Multimodal Large Language Models (MLLMs) are advancing the ability to reason about complex sports scenarios by integrating textual and visual information. To comprehensively evaluate their capabilities, we introduce SPORTU, a benchmark designed to assess MLLMs across multi-level sports reasoning tasks. SPORTU comprises two key components: SPORTU-text, featuring 900 multiple-choice questions with human-annotated explanations for rule comprehension and strategy understanding. This component focuses on testing models' ability to reason about sports solely through question-answering (QA), without requiring visual inputs; SPORTU-video, consisting of 1,701 slow-motion video clips across 7 different sports and 12,048 QA pairs, designed to assess multi-level reasoning, from simple sports recognition to complex tasks like foul detection and rule application. We evaluated four prevalent LLMs mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting on the SPORTU-text part. GPT-4o achieves the highest accuracy of 71\%, but still falls short of human-level performance, highlighting room for improvement in rule comprehension and reasoning. The evaluation for the SPORTU-video part includes 6 proprietary and 8 open-source MLLMs. Experiments show that models fall short on hard tasks that require deep reasoning and rule-based understanding. GPT-4o performs the best with only 57.8\% accuracy on the hard task, showing large room for improvement. We hope that SPORTU will serve as a critical step toward evaluating models' capabilities in sports understanding and reasoning. The dataset is available at [https://github.com/chili-lab/SPORTU](https://github.com/chili-lab/SPORTU).

With the capability of intelligent control and communicating with surrounding vehicles and infrastructures, connected and automated vehicles (CAVs) can drive cooperatively and have more positive effects on traffic efficiency. Cooperative and real-time path planning for CAVs stands as a pivotal solution to mitigate traffic congestion and augment travel efficiency. However, most of the existing path planning schemes predominantly concentrate on minimizing the travel times of vehicles, sidelining the broader issue of alleviating traffic congestion in urban settings. Therefore, in this paper, we propose a novel collaborative vehicle path planning scheme, leveraging the intelligent control and the communicating ability of CAVs. The primary objective is to reduce traffic congestion within the overall transportation system and improve traffic efficiency. Specifically, we focus on a general urban scenario with various types of vehicles, including CAVs, connected vehicles (CVs), and traditional human-driven vehicles (TVs), To enhance traffic efficiency in such a scenario, we design a collaborative path planning scheme to discover the efficient paths for both CAVs as well as CVs. In this scheme, we treat each CAV as an agent and formulate the multiple CAVs' path-planning problem as a Markov game. To solve the above Markov game, we design a multi-agent convolutional attention reinforcement learning (MACA) framework to generate paths with minimal travel time for CAVs. More concretely, the proposed MACA framework incorporates a convolutional neural network (CNN) layer to capture spatial correlation behind traffic conditions. Additionally, a graph attention network (GAT) layer is employed to integrate the influence of neighboring agents during the path-planning process. To further reduce traffic congestion, we extend the MACA framework into a collaborative MACA (C-MACA) scheme in vehicular networks, where CAVs are empowered to periodically broadcast their path information to surrounding CVs, providing valuable insights for their path planning. Subsequently, to prevent new congestion caused by the aggregation of CVs, we design a heuristic algorithm for CVs to make informed path decisions. We build up a simulator based on a real-world city road map and conduct extensive experiments. The experimental results demonstrate that the proposed scheme can decrease CVs' travel time by up to 10.9 % and reduce the average queue length around junctions by up to 6.5 % over several state-of-the-art approaches, without sacrificing the travel efficiency of CAVs.

In recent years, research combining max pressure (MP) with reinforcement learning for traffic signal control has become a hot topic in the field of intelligent transportation. However, existing MP methods ignore the importance of moving vehicles, which prevents the model from focusing on sufficient key information when extracting state features, thus making it suffer from unstable learning, slow convergence, and limited performance during the training process. To address this problem, this paper proposes DualLight, a signal control algorithm based on deep reinforcement learning. In DualLight, a new traffic state representation, is designed, which can help the model extract key information at intersections. To stabilize the learning process of the agent and accelerate the convergence speed, the DMP control method is designed as an expert method for agent imitation in the pretraining module, through which the parameters of the model are initialized. Comprehensive experiments on several real-world datasets show that DualLight improves its performance on the average travel time metric by an average of 17.05%, which significantly improves the efficiency of the transportation network.

