As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual modalities with a primary emphasis on English, which creates a gap in evaluation when processing multilingual input, especially in speech. To bridge this gap, we propose a novel Cross-lingual and Cross-modal Factuality benchmark (CCFQA). Specifically, the CCFQA benchmark contains parallel speech-text factual questions across 8 languages, designed to systematically evaluate MLLMs' cross-lingual and cross-modal factuality capabilities. Our experimental results demonstrate that current MLLMs still face substantial challenges on the CCFQA benchmark. Furthermore, we propose a few-shot transfer learning strategy that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training. We release CCFQA as a foundational research resource to promote the development of MLLMs with more robust and reliable speech understanding capabilities.

Existing zero-shot fault diagnosis methods are typically system-specific and numerically sensitive, which lack adaptive deployment capabilities across heterogeneous photovoltaic (PV) system scales and topologies. Multimodal large language models (MLLMs) emerge as a powerful solution in cross-system generalization, but their adoption in PV fault diagnosis has been limited by the lack of PV knowledge integration and challenges in processing diverse operating conditions. To bridge this gap, an MLLMs-empowered framework for zero-shot PV fault diagnosis is proposed for the first time, which jointly integrates data-driven and knowledge-driven schemes. First, a chain-of-thought-based data augmentation pipeline is constructed to achieve data-knowledge alignment and interpretable results. Second, a two-stage adaptation strategy is specifically designed for PV data to overcome system scales, diverse topologies, and numerical differences. It consists of a Kolmogorov–Arnold networks-based condition adaptive layer embedded in vision transformer and a low-rank adaptation-based PV domain fine-tuning. Third, we design a microservices-based architecture for PV-MLLM deployment that enables flexible component decoupling and adaptive inference, significantly reducing hardware requirements and resource consumption. The proposed method achieves 99.66% and 97.25% diagnostic accuracy on simulated and real-world datasets.

In microservice architecture, each industrial application is decomposed into multiple microservices and deployed on cloud servers to provide timely services to users. However, existing methods rarely optimize service deployment strategies from the user's perspective to reduce the leasing costs of cloud servers. Furthermore, accurately estimating the required number of instances and resource utilization for microservices remains challenging, and decision-making in large-scale scenarios also faces significant timeliness constraints. To solve this problem, this article proposes a Column Generation deployment strategy, which decomposes the microservice deployment problem into a master problem for scheme selection and subproblems for scheme generation and proves the gap between its convergent solution and the optimal solution. A Distributed Column Generation strategy is further introduced to enable efficient problem-solving. Experimental results based on real-world server pricing demonstrate that the proposed method exhibits a high degree of consistency with the theoretically optimal solution. Compared to the baseline methods, it reduces the average total cost of ownership (TCO) for users by 11.3%, while the decision-making time is only 21.5% of that of the comparative methods. At the same time we used our approach to make deployment decisions for real industrial microservices and deployed them on real cloud servers. Compared to the baseline approach, it reduces TCO by 4%, but decision-making is 97% faster.

Yifan Yang, Zheshu Song, Jianheng Zhuo, Mingyu Cui, Jinpeng Li, Bo Yang, Yexing Du, Ziyang Ma, Xunying Liu, Ziyuan Wang, Ke Li, Shuai Fan, Kai Yu, Wei-Qiang Zhang, Guoguo Chen, Xie Chen. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Yexing Du, Youcheng Pan, Ziyang Ma, Bo Yang, Yifan Yang, Keqi Deng, Xie Chen, Yang Xiang, Ming Liu, Bing Qin. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Data-driven fault diagnosis methods for photovoltaic modules often encounter issues of sample scarcity and insufficient generalization, whereas knowledge-driven multimodal large language models (MLLMs) can comprehend human-summarized prior knowledge for logical reasoning, significantly enhancing the model’s general applicability. This paper proposes a high-generalization diagnostic framework based on knowledge-driven approaches, featuring a state correction vision transformer on MLLMs to solve the problem of sample scarcity, thereby enabling fault diagnosis grounded in photovoltaic knowledge. To mitigate the high computational cost of the large model inference, the framework incorporates an edge-based small model using Support Vector Machines to filter faulty samples. Additionally, a carefully designed photovoltaic knowledge datasets, along with an adaptive fine-tuning method, facilitates efficient domain-specific refinement of the pre-trained model. To address the potential issue of frequent model updates, each framework component is encapsulated as a microservice for easy orchestration. The framework has been deployed and tested on real cloud-edge-end cluster, achieving a diagnostic accuracy of 97.25% and reducing the invocation of large models by 90%.

Voltage prediction is critical for ensuring both safety and operational efficiency of vanadium redox flow batteries (VRFBs) in long-duration energy storage. In this paper, we propose a physics-data fusion model framework for long-term voltage prediction of VRFBs. First, a parameterized Nernst equation is introduced to construct a physically meaningful latent space. Second, the temporal dynamics of hidden state variables are modeled based on electrochemical principles to precisely capture their time-dependent behavior. Subsequently, auxiliary variables are constructed using a physics-guided approach based on the polarization. Finally, a deep neural network is employed as the output layer of the model to establish the mapping between multidimensional feature variables and voltage. Experimental results demonstrate that this approach effectively captures the long-term voltage aging trends under diverse operational conditions, improving both accuracy and generalization performance.

The uncertainty of wireless communication seriously affects the control performance of the platoon. In this paper, a model predictive control (MPC) method based on dynamic event-triggering is proposed to address the impact of non-ideal communications on multi-vehicle systems. Firstly, a hierarchical platoon architecture combining backbone layer and sub-platoon layers is proposed to achieve efficient coordination among multiple platoons, and a communication-aware control mechanism is designed for each vehicle to effectively mitigate the adverse effects of non-ideal communication scenarios. Secondly, a dynamic event-triggering mechanism is established for each vehicle, which is related to time-varying delay and random packet loss parameters, so as to effectively reduce the frequency of MPC solutions and data transmission. Additionally, based on different communication topologies, distributed model predictive controllers are suggested for backbone layer and sub-platoon layer to achieve precise and comfortable tracking. Then, sufficient conditions are provided to ensure the recursive feasibility of the MPC algorithm and the stability of the platoon system. Finally, extensive simulations are conducted, and the results demonstrate the effectiveness of the proposed algorithm in terms of control performance and low computational complexity under non-ideal communication conditions.

The confluence of Internet-of-Things (IoT) and artificial intelligence has advanced smart home (SH) systems, enabling the provision of complex scene-aware services. Central to these services is the precise perception of the indoor environment. Indoor scenes present unique challenges due to diverse layouts, frequent object occlusions, and dynamic human activities, which hinder the comprehensive understanding by individual SH devices/sensors. Moreover, the diversity of sensors equipped by SH devices introduces the multimodal data issue, necessitating the reconciliation of discrepancies among various data modalities. This article presents multimodal collaborative perception (MMCP), a collaborative perception paradigm for SH systems with multimodal raw data. MMCP leverages the intermediate collaboration framework and tailors it to an edge-assisted SH system. It deploys dedicated encoders at SH devices to convert multimodal raw data to uniform intermediate features, which are then sent to an edge computing box for aggregation and perception. MMCP introduces a critical information identifier to selectively transmit informative parts within intermediate features, thereby mitigating the communication overhead for bandwidth-constrained SH devices. Moreover, MMCP designs collaborative infomax (CIM) to facilitate intermediate feature aggregation. CIM defines multiview mutual information (MVMI) to capture dependencies between the aggregated feature and individual intermediate features from multiple SH devices. It employs contrastive learning to estimate and maximize MVMI in an unsupervised manner, such that the aggregated feature can retain discriminative information from individual intermediate features. We evaluate MMCP in four real-world indoor scene datasets. Experimental results show that MMCP outperforms noncollaborative strategy by 18% in average precision (AP). Particularly, MMCP strikes a favorable balance between perception performance and communication overhead, compressing intermediate features to a ratio of 13% while maintaining higher AP compared to state-of-the-art methods.

Edge computing-enabled virtual reality (VR) is increasingly explored in smart healthcare systems due to its potential to deliver immersive, real-time medical services. However, ensuring ultra-low latency and interpretable decision-making in such systems remains a significant challenge. In this paper, we propose an explainable deep reinforcement learning (XDRL)-enhanced VR video streaming framework for immersive healthcare systems to provide smooth and reliable VR services. Specifically, we first model the VR content analysis process at the edge sides and formulate a joint caching, communication, and computing (3C) resource optimization problem to maximize the VR quality of service (QoS) and minimize service latency. To address this complex 3C resource scheduling decision problem, we propose HXRL, a novel implementation of explainable deep reinforcement learning (XDRL), specifically designed to optimize immersive healthcare VR services. Comprehensive experiments show that our HXRL method improves average tile bitrate by 18.3%, cache hit ratio by 24.7%, and reduces system latency by 32.5% compared to baselines on real-world VR healthcare datasets. Moreover, a class activation map (CAM)-based visual analysis is integrated to interpret the learned policies of our model, highlighting the spatial attention of decision-making and enhancing trustworthiness in medical contexts.

