With the rapid expansion of the Internet of Things (IoT), traditional centralized data management frameworks suffer from challenges such as data fragmentation and silos. IOTA, a decentralized architecture, offers a promising approach to mitigate these issues within the IoT ecosystem. However, the inherently sensitive nature of IoT-generated data demands more sophisticated access control than IOTA alone can provide. Additionally, the IOTA system lacks mechanisms for precise and flexible data retrieval. To conquer these limitations, we present an integrated framework combining IOTA with the InterPlanetary File System (IPFS), Proxy Re-Encryption (PRE), Multi-hop PRE (MPRE), and smart contracts. IPFS provides persistent, content-addressable, and decentralized data storage. PRE and MPRE, complemented by our novel Hashtag-based search scheme, enable fine-grained access control alongside efficient and secure data retrieval. This integration facilitates secure and confidential sharing and management of IoT data access permissions, thereby enhancing user trust in data sharing and mitigating privacy leakage risks.

Federated Learning (FL) is a promising framework for edge intelligence, allowing clients to preserve user privacy by collaboratively training a shared model. However, in real-world scenarios, heterogeneous resource challenges, such as the straggler effect among devices, degrade training efficiency. Even worse, existing approaches, such as model heterogeneity that rely heavily on contributions from strong devices, tend to trigger model bias issues. In contrast, resource-constrained devices are only able to train the initial few layers, eventually leading to uneven parameter training. In this paper, we propose a HeteroSplit framework that enables all devices to iteratively train the full depths of the model, thereby addressing the FL training challenges mentioned above. We design a Progressive Least Contribution First training strategy based on D2D-assisted split learning to dynamically balance each device’s contribution and prevent model bias from strong devices. Additionally, we introduce an early transmission mechanism to accelerate overall training time. The experiments show that HeteroSplit improves accuracy by 15% and reduces training time by 41% compared to other state-of-the-art baselines under various device distributions and Non-IID data settings.

Edge intelligence empowered by 6G is a promising technique for realizing AIoT applications. However, making intelligent decisions through distributed training across various mobile devices, considering model accuracy, system heterogeneity, and training latency, is still an open challenge. In this paper, we propose a United Split Federated Learning (U-SFL), a two-level collaboration framework with a "first-sequential-then-parallel" principle that integrates sequential split learning within clusters and parallel training across clusters to achieve fine-grained and coarse-grained knowledge sharing jointly. Furthermore, we design an evolutionary game-based clustering approach that enables devices to identify the environmental fitness of the cluster and self-organize themselves into a suitable cluster with a theoretical evolutionary equilibrium proof. By integrating the U-SFL framework with evolutionary game-based clustering, we effectively mitigate the overhead of sequential training, achieving faster convergence with fewer clusters and reversing the conventional belief that only higher parallelism can reduce training latency. The experimental results show that the U-SFL framework outperforms the SOTA edge intelligence frameworks and preserves optimized training latency in a large-scale heterogeneous split federated learning system.

Semantic communication has emerged as a promising paradigm to overcome Shannon’s transmission limits. Existing research has primarily focused on deep neural network (DNN) solutions to realize semantic communication. However, these approaches often suffer from inherent limitations in terms of interpretability and transparency in feature extraction. To address this challenge, we propose a relation-aware Knowledge Graph Bidirectional Encoder Representations from Transformers (KG-BERT) semantic communication system, which combines two complementary approaches: the structured representation of entity relationships in knowledge graphs and BERT’s ability to understand natural language context. This integration enables our system to maintain semantic meaning even in noisy channels while providing transparent reasoning processes. Furthermore, we enhance the system with two key innovations: (1) a relation-aware strategy that significantly improves transmission privacy and reduces bandwidth, and (2) an entity correction algorithm that enables robust entity recovery. Experimental results demonstrate that our KG-BERT semantic communication system significantly outperforms state-of-the-art (SOTA) KG-based and DNN-based semantic communication baselines, achieving sentence similarity scores that are 78 percentage higher in the Additive White Gaussian Noise (AWGN) channel and 55 percentage higher in the Rayleigh fading channel at signal-to-noise ratio (SNR) of -5dB, demonstrating particular advantages in low SNR environments.