Decentralized Federated Learning (DFL) has been proposed to address the potential single point of failure issues in traditional federated learning. However, existing DFL frameworks face challenges such as significant computational and communication overhead, along with low node collaboration efficiency, which limits their applicability in lightweight scenarios. Moreover, privacy-preserving mechanisms in DFL frameworks further increase these inefficiencies, adding delays and resource consumption. In this paper, we propose a group-based decentralized federated learning framework (HEGD-FL) that integrates homomorphic encryption to enhance privacy protection. Considering the computationally demanding nature of the Paillier homomorphic encryption method, we optimize its exponentiation and modular operations. To strengthen privacy preservation, we introduce a client selection mechanism and a contribution mechanism, dynamically adjusting client roles to ensure fairness and security throughout the federated learning process. Experimental results show that HEGD-FL effectively ensures data privacy without compromising the model’s accuracy. At the same time, the group-based DFL framework design and encryption algorithm optimizations enhance system efficiency and broaden the framework’s applicability.

A content delivery network (CDN) aims to reduce the content delivery latency to end-users by using distributed cache servers. Nevertheless, deploying and maintaining cache servers on a large scale is very expensive. To solve this problem, CDN providers have developed a new content delivery strategy: allowing end-users’s IoT edge devices to share their storage/bandwidth resources. This new edge CDN platform must address two core questions: (1) how can we incentivize end users to share IoT devices? (2) how can we facilitate a safe and transparent content transaction environment for end users? This paper introduces SmartSharing, a new content delivery network solution to address these questions. In smartSharing, the over-the-top (OTT) IoT devices belonging to end-users are used as mini-cache servers. To motivate end users to share the idle devices and storage/bandwidth resources, SmartSharing designs the content delivery schedule and the pricing scheme based on game theory and machine learning algorithms (specifically, a tailored Expectation-Maximization (EM) algorithm). To facilitate content trading among end users, SmartSharing creates a secure and transparent transaction platform based on smart contracts in Ethereum. In addition, SmartSharing’s performance evaluation is through trace-driven simulations in the real world and a prototype using content metadata and the achieved pricing schemes. The evaluation results show that CDN providers, end users and content providers can all benefit from our SmartSharing framework.

TCP is currently the most widely used Internet transmission protocol, which is extensively applied to applications on the Internet to enable reliable data transmission. The TCP congestion control algorithm has a significant performance impact on all applications that use the TCP. However, traditional TCP congestion control algorithms rely on fixed feedback mechanisms, which can be challenging to adapt to complex and changing network environments and application scenarios, resulting in network performance bottlenecks. To address this issue, we design a congestion control windowing solution, DRLFcc, which is based on deep reinforcement learning and the TCP fast recovery mechanism. DRLFcc has demonstrated the ability to facilitate real-time adaptation of the congestion window to dynamic changes in network conditions while incorporating fast recovery mechanisms, thereby effectively enhancing network throughput and improving data transmission capacity recovery in high-loss wireless networks. The DRLFcc algorithm is validated in NS-3, and experimental results show an average improvement of 196% in effective throughput and a 22.4% reduction in round trip time. Compared to traditional TCP congestion control algorithms, the DRLFcc algorithm demonstrates superior performance and robustness.

In Green Vehicular Ad-hoc Networks (VANET), how to establish and maintain stable routes to ensure fast and efficient transmission of messages is quite an important and demanding task because of the intrinsic characteristics of VANET, such as uneven distribution and high mobility of vehicles. In this paper, we propose a novel vehicle density prediction-based routing protocol assisted by Green Vehicular Fog Computing (VFC) architecture named VVDP. Since buses have specific trajectories and departure intervals, they are considered fog nodes to improve fog coverage and transmission efficiency. Specifically, we first introduce a vehicle density prediction model to capture the spatio-temporal features of vehicle density effectively. Moreover, we divide the map into streets. The cloud layer of VFC performs precise vehicle density prediction and comprehensively considers the density of buses and common vehicles to assign weights to each street, which can reduce transmission failures due to uneven distribution of vehicles. Besides, buses are used to provide a street-based global path for messages assisted by the weights of each street. To enhance the transmission efficiency, we propose a novel concept: the link trust factor, which combines the mobility factor and direction factor as metrics for selecting the optimal relay. Overall, VVDP not only fully utilizes the rule of vehicle density but also allows for flexible adjustment in accordance with the current circumstance. Simulation results reveal that our proposed routing scheme outperforms others in terms of delivery ratio and end-to-end delay.