Smart homes depend on collaborative sequential prediction tasks to optimize energy consumption and appliance scheduling. Federated learning (FL) offers a promising approach by enabling decentralized model training to balance privacy and usability. Yet, standard FL techniques fail to effectively address data diversity and individual user preferences in smart home contexts. To address these issues, we propose P3FL: a Privacy-Preserving Personalized Federated Learning framework that integrates tailored model training and privacy enhancements for federated collaborative predictions and decision-making. Our framework introduces the Personalized Collaborative Decision-Making (PCDM) algorithm, which dynamically adapts to different household environments while ensuring privacy and personalization. P3FL combines a global model for knowledge aggregation with a personalized adaptation module to provide fine-tuned predictions based on user preferences, environmental factors, and device configurations. Theoretical convergence bounds analysis confirms the robustness and efficiency of PCDM under conditions of strong convexity, smoothness, and bounded variance. Extensive experiments on real-world smart home datasets demonstrate that P3FL outperforms state-of-the-art methods, with PCDM achieving a training accuracy of 92.14%. Our approach enhances operational efficiency and ensures personalized user satisfaction, privacy enhancement in smart homes.

Intelligent fault diagnosis of photovoltaic (PV) arrays in small-sample scenarios remains challenging due to poor model accuracy and generalization. Existing methods fail to simultaneously address issues of varied operation conditions and insufficient samples, leading to the limited applicability of models built by few-shot learning. In addition, factors, such as data transmission and computation costs, also need to be considered. Therefore, this article proposes a cloud-edge collaborative self-correcting-guided generalized contrastive learning framework for small-sample PV fault diagnosis. First, an end-to-end self-correcting model is proposed to eliminate the influence of variable environments. Then, a self-correcting scheme is integrated with contrastive learning to achieve model generalization, and a type screening method is designed to improve model accuracy. Furthermore, a fast fault filtering mechanism is proposed to enhance the algorithm efficiency with cloud-edge collaboration. Both simulation and real data are utilized to validate the proposed method.

The dynamic fault environment, incremental data accumulation, and specific needs in train transmission systems make continual learning essential for fault diagnosis. Recent advancements in continual learning have improved diagnostic adaptability, but current methods face challenges: 1) Complex architectures to prevent catastrophic forgetting increase training difficulty and computational costs, hindering deployment. 2) Lack of new class samples leads to delayed model evolution due to long sample accumulation periods. This article introduces a lightweight continual learning method based on model expansion. A hash space metric mechanism using lightweight convolution is developed to reduce computational costs while maintaining accuracy. Additionally, a joint strategy of knowledge enhancement and compression improves model evolution by refining knowledge subsets. Compared with the state-of-the-art method, the proposed method reduces parameters by 2.59 times, FLOPs by 2.67 times, and inference time by 2.89 times, and leads by 2.5% and 0.23% in incremental accuracy and incremental forgetting rate, respectively.

Real-time transmission of high-frequency signals in online fault diagnosis challenges the limited bandwidth. However, reducing the volume of data transmission will compromise the data quality and drop the accuracy of fault diagnosis. This article synergizes data transmission and fault diagnosis to simultaneously achieve high transmission reduction ratio and fault diagnostic accuracy. First, a novel long sequence dual prediction scheme (L-DPS) is proposed to reduce the high-frequency data transmission online while ensuring the data precision. Second, a resource-efficient transformer model is proposed to improve the precision and speed of long sequence prediction in L-DPS, thus effectively improving its transmission reduction ratio and applicable frequency. Finally, a precision-adaptive fault diagnosis model is proposed to tackle precision differences in the transmission-restored data, thus effectively improving the accuracy of fault diagnosis. Experiments based on the real-world dataset confirm that the solution can cope with high-frequency data up to 20.69 KHz and achieve 94.16% transmission reduction and 99.43% fault diagnosis accuracy.

Intelligent reflecting surface (IRS) and rate-splitting multiple access (RSMA) technologies are at the forefront of enhancing spectrum and energy efficiency in the next generation multi-antenna communication systems. This paper explores a RSMA system with multiple IRSs, and proposes two purpose-driven scheduling schemes, i.e., the exhaustive IRS-aided (EIA) and opportunistic IRS-aided (OIA) schemes. The aim is to optimize the system weighted energy efficiency (EE) under the above two schemes, respectively. Specifically, the Dinkelbach, branch and bound, successive convex approximation, and the semidefinite relaxation methods are exploited within the alternating optimization framework to obtain effective solutions to the considered problems. The numerical findings indicate that the EIA scheme exhibits better performance compared to the OIA scheme in diverse scenarios when considering the weighted EE, and the proposed algorithm demonstrates superior performance in comparison to the baseline algorithms.

High-frequency time-series data such as vibration signals will consume a lot of communication resources and require very high network bandwidth. Reducing the amount of data transmission while ensuring its availability is particularly important and challenging in high-frequency scenarios. Dual prediction scheme (DPS) can significantly reduce the amount of data transmission while ensuring data accuracy. However, traditional DPS cannot be applied to high-frequency scenarios due to the limitation of the mechanism design and model inference speed. We propose a novel long sequence DPS to efficiently reduce the volume of high-frequency data transmission in real time. To overcome the accuracy degradation due to gradient vanishing in long sequence prediction, we also propose an attention-based prediction model. Furthermore, we propose Informer to reduce the model’s computational complexity and enable fast inference and deployment on resource-constrained edge gateways. Experiments based on the real-world dataset show that the proposed scheme can efficiently cope with high-frequency data, reduce its transmission volume, and ensure data accuracy.

With the rapid development of smart manufacturing, existing microservice deployment strategies based on the TCP protocol tend to encounter problems such as network latency, excessive header length, and port exhaustion in high concurrency scenarios. MQTT Broker can relay data between microservices, effectively alleviating these issues. However, the communication overhead of the Broker is significantly related to its deployment and the dependency of microservices. An appropriate deployment solution can significantly improve service quality. To address this issue, this paper models the deployment of MQTT Broker and microservices as a graph with cycles. By introducing auxiliary variables, the NP-hard problem is transformed into a mixed-integer quadratic programming problem, improving problem-solving efficiency and optimizing the microservices deployment strategy to reduce communication overhead. Meanwhile, a real-world heterogeneous cluster was constructed to experiment on fault detection applications, elaborating on the superiority of the microservice deployment strategy designed in this paper. Experimental results demonstrate that our approach reduces communication overhead by 20% in comparison to both the greedy strategy and the K8s strategy. This suggests that achieving an optimal balance between the number of Brokers and microservices is vital for ensuring efficient resource utilization and maintaining low communication latency, particularly as the scale of services expands.

This study focuses on an intelligent reflecting surface (IRS) enabled simultaneous wireless information and power transfer (SWIPT) system with the coexistence of legitimate users (LUs) and Eavesdroppers (Eves). The main objective is to jointly optimize the transmit beamforming and artificial noise covariance matrix at the access point, the phase shift matrix at the IRS, and the power splitting ratio at the LUs, to maximize the system’s min-secrecy rate. Due to the imperfect channel state information of Eves, an outage rate constraint is contained. The formulated problem is a challenging nonconvex optimization problem since it involves nonconvex objective function and constraints, and the outage rate constraint does not have simple closed form expression. To address this problem, an algorithm based on the alternating optimization method is proposed, which breaks down the nonconvex problem into three subproblems. The algorithm employs several techniques to solve these subproblems. Specifically, the outage rate constraint is approximated using the Bernstein-type inequality. And the Taylor formula, semi-definite relaxation, and successive convex approximation methods are employed to transform the nonconvex subproblems into convex ones. Simulation results demonstrate the effectiveness of the proposed algorithm compared to baseline algorithms under different conditions.

The packet loss during transmission of load control commands can lead to regulation errors in the smart grid and further increase the cost of utility companies due to the purchase of additional automatic generation control services. This article considers a cooperative communication network consisting of multiple data aggregation units (DAUs) and multiple relays in smart grid, and each relay can forward data for all DAUs. We optimize the transmission power allocation of the relays to reduce the demand-side regulation errors and the cost of utility companies. However, additional cost is incurred due to the rental of relay in commercial networks. In order to minimize the total costs of utility companies, a two-layer game model is proposed and an iterative algorithm is developed. Simulation results show that the cost of utility companies can be reduced under the proposed scheme.

In this paper, we investigate a mixed-traffic control problem considering uncertainties of HDVs flow. The challenges mainly lie in modeling the stochastic characteristics of mixed-traffic flow and developing less-conservative algorithm to deal with the uncertainties. To tackle the problem, we propose a stochastic model predictive control (MPC) strategy based on data-driven distributionally robust optimization (DRO). First, a stochastic mixed-traffic model, extended from cell transmission model, is proposed to describe the traffic dynamics. Then, utilizing historical traffic data, an incremental principal component analysis (IPCA) based method is given to construct ambiguity set and incorporate generalized moment information of uncertainties. Based on the above predictive model and ambiguity set, a DRO-based MPC problem is formulated and further converted into an equivalent dual form for efficient solutions, i.e., ramp metering and variable speed limit control. Finally, simulation results based on real data collected in Shanghai, China, demonstrate that our proposed strategy can significantly reduce traffic congestion, achieving 5.74 % total travel time reduction compared to robust MPC.