With advancements in Beyond 5G (B5G) and 6G, semantic communication is emerging as a promising technique for supporting diverse multimodal AIoT tasks. However, previous research has not fully addressed the practical challenges when jointly considering transmission efficiency and system robustness. In this paper, we design a Multimodal Data Fusion Semantic Communication (MDF-SC) system with a cross-attention strategy to integrate multiple modalities at the transmitter. We ensure robust noise resilience across low and high SNR regimes by extracting critical features under symbol constraints. This fusion-aware approach eliminates the need for modality-specific encoders and decoders, significantly reducing parameter count and computational complexity as a unified semantic communication system. Experiment results demonstrate that our MDF-SC system outperforms existing state-of-the-art (SOTA) transformer-based approaches, achieving superior performance with 26.7% fewer transmitted semantic symbols using Rayleigh fading channel, 22% fewer model parameters, and 37.5% computational load reduction while maintaining robust performance across varying SNR regimes.

In endovascular surgery, the precise identification of catheters and guidewires in X-ray images is essential for reducing intervention risks. However, accurately segmenting catheter and guidewire structures is challenging due to the limited availability of labeled data. Foundation models offer a promising solution by enabling the collection of similar-domain data to train models whose weights can be fine-tuned for downstream tasks. Nonetheless, large-scale data collection for training is constrained by the necessity of maintaining patient privacy. This paper proposes a new method to train a foundation model in a decentralized federated learning setting for endovascular intervention. To ensure the feasibility of the training, we tackle the unseen data issue using differentiable Earth Mover's Distance within a knowledge distillation frame-work. Once trained, our foundation model's weights provide valuable initialization for downstream tasks, thereby enhancing task-specific performance. Intensive experiments show that our approach achieves new state-of-the-art results, contributing to advancements in endovascular intervention and robotic-assisted endovascular surgery, while addressing the critical issue of data sharing in the medical domain.

Traditional vision-based autonomous driving systems often face difficulties in navigating complex environments when relying solely on single-image inputs. To overcome this limitation, incorporating temporal data such as past image frames or steering sequences, has proven effective in enhancing robustness and adaptability in challenging scenarios. While previous high-performance methods exist, they often rely on resource-intensive fusion networks, making them impractical for training and unsuitable for federated learning. To address these challenges, we propose lightweight temporal transformer decomposition, a method that processes sequential image frames and temporal steering data by breaking down large attention maps into smaller matrices. This approach reduces model complexity, enabling efficient weight updates for convergence and real-time predictions while leveraging temporal information to enhance autonomous driving performance. Intensive experiments on three datasets demonstrate that our method outperforms recent approaches by a clear margin while achieving real-time performance. Additionally, real robot experiments further confirm the effectiveness of our method. Our source code can be found at: https://github.com/aioz-ai/LTFed.

To deliver immersive experiences with the Metaverse, rendering must be carefully orchestrated in high-resolution environments with minimal latency. To address this fundamental challenge and NP-hard problem, in this paper, we consider joint computation, communication, and caching optimization in rendering using Edge Computing. With our Latency-aware, Resolution-focused, and Cache-optimized (LaReCa) framework involving heterogeneous resource allocation and rendering task offloading, we achieve the desired minimization of computational requirements and 25–30 % reduction of service latency without losing visual immersion compared with the SOTA baseline. Importantly, our LaReCa framework ensures the quality of immersion by surpassing normal HD resolution, which represents a substantial contribution to the broad landscape Metaverse rendering service.

Recently, Federated Learning (FL) has realized Artificial Intelligence of Things (AIoT) applications to train a shared model while preserving user privacy collectively. However, the legacy FL framework performance is fundamentally threatened by scale limitation, non-independent and identically distributed (non-IID) data, and communication costs. Therefore, we propose VIrtual-targeted SequentIal Training with Hierarchical Federated Learning (VISIT), a novel framework to systematically distribute clients to suitable clusters for balancing data distributions among all FL subgroups. To the best of our knowledge, this work is the first attempt to introduce a Virtual Target concept along with a key metric, Virtual Target Similarity (VTS), to quantify the data harmonization in the whole HFL system. Based on our insightful Client Set arranging strategy, VISIT can wisely select each FL subgroup member to optimize diversity within each Client Set and similarity across different clusters while preserving user privacy. Numerical results demonstrate that VISIT improves accuracy by 41% and reduces total communication rounds by 82% compared to other state-of-the-art baselines with non-IID data on EMNIST and CIFAR-10 datasets.