With the advent of edge computing, more and more tasks are offloaded to edge servers, but the computing and storage capabilities of edge servers are limited. Although some works propose efficient schemes for task allocation and pricing, they may ignore users' preferences for continuous tasks. However, the combinatorial preference causes high computational complexity. In this paper, we propose a dominant-strategy incentive compatibility (DSIC) and computationally efficient mechanism for green continuous task allocation based on the combinatorial auction. Besides, the activity on edge (AOE) network is introduced to describe the continuity of tasks. The proposed mechanism gives an approximate solution to the winner determination problem (WDP) in polynomial time and a pricing strategy that can guarantee the truthfulness and individual rationality of auction participants. We demonstrate the approximate ratio of the proposed algorithm through theoretical analysis. Experimental results show that the proposed mechanism achieves truthfulness, individual rationality, and high computational efficiency while considering green continuous task allocation.

Age of information (AoI) is an important metric used to quantify the freshness of data. By utilizing resources of the edge server near the source nodes, mobile edge computing (MEC) can speed up the processing of information updates and ensure data freshness. However, the resources of the edge server are usually limited, so it is necessary to study the resource allocation strategy to ensure data freshness and optimize the profit of the edge server. In this paper, we propose a game-theoretic approach for resource allocation in mobile edge computing to guarantee information freshness. First, with the purpose of ensuring information freshness, we formalize the problem as minimizing the computational cost of source nodes and maximizing the profit of the edge server. Then, we introduce a two-stage dynamic game model to simulate the competitive process. We further transform the resource allocation problem into a knapsack problem and propose an iterative resource allocation algorithm based on dynamic programming. Experimental results show that the proposed algorithm can obtain a Nash equilibrium and maximize the profit of the edge server while ensuring information freshness.

In recent years, there’s been a surge in the popularity and affordability of distributed power generation equipment, such as photovoltaic systems (PV) and energy storage systems. At present, however, most solutions target individual user’s energy management. Given the varied energy consumption habits, networking neighboring users and managing energy as a unified system could boost efficiency. Yet, this comes with challenges: unpredictable dynamic demands, significant computational loads, and concerns over data privacy. To tackle these challenges, we introduce a management system that merges deep reinforcement learning (DRL) with federated learning (FL) techniques, named PDDPG-FL. In this setup, each home possesses an agent responsible for decisions like charging/discharging and trading energy with other users. For every agent, we employ a priority-aware deep deterministic policy gradient (PDDPG) algorithm. This not only addresses fluctuating demand adeptly but also offers computational advantages over the conventional DDPG algorithm. Moreover, by incorporating the FL framework, agents can collaborate without risking data privacy breaches. Simulation results show that PDDPG-FL can reduce dependency on main supply grids by up to 9.7% and offers a more streamlined computational process.

This paper presents a computing power scheduling framework based on reinforcement learning (CSFRL) for custom fine-grained resource scheduling on Kubernetes. With the rise of edge computing networks, efficiently adapting computing resources is essential to support various services. While Kubernetes is widely used for container orchestration, few studies have implemented fine-grained resource scheduling using AI algorithms. CSFRL enables the scheduling algorithm to be trained according to user requirements and capable of handling complex scheduling environments, leading to more effective computing resource scheduling on Kubernetes. By conducting a detailed analysis of microservices that require different computing power and using the sorting-based PPO algorithm, CSFRL achieves efficient scheduling of computing power. Experimental results show that CSFRL outperforms the default scheduler on Kubernetes and achieves the expected scheduling results.

With the sixth generation (6G) proposal, collaboration at the edge of the Internet of Things (IoT) has been widely studied to coordinate limited edge resources. Kubernetes has emerged as a promising solution for flexible and efficient resource scheduling. However, the default scheduler of Kubernetes only allocates pods separately according to the resource utilization condition of the cluster, which ignores the effect of the correlation between micro-services on latency. Under this circumstance, we propose a micro-service deployment strategy based on edgeedge collaboration, which takes the correlation between micro-services into account and models it as Service Function Chain (SFC), aiming to reduce the delay and balance the utilization rate in the edge cluster. Furthermore, we propose a model-free Distributed Deep Reinforcement Learning Deployment (DDRLD) algorithm to solve the multi-objective optimization problem. The master node trains the Q network and updates the parameters to the other nodes in the cluster, where each node can determine the deploying decision separately. Simulation results show that the proposed scheduling strategy can reduce user delay while ensuring the balance of the utilization rate.