Cooperative adaptive cruise control (CACC) can optimize velocity planning by interaction between connected vehicles, and thus increase energy efficiency. It is much significant for platoon of electric vehicles (EVs) powered by hybrid energy storage system (HESS). HESS which is composed of battery and supercapacitor (SC), has been implemented to improve energy efficiency by regulating the distribution of internal energy sources. Different from most existing works on energy management for EVs, this paper is concerned with a bi-level control strategy for platoon’s velocity planning and HESS management. The upper layer focuses on the cooperative velocity planning for platoon to guarantee internal stability of individual vehicle and platoon robust string stability. The optimal velocities for each vehicle in the platoon could be determined by using distributed model predictive control (DMPC) method. The safety condition and the constraint on communication delay are considered. In the lower layer, a rolling horizon optimization method is proposed to optimize the power of HESS with the assistance of planned velocities in the upper layer. The simulation results indicate the effectiveness of the proposed strategy and methods.

Owing to the openness and diversification of heterogeneous communication network, communication security becomes a pressing problem. In this paper, we consider a heterogeneous communication network in which spectrum resources are shared by electric power communication network and licensed network. First, we establish the utility companies’ cost model based on Taguchi loss function. Next, we utilize cooperative relay strategy to enhance the transmission quality and achieve high-speed information transmission in smart grids. Under the premise of ensuring high-quality transmission of electric power communication services, we propose a secure transmission strategy for information resource sharing and interference price trading that utilizes smart grid infrastructure and relay to interfere with eavesdroppers to improve the security rate of licensed user (LU), which achieves mutual benefits. Furthermore, the bernstein approximation method and the successive convex approximation are adopted to obtain the open-form expression of the constraint and transform the non-convex problem into the convex problem, respectively. A distributed robust power control algorithm is then proposed to obtain the optimal solutions. Finally, numerical results verify that the proposed secure scheme and algorithm can increase the secrecy rate at LU, reduce the total electricity cost, and improve both the profit of relay and the social welfare.

The microservice architecture has gained widespread adoption in smart manufacturing, enabling the collaborative completion of production tasks through the integration of multiple microservices. However, migrating microservices in dynamic environments poses challenges for maintaining production quality and service efficiency. First, there are complex dependencies between microservices, such as layered and chain structures, making microservice migration a difficult process. Second, large-scale production scenarios require rapid decision-making based on high-dimensional variables to adapt to the dynamic environment. Third, microservice migration can cause interruptions, so careful selection of microservices is crucial to minimize production stagnation during migration. To tackle these challenges, we develop an efficient and economical migration strategy ($E^{2}MS$). This approach considers the complex dependencies between microservices and optimizes the system cost by selecting appropriate microservices for migration. We formulate an integer non-convex quadratic programming problem and employ techniques such as variable reduction, penalty functions, and successive convex approximation (SCA) to solve it. The proposed strategy enables efficient decision-making for microservice migration in dynamic production environments and exhibits strong scalability. Our experimental results demonstrate the exceptional dynamic performance of the proposed method, significantly reducing the time required to obtain migration strategies and achieving a 90% reduction in microservice interruptions compared to other methods.

The uncertainty of human-driven vehicles (HDVs) has a significant impact on the movement of connected and automated vehicles (CAVs), especially on the CAV platoon. In this regard, the future trajectory information of the preceding HDV is essential for CAV platoon to develop a safe and smooth speed control strategy. However, constrained by computation and energy resources, on-board unit can not provide accurate predictions, which results in inefficient control strategy and even safety issues. Hence, we propose an edge-assisted prediction and a flexible cooperative adaptive cruise control (CACC) strategy in this paper. The challenges mainly lie in the design of coordination mechanism and control strategy. Considering the inaccuracy of prediction, an error-aware communication trigger scheme is first designed to decide whether to request the roadside unit (RSU) for performing accurate prediction with the aid of mobile edge computing (MEC). Further, a novel flexible tracking policy is proposed to deal with prediction error, which is integrated with model predictive control method to determine control inputs. Simulations based on real data, collected in Shanghai, China, demonstrate that our proposed method can significantly improve driving safety and speed smoothness.

V2X communication is a key technology for intelligent transportation system to improve traffic safety and efficiency. Electric vehicles can reduce greenhouse gas emissions and fossil fuel dependence, but they face challenges such as limited driving range, high battery cost, and long charging time. This paper proposes a V2X communication assisted hierarchical cooperative control strategy for EVs that aims at improving driving performance and energy efficiency. The upper layer uses improved model predictive control (MPC) method for cooperative motion control. A mechanism is designed for V2X communication loss in the algorithm. The lower layer employs a hybrid energy storage system for powertrain management. The algorithm in the lower layer uses the predictive information from the upper layer to enhance the powertrain efficiency and prolong the battery life. The proposed strategy is simulated using a Prescan-Carsim simulation platform. The results demonstrate that the proposed method can improve the battery lifetime over 13% compared with baseline method.

In order to improve the profits of electricity utility company (EUC) and gas utility company (GUC) and reduce the electricity and heat cost of users, an energy trading and pricing scheme based on three-stage game is proposed. Firstly, a three-stage optimization problem is established, and the conversion between electricity and gas is considered. Meanwhile, the conversion factor is introduced and coordinated with the energy price to adjust the balance of supply and demand. Then, the equilibrium solution of the game is obtained by using Lagrange function and backward induction method. In addition, an iterative algorithm is developed to obtain the optimal conversion factor between electricity and natural gas. Numerical results show that the profits of EUC and GUC are increased by 31.6% and 14.4%, the electricity and heat profits of energy hubs (EHs) are increased by 3% and 6.4%, and the electricity and heat cost of users are reduced by 9.25% and 14.05%. Note to Practitioners—In the multi-energy market, trading and pricing strategies have attracted more and more attention. Based on this, many scholars only studied pricing strategy to balance the supply and demand. However, in the context of multi-energy coupling, the previous pricing strategy is not effective. In this paper, we propose a new pricing strategy, with which the conversion factor can cooperate with the energy price to achieve the balance between supply and demand. The new pricing strategy can increase the profits of electricity utility companies and gas utility companies and reduce the costs of users.

Many computation-intensive industrial applications need to be run in the cloud, which relies on a lot of sharply varying data transmitted from the industrial field. To save the communication bandwidth and ensure data with required accuracy obtained by the cloud, we design a data transmission architecture based on dual prediction scheme and cloud-edge collaboration and a dual-mode algorithm based on deep learning. With the proposed architecture, a deep learning model is deployed and synchronized on the edge and cloud sides. Further, the proposed algorithm can help the cloud for computation with locally predicted data or real-time data from the edge, depending on whether the predicted data are adequately accurate. A physical validation platform including a sensor, an edge gateway, and a cloud server is built, and drastically changing real vibration data are collected to validate the proposed scheme. The results show that the proposed scheme can reduce 88.66% of data transmission while guaranteeing deviations less than 0.1.

With the rapid development of smart manufacturing, edge computing-oriented microservice platforms are emerging as an important part of production control. In the containerized deployment of microservices, layer sharing can reduce the huge bandwidth consumption caused by image pulling, and chain sharing can reduce communication overhead caused by communication between microservices. The two sharing methods use the characteristics of each microservice to share resources during deployment. However, due to the limited resources of edge servers, it is difficult to meet the optimization goals of the two methods at the same time. Therefore, it is of critical importance to realize the improvement of service response efficiency by balancing the two sharing methods. This paper studies the optimal microservice deployment strategy that can balance layer sharing and chain sharing of microservices. We build a problem that minimizes microservice image pull delay and communication overhead and transform the problem into a linearly constrained integer quadratic programming problem through model reconstruction. A deployment strategy is obtained through the successive convex approximation (SCA) method. Experimental results show that the proposed deployment strategy can balance the two resource sharing methods. When the two sharing methods are equally considered, the average image pull delay can be reduced to 65% of the baseline, and the average communication overhead can be reduced to 30% of the baseline.

Traffic optimization strategies are imperative for improving the performance of transportation networks. Most traffic optimization strategies only depend on traffic states of congested road segments, where congestion propagation is neglected. Therefore, we propose a distributed traffic optimization strategy for urban freeways considering the potential congested road segments caused by congestion propagation, calledpotential-homogeneous-area(PHA). Utilizing the historical traffic density data, we first quantify the effect of congestion propagation and identify PHA by applying the proposed spatiotemporal lambda-connectedness method. Meanwhile, dynamic capacity constraints of PHA are determined and are integrated with the cell transmission model (CTM) in a centralized traffic optimization problem. To reduce computational complexity and improve scalability, we then propose a double-consensus-based alternating direction method of multipliers algorithm (DC-ADMM) to handle the neighbor coupling constraints and global coupling constraints for solving the problem in a fully distributed way. We prove that the proposed DC-ADMM algorithm converges to the optimal solution in the condition of a convex objective function. Finally, simulations based on real traffic density data, collected in Inner Ring Road, Shanghai, China, reveal the effectiveness of our proposed strategy.

