Underwater image enhancement (UIE) aims to address image degradation caused by water absorption and scattering effects. Despite significant progress in deep learning-based UIE methods, existing approaches still face key challenges due to the neglect of physical imaging principle. Moreover, while current Mamba models achieve global modeling via multi-directional scanning, their local sequential strategy lacks sufficient global context. To this end, we propose a novel Physical Model-Guided Global Mamba (PGMamba) that combines the efficient sequential modeling capability of Mamba with underwater imaging physical model. Specifically, we first design a Spatial-Aware Global Mamba (SAGMamba) that achieves efficient long-range dependency modeling through a spatial-aware ranking strategy with global context information. Second, we develop a Physical Model-Guided Feed-Forward Network (PMGFFN) that explicitly incorporates underwater optical imaging principles into the network architecture. Extensive experimental results and comprehensive ablation studies demonstrate the outstanding performance and importance of our proposed method.

Cross-domain sequential recommendation (CDSR) aims to utilize users' interactions across multiple domains to alleviate the problem of interaction sparsity that is prevalent in web platforms, thereby providing more accurate personalized recommendations. Although current CDSR methods have made some progress, they suffer from two main limitations: (i) assuming uniformly distributed interactions over time; and (ii) neglecting temporal influences during cross-domain transfer. In order to address the above issues, we propose a novel Time-Aware Cross-Domain Sequential Recommendation framework (TA-CDSR ). First, we design a time-sensitive attention which captures user preferences over time by decoupling interaction sequences and time sequences. Second, we propose a time-guided preference generator that can reconstruct the lacking interactions in the target domain by taking the source domain interactions time as guidance information. Finally, we design a multi-scale time windows based domain transfer module, which can dynamically identify the temporal interaction density and thus adaptively assign the weights of cross-domain information. Extensive experiments on three real-world datasets indicate that TA-CDSR achieves competitive time complexity while outperforming other baselines.

In recent years, social recommendation systems have emerged as a pivotal technology for enhancing recommendation accuracy by leveraging user social homophily and influence. Although many works have been devoted to this area, existing works still struggle to extract the beneficial structural information from social relationships that is beneficial for recommendations and neglect the inherent popularity bias in the social networks, which leads to suboptimal recommendation performances. To address these challenges, we propose a novel framework termed Causal Disentanglement-Enhanced Diffusion Denoising for Social Recommendation (CaDDiSR). This framework first employs causal graphs to disentangle the complexities of social relationships, generating user representations with high-order structures, which are subsequently used as inputs to a diffusion process to effectively denoise social networks and retain social signals beneficial for recommendation tasks. Furthermore, the framework integrates a bidirectional knowledge distillation mechanism, which balances user representations between social and recommendation contexts, thereby facilitating the effective fusion of their respective advantages while simultaneously mitigating noise interference and enhancing overall system performance. Finally, cross-domain contrastive learning is utilized to optimize user and item representations, ensuring consistency in recommendation performance across diverse scenarios. Experimental results on multiple real-world datasets demonstrate that CaDDiSR significantly outperforms existing baseline models, substantiating its superior performance.

The adoption of federated learning (FL) in industrial IoT (IIoT) facilitates the deployment of field-level industrial intelligence by multi-node collaborative and distributed learning. Numerous studies on FL primarily concentrate on enhancing model accuracy under non-independent and identically distributed data. Nevertheless, this focus is inadequate for time-critical industrial systems, as these systems necessitate real-time processing during the FL model training phase and any strategy that prioritizes incremental accuracy gains at the expense of latency risks violating real-time deadlines. However, the system heterogeneity of computing and communication capabilities will impose a formidable bottleneck to the overall time consumed for FL model training. In this paper, we present a FL-enabled Time-Sensitive IIoT (FETI) framework that integrates FL with Time-Sensitive Networking (TSN) to support the deterministic forwarding of FL flows in industry. Aiming to speed up FL convergence within a targeted accuracy gap, we formulate a heterogeneity-aware FL-TSN joint optimization problem, which is theoretically transformed into a stochastic mixed- integer programming problem solved at each FL round. To address this problem, we propose a hierarchical reinforcement learning-based scheduling scheme, called HierTFL, with two interacting layers of policies. With the assistance of a proposed spatial-temporal state encoder, the high-level policy dynamically selects client participants based on data quality and resource availability in each FL round, while the low-level policy optimizes TSN flow scheduling of each selected client using non-cumulative Bellman updates. Experimental results under industrial monitoring datasets have shown the effectivity of HierTFL in achieving a balanced trade-off between model precision and convergence time compared to existing benchmarks.