Fastener needs to be monitored and inspected periodically to ensure the rail’s safety due to its easily damaged accessory for railway infrastructure. Recently, Industrial Internet of Things (IIoT) and artificial intelligence (AI)-based visual inspection techniques have been exploited to realize the online inspection of fastener’s fault by using a fault detection IoT vehicle that is mounted with multitype sensors and cameras according to the design of our research team. However, instead of traditional artificial inspection, the AI-based automatic fastener inspection approach is still faced with some challenges, for example, collection of enough samples of faulted fastener. In this article, we propose a cascade learning embedded vision inspection method of rail fastener based on the deep convolutional neural network (DCNN). The proposed method has two steps: 1) region position and 2) fault detection. First, a modified single shot multibox detector (SSD) model is adopted to locate the fastener regions from the captured railway images. Then, a key component detection (KCD) method based on the improved faster region convolutional neural network (RCNN) is proposed to realize the detection of faulted fastener. Extensive experiments are conducted to demonstrate the performance of the proposed method. The experiment results show that the proposed method achieves an average precision of 95.38% and an average recall of 98.62% on fastener detection, which is much better than the manual operation.

In recent years, the fast development of mobile communications and cloud systems has substantially promoted edge computing. By pushing server resources to the edge, mobile service providers can deliver their content and services with enhanced performance, and mobile-network carriers can alleviate congestion in the core networks. Although edge computing has been attracting much interest, most current research is application-specific, and analysis is lacking from a business perspective of edge cloud providers (ECPs) that provide general-purpose edge cloud services to mobile service providers and users. In this article, we present a vision of general-purpose edge computing realized by multiple interconnected edge clouds, analyzing the business model from the viewpoint of ECPs and identifying the main issues to address to maximize benefits for ECPs. Specifically, we formalize the long-term revenue of ECPs as a function of server-resource allocation and public data-placement decisions subject to the amount of physical resources and inter-cloud data-transportation cost constraints. To optimize the long-term objective, we propose an online framework that integrates the drift-plus-penalty and primal-dual methods. With theoretical analysis and simulations, we show that the proposed method approximates the optimal solution in a challenging environment without having future knowledge of the system.

With the advent of the 5G era, high-speed and secure network access services have become a common pursuit. The QUIC (Quick UDP Internet Connection) protocol proposed by Google has been studied by many scholars due to its high speed, robustness, and low latency. However, the research on the security of the QUIC protocol by domestic and foreign scholars is insufficient. Therefore, based on the self-similarity of QUIC network traffic, combined with traffic characteristics and signal processing methods, a QUIC-based network traffic anomaly detection model is proposed in this paper. The model decomposes and reconstructs the collected QUIC network traffic data through the Empirical Mode Decomposition (EMD) method. In order to judge the occurrence of abnormality, this paper also intercepts overlapping traffic segments through sliding windows to calculate Hurst parameters and analyzes the obtained parameters to check abnormal traffic. The simulation results show that in the network environment based on the QUIC protocol, the Hurst parameter after being attacked fluctuates violently and exceeds the normal range. It also shows that the anomaly detection of QUIC network traffic can use the EMD method.

With various industrial wireless networks greeting booming development, modern industrial devices configured with several network interfaces increasingly become the norm. Such multihomed industrial devices can increase application throughput by making use of multiple network paths, enabled by the multipath transmission control protocol (MTCP) (MPTCP). However, MPTCP might be challenged in the heterogeneous industrial networks because concurrent transmitting industrial application data over asymmetric network paths with different delays is almost bound to the receive buffer blocking problem, which is caused by out-of-order packet arrival and is harmful to the performance of the multipath transmission. The existing MPTCP solutions generally use static mathematical models to evaluate path quality and prohibit transmission on paths with poor quality, which are unable to perform efficiently under highly dynamic and complex network environments. Therefore, in this article, we propose a learning-driven latency-aware MPTCP variant, called${l}\,^2$-MPTCP, which seeks to possibly mitigate the out-of-order packet arrival and receive buffer blocking problems associated with the network heterogeneity in the industrial Internet.${l}\,^2$-MPTCP accurately computes each MPTCP path’s forward delay and assigns application data to multiple paths according to their calculated forward delay differences by using a novel multiexpert learning-enabled forward delay estimator.${l}\,^2$-MPTCP dynamically manages path usage and chooses the optimal path collection for bandwidth aggregation and multipath transmission by using a promising reinforcement learning-empowered multipath manager. Experimental results demonstrate that${l}\,^2$-MPTCP outperforms the current MPTCP solutions in terms of multipathing service quality.

