), but also adapts to various situations in terms of task type, user amount, and task frequency.

Many mobile applications such as games and social applications are emerging for mobile devices. These powerful applications consume more and more running time and energy. So they are badly confined by mobile device with limited resource. Since cloud infrastructure has great potential to benefit task execution, this paper presents SmartVirtCloud (SmartVC). A system can offload methods in applications to achieve better performance in indoor environment. SmartVC decides at runtime whether and when the methods in application should be executed remotely. And two types of cloud service models, namely load-balancing and application-isolation, are constructed for concurrent requests. The empirical results show that, by using SmartVC, the CPU-intensive calculation application consumes two orders of magnitude less energy on average; the processing speed of latency-sensitive image translation application gets doubled; the performance of network-intensive picture download application is improved with the increase of picture amount. In addition, the proposed two cloud models support concurrent requests from smartphones very well.

By splitting up an underutilized physical host into several virtualized domains, Virtualization can make the optimal use of resources and reduce the energy consumption. By delving into the types of I/O applications, adjusting amount of resource, and combining different applications in one or more domains, several insights are observed in this paper: using a few exclusive physical CPU driver domain can improve the efficiency of forwarding, which makes over 17% performance improvement for I/O applications; in addition, the domain providing mixed services can achieve 70% performance gain, when compared with others that provide single service; last but not least, avoiding running too many network-provider domains simultaneously can relieve the inter-domain interference. These observations not only help to bring performance improvement to cloud consumers but also service stability to cloud providers.