Low Earth Orbit (LEO) satellite networks hold great promise in the field of wireless communication due to their global coverage. However, the long communication distances and massive data computations present significant challenges for current satellite networks. To overcome these barriers, we propose SkyLink, a universal Integrated Ground-Air-Space Collaborative Edge Computing system that leverages horizontal collaboration among aerial platforms (AirXs) as well as vertical collaboration among Ground-Air-Space. We propose a bi-level optimization framework based on a Multi-Agent Twin Delayed Deep Deterministic policy gradient (MATD3) with Hybrid Action Space and constructe a latent representation space for each agent to allow the agent to learn the latent policy. This enabling each AirX to act as an agent and autonomously optimize its hybrid action decisions to improve system efficiency in real-time based on the dynamic network environment, a capability not achievable by conventional DRL methods. This includes continuous optimization variables such as AirX deployment (location changes) and resource allocation, as well as discrete optimization variables for collaborative task offloading decisions. Extensive experiments against state-of-the-art algorithms (e.g., MADDPG, QMIX) demonstrate that the proposed system improves energy efficiency by 27.2% and task completion rate by 6.8% compared to traditional Integrated Ground-Air-Space (IG) Network.

Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite its benefits, FFT on resource-constrained clients relies on the high computational and memory demands of full-model fine-tuning, which limits the potential advancement. This paper presents FedSODA, a resource-efficient FFT framework that enables clients to adapt LLMs without accessing or storing the full model. Specifically, we first propose a similarity group pruning (SGP) module, which prunes redundant layers from the full LLM while retaining the most critical layers to preserve the model performance. Moreover, we introduce an orchestrated distillation alignment (ODA) module to reduce gradient divergence between the sub-LLM and the full LLM during FFT. Through the use of the QLoRA, clients only need to deploy quantized sub-LLMs and fine-tune lightweight adapters, significantly reducing local resource requirements. We conduct extensive experiments on three open-source LLMs across a variety of downstream tasks. The experimental results demonstrate that FedSODA reduces communication overhead by an average of 70.6%, decreases storage usage by 75.6%, and improves task accuracy by 3.1%, making it highly suitable for practical FFT applications under resource constraints.

The growing demand for intelligent mobile applications has made the deployment and operation of Deep Neural Networks (DNNs) on mobile Edge Devices (EDs) increasingly essential. However, the limited computational resources of EDs often result in significant energy consumption and compromised inference quality. To address these challenges, we propose a Partitioned Collaborative Inference (PCI) system that reduces on-device model inference costs by distributing the inference process across multiple EDs and MEC servers. To dynamically model the relationships between computing nodes, inference tasks, and resources, we employ Graph Neural Networks to construct the current state representation of the system. Furthermore, we develop a Cross-Entropy Method (CEM) based Evolutionary Reinforcement Learning algorithm, which leverages negative temporal difference (TD) error as a population fitness metric to generate elite individuals. The elite produces high-quality samples to improve learning efficiency, thereby obtaining optimal partitioned collaborative inference decisions and resource allocation in highly dynamic and complex search spaces. Extensive simulations demonstrate that the proposed approach significantly outperforms existing methods and benchmark schemes, achieving a 57. 5% increase in the inference task completion rate and a 65.7% reduction in system costs.

Present Advanced Driving Assistance System (ADAS) responds to the dangerous crossing of pedestrians after the occurrence of the incident, occasionally causing severe accidents due to the stringent response window. Inference of pedestrian crossing intention may help vehicles operate in advance and enhance the safety of the vehicle by predicting the crossing probability. Recent studies usually ignore the demand of real-time forecast that required in the realistic driving scenario, and mainly focus on improving the model representation capacity on public datasets by increasing modality and observation time. Consequently, a new framework named EfficientPIE is proposed to predict the pedestrian crossing intention in real time with sole observation of the incident. To achieve reliable predictions, we propose incremental learning based on intention domain to relieve forgetting and promote performance with a progressive perturbation method. Our EfficientPIE outperforms all the SOTA models on two datasets PIE and JAAD, running nearly 7.4x faster than the previously fastest model. Our code is available at https://github.com/heinideyibadiaole/EfficientPIE.

Large Language Models (LLMs) have attracted significant attention in recommender systems for their excellent world knowledge capabilities. However, existing methods that rely on Euclidean space struggle to capture the rich hierarchical information inherent in textual and semantic data, which is essential for capturing user preferences. The geometric properties of hyperbolic space offer a promising solution to address this issue. Nevertheless, integrating LLMs-based methods with hyperbolic space to effectively extract and incorporate diverse hierarchical information is non-trivial. To this end, we propose a model-agnostic framework, named HyperLLM, which extracts and integrates hierarchical information from both structural and semantic perspectives. Structurally, HyperLLM uses LLMs to generate multi-level classification tags with hierarchical parent-child relationships for each item. Then, tag-item and user-item interactions are jointly learned and aligned through contrastive learning, thereby providing the model with clear hierarchical information. Semantically, HyperLLM introduces a novel meta-optimized strategy to extract hierarchical information from semantic embeddings and bridge the gap between the semantic and collaborative spaces for seamless integration. Extensive experiments show that HyperLLM significantly outperforms recommender systems based on hyperbolic space and LLMs, achieving performance improvements of over 40%. Furthermore, HyperLLM not only improves recommender performance but also enhances training stability, highlighting the critical role of hierarchical information in recommender systems.