Federated Learning (FL) is a promising framework for enabling edge intelligence while preserving privacy and enhancing communication efficiency. In real-world scenarios, limited and heterogeneous hardware resources among users threaten the overall training efficiency in FL. To address this issue, several model heterogeneity frameworks have emerged in recent years. However, existing studies primarily focus on mitigating idle times on powerful devices, overlooking the fact that strong devices may not always have a positive impact and can potentially become a burden instead. Furthermore, as the resource gap among clients widens or the number of weak devices increases, the model may be hindered by the influence of strong devices. Directly applying existing model heterogeneity frameworks leads to model performance degradation due to the neglect of contributions from weak devices. To make a performance breakthrough, we proposed a novel FL framework called Progressive Width Mixing (PWM), which extracts diverse features and balances the contribution of strong and weak devices and mitigates straggler effects under scenarios with various device distributions. To our best knowledge, we are the first model heterogeneity work that considered straggler effects from the weak devices' point of view. The experiments show that PWM maintains stability over different datasets and outperforms all baselines across various device distributions and non-IID scenarios. PWM makes a leap forward and surpasses all baselines by 7%, and mitigates the negative impact from the strong devices.

Federated learning has been widely applied in autonomous driving since it enables training a learning model among vehicles without sharing users’ data. However, data from autonomous vehicles usually suffer from the non-independent-and-identically-distributed (non-IID) problem, which may cause negative effects on the convergence of the learning process. In this paper, we propose a new contrastive divergence loss to address the non-IID problem in autonomous driving by reducing the impact of divergence factors from transmitted models during the local learning process of each silo. We also analyze the effects of contrastive divergence in various autonomous driving scenarios, under multiple network infrastructures, and with different centralized/distributed learning schemes. Our intensive experiments on three datasets demonstrate that our proposed contrastive divergence loss significantly improves the performance over current state-of-the-art approaches. Our source code is available at https://github.com/aioz-ai/CDL.

Mobile/multi-access edge computing (MEC) is developed to support the upcoming AI-aware mobile services, which require low latency and intensive computation resources at the edge of the network. One of the most challenging issues in MEC is service provision with mobility consideration. It has been known that the offloading decision and resource allocation need to be jointly handled to optimize the service provision efficiency within the latency constraints, which is challenging when users are in mobility. In this paper, we propose Mobility-Aware Deep Reinforcement Learning (M-DRL) framework for mobile service provision in the MEC system. M-DRL is composed of two parts:glimpse, a seq2seq model customized for mobility prediction to predict a sequence of locations just like a “glimpse” of the future, and a DRL specialized in supporting offloading decisions and resource allocation in MEC. By integrating the proposed DRL and glimpse mobility prediction model, the proposed M-DRL framework is optimized to handle the MEC service provision with average 70% performance improvements.

Recently, mobile edge computing (MEC) assisted unmanned aerial vehicles (UAVs) have brought a revolution to the existing precision agriculture (PA). The target UAVs can execute various PA tasks with different heterogeneous resource requirements on the farm. However, due to the stringent service deadline of PA tasks and the battery limitation of UAVs, one of the promising solutions is to offload those computation tasks to MEC servers jointly. This paper explores the MEC-assisted task offloading problem with multi-UAVs under different deadline constraints in uncertain real-world environments. The diverse requirements of PA tasks, the heterogeneous network status, and the dynamic loading of MEC edge servers make the offloading decision an NP-hard problem. Therefore, we propose a reinforcement learning (RL)-based task offloading approach, BANDIT-SCH, to minimize total MEC system costs to achieve online task dispatching and scheduling in uncertain environments without further global information. The experiment results show that the performance of BANDIT-SCH is approximate to the upper bound strategy, which can foresee all edge servers' detailed status.