With the popularity of mobile devices and development of computationally intensive applications, researchers are focusing on offloading computation to the mobile-edge computing (MEC) server due to its high computational efficiency and low communication delay. As the computing resources of an MEC server are limited, vehicles in the urban area who have abundant idle resources should be fully utilized. However, offloading computing tasks to vehicles faces many challenging issues. In this article, we introduce a vehicular fog-edge computing paradigm and formulate it as a multistage Stackelberg game to deal with these issues. Specifically, vehicles are not obligated to share resources, and let alone disclose their private information (e.g., stay time and the amount of resources). Therefore, in the first stage, we design a contract-based incentive mechanism to motivate vehicles to contribute their idle resources. Next, due to the complicated interactions among vehicles, roadside unit (RSU), MEC server, and mobile device users, it is challenging to coordinate the resources of all parties and design a transaction mechanism to make all entities benefit. In the second and third stages, based on the Stackelberg game, we develop pricing strategies that maximize the utilities of all parties. The analytical forms of optimal strategies for each stage are given. Simulation results demonstrate the effectiveness of our proposed incentive mechanism, reveal the trends of energy consumption and offloading decisions of users with various parameters, and present the performance comparison between our framework and existing MEC offloading paradigm in vehicular networks.

Multiobject tracking (MOT) is a crucial technology for security surveillance, which is computationally intensive due to the requirement of processing a large number of video streams within low latency in practice. The input video streams of MOT are processed on a cloud computing center with abundant computational capability, posing heavy pressures on delivering video streams to the cloud. Recent advances in the Internet-of-Things (IoT) technology provide edge-computing-based solutions for video analytics at scale. However, the gap between MOT’s high computational capability demand and IoT devices’ resource-constrained nature remains significant. In this article, a resource-efficient MOT (REMOT) method is proposed for real-time surveillance on IoT embedded devices, including an affinity measurement based on an appearance model with angular triplet loss and a motion association that substitutes the time-consuming graph-based data association stage. Considering the tradeoff between latency and accuracy, we design an optimization strategy on the parallel processing of deep learning models’ layers to accelerate the inference speed with less accuracy loss. Besides, we employ a model compression strategy for model size reduction. Experiments on MOT16 and MOT17 benchmarks demonstrate that REMOT reduces 2.4$\times $latency compared with the original implementation and achieves a running speed of 81 frames per second (fps) on an embedded device with only a marginal accuracy loss (6%), which meets the requirements of real-time processing and low-latency response for surveillance.

Task offloading in edge computing is important for the Industrial Internet of Things (IIoT) to implement computation-intensive applications in real time. However, achieving efficient task offloading in IIoT is very challenging due to the limited computing resources of IIoT devices, the coupling of computing and communication resources, and the unreliability in multihop wireless transmission. In this article, we construct a link model by considering the influence of unreliable links in multihop transmission to reveal the relationship between reliability and transmission delay. Then, a nonconvex optimization problem that minimizes task processing delay is formulated, and task offloading is decided by considering transmission path selection, bandwidth allocation, and computational resource allocation. To solve this problem, an algorithm based on the alternating direction method of multipliers (ADMM) is designed using auxiliary variables and reformulation linearization technology (RLT). The simulation results show that our proposed algorithm can fully utilize the computing power of the edge server and reduce the task processing delay. Compared with the centralized algorithms, the performance of the proposed scheme is only 1% worse, but the calculation time can be reduced by 40%.

In photovoltaic (PV) systems, machine learning-based methods have been used for fault detection and diagnosis in the past years, which require large amounts of data. However, fault types in a single PV station are usually insufficient in practice. Due to insufficient and non-identically distributed data, packet loss and privacy concerns, it is difficult to train a model for diagnosing all fault types. To address these issues, in this paper, we propose a decentralized federated learning (FL)-based fault diagnosis method for insulated gate bipolar transistor (IGBT) open-circuits in PV inverters. All PV stations use the convolutional neural network (CNN) to train local diagnosis models. By aggregating neighboring model parameters, each PV station benefits from the fault diagnosis knowledge learned from neighbors and achieves diagnosing all fault types without sharing original data. Extensive experiments are conducted in terms of non-identical data distributions, various transmission channel conditions and whether to use the FL framework. The results are as follows: 1) Using data with non-identical distributions, the collaboratively trained model diagnoses faults accurately and robustly; 2) The continuous transmission and aggregation of model parameters in multiple rounds make it possible to obtain ideal training results even in the presence of packet loss; 3) The proposed method allows each PV station to diagnose all fault types without original data sharing, which protects data privacy.

The inverter is the most vulnerable module of photovoltaic (PV) systems. The insulated gate bipolar transistor (IGBT) is the core part of inverters and the root source of PV inverter failures. How to effectively diagnose the IGBT faults is critical for reliability, high efficiency, and safety of PV systems. Recently, deep learning (DL) methods are widely used for fault detection and diagnosis. Different from traditional diagnosis methods, DL methods use deep neural networks which can automatically extract the useful representative features from raw data. However, DL methods require large amounts of data, which leads to the high cost of communication, storage, and computation. To tackle these issues, a data-driven fault detection and diagnosis method for IGBT open-circuit faults based on compressed sensing (CS) and convolutional neural networks (CNN) is proposed in this paper. CS is adopted to compress raw signals, and the optimal value of compression ratio (CR) is determined by considering the trade-off between classification accuracy and model training time. The overlap sampling method is adopted for data segmentation. Meanwhile, overlap sampling can also increase the number of training samples and improve the sample correlation. The compressed signals are segmented and reconstructed into two-dimensional feature maps for model training. Finally, compared with CNN of the same structure, the developed CS-CNN model can compress 85% of data without accuracy loss. The performance comparison with the state-of-the-art networks demonstrates that the test accuracy is 98.68% and the model training time is much shorter than other methods.

Recently, the intelligent reflecting surface (IRS) is an emerging and promising technology for achieving higher spectrum and energy efficiency in wireless communication systems. In this paper, we consider a wireless powered mobile edge computing (MEC) network that is equipped with an IRS. The IRS is able to provide a reflecting channel to enhance the offloading capability for edge users. Based on this system model, we investigate an optimisation problem to maximize the sum of users' utilities, which jointly consider the energy efficiency, time latency, and price of offloading computations. With task offloading, power limited users can complete the computational tasks even when they face data-intensive workloads. However, in a dynamic system, it is complicated to design the optimal offloading decision strategy. To tackle this problem, we propose a deep reinforcement learning (DRL) based approach. In the designed algorithm, in order to get a better reward, the agent chooses a near optimal solution to adjust the workload partitions, the time allocation, and IRS parameters according to the dynamic channel environment and the random arrival of task workload. Numerical results show that the proposed DRL based IRS-aided offloading algorithm can achieve better system performance compared with that without IRS and the relative benchmark algorithms.

This article considers both the influence of relay power and load control period on the load tracking performance in smart grid communication. First, based on regulation errors caused by load control with imperfect channel state information (CSI), the load tracking cost model integrated of load control period and relay power is established in smart grid communication. Then, a coordination mechanism of cost-sharing contract (CSC) is presented. In the CSC, the utility companies select the preferred contractual terms offered by the telecom operator (TO) to reduce their costs and coordinate the whole network system simultaneously. Finally, the theoretical analysis and simulation demonstrate that the simultaneous consideration of the relay power and load control period can reduce the costs of the utility companies, increase the profit of the TO, and improve the social welfare. Besides, the proposed coordination mechanism of CSC can coordinate the whole network system.

This article studies the data collection problem in an Internet-of-Things (IoT) network with multiple unmanned aerial vehicles (UAVs) where UAVs first power multiple IoT devices by wireless power transfer, and then IoT devices utilize the harvested energy to transmit data to UAVs. Different from most of the existing works that often assume the channel between the UAV and the IoT device is a simplified Line-of-Sight (LoS) channel, a more practical and accurate probabilistic LoS channel model is adopted, in which both the elevation angle and the distance between the UAV and the IoT device determine the channel gain. Our objective is to maximize the UAV's minimum data collection rate among all IoT devices by jointly optimizing time allocation and 3-D trajectory of UAVs within a limited time duration. This results in a nonconvex optimization problem, which is challenge to solve. To tackle this difficulty, we transform the nonconvex problem to a difference of convex (D.C.) optimization problem by subtly using several methods. To solve the D.C. optimization problem, an efficient iterative algorithm is designed via a successive convex approximation method. Numerical simulation results are provided to verify the performance of the proposed algorithm compared to two benchmark algorithms, the algorithm with simplified LoS model and that with 2-D trajectory optimization, under various conditions.