Personalized federated learning (PFL) addresses the challenge of data heterogeneity across clients. However, existing efforts often struggle to balance model personalization and generalization under Non-IID data scenarios. This paper proposes uFedMBA, a novel PFL framework that decouples neural network parameters into global base-layer parameters and client-specific personalized-layer parameters. On the client side, uFedMBA adds a penalty term with base-layer parameters into the local loss function to prevent overfitting to local data and integrates the historical model into personalized-layer parameters for accelerating convergence. The server employs layer-wise aggregation based on gradient alignment to adaptively aggregate personalized layers, enhancing compatibility across heterogeneous clients. Extensive experiments demonstrate that the uFedMBA achieves state-of-the-art results on four image classification datasets. Code is available at: https://github.com/yjzhai-cs/uFedMBA.

The utilization of federated learning (FL) has witnessed notable advancements in the domain of edge computing (EC). However, limited edge resources and heterogeneous devices restrict the accelerated training of the FL model. To address this issue, we introduce the biological evolutionary mechanism and momentum gradient descent (MGD) update approach into FL, called the EMAFL scheme, aiming to achieve accelerated model training and maximize resource utilization, simultaneously. Specifically, we first update the local model with particle swarm optimization (PSO) for each device and perform MGD on the updated local model. Next, by a toy example, we illustrate the necessity of adopting the different number of local iterations for heterogeneous devices in a resource-limited environment. Analytical convergence of the EMAFL scheme, premised on a delineated resource budget is subsequently explored. This yields a mathematical delineation correlating the quantity of local iterations for heterogeneous devices with the optimal model parameters. Predicated on the prior theoretical examinations, an adaptive control algorithm is devised to ascertain the local iteration count pertinent to each device following every communication round. Finally, through a lot of experiments compared with the benchmarks, the advantages of EMAFL in model accuracy, resource consumption, and Non-IID issues are verified.

Social recommendation (SocialRS), which utilizes user social information to improve recommendation performance, has received increasing attention. Graph neural networks (GNNs) facilitate the integration of both user preference and social features in SocialRS. However, existing techniques face two challenges: 1) the inherent sparse supervision signals and noise issues in real-world social networks; 2) current social recommendation methods suffer from the neglect of user preference and social attribute heterogeneity, which hinders the extraction of preference-related information from social networks. Taking inspiration from social enhancement and contrastive learning methods, we propose a social recommendation model DSVC based on dual social view contrastive learning. Specifically, in response to the first challenge, our model derives the consistency factors of users in different augmented social views, which are used to highlight noise-resistant users and jettison preference-independent social relationships in social views. To address the second challenge, we adopt probability vectors generated from consistency factors. These vectors guide the cross-view augmentation process of the interaction graph, which helps supplement social self-supervised signals and effectively avoid noise retained due to indiscriminate augmentation. The baseline model comparison experiment, ablation experiment, parameter adjustment experiment and robustness experiment conducted on three different real-world datasets consistently validated the effectiveness of our model in improving recommendation performance.

Compared with synchronous federated learning (FL), asynchronous FL (AFL) has attracted more and more attention in edge computing (EC) fields because of its strong adaptability to heterogeneous application scenarios. However, the non-independent and identically distributed (Non-IID) data across devices and the staleness-aware estimation of unreliable wireless connections and limited edge resources make it much more difficult to achieve better AFL-related applications. To handle this problem, we propose anAdaptiveStaleness-awareMomentumAcceleratedAFL(ASMAFL) algorithm to reduce the resources consumption of heterogeneous wireless communication EC (WCEC) scenarios, as well as decrease the negative impact of Non-IID data for model training. Specifically, we first introduce the staleness-aware parameter and a unified momentum gradient descent (GD) framework to reformulate AFL. Then, we establish global convergence properties of AFL, derive an upper bound on AFL convergence rate, and find that the bound is related to the staleness-aware parameter and Non-IIDness. Next, we formulate the bound into a minimization problem of resource consumption under given model accuracy, and the corresponding staleness-aware parameter of devices will be recomputed after each asynchronous aggregation to eliminate the differences of local models’ contribution to global model aggregation. Finally, extensive experiments are carried out to validate the superiority of ASMAFL in model accuracy, convergence rate, resources consumption, Non-IID issue, etc.

The emerging federated learning enables distributed autonomous vehicles to train equipped deep learning models collaboratively without exposing their raw data, providing great potential for utilizing explosively growing autonomous driving data. However, considering the complicated traffic environments and driving scenarios, deploying federated learning for autonomous vehicles is inevitably challenged by non-independent and identically distributed (Non-IID) data of vehicles, which may lead to failed convergence and low training accuracy. In this paper, we propose a novel hierarchically Federated Region-learning framework of Autonomous Vehicles (FedRAV) that adaptively divides a large area containing vehicles into sub-regions based on the defined region-wise distance, and achieves personalized vehicular models and regional models. Specifically, the architecture employs a designated hypernetwork to learn personalized mask vectors per vehicle used in the linear combination of models shared by vehicles in the same region. This approach ensures that the updated vehicular model adopts the beneficial models while discarding the unprofitable ones. We validate our FedRAV framework against existing federated learning algorithms on four real-world autonomous driving datasets in various heterogeneous settings. Extensive experiment results demonstrate that FedRAV framework achieves superior performance than the state-of-the-art algorithms, and improves the accuracy by 9.36%. The source code of FedRAV is available at:https://github.com/yjzhai-cs/FedRAV.