Recently, Google proposed a privacy-preserving framework, Federated Learning (FL), to realize the era of edge intelligence. However, the limited labeled data that can only be labeled by the data owner with domain know-how threatens the feasibility of FL. In fact, Semi-supervised Learning (SSL) is a key to leveraging the unlabeled data on the client side while the confirmation bias issue triggered by incorrect predictions in the old-fashion Teacher-Student structure drops the model accuracy significantly. In this paper, we introduce the state-of-the-art SSL technique called Meta Pseudo Labels (MPL), which advocates a feedback strategy in the Teacher-Student architecture to mitigate the performance degradation. Unfortunately, in FL the heterogeneous data without sharing among clients are non-Independent and Identically Distributed (non-IID). The knowledge that shuttles between the Teacher and Student model may be partial and undermine the effectiveness of MPL. To make a performance breakthrough, we proposed a novel FL framework called Federated Meta Learning with Synergetic Strategy (SynFMPL), which combines the advantages of both Teacher and Student models. To our best knowledge, we are the first work that integrates MPL technique in FL. Moreover, we specifically focus on the client side, which fully leverages the unlabeled data for model generalization. The experiment shows that SynFPML outperforms all baselines in various non-IID scenarios. The Student model in SynFMPL even exceeds the upper bound in all baselines by 4% and maintains a virtuous cycle in the learning process.

Addressing edge computing's economic issues is critical as we need to motivate edge devices as resource providers to devote their computing resources to the service. There are multiple users and resource providers in most edge computing service scenarios. The communication delays between users and providers are not the same since their physical distances are different. However, most existing works on edge computing regarding network economics adopt single market models that do not consider the influence of communication delay. Moreover, due to the high cost of deploying 5G ultra-dense small cells, barely a network operator can reach full network coverage. Users cannot rely on a single network, but existing multi-market models do not allow resource trading between different groups. Thus, in this paper, we propose a novel multi-market trading (MMT) framework to address these shortcomings. The framework combines the double auction at each group and a market selection game to enable the resource providers to participle in multiple auctions and analyze their behavior of choosing markets. Through extensive simulations using real-world datasets of vehicular networks, we show that the proposed framework can improve the social welfare by 14.45% and 36.74%, respectively, compared with classic multi-market and single market models.

Beam-based wireless power transfer and Fog/edge computing are promising dual technologies for realizing wireless powered Fog computing networks to support the upcoming B5G/6G IoT applications, which require latency-aware and intensive computing, with a limited energy supply. In such systems, IoT devices can either offload their computing tasks to the proximal Fog nodes or execute local computing with replenishing energy from the dedicated beamforming. However, effective integration of these techniques is still challenging, where two new issues arise: energy-aware task offloading and signal interferences from spillovers of wireless beamforming. In this paper, we observe that the beam-ripple phenomenon, which takes advantage of beamformer defects to transfer energy to IoT devices, is the key to jointly addressing these two issues. Different from traditional SWIPT technology, as in our approach the stream is not separately divided into data/energy streams, but target IoT devices can potentially harvest the whole stream. Inspired by this phenomenon, we treat the collaborative energy beamforming and edge computing design as a strongly$\mathcal {NP}$-hard optimization problem. The proposed solution is an iterative algorithm to cascadingly integrate a polynomial-time$\left({1 - \frac {1}{e}}\right)$-approximation algorithm, which achieves the theoretical upper bound in approximation ratio unless$\mathcal {P} = \mathcal {NP}$, and an optimal dynamic programming algorithm. The numerical results show that the energy minimization goal among IoT devices can achieve, and the developed harvest-when-interfered protocol is practical in the wireless powered Fog computing networks.

With the upcoming edge AI, federated learning (FL) is a privacy-preserving framework to meet the General Data Protection Regulation (GDPR). Unfortunately, FL is vulnerable to an up-to-date security threat, model poisoning attacks. By successfully replacing the global model with the targeted poisoned model, malicious end devices can trigger backdoor attacks and manipulate the whole learning process. The traditional researches under a homogeneous environment can ideally exclude the outliers with scarce side-effects on model performance. However, in privacy-preserving FL, each end device possibly owns a few data classes and different amounts of data, forming into a substantial heterogeneous environment where outliers could be malicious or benign. To achieve the system performance and robustness of FL's framework, we should not assertively remove any local model from the global model updating procedure. Therefore, in this paper, we propose a defending strategy called FedEqual to mitigate model poisoning attacks while preserving the learning task's performance without excluding any benign models. The results show that FedEqual outperforms other state-of-the-art baselines under different heterogeneous environments based on reproduced up-to-date model poisoning attacks.