Rail corrugation (RC) is one of the most important indicator to evaluate the quality of rail, which is used to describe the irregularity of rail surface, also known as rail’s vertical flatness. However, the definition of RC is still an empirical description for low-speed measurement devices. In this paper, the process of RC measurement is divided into two steps, sampling and extraction, which helps the users to understand more clearly. Then a new mathematic model is proposed to make the process of RC’s extraction be an executable operation for machine calculation. The model adopts a new concept of flexible virtual ruler to perform sliding filtering on an overall rail and extract the instantaneous RC with a successive approximation algorithm according to user’s requirements and national standards. The proposed FVR model can not only be fully compatible with the traditional extraction method of RC, but also provide a new idea for evaluating RC’s quality. Comparing with the current popular methods, the proposed model gives a meaningful strategy for rail maintenance with a complete mathematic description having more degrees of freedom. Experiment results demonstrate its validity and reliability for both indoor simulation and actual outdoor experiments.

As a key technology of the sixth generation (6G), cloud-edge collaboration has attracted attention in the industrial Internet of Things (IIoT). However, the delay-sensitive and resource-intensive intelligent services in IIoT not only require a large number of computing resources to reduce the delay cost and energy consumption of devices but also require fast and accurate intelligent decisions to avoid service congestion. In this paper, we design an offloading scheme based on cloud-edge collaboration and edge collaboration, including four computing modes, which jointly consider the delay and energy optimization of devices. We propose a parallel deep learning-driven cooperative offloading (PDCO) algorithm, which weighs the real-time and accuracy of offloading scheme. To deal with the difficulty of obtaining labels, a low-complexity hybrid label processing method is designed to reduce the cost of labeling data, and then multiple parallel deep neural networks (DNNs) are trained to generate the best offloading decision timely. Simulation results show that the proposed algorithm can generate offloading decisions with more than 90% accuracy in 0.1s while considering green scheduling.

Abstract Accurate demand prediction of bike-sharing is an important prerequisite to reducing the cost of scheduling and improving the user satisfaction. However, it is a challenging issue due to stochasticity and non-linearity in bike-sharing systems. In this paper, a model called pseudo-double hidden layer feedforward neural networks is proposed to approximately predict actual demands of bike-sharing. Specifically, to overcome limitations in traditional back-propagation learning process, an algorithm, an extreme learning machine with improved particle swarm optimization, is designed to construct learning rules in neural networks. The performance is verified by comparing with other learning algorithms on the dataset of Streeter Dr bike-sharing station in Chicago.

The multipath TCP (MPTCP) enables multihomed mobile devices to realize multipath parallel transmission, which greatly improves the transmission performance of the mobile communication network. With the rapid development of all kinds of emerging technologies, network attacks have shown a trend of development with many types and rapid updates. Among them, low‐rate distributed denial of service (LDDoS) attacks are considered to be one of the most threatening issues in the field of network security. In view of the current research status, by using the network simulation software NS2, this paper first compares and analyzes the throughput and delay performance of the MPTCP transmission system under LDDoS attacks and, further, conducts simulation experiments and analysis on the queue occupancy rate of the LDDoS attack flow to extract the basic attack characteristics of the LDDoS attacks. The experimental results show that the LDDoS attacks will have a major destructive effect on the throughput performance and delay performance of the MPTCP transmission system, resulting in a decrease in the robustness of the transmission system. By analyzing and comparing the occupancy rate of the LDDoS attack flow in the MPTCP transmission system, it can be concluded that (1) the occupancy rate of the LDDoS scattered pulse traffic sent by each puppet machine changes slightly, and (2) the occupancy rate of LDDoS attack data flow is much greater than that of ordinary TCP data flow.