The emergence of 5G technology has enabled the development of Metaverse applications that provide users with immersive experiences through augmented reality (AR) devices, and the integration of federated learning (FL) with the Metaverse AR (MAR) systems can enable many edge intelligence services in 5G. However, the presence of nonindependent and identically distributed (Non-IID) data across all AR users' devices, coupled with limited edge communication resources, makes it challenging to achieve human-centric Metaverse-related applications such as target detection or image classification that combine virtual content with real-world. To address these challenges, we propose a novel adaptive resource-efficient Metaverse-based FL (AMFL) algorithm for AR applications that mitigates the negative effect of Non-IID data and reduces resource costs as well as improves the quality of experience (QoE). We first analyze the impact of wireless communication factors such as CPU frequency, bandwidth, and transmission power on FL training performance by a toy example in the MAR systems. Based on this analysis, furthermore, we establish a Non-IID degree, model accuracy, and resource consumption-related QoE maximization problem under given resource budgets, which is a stochastic optimization problem with strongly coupled variables, including bandwidth, CPU frequency, and transmission power. Guided by the theoretical analysis, to solve this issue, AMFL employs a deep reinforcement learning (DRL)-based method to adaptively allocate resources. Numerical results demonstrate that AMFL can significantly improve the QoE by up to 30.28%, and reduce communication round and energy costs by up to 81.08% and 72.20%, respectively, even under the worst Non-IID case, compared to benchmarks.

In the era of Big Data, graph data is often collected from dispersed addresses and stored separately, making our research on this data subject to transmission and privacy constraints. So we often introduce federated learning, a novel distributed machine learning algorithm, in our studies of graph data. However, the application of federated learning in the field of graph data research is constrained by issues such as the surge in communication costs and the decrease in model accuracy caused by data heterogeneity. To address both the communication stress problem and the accuracy impairment caused by heterogeneity in graph federated learning, we propose a communication-efficient personalized federated learning algorithm, named FedGDC-P. In this algorithm, we introduce the dataset condensation technique in the global information collection process to transfer the features of local data with a one-time transmission of the distilled data instead of multiple transmissions of the model parameters, helping the model on the server to build a panorama of data distribution in order to reduce the amount of communication data during the training process. Subsequently, we execute the obtained model locally to personalize the training process to improve the adaptation of the model to personalized local data in order to enhance the overall training effect. The experiments demonstrate that our algorithm can achieve or even outperform SOTA with only 5% communication budget.

Federated learning may protect user privacy, reduce the transmission of a large amount of raw data, and is more compatible with smart home applications. Current federated learning faces two major problems including non-independent and identically (Non-IID) distributed data and high communication overhead. Personalized federated learning is a good method to deal with Non-IID data, but current personalized federated learning methods overlook the shared features of users' living habits in the same region. Hierarchical federated learning can reduce traffic on the core network, but its potential for personalization for smart home applications has not been considered. Therefore, to address these issues simultaneously, we propose hierarchical personalized federated learning. Specifically, we adopt a three-layer federated learning architecture of cloud-edge-client. On this basis, we use differential learning classification loss (DLCL), hierarchical balance loss (HBL) and balanced edge data selection (BEDS) methods to achieve the personalization of models on both the device side and the edge side. Finally, our experiments demonstrate that compared to state-of-the-art federated learning methods, hierarchical personalized federated learning has improvements in model accuracy and communication overhead.

The emerging federated learning enables distributed autonomous vehicles to train equipped deep learning models collaboratively without exposing their raw data, providing great potential for utilizing explosively growing autonomous driving data. However, considering the complicated traffic environments and driving scenarios, deploying federated learning for autonomous vehicles is inevitably challenged by non-independent and identically distributed (Non-IID) data of vehicles, which may lead to failed convergence and low training accuracy. In this paper, we propose a novel hierarchically Federated Region-learning framework of Autonomous Vehicles (FedRAV), a two-stage framework, which adaptively divides a large area containing vehicles into sub-regions based on the defined region-wise distance, and achieves personalized vehicular models and regional models. This approach ensures that the personalized vehicular model adopts the beneficial models while discarding the unprofitable ones. We validate our FedRAV framework against existing federated learning algorithms on three real-world autonomous driving datasets in various heterogeneous settings. The experiment results demonstrate that our framework outperforms those known algorithms, and improves the accuracy by at least 3.69%. The source code of FedRAV is available at: https://github.com/yjzhai-cs/FedRAV.