With the popularity of AIoT (Artificial Intelligence of Things) services, we can foresee that smart end devices will generate tremendous user data at the edge. In particular, it is critical to address how to properly distill knowledge from the edge network in a communication-efficient and privacy-preserving manner. Federated learning (FL), one of the promising machine learning frameworks, ensures data privacy by allowing end devices to collaboratively train a shared model without exposing raw data to an aggregation server. However, due to its distributed nature, the framework is vulnerable to two major threats: the Model Inversion Attacks and the Model Poisoning Attacks. An abnormal aggregator or malicious end devices may probably launch these attacks in the training phase. The former leaks sensitive information by reversing the model weights to users' raw data. Still, the latter can break the model security and mislead the global model to wrong inference results. Unfortunately, the existing research has not tackled such two-sided model attacks that occurred concurrently in FL. Therefore, in this paper, we propose a dual-masking federated learning (DMFL) framework that advocates partial weights uploading in the aggregation process and applies two kinds of masks on both the end device and the aggregator sides. Based on the benchmark data for image classification, our experimental results show that the proposed DMFL framework outperforms other baselines, confirming that it can successfully preserve weights privacy and protect model security for AIoT.

Mobile/multi-access edge computing (MEC) is therefore developed to support the upcoming AI-aware mobile services, which require low latency and intensive computation resources at the edge of the network. One of the most challenging issues in MEC is service provision with mobility consideration. It has been known that the offloading and migration decision need to be jointly handled to maximize the utility of networks within the latency constraints, which is challenging when users are in mobility. In this paper, we propose Mobility-Aware Deep Reinforcement Learning (M-DRL) framework for mobile service provision problems in the MEC system. M-DRL is composed of two parts: DRL specialized in supporting multiple users joint training, and glimpse, a seq2seq model customized for mobility prediction to predict a sequence of locations just like a “glimpse” of future. Through integrating the proposed DRL and glimpse mobility prediction model, the proposed M-DRL framework is optimized to handle the service provision problem in MEC with acceptable computation complexity and near-optimal performance.

Thanks to the advances in wireless communication and machine learning technologies, we can envision a novel AIoT (AI + IoT) service platform that collects video data from the individuals' edge devices. Then, it transforms the video data into useful information, providing services to IoT or smart city applications. However, collecting raw video data directly to the cloud server is merely possible due to network bandwidth limitations and data privacy concerns. One possible solution is to adopt federated learning, which enables edge devices to collaboratively train a shared model without sending the raw data to the cloud. Unfortunately, this scheme cannot directly be applied to the targeted scenario since it assumes labeled data for training, and only at the cloud, we have the human power and time to label the video data. Thus, to tackle those issues, we propose an edge learning system based on semisupervised learning and federated learning technologies. The system trains AI models at edge devices using an improved semisupervised learning scheme and periodically uploads the training results to the cloud server to form a single model by adapting the federated learning technology. Then, we observe that in the real world, the data on the end devices are nonindependent and identically distributed (non-IID) such that it may cause weight divergence during training and result in a considerable decrease in the model performance. Therefore, we propose a new operation called federated swapping (FedSwap) to replace partial federated learning operations based on a few shared data during federated training to alleviate the adverse impact of weight divergence. We evaluate our system on both image classification using the state-of-the-art benchmark data and object detection using real-world video data. The experimental results show that the proposed system can have up to 5.9% higher accuracy of object detection for the video analysis applications by fully utilizing unlabeled data, compared with the situation that only labeled data are used. Moreover, the proposed FedSwap can improve the accuracy of image classification by 3.8% and the object detection task by 1.1%.