In industrial wireless sensor networks (IWSNs), a lot of energy is wasted in the form of electromagnetic radiations. It can be effectively utilized with energy harvesting (EH), which absorbs part of the energy in the transmission signal but reduces the throughput and reliability of IWSNs. In this article, we study the throughput optimization of IWSNs with EH from the interference radio-frequency (RF) signal considering the reliability constraint of the industrial information transmission. Under the premise of limited energy supply of EH relays, the throughput maximization of IWSNs is formulated as a nonconvex optimization problem. In order to transform the nonconvex problem to a convex optimization problem, the successive convex approximation (SCA) approach is adopted. Furthermore, a power allocation algorithm is designed to maximize the total transmission rate of the network. Simulation results demonstrate that the proposed algorithm can maximize the throughput under the primise of SINR reliability.

The fast-growing demand of refueling electric vehicles (EVs) blocks the application and popularization of EVs. Battery swapping provides the EV users with a quick and convenient refueling way. In this article, an aggregative shared battery station (SBS) model is proposed, which is composed of a control center and a group of SBSs. With the SBS, the customers can rent the battery and pay a corresponding fee based on the swapped energy and satisfaction level. In order to enhance the SBS system responsiveness and reconfiguration to meet the changeable customers' battery demand and peak shaving and valley filling task, a two-stage framework for the multi-SBS is designed based on a self-adaptive dispatching strategy. On behalf of the SBS operator, an optimization objective function is established to maximize the operating revenue by optimizing the charging, discharging, and sleeping process of the batteries. Using the genetic algorithm, we perform extensive simulations to validate the optimization model and demonstrate the efficiency of the self-adaptive dispatching strategy. The results suggest that the proposed dispatching strategy is effective for scheduling SBSs to satisfy the EV refueling demand, provide peak shaving and valley filling service, and achieve the revenue maximization.

The mixed traffic flow, which comprises both cooperative automated vehicles (CAVs) and human-driven vehicles, is becoming more common in modern urban areas. CAVs can expand the capabilities such as that can be achieved with automation and vehicular communication individually. However, the energy-saving benefits may be one of the exceptions when three or more vehicles drive in a row under the mixed traffic scenarios. The undesired driving behaviors of human-driven vehicles can introduce a high level of randomness to traffic flow, which results in energy-inefficient driving profiles for CAVs with aggressive operations or even vehicle crashing. In this paper, we investigate an eco-platooning problem for CAVs under the mixed traffic flow. This is a challenging problem due to both of the platoon-wide energy-saving and driving security requirements. To address this problem, an ecological and string stable platooning scheme, called E-CACC, is provided. First, novel spacing policies are presented to enforce that all platoon members track energy-efficient driving profiles. Then, control laws are designed to ensure the tracking performances of the proposed spacing policies. Furthermore, the theoretical proof is provided to prove the platoon string stability of the proposed strategy. Finally, performance evaluation is conducted. Results have illustrated the energy efficiency of the proposed E-CACC scheme.

Recently, the development of Industrial Internet of Things has made the emergence of innovative applications which are usually computation-intensive and latency-critical. In this paper, we study the task offloading in software-defined access network, where the industrial devices and edge computing servers are connected to wireless access points. To meet applications' requirements about latency and computing capacity and realize computational load balancing, we formulate a mixed integer non-linear program problem to minimize the overall cost. First, we propose an algorithm based on convex optimization and matching theory to minimize the overhead. Then, we consider load balancing of edge servers and extend our problem with regard to overhead and load balancing cost. We adopt alternating direction method of multipliers algorithm to solve the extended problem. Finally, simulation results demonstrate the effectiveness and superiority of our proposed algorithm.

The advancements in automation and vehicular communication have enabled the platoon systems. The vehicles in a platoon are dynamically decoupled but constrained by spatial geometry. To coordinate decisions and act cooperatively, information sharing among vehicles is required, which means the platooning problem involves both communication and control issues. We consider a communication resource-aware control problem for platoon systems in this paper. To provide desirable driving performances and flexible communication scheduling opportunities for platoon systems, the distributed model predictive control (DMPC) method and communication trigger mechanism are jointly designed, which yields the communication-aware DMPC (CA-DMPC) algorithm. Simulations have been conducted to demonstrate the satisfactory control performances and significant communication savings.

Traffic flow prediction is one of the core technologies in Intelligent Transportation System (ITS) to improve traffic management. However, in metropolitan circumstances, the complex traffic road networks and numerous unpredictable traffic anomalies are still tough problems, which bring challenges of leveraging topological and anomalies information to accurate traffic flow prediction. In this paper, we propose a Dynamic Hidden Markov Model (DHMM) based on global PageRank algorithm to overcome these challenges. The global PageRank algorithm is more applicable than traditional algorithm for traffic scenarios, through which the PageRank metric is calculated to measure the accumulation of traffic anomalies at intersections. By incorporating the PageRank metric, DHMM leverages topological and anomalies information to dynamically model the traffic variations. Experiments on real-world dataset demonstrate that the PageRank metric can describe the degree of traffic anomalies intuitively, and the proposed model has superior traffic flow prediction performance both under normal and abnormal traffic conditions.

Wireless charging technology provides a solution to the insufficient battery life of electric vehicles (EVs). However, the conflict of interests between wireless charging lanes (WCLs) and EVs is difficult to resolve. This paper proposes a charging scheduling algorithm based on a double-layer game model. In lower layer, the potential game is used to model the multi-vehicle game of vehicle charging planning. A shortest path algorithm based on the three-way greedy strategy is designed to solve in dynamic charging sequence problem, and the improved particle swarm optimization algorithm are used to solve the variable ordered potential game. In the upper layer, the reverse Stackelberg game is adopted to harmonize the cost of wireless charging lanes and electric vehicles. As the leader, WCLs stimulate EVs to carry out reasonable charing action by electricity price regulation. As the follower, EVs make the best charging decisions for a given electricity price. An iteration algorithm is designed to ensure the Nash equilibrium convergence of this game. The simulation results show that the double-layer game model proposed in this paper can effectively help WCLs operations and ensure the high endurance and traveling experience of EVs.

With the development of smart vehicles, computing-intensive tasks are widely and rapidly generated. To alleviate the burden of on-board CPU, connected vehicles can offload tasks to or make request from nearby edge server thanks to the emerging Mobile Edge Computing (MEC). However, such approach may sharply increase the workload of an edge server, and cause network congestion, especially in rural and mountain areas where there are few edge servers. To this end, a UAV-assisted MEC system is proposed in this paper, and joint optimization algorithm of the deployment and resource allocation of UAVs (JOAoDR) is proposed to decide the location and balance the resource and rewards of the UAVs. We solve a long-term profit maximization problem in terms of the operator. Numerical results demonstrated that our algorithm outperforms other benchmarks algorithm, and validated our solution.

In this article, we study an interference management and power allocation problem when electrical power communication (EPC) networks are densely deployed in the coverage of licensed networks. The purpose is to reduce the electricity cost and improve the licensed operator's profit subject to the quality-of-service (QoS) of licensed users (LUs). First, the electricity cost is modeled based on the Taguchi loss function, which links the cost to the communication errors in the EPC networks. The operator's profit is formulated by introducing a bonus-penalty mechanism, and a rational interference threshold (IT) of the licensed base station (LBS) is set to ensure the QoS of the LU. Second, we formulate the interference management and power allocation problem as a Stackelberg game, and a successive convex approximation algorithm is used to solve this problem to achieve the optimal IT and relay power. The simulation results indicate that the cost to the utility company is reduced and the profit of the LBS increases.

Hybrid electric storage system (HESS) is a promising power supply for electric vehicles (EVs) to prolong battery cycling life. Battery longevity is affected by the magnitude and fluctuation of the charging/discharging power profiles. While vehicle driving, unexpected high power demand can cause battery degradation and should be supplied by the supercapacitor (SC) in the HESS. However, the limited capacity of SCs restricts the HESS benefit. Thus, one of the crucial while challenging issues for an HESS is how to effectively manage the power splitting between batteries and SCs to satisfy the vehicle's driving demand as well as reducing battery degradation rate. In this paper, a proactive power management scheme is proposed to extend the EVs battery life with the HESS. First, we exploit a time-series forecasting method to predict the short-term vehicle velocity and calculate the future power demand based on prediction results. Next, due to the nonlinear dynamics of the HESS, the T-S fuzzy modeling method is adopted to approximate system nonlinearity and develop an empirical model. Finally, a model predictive control (MPC) based power management problem is formulated. Prediction errors are considered in MPC formulation to improve system robustness. Based on driving profile tests, simulation results demonstrate that the magnitude and fluctuation of battery current are both reduced and the battery life is prolonged by 17.81% compared with the existing methods.

With the development of smart vehicles and computation-intensive vehicular applications, it is a challenge to maintain high performance for vehicles with scarce local computational resources. Mobile Edge Computing (MEC) is a computing paradigm with high potential to improve vehicular services by offloading computation-intensive tasks to the MEC servers. However, as the computational resources of MEC servers are limited, parking lots (PLs) having abundant idle computational resources should be utilized. We introduce a new computing paradigm, named by Vehicular Parked-Edge Computing (VPEC). We formulate a three-stage contract-stackelberg offloading incentive mechanism to describe this problem. The PLs are classified into different types according to their idle computational resources, and parking lot agent (PLA) offers different contracts to different types of PLs. The optimal problem is designed to maximize the utilities of vehicles, operator and PLA. We use backward induction method to solve this three-stage problem, and give the closed-form expressions of the optimal strategies for each stage. Simulation results demonstrate the feasibility of the proposed incentive mechanism and reveal the changing trend of optimal strategies in each stage when traffic density changes.