Vehicle speed prediction is crucial for intelligent transportation systems, promoting more reliable autonomous driving by accurately predicting future vehicle conditions. Due to variations in drivers’ driving styles and vehicle types, speed predictions for different target vehicles may significantly differ. Existing methods may not realize personalized vehicle speed prediction while protecting drivers’ data privacy. We propose a Federated learning framework with Personalized Aggregation Weights (FedPAW) to overcome these challenges. This method captures client-specific information by measuring the weighted mean squared error between the parameters of local models and global models. The server sends tailored aggregated models to clients instead of a single global model, without incurring additional computational and communication overhead for clients. To evaluate the effectiveness of FedPAW, we collected driving data in urban scenarios using the autonomous driving simulator CARLA, employing an LSTM-based Seq2Seq model with a multi-head attention mechanism to predict the future speed of target vehicles. The results demonstrate that our proposed FedPAW ranks lowest in prediction error within the time horizon of 10 seconds, with a 0.8% reduction in test MAE, compared to eleven representative benchmark baselines.

Unmanned aerial vehicle (UAV) edge computing systems provide easy-to-deploy and low-cost services at those areas with inadequate infrastructure by deploying UAVs as moving edge servers for large-scale users. However, user devices are generally distributed unevenly in a large area, which makes it difficult for existing efforts to cope with this realistic scenario for optimal deployment of UAVs. Therefore, this paper considers a multiple UAV (Multi-UAV) Collaborative edge Computing (UCC) system by utilizing collaboration among them to split computation tasks at UAVs to balance the load and improve resource utilization. In order to maximize the energy-efficiency of the UCC system under the satisfaction of the delay constraint, we study the joint problem of UAV deployment, task collaborative offloading, computation and communication resource allocation in UCC system. We propose a bi-level optimization framework to solve the formulated non-convex mixed-integer optimization problem. In the upper level, the UAV deployment is optimized based on an improved differential evolution (DE) algorithm, and in the lower level the offloading decision and resource allocation are optimized based on a Reinforcement Learning (RL) algorithm with Twin Delayed Deep Deterministic policy gradient. Experimental results demonstrate the effectiveness and superiority of multi-UAV collaborative computing, with the proposed framework achieving a 32.4% reduction in energy consumption and an average 30% increase in task completion rate compared to DDPG, ToDeTaS, and other benchmark schemes.

The Internet of Vehicles (IoV) enhances data availability by equipping a plethora of sensors, driving the automotive industry towards data-driven Predictive Maintenance (PreM) models. However, traditional centralized PreM solutions, requiring complete access to training data, raise concerns about data privacy. PreM in the automotive domain is more challenging than in many other fields, partly due to the varying distribution nature of data samples and the limited network connectivity time caused by vehicle mobility. To address these challenges, we propose the PreM-FedIoV framework, extending single-agent Double Deep Q-Network (DDQN) to Multi-Agent Double Deep Q-Network (MADDQN). In each round, each vehicle client uploads a data packet to the server based on the current contention window, containing its local model, local test Mean Absolute Error (MAE), and a timestamp. The server initially performs federated aggregation on the received local models. The MADDQN module then dynamically adjusts the contention window of each vehicle for the next round based on the local test MAE and communication statistical state, aiming to optimize communication costs and predictive performance. Additionally, we utilize NS-3 to create IoV simulations and deploy the PreM-FedIoV framework within NS3-gym. We choose Federated Averaging (FedAvg) and FedAdam following the IEEE 802.11p standard as baselines. The experiments demonstrate significant improvements in our framework compared to state-of-the-art algorithms. On the C-MAPSS dataset, we achieve reductions of up to 10.2% in MAE, 26.31% in average communication clock time per round, and 65.6% in the number of participating clients per round. For the Random Battery Usage dataset, with up to 4.55%, 24.44%, and 36.58% improvements in the respective metrics.

Deep integration of wireless power transmission and mobile edge computing (MEC) promotes wireless powered MEC to become a new research hotspot in the field of Internet of Things. In this paper, we focus on the joint optimization problem of online offloading decision and charging resource allocation for minimizing task accomplishing time in dynamic time-varying wireless channel scenarios. The optimal solution involves addressing a mixed integer programming problem in real time, which is proved to be NP-hard, and imposes nontrivial challenges to design with conventional optimization methods. To efficiently address this problem, we leverage the deep reinforcement learning (DRL) technology to propose an energy-aware online offloading algorithm called EAOO. EAOO algorithm learns empirically the online offloading decision policies via a well-designed DRL framework, and adopts the feasible solution region analysis method to implement the charging resource allocation. We further propose a novel feasible decision vector generation method, and incorporate the crossover and mutation technology to expand the offloading vector search space with the provable feasibility guarantee. Extensive experimental results show that, our EAOO algorithm outperforms existing baseline algorithms, and achieves near-optimal performance with low CPU execution latency, which well satisfies the practical requirements of real-time and efficiency.

