Using solar power to drive ground sensors in a UAV-IoT MEC system deployed in inaccessible or hazardous areas provides a sustainable solution to battery replacement for IoT sensors. Nevertheless, this approach faces two critical challenges. Firstly, terrain variations and landscape shadowing cause uneven light distribution, leading to significant disparities in solar energy harvesting among nodes, which subsequently affects system throughput fairness due to unequal energy availability for data computation and task offloading; Secondly, atmospheric attenuation dynamics introduce stochastic variations in solar panel output, resulting in energy conversion instability and potential temporal battery outages. These challenges are further aggravated by the randomness of data arrival, which can destabilize the data queue. To address these difficulties, in this paper, we first design an α-fairness utility function to tackle the throughput fairness issue. After that, to handle the randomness of energy and data arrivals, we employ a Lyapunov-based optimization approach to maximize the long-term system utility function, formulating the problem as a multi-stage online stochastic optimization, with time average constraints on solar energy supply, data queue stability, and energy consumption of the sensor. We then decompose the original problem into a series of deterministic per-slot optimization problems to decouple control solutions across slots. Afterward, we iteratively optimize the data admission control, communication and computation resource allocations, and the UAV’s trajectory in each slot. The proposed scheme has low computation complexity for online execution. Extensive simulations demonstrate its effectiveness in achieving application-specific throughput fairness while maintaining energy and data queue stability under fluctuating working conditions. In addition, compared with benchmark algorithms, our scheme achieves higher system throughput through more judicious resource management and trajectory control strategies.

Learning network representations, also known as network embeddings, has attracted significant attention in recent years. Real-world scenarios often involve networks with multiple views, where each view captures a distinct aspect of the network’s structure. Existing network embedding methods mainly focus on the global information from each view, neglecting the implied relations among multiple views. Additionally, maintaining the scalability of node embeddings while adapting to changes in network topology remains a major challenge. To this end, this article proposes a Cloud-edge Collaboration Network (CC-Net) to learn robust node embeddings in multi-view networks. Specifically, we design a decomposition and regrouping module to capture implied relations within multi-view networks, enabling the generation of comprehensive node representations that integrate information from all sub-networks. Besides, by leveraging the hybrid approach of cloud and edge computing, our proposed CC-Net can efficiently handle the complexities and dynamics of multi-view networks without retraining the entire network. Extensive experiments and analyses on real-world Twitter and YouTube datasets demonstrate the superiority of our approach compared to several benchmark methods, and validate its effectiveness in capturing implied relations and generating robust node embeddings.

Using solar power to drive ground sensors in a UAV-assisted IoT MEC system deployed in inaccessible or hazardous areas offers a sustainable solution to battery replacement for IoT sensors. However, the uneven distribution of solar power leads to unbalanced throughput among sensors. Additionally, fluctuations in solar energy and the stochastic nature of data arrivals destabilize the energy and data queues. To address these issues, we first design an α-fairness utility function to ensure throughput fairness. Then, to stabilize the system queues, we employ Lyapunov optimization to maximizing the utility by formulating it as a multi-stage online stochastic optimization problem. We decompose the original problem into a series of deterministic per-slot optimizations and iteratively optimize data admission control, resource allocation, and the UAV’s trajectory in each time slot. The proposed scheme achieves the desired level of throughput fairness in time-varying environments. Moreover, compared to benchmark algorithms, it attains higher system throughput and energy efficiency.

Semantic communication (SC) has emerged as a promising paradigm for upcoming intelligent applications, enabling mobile devices to collaboratively execute intelligent tasks with edge servers through computation offloading. However, few studies have addressed the problem of collaborative inference in SC networks. Traditional collaborative inference mechanisms may suffer performance decline in SC systems and are vulnerable to eavesdroppers. To address these issues, first, we present an encryptor that encrypts semantic information to avoid privacy leakage and a decryptor for restoration. Besides, we propose a novel SC-empowered edge computing framework enabling mobile devices to deploy a partial semantic encoder and offload the rest to edge servers. Based on this framework, we formulate the collaborative inference optimization problem, jointly optimizing delay, energy consumption, and privacy leakage. DNNPart is devised based on deep deterministic policy gradient to address the problem, which consists of a semantic attention mechanism that enables it to focus on important state variables, a hybrid action representation method that makes it adapt to mixed discrete and continuous action spaces, a dynamic model splitting algorithm that locates the optimal partition layer and adaptively splits the semantic coders. Integrated with these components, DNNPart iteratively optimizes the offloading strategy to find the optimal offloading strategy. Extensive simulations were conducted to verify the effectiveness of the proposed method by comparing it with baseline mechanisms.