It is an inspiring way to provide emergence communication services in natural disaster areas by deploying wireless routers on the ground and multiple unmanned aerial vehicles (UAVs) in the air. The wireless routers serve as access points. UAVs relay data from routers and themselves to a remote base station in a safe place. Thus, people can communicate with others outside the disaster. The network lifetime is restricted to battery lifetime of routers which are scattered over a complex post-disaster area. There is a potential to prolong the network lifetime by utilizing UAV mobility. We consider the trajectory planning of UAVs with the goal of maximizing the network lifetime, which is modeled as a cooperative game with complete information. However, the time complexity of the problem increases exponentially with the number of UAVs as well as UAV candidate strategies. In our proposal, we boost the game process by excluding some of candidates from the strategy space for each UAV. Specifically, there is no influence for a given UAV, taking the strategies excluded, over the other UAVs. In addition, these strategies are dominated by another strategy at least. Our proposed model is verified through simulations that show its advantage on time complexity over others.

In recent years, the rapid development of cloud computing, networking, and mobile computing have substantially promoted mobile edge computing (MEC). Currently, most of the MEC services can be roughly divided into two categories: computation offloading to accelerate computation and save the energy of mobile devices and data services to shorten the latency between the content providers and the mobile users. Although emerging services such as user-specified transcoding and AR/VR systems require joint optimization of computing resource allocation and data placement, there is little research on it. In this work, we carry out an in-depth study on the interaction of computing resource allocation and data placement in mobile edge computing environments. Based on the analysis of the temporal and spatial characteristics of the two tasks, we propose a joint optimization framework that works with online manner. The proposed method employs hybrid timescales: a coarse-grained timescale to update the data placement and a fine-grained timescale to decide computing resource allocation. The proposed method achieves provable near-optimal performance without buffering users' requirements and does not assume that future trends in user requirements are predictable.

Facilitating real-time query over massive IoT data streams becomes increasingly important nowadays, for that it can boost the performances of real-time network services significantly. Let δ = e1, e2, ⋯ , et, ⋯ represent an IoT data stream, where each element et arrives at time point t. In this paper, we consider the problem of how to support fast range emptiness querying over an IoT data stream δ in sliding window model with a space-efficient data structure, and we denote this problem as the (ε, L)-ARE-problem. To be more formally, subjected to the constraint of one-pass scan of stream δ, the main task of the (ε, L)-ARE-problem is to design a space-efficient data structure that is capable of always representing W(t, n), which are the n latest elements of stream δ until time point t (i.e., W(t, n) = emax{1,t-n+1}, ⋯ , et-1, et), and quickly answering an emptiness query of the form ”W(t, n) ∩ I = 0?”, with a false positive rate no larger than ε, for any query interval I of length up to L. We design a space-efficient data structure D to solve the (ε, L)-ARE-problem and prove that D has constant time cost for querying an interval, inserting a stream element and evicting outdated elements. The efficiency is demonstrated with extensive simulation results as well.

In recent years, the fast development of mobile computing has substantially promoted the mobile edge computing (also known as multi-access edge computing, MEC). Placing content in edges is one of the most important uses of MEC for that it can benefit a variety of service and applications such as video streaming and VR/AR. Currently, most of the existing researches are application specified, and the heterogeneities in data allocating devices and content have not been sufficiently explored. Aiming at developing a general optimal data allocating decision algorithm for MEC, in this work, we carry out in-depth study on the interaction of data allocating and fetching in heterogenous edge computing networks, showing the NP-hardness of the optimal decision problem. We then present polynomial algorithms with 1 - 1/e-approximation factor. Our algorithms has reasonable performance guarantee with low computation complexity. We verify the proposed approach with analysis and simulations.

With the rapid development of construction of railway in China, forecast of track irregularity becomes more significance for more efficient maintenance works. The piecewise linear prediction model is established under the conditions of known tamping operation efficiency and initial quality of railway track. The changing trend of track irregularity between two tamping operations. So in this paper, a piecewise linear representation based forecasting method is proposed to predict the track irregularity by mining the Track Quality Index (TQI) with underlying "memory" of track changing information of its special characteristic. Experiment results demonstrate that the accuracy of the proposed prediction model is over 94%, which can be used as important reference for arranging maintenance works.