Smart transportation shall address utility waste, traffic congestion, and air pollution problems with least human intervention in future smart cities. To realize the sustainable operation of smart transportation, we leverage solar-harvesting charging stations and rooftops to power electric autonomous vehicles(AVs) solely via design. With a fixed budget, our framework first optimizes the locations of charging stations based on historical spatial-temporal solar energy distribution and usage patterns, achieving $(2+\epsilon)$ factor to the optimal. Then a stochastic algorithm is proposed to update the locations online to adapt to any shift in the distribution. Based on the deployment, a strategy is developed to assign energy requests in order to minimize their traveling distance to stations while not depleting their energy storage. Equipped with extra harvesting capability, we also optimize route planning to achieve a reasonable balance between energy consumed and harvested en-route. As a promising application, utility optimization of shared electric AVs is discussed, and $(2k\!+\!1)$ -approx algorithm is proposed to manage $k$ vehicles simultaneously. Our extensive simulations demonstrate the algorithm can approach the optimal solution within 10-15% approximation error, improve the operating range of vehicles by up to 2-3 times, and improve the utility by more than 50% compared to other competitive strategies.

Internet of Things (IoT) is progressively becoming an essential aspect of daily life that can be sensed anywhere and anytime, transforming the traditional lifestyle into a high-tech one. Numerous applications in the edge are brought to life based on IoT infrastructures. Especially, edge computing has witnessed the proliferation and impact of IoT-enabled devices benefiting from the data collection and computation capabilities of IoT. However, establishing an IoT from scratch can be monetarily expensive, and leasing the existing sub-networks confronts the potentially dishonest behavior of service providers. To address these issues, we propose a novel framework of leasing edge IoT networks and analyze the influence of sub-network owners’ dishonest behavior on the network. We model the interaction between the edge user and the owners of sub-networks by a Stackelberg game with a unique equilibrium, jointly analyzing the pricing and data collection mechanisms. The Primal-dual Decomposition algorithm and its theoretical analyses are provided for the corresponding strategies of the edge user and sub-network owners. Evaluations demonstrate that the proposed algorithm in the leasing model can save data collection cost up to 53% compared with existing data collection strategies, and illustrate the difference in network performance compared with the game without dishonest owners.

Multi-armed bandits problem has been widely utilized in economy-related areas. Incentives are explored in the sharing economy to inspire users for better resource allocation. Previous works build a budget-feasible incentive mechanism to learn users’ cost distribution. However, they only consider a special case that all tasks are considered as the same. The general problem asks for finding a solution when the cost for different tasks varies. In this paper, we investigate this problem by considering a system with$k$levels of difficulty. We present two incentivizing strategies for offline and online implementation, and formally derive the ratio of utility between them in different scenarios. We propose a regret-minimizing mechanism to decide incentives by dynamically adjusting budget assignment and learning from users’ cost distributions. We further extend the problem to a more generalized k-MAB problem by removing the contextual information of difficulties. CUE-UCB algorithm is proposed to address the online advertisement problem for multi-platforms. Our experiment demonstrates utility improvement about 7 times and time saving of 54% to meet a utility objective compared to the previous works in sharing economy, and up to 175% increment of utility for online advertising.

With the aggravation of data explosion and backhaul loads on 5 G edge network, it is difficult for traditional centralized cloud to meet the low latency requirements for content access. The federated learning (FL)-basedproactive contentcaching (FPC) can alleviate the matter by placing content in local cache to achieve fast and repetitive data access while protecting the users’ privacy. However, due to the non-independent and identically distributed (Non-IID) data across the clients and limited edge resources, it is unrealistic for FL to aggregate all participated devices in parallel for model update and adopt the fixed iteration frequency in local training process. To address this issue, we propose a distributed resources-efficient FPC policy to improve the content caching efficiency and reduce the resources consumption. Through theoretical analysis, we first formulate the FPC problem into a stacked autoencoders (SAE) model loss minimization problem while satisfying resources constraint. We then propose an adaptive FPC (AFPC) algorithm combined deep reinforcement learning (DRL) consisting of two mechanisms of client selection and local iterations number decision. Next, we show that when training data are Non-IID, aggregating the model parameters of all participated devices may be not an optimal strategy to improve the FL-based content caching efficiency, and it is more meaningful to adopt adaptive local iteration frequency when resources are limited. Finally, experimental results in three real datasets demonstrate that AFPC can effectively improve cache efficiency up to 38.4$\%$and 6.84$\%$, and save resources up to 47.4$\%$and 35.6$\%$, respectively, compared with traditional multi-armed bandit (MAB)-based and FL-based algorithms.

Energy provisioning plays a key role in the sustainable operations of Wireless Sensor Networks (WSNs). Recent efforts deploy multi-source energy harvesting sensors to utilize ambient energy. Meanwhile, wireless charging is a reliable energy source not affected by spatial-temporal ambient dynamics. This article integrates multiple energy provisioning strategies and adaptive adjustment to accomplish self-sustainability under complex weather conditions. We design and optimize a three-tier framework with the first two tiers focusing on the planning problems of sensors with various types and distributed energy storage powered by environmental energy. Then we schedule the Mobile Chargers (MC) between different charging activities and propose an efficient, 4-factor approximation algorithm. Finally, we adaptively adjust the algorithms to capture real-time energy profiles and jointly optimize those correlated modules. Our extensive simulations demonstrate significant improvement of network lifetime ( ), increase of harvested energy (15%), reduction of network cost (30%), and the charging capability of MC by 100%.