In this paper, to optimize the Wireless Charging Lane (WCL) deployment in urban areas, we focus on installation cost reduction while achieving regional balance of energy supply and demand, as well as vehicle continuous operability issues. To explore the characteristics of energy demand, we first analyze the daily trajectory of taxis in different regions and find different fluctuating features of daily energy demand. Then, we establish the WCL power supply model to obtain the wireless charging supply situation in line with the real urban traffic condition, which is the first work considering the influence of traffic lights on charging situation. To ensure minimum deployment cost and to coordinate the contradiction between regional energy supply-demand balance and overall supply-demand matching, we formulate optimization problems ensuring the charge-energy consumption ratio of vehicles. In addition, we rank the priority of WCL efficiency to reduce the complexity of solution and solve the Mixed Integer NonLinear Programming (MINLP) problem to determine deployment plan. Compared with the baseline, the proposed method has significantly improved the effect.

The secure state estimation (SSE) problem is investigated for a kind of power systems where the smart meters' measurements are transmitted to a remote estimator. In this paper, we mainly focus on the transmission via wireless networks. Taking consideration of the possible increase in transmission failure rate due to risk events, such as jamming attacks, a so-called risk-averse transmission path selection (RaTPS) method is proposed to improve SSE robustness. Based on the idea of reinforcement learning, the transmission acknowledgments are applied as the reinforcement signals to reward the source node (smart meter) for choosing more reliable paths. The multipath traffic allocation can adaptively performed according to the transmission failure rate of each path. The theoretical analysis about convergence of RaTPS and SSE is given with the technique of Markov chain, and it is illustrated in the simulation that the robustness of SSE can be improved by using RaTPS.

The frequent stop-and-go operations require high and fast burst driving power, which accelerates the electric vehicle batteries degradation. Hybrid electric storage system (HESS) is a promising solution, which supplements the battery with supercapacitor for rapid charging/discharging. If future power demand is available, effective power management can be done by fully exploiting the HESS benefits. Recent advances in the Internet of Things (IoT) have made the future information prediction practical, since surroundings information is obtainable. In this paper, a proactive energy management strategy is developed for the HESS with the IoT support. By analyzing the traffic data, a probabilistic graphical model, i.e., the conditional linear Gaussian (CLG), is designed for future driving information prediction. Since, the CLG prediction results are probability distributions, a scenario-tree method is developed to approximate the future power demand by sampling the possible future velocity profiles from the results. A stochastic model predictive control problem is established by incorporating the sampled trajectories. A fast dual proximal gradient method is proposed to solve the problem and facilitate real-time implementation. Simulation results demonstrate that the magnitude and fluctuation of the battery discharging power are reduced by 46.4% and 27.7%, respectively, compared with the battery only case.

In this paper, we investigate the secure state estimation (SSE) problem in power systems, where the physical system is measured by meters and mainly focuses on the measurements sent to a remote estimator via wireless networks faced with jamming attacks. Malicious attacks on the transmission paths block the data transmission and deteriorate the performance of estimation. Various works have been proposed to cope with the transmission failure. Few of them have considered the case that a smart attacker could adjust strategies according to the defensive methods with advanced communication techniques. We propose the antijamming game framework for SSE. Under this framework, defensive path selection (DPS) is proposed based on multiagent reinforcement learning to make optimal path selection against the intelligent attacker and improve the transmission performance for SSE. The effectiveness of the proposed method is theoretically proved to improve the robustness of estimation and the capability of DPS is analyzed.

Emergency information dissemination is the most important application of Vehicular Ad-hoc Networks (VANETs). Its performance is affected by transmission mechanisms and traffic conditions. There are two typical transmission mechanisms, i.e., Internet Protocol (IP) and Information- Centric Networking (ICN). How to integrate these two mechanisms in order for timely dissemination in different traffic conditions is a critical problem. To solve this problem, in this paper, we propose a traffic-related mission-critical transmission mechanism, which can adaptively select the proper transmission mechanism according to real-time traffic conditions. First, we find the relationship between the performance of transmission mechanisms and traffic conditions, and then provide its mathematical model. Then, the traffic-related transmission algorithm is designed to achieve an adaptive switching of transmission mechanisms, in which a positive utility gain is guaranteed considering the switch benefit and cost. Lastly, we conduct extensive simulations to demonstrate the effectiveness of the proposed algorithm using SUMO and NS-3. It shows that the transmission delay is decreased by 88.2% over the IP mechanism and 37.6% over the ICN mechanism.

The wide application of Internet of Things (IoT) in industrial automation encourages the emergence of a new paradigm of industrial IoT systems, wireless control system (WCS), where the system and/or control information is delivered over wireless channels. In practical systems, WCSs would consist of multiple control-loops in general, the resource competition among which would seriously increase mutual interferences and transmission collisions, making it is difficult to provide the required transmission reliability for the control strategy. To address this issue, we design the control strategy together with the hybrid cooperative transmission scheme for multiloop WCSs in a proactive way. We first define the overall system cost function to explore the impacts of standard linear quadratic regulator control cost and wireless transmission reliability on the control performance. In order to further minimize the overall system cost while guaranteeing the control stability, we then propose a control performance aware cooperative transmission scheme, which is formulated as a constrained optimization problem. Decomposition method and heuristic algorithms are designed based on the feature of network structure to solve the formulated mixed integer nonlinear programming problem efficiently. Finally, simulation results demonstrate that by using the proposed strategy, the overall system cost is significantly reduced, decreasing by 78% and 82% compared to the cases without considerations of system dynamics and without cooperative transmission, respectively.

This paper investigates the resource allocation problem in orthogonal frequency division multiple access multi-user networks, where subcarriers are grouped into chunks due to simplicity of implementation. The aim is to achieve max-min fairness among users by adjusting the transmission power allocation and chunk allocation while taking into account several important constrains. The problem is formulated as a mixed integer nonlinear programming problem, whose optimal solution is extremely hard to find. Then a low complexity suboptimal algorithm is proposed, which solves the chunk allocation and power allocation in two steps separately. A fast optimal power allocation algorithm is designed by exploiting the special structure of the problem. Simulations verify the performance of the proposed algorithm in terms of the users' minimal transmission rate and running time comparing with benchmark algorithms.

In an increasingly dense and heterogeneous wireless network with various access points, the users are likely to lie in the overlapping coverage areas of multiple radio access technologies, which motivates the boost of user throughput and quality of service via small cell dual-connectivity. In this paper, with the objective of improving network throughput and considering fairness among users, we formulate a small cell selection problem to maximize the network utility reflecting proportional fairness, which is actually the sum of the logarithm of long-term rate of users. However, the formulated problem turns out to be non-convex and combinatorial, and is difficult to be transformed into a convex problem and traditional game-theoretic methods cannot be used. In this context, we introduce a many-to-one matching game with externalities, and develop a distributed algorithm that converges to a stable matching. To further enhance network throughput by mitigating co- channel interference among cellular small cells, a joint cell selection and power control algorithm is developed by adopting an iterative approach to determine them separately and sequentially. Lastly, compared with the nearest distance-based cell selection scheme and the cell selection scheme maximizing the total long-term rate of users, numerical results show the convergence of the matching-based cell selection algorithm and the joint cell selection and power control algorithm, as well as their significant improvement on both total long-term rate of users and user fairness.

Mobile crowdsensing has become a novel and promising paradigm in collecting, analyzing, and exploiting massive amounts of data. However, the issue of data quality has not been carefully addressed. Low quality data contributions undermine the effectiveness and prospects of crowdsensing, and thus motivate the need for approaches to guarantee the high quality of the contributed data. In this paper, we integrate quality estimation and monetary incentive, and propose a quality-based truth estimation and surplus sharing method for crowdsensing. Specifically, we design an unsupervised learning approach to quantify the users' data qualities and long-term reputations, and exploit an outlier detection technique to filter out anomalous data items. Furthermore, we model the process of surplus sharing as a co-operative game, and propose a Shapley value-based method to determine each user's payment. We have conducted a real crowdsensing experiment and a large-scale simulation to evaluate our method. The evaluation results show that our approach achieves good performance in terms of both quality estimation and surplus sharing.

Traditional compressive sensing (CS) methods assume the data sparsity to be constant over time, which holds well in many long‐term scenarios. However, the authors’ recent study on electrocardiogram (ECG) monitoring reveals that data sparsity varies dramatically for real‐time monitoring systems where the data latency must be bounded, due to limited data collected within the delay bound. The variation of data sparsity makes the reconstruction error (RE) unstable. Furthermore, the variation of wireless channel quality also impacts the reconstruction quality. To accommodate both variations, this study proposes a novel adaptive feedback architecture for real‐time wireless ECG monitoring based on the CS technique, which can bound the REs in the presence of the variations of data sparsity and wireless channel. An experiment testbed has been built to evaluate the performance of the proposed system. The results show that the data latency can be limited to <300 ms and the RE can be controlled to 9%.