Deploying wireless routers on the ground and unmanned aerial vehicles (UAVs) in the air is believed to be a fast and efficient approach to providing the emergency communication service to disaster areas. The network lifetime is restricted to the lifetime of mesh networks of routers that are scattered across a complex disaster environment. We consider the problem of multi-UAVs relaying and moving with the goal of maximizing the network lifetime. UAVs must learn where to move in order to relay messages from the routers efficiently. However, under the dynamics of the router traffic, that is, the uncertainty of the environment, it is challenging for UAVs to find a movement mechanism that maximizes the network lifetime. By embracing the on-policy reinforcement learning algorithm Sarsa, we are able to demonstrate a greedy movement policy. Specifically, we study the trajectory planning of multiple UAVs in a dense wireless router mesh networks (WMNs) on the ground. UAVs can learn the unknown environment by a little movement of UAVs in each step, in which communication connections between routers with UAVs are retained. A Q-table of movement actions and environment states is formed after multiple attempts of movements. Simulation results show the proposal effectiveness comparing with other methods.

Recently, as the development of content-centric networking and Telco-CDNs, inter-domain cache sharing has attracted increased attention. With inter-domain cache sharing, ISPs can further reduce transit cost and improve the quality-of-service (QoS) by accessing their neighbors' caching devices. Currently, cache sharing is limited to free-peering ISPs. Enabling eyeball ISPs to share caches with their transit providers has substantial benefits, but both technical and economic challenges must be addressed. In this study, we consider the inter-domain cache-sharing problem as a double-sided market. In this market, eyeball ISPs receive reimbursement from transit providers for sharing their local caches, while transit ISPs obtain content from the caches of eyeball ISPs at lower cost than by obtaining content from upper tier ISPs. We propose an efficient cooperative mechanism based on Nash bargaining solution to address resource allocation issues in the double-sided market. The proposed mechanism can satisfy both the technical and economic properties desired.

The rising popularity of big data processing for semantically rich applications such as social networks and IoT (Internet of Things) has made the range queriable cloud storage increasingly important. To support range queries, the data locality is preserved strictly, which makes the load balancing among nodes a challenging task. Currently, most of the range queriable cloud storage systems adopt the combination of neighbor item exchange and neighbor migration methods, which incurs large overhead, and suffers from slow convergence. In this work, we present a novel virtual node based distributed load balancing method for range queriable cloud systems. In our method, each physical node is partitioned into multiple virtual nodes, and all the virtual nodes are organized with range queriable P2P network. Load balancing is conducted in both overlay level (betweenneighboring virtual nodes) without global knowledge and physical level (among physical nodes) with limited global knowledge. Both theoretical analysis and simulations show that our method can significantly reduce the overhead and shorten the convergence time.

The rapid development of sensor networks has made it possible to build large-scale sensor overlay networks by integrating separated sensing resources. As the overlay substrate of sensor overlay networks, range queriable P2Ps such as Skip Graph are often applied since they enable retrieving sensing resources whose properties are within the specified range in an effective and scalable way. The range queriable P2P-based sensor overlay networks have proven to be effective in many scenarios, however, the sensor overlay nodes will suffer from flash crowds of queries when disasters, accidents or some events happen. In this paper, we present a virtual node-based approach to alleviate flash crowds for sensor overlay networks. In our approach, a hot-spot node can ask physically spare nodes located in any where in the overlay to generate virtual nodes with the same key as itself, and make the virtual nodes join the overlay network as if they were normal nodes around the hot-spot. With this method, both the query service load of the hot-spot node and the query routing load of the nearby nodes of the hot-spot node can be well distributed with low cost. With theoretical analysis and simulations, we show that our method is efficient, feasible and scalable.

The rapid development of crowd sensing and cloud computing makes it possible to build world wide Cyber Physical Systems (CPS). Range queriable P2P overlay technologies are considered as promising candidate for realizing some important functionalities of CPS, for example, retrieval based on the properties of sensors. However, it is difficult to build world wide systems with existing range queriable P2Ps efficiently as the lack of proximity awareness. In this paper, we propose the hierarchical neighbor selection (HNS) mechanism for range queriable P2P overlays, which can integrate the hierarchy of physical Internet into overlay construction and routing to improve the performance. We also implement HNS based on Skip Graph (SG), an efficient range queriable P2P technology. With extensive simulations, we show that HNS based Skip Graph (HSG) can improve the routing latency and locality significantly with little overhead.

Multihoming is widely used by Internet service providers (ISPs) to obtain improved performance and reliability when connecting to the Internet. Recently, the use of overlay routing for network application traffic is rapidly increasing. As a source of both routing oscillation and cost increases, overlay routing is known to bring challenges to ISPs. In this paper, we study the interaction between overlay routing and a multihomed ISP's routing strategy with a Nash game model, and propose a routing strategy for the multihomed ISP to alleviate the negative impact of overlay traffic.We prove that with the proposed routing strategy, the network routing game can always converge to a stable state, and the ISP can reduce costs to a relatively low level. From numerical simulations, we show the efficiency and convergence resulting from the proposed routing strategy. We also discuss the conditions under which the multihomed ISP can realize minimum cost by the proposed strategy.