Originated from distributed learning, federated learning enables privacy-preserved collaboration on a new abstracted level by sharing the model parameters only. While the current research mainly focuses on optimizing learning algorithms and minimizing communication overhead left by distributed learning, there is still a considerable gap when it comes to the real implementation on mobile devices. In this article, we start with an empirical experiment to demonstrate computation heterogeneity is a more pronounced bottleneck than communication on the current generation of battery-powered mobile devices, and the existing methods are haunted by mobile stragglers. Further, non-identically distributed data across the mobile users makes the selection of participants critical to the accuracy and convergence. To tackle the computational and statistical heterogeneity, we utilize data as a tuning knob and propose two efficient polynomial-time algorithms to schedule different workloads on various mobile devices, when data is identically or non-identically distributed. For identically distributed data, we combine partitioning and linear bottleneck assignment to achieve near-optimal training time without accuracy loss. For non-identically distributed data, we convert it into an average cost minimization problem and propose a greedy algorithm to find a reasonable balance between computation time and accuracy. We also establish an offline profiler to quantify the runtime behavior of different devices, which serves as the input to the scheduling algorithms. We conduct extensive experiments on a mobile testbed with two datasets and up to 20 devices. Compared with the common benchmarks, the proposed algorithms achieve 2-100× speedup epoch-wise, 2–7 percent accuracy gain and boost the convergence rate by more than 100 percent on CIFAR10.

The rise of dockless electric bike sharing becomes a new urban lifestyle recently. More than just the first-and-last mile, it offers a new modality of green transportation. However, in addition to the traditional re-balance and overcrowding problems, it also brings new challenges to urban management and maintenance. Due to the safety risks of batteries, customers are regulated to park at designated locations, which potentially causes dissatisfaction and customer loss. Meanwhile, service providers should charge those scattering low-energy batteries in time. To address these issues, we propose E-sharing, a two-tier optimization framework that leverages data-driven online algorithms to plan parking locations and maintenance. First, we balance the user dissatisfaction and the number of parking locations by minimizing their sum. To account for real-time dynamics while not losing track of the historical optimality, we propose an online algorithm based on its near-optimal offline solution. Second, we develop an incentive mechanism to motivate users to aggregate low-battery bikes together, saving the cost of bike charging. Our experiment based on the public dataset demonstrates that the online algorithm can minimize the cost from the conflicting objectives and incentive mechanism further reduces the maintenance cost by 47%.

Electric autonomous vehicles provide a promising solution to the traffic congestion and air pollution problems in future smart cities. Considering intensive energy consumption, charging becomes of paramount importance to sustain the operation of these systems. Motivated by the innovations in renewable energy harvesting, we leverage solar energy to power autonomous vehicles via charging stations and solar-harvesting rooftops, and design a framework that optimizes the operation of these systems from end to end. With a fixed budget, our framework first optimizes the locations of charging stations based on historical spatial-temporal solar energy distribution and usage patterns, achieving (2 + ε) factor to the optimal. Then a stochastic algorithm is proposed to update the locations online to adapt to any shift in the distribution. Based on the deployment, a strategy is developed to assign energy requests in order to minimize their traveling distance to stations while not depleting their energy storage. Equipped with extra harvesting capability, we also optimize route planning to achieve a reasonable balance between energy consumed and harvested en-route. Our extensive simulations demonstrate the algorithm can approach the optimal solution within 10-15% approximation error, and improve the operating range of vehicles by up to 2-3 times compared to other competitive strategies.

Federated learning learns a collaborative model by aggregating locally-computed updates from mobile devices for privacy preservation. While current research typically prioritizing the minimization of communication overhead, we demonstrate from an empirical study, that computation heterogeneity is a more pronounced bottleneck on battery-powered mobile devices. Moreover, if class is unbalanced among the mobile devices, inappropriate selection of participants may adversely cause gradient divergence and accuracy loss. In this paper, we utilize data as a tunable knob to schedule training and achieve near-optimal solutions of computation time and accuracy loss. Based on the offline profiling, we formulate optimization problems and propose polynomial-time algorithms when data is class-balanced or unbalanced. We evaluate the optimization framework extensively on a mobile testbed with two datasets. Compared with common benchmarks of federated learning, our algorithms achieve 210× speedups with negligible accuracy loss. They also mitigate the impact from mobile stragglers and improve parallelism for federated learning.