In a dynamic network environment, the applicability of traffic engineering techniques requires fresh traffic measurements, fast routing solvers and frequent network reconfigurations. However, the ages of traffic measurements exhibit significant variation due to asynchronization and random communication delays between routers and controllers. Besides, frequent reconfigurations may incur routing instability, and hence impair network utilization. We devise a controller-assisted distributed routing scheme with recursive link weight reconfigurations, accounting for the impact of measurement ages and routing instability. In particular, the controller estimates the current traffic conditions using an autoregressive model to account for the uncertainty of the age of measurements. A fast load-sensitive link weight update algorithm swiftly computes a new set of OSPF weights by using the estimated link loads. To reduce complexity, a myopic policy is used to determine link weight reconfiguration, which takes into consideration congestion, measurement ages, and possible instability. Since distributed routing offers stronger robustness against link failures compared to centralized routing, the proposed adaptive routing approach offers desirable robustness and further benefits from the controller assistance via iterative search of better OSPF weights.

Fog computing, evolves from the cloud and migrates the computing to the edge, is a promising solution to meet the increasing demand for ultra-low latency services in wireless networks. Via the forward-looking perspective, we advocate a Fog Radio Access Network (F-RAN) model, which leverages the existing infrastructure such as small cells with limited computing power, to achieve the ultra-low latency by joint edge computing and near-range communications across multiple Fog groups. We formulate the low latency design as an NP-hard optimization problem, which demonstrates the tradeoff between communication and computing in the time domain. Due to each F-RAN node's potential as each user's master F-RAN node with 1) different self computing power; and 2) different cooperative power of assisted F-RAN nodes, we first tackle globally optimized master F-RAN node selection for each user and propose a latency-driven cooperative Fog algorithm with dynamic programming solution for simultaneous selection of the F-RAN nodes to serve proper heterogeneous Fog resource allocation for multi-Fog groups. Considering the limited heterogeneous Fog resources shared among all users, we propose the one-for-all strategy for every user putting him/herself into others' shoes and reaching a “win-win” outcome. The numerical results show that the low latency services can be accomplished by F-RAN via latency-driven Fog cooperation approach.

With the advance of wireless technologies, the rapid mobile data traffic growth will lead to severe network resource consumption and exceptionally long latency to access services, especially for cloud-based applications. To tackle these issues, Fog Radio Access Network (F-RAN) is recently emerged for next generation cellular networks. F-RAN is considered as an extension of the cloud computing paradigm to the edge of the network and a highly virtualized platform that provides computing, storage, and network services for mobile devices. However, how to appropriately place virtual machines (VMs) into fog nodes in F-RAN systems is very challenging, and will significantly affect the bandwidth consumption of backhaul links. Thus this paper studies the replication-based VM placement problem, and aims at minimizing the total backhaul traffic generated by VM migrations and data transmissions. We observe that the VM placement operation should not be frequently executed and practically considers the problem in a long term aspect. Then we propose a heuristic algorithm to solve the problem. The simulation results agree our observation and show that compared with a greedy approach and an optimal algorithm, the proposed algorithm demonstrates with favorable results for the overall backhaul network usage.

Fog computing is emerging as one promising solution to meet the increasing demand for ultra-low latency services in wireless networks. Taking a forward-looking perspective, we propose a Fog-Radio Access Network (F-RAN) model, which utilizes the existing infrastructure, e.g., small cells and macro base stations, to achieve the ultra-low latency by joint computing across multiple F-RAN nodes and near-range communications at the edge. We treat the low latency design as an optimization problem, which characterizes the tradeoff between communication and computing across multiple F-RAN nodes. Since this problem is NP-hard, we propose a latency-driven cooperative task computing algorithm with one-for-all concept for simultaneous selection of the F-RAN nodes to serve with proper heterogeneous resource allocation for multi-user services. Considering the limited heterogeneous resources shared among all users, we advocate the one-for-all strategy for every user taking other's situation into consideration and seek for a "win-win" solution. The numerical results show that the low latency services can be achieved by F-RAN via latency-driven cooperative task computing.