In this paper, we present an in-band on-channel (IBOC) broadcasting system suitable for digital audio and data broadcasting in FM and AM channels. The new system utilizes a combination of frequency hopping, LDPC coding, hierarchical modulation and band aggregation techniques to increase the data rate, improve spectrum efficiency, and at the same time, provide spectrum flexibility to meet the requirements of high quality audio and multimedia services. A prototype has been developed on a personal computer (PC) based software defined radio (SDR) platform. Numerical results and initial laboratory tests demonstrate significant performance advantages of the new design over existing systems such as the Digital Radio Mondiale (DRM) and Hybrid Digital (HD) radio.

The impact of inaccurate channel knowledge on the system performance of a cooperative multi-cell system is studied. Using optimization theory, we investigate the performance degradation due to optimizing the collaborative downlink transmit signals of multiple base stations (BSs) based on inaccurate channel knowledge. Two important sources of channel knowledge inaccuracy are considered: quantization and delay. Based on mathematical analysis, multi-cell systems with different levels of cooperation are numerically evaluated and compared.

Linear precoding (LP) techniques for a multiuser multiple-input-multiple-output broadcast channel is investigated and analytical results of the achievable sum capacity and error performance for zero forcing (ZF) linear precoders is presented. It is shown that the detection signal-to-noise ratio of ZF-LP can be accurately approximated by a shrinking Chi-square distribution. The symbol error rate and its achievable diversity gain of ZF-LP are given. Then, an improved linear precoder based on the minimum mean-square error (MMSE) criterion is derived. Its error performance and sum capacity are analysed and compared with that of the ZF-LP. It is shown that the MMSE-LP can achieve much better error performance and a high sum capacity than the existing ZF-LP.

This paper considers precoder designs in downlink MIMO broadcast channels (BC). A preceding scheme that is analog to the MMSE decision feedback equalizer in the uplink MIMO multiple access channels is first introduced. The proposed scheme can asymptotically achieve the sum-capacity of MIMO-BC at high SNRs. At medium SNRs, its achievable sum capacity is very close to that of MIMO-BC and larger than that of ZF-DR. The new scheme can also offer a significant gain over linear pre-equalization techniques in terms of average error probability. Furthermore, by linking the proposed precoder with the sphere encoder, a modified sphere encoder is devised. The modified sphere encoder is shown to be able to achieve the same diversity order as the maximum likelihood (ML) receiver in dual uplink. Its performance is also approaching the corresponding ML receiver.

We study the multiuser diversity in both multiple-input multiple output (MIMO) multiple-access channel (MAC) and MIMO broadcast channel (BC). We consider multiuser scheduling with linear receivers for uplink and linear precoders for downlink. In each time slot, a group of users are selected in either transmission or reception. Based on the performance analysis, a criterion of selecting a number of active users to optimize error performance is presented. We show that the linear processing for downlink and uplink achieves the same SNR. This makes it convenient to use a single scheduling algorithm in both downlink and uplink. Furthermore, we present an analysis of the performance of the proposed scheduling algorithm. It is shown that the analysis agrees with the simulation.

In rapidly time varying channels, the channel impulse response estimation might not be successful by the conventional decision directed scheme following the supervised training. The blind sequence detection would be the only solution in these scenarios. In this paper we proposed a new blind sequence detection algorithm, which has a significant robustness against bit ambiguity and whose performance with uncoded sequence is better than that of some existing blind algorithms with coded systems. Bit error performances have been investigated by computer simulation and compared with coded system. A significant gain has been achieved in SNR as much as 6 dB or more.

This paper proposes the code design criteria for robust space-time trellis codes (STTCs) in orthogonal frequency division multiplexing (OFDM) systems over quasi-static frequency selective fading channels. The code design criteria consider the channels with multiple uncorrelated taps and various channel delay distributions such that the robust code performance over various channel conditions can be guaranteed. Based on the code design criteria, new 4, 8, and 16-state 4-PSK STTCs are constructed. Simulation shows that the new codes achieve the robust code performance over various quasi-static frequency selective fading channels.