Incentives are explored in the sharing economy to inspire users for better resource allocation. Previous works build a budget-feasible incentive mechanism to learn users' cost distribution. However, they only consider a special case that all tasks are considered as the same. The general problem asks for finding a solution when the cost for different tasks varies. In this paper, we investigate this general problem by considering a system with k levels of difficulty. We present two incentivizing strategies for offline and online implementation, and formally derive the ratio of utility between them in different scenarios. We propose a regret-minimizing mechanism to decide incentives by dynamically adjusting budget assignment and learning from users' cost distributions. Our experiment demonstrates utility improvement about 7 times and time saving of 54% to meet a utility objective compared to the previous works.

Energy supply remains to be a major bottleneck in Wireless Sensor Networks (WSNs). A self-sustainable network operates without battery replacement. Recent efforts employ multi-source energy harvesting to power sensors with ambient energy. Meanwhile, wireless charging is considered in WSNs as a reliable energy source. It motivates us to integrate both fields of research to build a self-sustainable network and guarantee operation under any weather condition. We propose a three-step solution to optimize this new framework. We first solve the Sensor Composition Problem (SCP) to derive the percentage of different types of sensors. Then we enable self-sustainability by bringing energy harvesting storage to the field for charging the Mobile Charger (MC). Next, we propose a 3-factor approximation algorithm to schedule sensor charging and energy replenishment of MC. Our extensive simulation results demonstrate significant improvement of network lifetime and reduction of network cost. The network lifetime can be extended at least three times compared with traditional approaches and the charging capability of MC increases at least 100%.

Energy remains a major hurdle in running computation-intensive tasks on wireless sensors. Recent efforts have been made to employ a Mobile Charger (MC) to deliver wireless power to sensors, which provides a promising solution to the energy problem. Most of previous works in this area aim at maintaining perpetual network operation at the expense of high operating cost of MC. In the meanwhile, it is observed that due to the low cost of wireless sensors, they are usually deployed at high density so there is abundant redundancy in their coverage in the network. For such networks, it is possible to take advantage of the redundancy to reduce the energy cost. In this paper, we relax the strictness of perpetual operation by allowing some sensors to temporarily run out of energy while still maintaining target $k$k-coverage in the network at lower cost of MC. We first establish a theoretical model to analyze the performance improvements under this new strategy. Then, we organize sensors into load-balanced clusters for target monitoring by a distributed algorithm. Next, we propose a charging algorithm named $\lambda$λ-GTSP Charging Algorithm to determine the optimal number of sensors to be charged in each cluster to maintain $k$k-coverage in the network and derive the route for MC to charge them. We further generalize the algorithm to encompass mobile targets as well. Our extensive simulation results demonstrate significant improvements of network scalability and cost saving that MC can extend charging capability over 2-3 times with a reduction of 40 percent of moving cost without sacrificing the network performance.

This paper considers a mobile data collecting problem in a wireless sensor network with private residual sensor networks for the scenario in which the owners of residual sensor networks may perform dishonest behavior. The interaction between the wireless sensor network operator and the owners of residual sensor networks is modeled by a Stackelberg game which has a unique Stackelberg equilibrium. The influence of the Stackelberg equilibrium caused by the dishonest residual sensor networks owner are analyzed. An algorithm and a theoretical analysis are provided for the corresponding strategies of the operator and owners. Simulations are conducted to illustrate the difference of network performance compared with the game without dishonest residual owners.

This paper studies a data gathering problem in a wireless sensor network containing multiple private residual subnetworks. The interaction between the wireless sensor network operator and the owners of residual sub-networks is modeled by a Stackelberg game, which forms a novel framework for jointly analyzing the pricing, gathering data, and planning routes. It is shown that the game has a unique Stackelberg equilibrium at which the wireless sensor network operator sets prices to minimize total cost, while owners of residual sub-networks respond accordingly to maximize their utilities subject to their bandwidth constraints. An algorithm and theoretical analyses are provided for the corresponding strategies of the operator and owners, and validated by extensive simulations. It is demonstrated that the algorithm achieves lower network cost compared with existing data gathering strategies.

Energy remains a major hurdle in running computation-intensive tasks on wireless sensors. Recent efforts have been made to employ a Mobile Charger (MC) to deliver wireless power to sensors, which provides a promising solution to the energy problem. Most of previous works in this area aim at maintaining perpetual network operation at the expense of high operating cost of MC. In the meanwhile, it is observed that due to low cost of wireless sensors, they are usually deployed at high density so there is abundant redundancy in their coverage in the network. For such networks, it is possible to take advantage of the redundancy to reduce the energy cost. In this paper, we relax the strictness of perpetual operation by allowing some sensors to temporarily run out of energy while still maintaining target k-coverage in the network at lower cost of MC. We first establish a theoretical model to analyze the performance improvements under this new strategy. Then we organize sensors into load-balanced clusters for target monitoring by a distributed algorithm. Next, we propose a charging algorithm named λ-GTSP Charging Algorithm to determine the optimal number of sensors to be charged in each cluster to maintain k-coverage in the network and derive the route for MC to charge them. We further generalize the algorithm to encompass mobile targets as well. Our extensive simulation results demonstrate significant improvements of network scalability and cost saving that MC can extend charging capability over 2-3 times with a reduction of 40% of moving cost without sacrificing the network performance.