Time synchronization and localization are basic services in a sensor network system. Although they often depend on each other, they are usually tackled independently. In this work, we investigate the time synchronization and localization problems in underwater sensor networks, where more challenges are introduced because of the unique characteristics of the water environment. These challenges include long propagation delay and transmission delay, low bandwidth, energy constraint, mobility, etc. We propose a joint solution for localization and time synchronization, in which the stratification effect of underwater medium is considered, so that the bias in the range estimates caused by assuming sound waves travel in straight lines in water environments is compensated. By combining time synchronization and localization, the accuracy of both are improved jointly. Additionally, an advanced tracking algorithm interactive multiple model (IMM) is adopted to improve the accuracy of localization in the mobile case. Furthermore, by combining both services, the number of required exchanged messages is significantly reduced, which saves on energy consumption. Simulation results show that both services are improved and benefit from this scheme.

Severe pollution induced by traditional fossil fuels arouses great attention on the usage of plug-in electric vehicles (PEVs) and renewable energy. However, large-scale penetration of PEVs combined with other kinds of appliances tends to cause excessive or even disastrous burden on the power grid, especially during peak hours. This paper focuses on the scheduling of PEVs charging process among different charging stations and each station can be supplied by both renewable energy generators and a distribution network. The distribution network also powers some uncontrollable loads. In order to minimize the on-grid energy cost with local renewable energy and non-ideal storage while avoiding the overload risk of the distribution network, an online algorithm consisting of scheduling the charging of PEVs and energy management of charging stations is developed based on Lyapunov optimization and Lagrange dual decomposition techniques. The algorithm can satisfy the random charging requests from PEVs with provable performance. Simulation results with real data demonstrate that the proposed algorithm can decrease the time-average cost of stations while avoiding overload in the distribution network in the presence of random uncontrollable loads.

Nowadays most metro advertising systems schedule advertising slots on digital advertising screens to achieve the maximum exposure to passengers by exploring passenger demand models. However, our empirical results show that these passenger demand models experience uncertainty at fine temporal granularity (e.g., per min). As a result, for fine-grained advertisements (shorter than one minute), a scheduling based on these demand models cannot achieve the maximum advertisement exposure. To address this issue, we propose an online advertising approach, called EveryoneCounts, based on an uncertain passenger demand model. It combines coarse-grained statistical demand modeling and fine-grained Bayesian demand modeling by leveraging realtime card-swiping records along with both passenger mobility patterns and travel periods within metro systems. Based on this uncertain demand model, it schedules advertising time online based on robust receding horizon control to maximize the advertisement exposure. We evaluate the proposed approach based on an one-month sample from our 530 GB real-world metro fare dataset with 16 million cards. The results show that our approach provides a 61.5% lower traffic prediction error and 20% improvement on advertising efficiency on average.

In this paper, we investigate the resource allocation for orthogonal frequency division multiple access relay networks, where the relay does not have embedded energy supply and needs to first harvest energy from the received signals from the source before forwarding transmission. The relay uses time switching scheme for wireless information and power transfer. We aim to maximize the weighted sum rate under several constraints by varying the source transmission power, the relay transmission power, and the time switching ratio. We formulate the joint resource allocation problem as an optimization problem, which is non-convex. Although it is difficult to solve the non-convex problem, we derive its closed-form solution by exploiting its special structure. We also prove that the closed- form solution is a partial optimum. Finally, simulations verify the proposed closed-form solution is superior to the equal power solution.

Participatory sensing has become a novel and promising paradigm in environmental data collection. However, the issue of data quality has not been carefully addressed. Low quality data contributions may undermine the effectiveness and prospects of participatory sensing, and thus motivates the need for approaches to guarantee the high quality of the contributed data. In this paper, we integrate quality estimation and monetary incentive, and propose a quality-based surplus sharing method for participatory sensing. Specifically, we design an unsupervised learning approach to quantify the users' data qualities and long-term reputations, and exploit an outlier detection technique to filter out anomalous data items. Furthermore, we model the process of surplus sharing as a cooperative game, and propose a Shapley value-based method to determine each user's payment. We have conducted a participatory sensing experiment, and the experiment results show that our approach achieves good performance in terms of both quality estimation and surplus sharing.

With the popularity of electric vehicles, numerous cities have adopted electric vehicles as a part of taxis system. Compared with traditional fuel taxis, electric taxis (ETs) have to rely on charging stations (CSs) to charge frequently, so that it is possible to use charging behavior to control the actions of ETs. This paper considers the problem of optimizing dispatch of electric taxis and charging stations' prices making. Specifically, based on the electricity price control strategy, electric taxis are guided to suitable charing stations deliberately to match a desired dispatch which could improve service quality or operating efficiency of taxis system. In this paper, a Stackelberg (leader-followers) game model is proposed to describe the optimal dispatch and price-making problems. The existence of Nash equilibrium of this game is analyzed, and a low computational complexity algorithm that is suitable for large scale problem is designed to solve this game. In addition, a practical situation is simulated and the impacts of several parameters are presented.

This paper considers multiaccess control for the uplink in orthogonal frequency division multiple access wireless networks. To avoid the extensive information exchange associated with centralized approaches, we formulate the decentralized access control problem with the contention power constraint as a Bayesian game, mapping time-varying channel state information into contention strategies. By exploiting the problem structure, a strategy where users access the channels with probability one if the observed channel gain is above a predetermined threshold is shown to be optimal. It is also shown that the energy consumption of the threshold strategy will not exceed that of randomized strategies. The game is then equivalently reformulated as one of finding the threshold value in a distributed manner, and the existence and uniqueness of Bayesian Nash equilibria is established. A distributed algorithm based on Lagrange duality is proposed to approach the unique equilibrium, and the algorithm is shown to be globally stable. In a homogeneous system, the performance loss of the proposed scheme is proved to be bounded compared with a centralized channel allocation scheme. Contrary to other proposals, our method allows for heterogeneous channel state information and achieves a comparable throughput with reduced power. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract Cognitive radio (CR) networks comprise a number of spectrum agile nodes with the capability of spectrum detection. Applying techniques of spectrum sharing in CR networks can achieve the efficient utilization of network resources. Usually, data rates of user sessions are time varied because of the dynamic behaviors of CR networks. It is expected that the occurrence of link outage should be avoided and incorporated into the routing design under conditions of increasingly crowded spectrum. This paper proposes an integral framework, which considers these two correlated schemes (resource reconfiguration and robust routing) simultaneously. For that, the resource reconfiguration scheme is developed for the efficient usage of network resources and aims at reducing the occupancy of licensed bands. The link outage, resulting from random session rate, is confined within an acceptable range by using strategy of virtual ‘network portfolio’. A robust optimization approach is proposed to guarantee reliable data transmission among possible interfering links. Both these two items (resource reconfiguration and robust routing) are formulated in a framework of cross‐layer optimization. The evolutionary process of CR network states is provided in simulations, where the results show that the joint design proposal can achieve the least interferences among different licensed users while realizing robust routing. Copyright © 2013 John Wiley & Sons, Ltd.

It has been proved that the adoption of traffic sensing data can reduce traffic jam, and improve traffic volume. However, traffic sensing by both vehicles and road monitoring infrastructures faces the problem of data missing on dimensions of time and space, which makes data reconstruction a challenge for full-time and wide-area traffic sensing. Exploiting the hidden structure of the traffic data, we raise a tensor-completion-based algorithm, HaTTC, to tackle the problem in this paper. We testify the high efficiency of the algorithm based on highway traffic data from static sensors. Employing our algorithm, we achieve full-time urban traffic sensing on some road segments of Shanghai via a probe-vehicle-based Vehicular Sensor Network (VSN) system.

We address the problem of subchannel and transmission power allocation in orthogonal frequency division multiple access relay networks with an aim to maximize the sum rate and maintain proportional rate fairness among users. Because the formulated problem is a mixed-integer nonlinear optimization problem with an extremely high computational complexity, we propose a low-complexity suboptimal algorithm, which is a two-step separated subchannel and power allocation algorithm. In the first step, subchannels are allocated to each user, whereas in the second step, the optimal power allocation is carried out on the basis of the given subchannel allocation and the nonlinear interval Gauss–Seidel method. Simulation results have demonstrated that the proposed algorithm can achieve a good trade-off between the efficiency and the fairness compared with two other existing relevant algorithms. In particular, the proposed algorithm can always achieve 100% fairness under various conditions. Copyright © 2012 John Wiley & Sons, Ltd.