Internet of Things (IoT) has recently emerged as an enabling technology for context-aware and interconnected “smart things.” Those smart things along with advanced power engineering and wireless communication technologies have realized the possibility of next generation electrical grid, smart grid, which allows users to deploy smart meters, monitoring their electric condition in real time. At the same time, increased environmental consciousness is driving electric companies to replace traditional generators with renewable energy sources which are already productive in user's homes. One of the most incentive ways is for electric companies to institute electricity buying-back schemes to encourage end users to generate more renewable energy. Different from the previous works, we consider renewable energy buying-back schemes with dynamic pricing to achieve the goal of energy efficiency for smart grids. We formulate the dynamic pricing problem as a convex optimization dual problem and propose a day-ahead time-dependent pricing scheme in a distributed manner which provides increased user privacy. The proposed framework seeks to achieve maximum benefits for both users and electric companies. To our best knowledge, this is one of the first attempts to tackle the time-dependent problem for smart grids with consideration of environmental benefits of renewable energy. Numerical results show that our proposed framework can significantly reduce peak time loading and efficiently balance system energy distribution.

With the increasing demand for ultra-low latency services in 5G cellular networks, fog with edge computing is one of promising solutions which migrate the computing from the cloud to the edge of the network. Rather than relying on the distant cloud or additional servers, we propose the Fog-Radio Access Network (F-RAN), which leverages the current infrastructures in the radio access network, such as small cells and macro base stations, to pursue the ultra-low latency by joint powerful computing of multiple F-RAN nodes and near-range communications at the edge. The optimization problem is firstly formulated to tackle the tradeoff between communication and computing resources into time domain within distributed computing scenario, and then we propose a cooperative task computing operation algorithm to simultaneously decide how many F-RAN nodes should be selected with proper communication resource allocation and computing task assignment. The numerical results show that the ultra low-latency services can be achieved by F-RAN via cooperative task computing.

With the rapid growth of mobile broadband traffic, adopting small cell is a promising trend for operators to improve network capacity with low cost. However, static small cells cannot be flexibly placed to fulfill time/space-varying traffic. The static small cells might stay in idle or under-utilized mode during some time periods, which wastes resources. Therefore, this paper utilizes the mobile small cell concept and studies the deployment problem for mobile small cells. The objective is to maximize the service time provided by mobile small cells for all users. If a finite number of mobile small cells can serve more users for more time, the mobile small cell deployment will have more gains. Specifically, we show an interesting trade-off in the service time maximization. Then, we prove our target problem is NP-hard and propose an efficient mobile small cell deployment algorithm to deal with the trade-off to maximize the total service time. We construct a series of simulations with realistic parameter settings to evaluate the performance of our proposed algorithm. Compared with a static small cell deployment algorithm and a random mobile small cell deployment algorithm, the simulation results show that our proposed scheme can significantly increase the total service time provided for all users.

With the rapid growth of mobile data traffic, operators are expected to densely deploy base stations to meet user demands. Recent researches have indicated that the densely deployed base stations lead to the significant increase of the operational expenses of operators due to the electricity bills to maintain their operation, and thus the profit of operators is greatly decreased. Different from the past works in dynamically switching on/off base stations for energy saving, we propose to consider the benefits of users in service fee discounts as a joint optimization process in cutting down the energy consumption of base stations to maximize the total profit of operators. The optimization problem is formulated and shown being NP-hard. We then propose a profit-aware algorithm to switch off base stations, as needed, with the adjustment of the data rates provided to the users who are willing to receive discounts. The simulation results show that the proposed algorithm can significantly increase the total profit of operators and introduce a win-win situation to both users and operators.

Wireless charging technology is considered as one of the promising solutions to solve the energy limitation problem for large-scale wireless sensor networks. Obviously, charger deployment is a critical issue since the number of chargers would be limited by the network construction budget, which makes the full-coverage deployment of chargers infeasible. In many of the applications targeted by large-scale wireless sensor networks, end-devices are usually equipped by the human and their movement follows some degree of regularity. Therefore in this paper, we utilize this property to deploy chargers with partial coverage, with an objective to maximize the survival rate of end-devices. We prove this problem is NP-hard, and propose an algorithm to tackle it. The simulation results show that our proposed algorithm can significantly increase the survival rate of end-devices. To our knowledge, this is one of very first works that consider charger deployment with partial coverage in wireless rechargeable sensor networks.