Traffic information is important for drivers and the traffic monitoring center (TMC) to avoid traffic congestions. VANET based systems use probe vehicles (PVs) to sense and upload the traffic information. However, due to the uneven distribution of the PVs, only a small part of the real-time traffic data can be gathered. Also, it is not efficient to estimate the traffic conditions at TMC and then publish to vehicles. We consider a service oriented algorithm for both PVs and TMC to estimate the missing traffic conditions, and propose a Matrix Completion (MC) based algorithm, HaTTEM, to estimate the missing traffic data in the traffic condition matrix (TCM). Temporal continuity and the bounds of the traffic data are introduced to reduce the error of estimation. To reduce the computational time, we propose the L0.5-based Iterative MC Algorithm so that the TCM can be fast estimated by the PVs and TMC. The simulations with real world data show the effectiveness and efficiency of HaTTEM even when the PVs can only sense 20% of the traffic data.

Despite the fact that wireless sensor networks (WSNs) have been applied to structural health monitoring (SHM) systems of civil infrastructure, the reliable data transmission is very challenging for structures far away from data center due to long transmission distance. In this paper, we present a novel architecture that high-speed train takes the role of a mobile sink to assist the data collection. In order to guarantee the recovery of monitoring data with high probability under unreliable transmission, a new data packing and reconstruction method called PackTrix is then proposed with Matrix Completion technique. It is proved that the proposed PackTrix algorithm is one of the optimal packing methods rendering the Matrix Completion technique effectiveness for data reconstruction. Theoretical analyses as well as simulations with real world data show that PackTrix can recover lost data with low relative error based on only very small percents of the original data.

An Orthogonal Frequency Division Multiple Access (OFDMA) downlink system with secure transmissions and delay constraints is investigated, in which a base station (BS) transmits both open data with delay limitations and private data with secrecy demands to each user. The time-varying channel is modeled as slow-fading and all channel state information (CSI) is assumed to be known to BS. An online cross-layer scheduling algorithm composed of flow control and resource allocation is proposed in this paper to maximize the downlink throughput with delay and power constraint. Furthermore, the algorithm makes decisions on current CSI instead of channel statistics. In addition, virtual queues of delay and power are constructed to track them so that those time-average constraints are fulfilled. In the end, it is proven by means of Lyapunov optimization technique that our algorithms will obtain a performance which can be extremely close to optimality and reduce operation complexity significantly.

This paper is concerned with the problem of filter design for target tracking over sensor networks. Different from most existing works on sensor networks, we consider the heterogeneous sensor networks with two types of sensors different on processing abilities (denoted as type-I and type-II sensors, respectively). However, questions of how to deal with the heterogeneity of sensors and how to design a filter for target tracking over such kind of networks remain largely unexplored.We propose in this paper a novel distributed consensus filter to solve the target tracking problem. Two criteria, namely, unbiasedness and optimality, are imposed for the filter design. The so-called sequential design scheme is then presented to tackle the heterogeneity of sensors. The minimum principle of Pontryagin is adopted for type-I sensors to optimize the estimation errors. As for type-II sensors, the Lagrange multiplier method coupled with the generalized inverse of matrices is then used for filter optimization. Furthermore, it is proven that convergence property is guaranteed for the proposed consensus filter in the presence of process and measurement noise. Simulation results have validated the performance of the proposed filter. It is also demonstrated that the heterogeneous sensor networks with the proposed filter outperform the homogenous counterparts in light of reduction in the network cost, with slight degradation of estimation performance.

In this paper, we study the power allocation strategy in a drive-thru scenario, where an access point (AP) is installed along the highway to provide Internet services to vehicles within its coverage range. We consider single-hop vehicle-to-roadside (V2R) communications for a vehicle that aims to upload data within the coverage range of the AP, where the bandwidth allocated to it is time-varying, and the size of the data is known upon it enters the area. The data bits received over a time slot are correctly received if the instantaneous channel capacity rtis greater than or equal to a threshold Rt, and corrupted otherwise. The vehicle has to pay an amount for data transmission according to the power consumption at each time slot whether the data bits are correctly received or not. The target is to complete the transmission of the traffic demand volume with the minimal cost. First, we consider the optimal power allocation strategy with a single AP and random vehicular traffic arrivals. We formulate it as a finite-horizon sequential power allocation problem. Then we solve the problem using dynamic programming and find the optimal power allocation strategy. The proof of the existing of the optimal value of the cost-to-go function is given after. Simulation results show that our proposed strategy achieves less cost than another heuristic strategy. The impacts of different traffic demand volumes, traffic densities, and outage probabilities on total cost are also analyzed.

Collaborative spectrum sensing has been proposed recently to improve the sensing performance in Cognitive Radio networks. However, cooperative sensing will also introduce extra cost to the collaborator, such as the cooperative time and energy consumption. In reality, whether the rational secondary users have incentive to join the collaboration depends upon whether the benefit of the collaboration could outweigh the cost. In this paper, we model it as the Cooperative Spectrum Sensing Game (CSSG). In this game, every secondary user could choose to collaborate or not in each time slot, and the payoff is measured in terms of data throughput. Since the effectiveness of collaboration is proportional to the number of the collaborators, secondary users' decisions are based on how many users will choose to collaborate. Thus, CSSG could be modeled as the classic game: the Stag Hunt Game. In addition, to avoid the cooperation failure, we propose Cooperative Communication Incentive Scheme (CCIS) to enhance the collaborative sensing. At last, the numerical analysis about CSSG as well as the proposed scheme CCIS is given.

Collaborative spectrum sensing has been proposed recently to facilitate precise detection of Primary Users in Cognitive Radio networks. However, it simultaneously introduces new security issue that the selfish or even misbehaving users could cheat a secondary user by depriving its access opportunity. To address this problem, we propose a novel User-centric Misbehavior Detection Scheme (UMDS) in this paper to detect malicious behaviors in collaborative spectrum sensing. The basic idea of UMDS is motivated by the fact that a mobile user tends to trust the sensing report generated by itself rather than the reports from other nodes. Therefore, a secondary user could independently determine if a sensing partner is malicious or not by calculating the correlation between the secondary user's own reports and those of other sensing nodes. We also discuss how to further improve the performance of the UMDS by choosing an optimized threshold. The effectiveness and efficiency of the proposed scheme is demonstrated by extensive analysis and numerical results.

This paper considers multiaccess control for the uplink in orthogonal-frequency-division-multiple-access (OFDMA) wireless networks. To avoid extensive information exchange with the access point in centralized approaches, we propose a distributed threshold-based scheme, where each user accesses multiple channels simultaneously based on a comparison between measured channel gains and a channel gain threshold. Each user will adapts its channel gain threshold based on local measurements of collision on each channel and the energy consumption for channel contention. The problem is formulated as a constrained non-cooperative game. We show existence and uniqueness of the Nash equilibrium. A gradient-based algorithm is proposed to update the channel gain threshold. Furthermore, the convergence of this algorithm is proved. In addition, for heterogeneous systems, our proposed scheme can maintain multiuser diversity gains considering the time-varying channel gain and energy consumption. Compared with peer distributed OFDMA schemes and random channel selection algorithms, our proposed schemes reduce overhead and achieve a higher throughput.

In this paper, we study the theoretical problem of the end-to-end rate assignment for multi-hop wireless networks. Specifically, we consider the problem of joint congestion control, random access and power control design with multi-hop transmissions and interference-limited link rates. In order to address both the end-to-end throughput maximization and energy efficiency, we formulate this problem into a cross-layer design problem under a realistic interference-based communication model, which captures the attainable link capacity in practice. There are primarily three challenges in this design: 1) how to formulate the cross-layer design; 2) how to solve the non- convex and non-separable problem efficiently; more importantly 3) under a reasonably complexity, how to design a distributed algorithm that can realize this formulation while maintaining the architectural modularity among different layers. First, we propose a novel method that can convert a non- convex and non-separable programming into an equivalent convex programming problem. The problem is solved by a dual decomposition technique. We show that the resulting algorithm can be practically realized. We then design a distributed algorithm that jointly considers random access and power control to adapt for the transport layer congestion status. Simulation results confirm that the proposed algorithm can achieve close to the global optimum within reasonable convergence times.

We consider the distributed random access algorithms for wireless ad hoc networks in which each node needs to tune its persistent probability so as to optimize its own the total throughput. First, we present an asynchronous algorithm for updating persistent probabilities and prices to avoid collision using local coordination. By casting this algorithm as a best response in a cooperative game, we characterize its convergence analytically. We further model that each node attempts to maximize a selfish local payoff function. We characterize the Nash equilibrium (NE) of the non-cooperative game and prove the convergence of a best response algorithm to the unique NE. Then we study the energy efficient throughput maximization problem when the wireless nodes are constrained by their battery power. Despite the inherent difficulty of non-separability of the constraint set, we propose a distributed primal-based algorithm. Its convergence is studied numerically

In this paper we consider a dual-gradient optimization flow control scheme. In an earlier work it was shown that such algorithms converge in a delay free case. We present the sufficient condition under which the stability can be global focusing on the scenario of a single flow and bottleneck link with delay. We first show that this synchronous algorithm is convergent in general network topology without delay. Then we provide a result that even with delays, the queue length increasing at the router is bounded. The upper bound grows with increase in the number of flows as well as the maximum source sending rate and the maximum round trip delay. The upper bound decreases as the link departing rate and stepsize increase.