Mobile edge computing (MEC) decentralizes the computational and storage capabilities of the network to edge nodes, providing support for the dynamic deployment and rapid response of mobile services. However, the large-scale distributed deployment of edge nodes, their widespread geographic distribution, multi-dimensional and complexly dependent service characteristics, and the dynamically changing network environment pose challenges to energy-efficient service deployment. In this paper, we consider multi-dimensional features for service deployment, including dynamic traffic demand, geography information, service semantics, and service popularity, with the aim of improving the availability of edge services and reducing network energy consumption. Firstly, to handle the large volume of edge service data, we design a multi-dimensional feature extraction approach based on the Transformer model, which does not rely on the sequential order of data and can enhance computational efficiency of edge models through parallel processing. Then, to adapt to the dynamically changing edge network environment, we propose an Energy-Efficient Service Deployment algorithm (EESD) based on the improved Dueling Deep Q-Network, which makes service deployment and base station switching decisions in a learning-based manner. Finally, simulation results demonstrate that EESD outperforms comparison algorithms in terms of model convergence, system total cost, and energy consumption.

Virtual reality (VR) provides users with an immersive and interactive experience through head-mounted devices, which has attracted increasing attention in recent years. Specifically, tile-based VR content transmission provides a promising approach to alleviate the conflict between limited bandwidth and high-performance requirements (e.g., high-resolution and low-delay). However, the tiling pattern affects the encoding efficiency and visual distortion of the VR content. Accounting for this issue, in this paper, a quality of experience (QoE)-aware cost minimization problem is investigated for a tile-based VR content transmission scenario. In particular, an edge server (ES) co-located at a cellular base station (BS) separates its generated VR content into several tiles according to the tiling pattern selection, and a weighted-to-spherically-uniform quality model is used to evaluate the effect of different tiling patterns on QoE. Moreover, to improve the transmission performance between the edge server and VR users (VRUs), unmanned aerial vehicles (UAVs) are leveraged as relay points to provide line of sight channels. Then, we formulate an optimization problem to minimize the sum of weighted total energy consumption and VR content distortion (i.e., QoE-aware cost) by jointly optimizing the tiling pattern selections, the VRUs-UAV grouping, partial computing decisions, and resource allocation. The formulated problem is a mixed integer non-linear programming problem, which is challenging to solve. To address this difficulty, we equivalently decompose the formulated problem into three subproblems and propose corresponding algorithms to solve them, respectively. Numerical results demonstrate that our proposed solution can effectively reduce the QoE-aware cost for VR content transmission in comparison with other baseline algorithms.

Federated edge learning(FEEL) is a popular distributed learning framework for privacy-preserving at the edge, in which densely distributed edge devices periodically exchange model-updates with the server to complete the global model training. Due to limited bandwidth and uncertain wireless environment, FEEL may impose heavy burden to the current communication system. In addition, under the common FEEL framework, the server needs to wait for the slowest device to complete the update uploading before starting the aggregation process, leading to the straggler issue that causes prolonged communication time. In this paper, we propose to accelerate FEEL from two aspects: i.e., 1) performing data compression on the edge devices and 2) setting a deadline on the edge server to exclude the straggler devices. However, undesired gradient compression errors and transmission outage are introduced by the aforementioned operations respectively, affecting the convergence of FEEL as well. In view of these practical issues, we formulate a training time minimization problem, with the compression ratio and deadline to be optimized. To this end, an asymptotically unbiased aggregation scheme is first proposed to ensure zero optimality gap after convergence, and the impact of compression error and transmission outage on the overall training time are quantified through convergence analysis. Then, the formulated problem is solved in an alternating manner, based on which, the noveljoint compression and deadline optimization(JCDO) algorithm is derived. Numerical experiments for different use cases in FEEL including image classification and autonomous driving show that the proposed method is nearly 30X faster than the vanilla FedSGD algorithm, and outperforms the state-of-the-art schemes.

Time series data widely exist in public services, industrial environments, and military applications. Traditionally, the transmission of a huge volume of data for analytic tasks poses challenges, particularly in mobile environments with limited computing and communication resources. Semantic communication emerges as a solution for intelligently extracting various features from source data and efficiently transmitting task-related information to receivers, thereby reducing bandwidth consumption significantly. In this paper, we introduce a novel federated semantic communication system tailored for forecasting-oriented time series transmission tasks. The correlation of source data collected from terminal devices is mined and the corresponding semantic information is transmitted to an edge server for collaborative inference. To optimize the semantic analysis process, we devise a deep decomposition block at the transmitter side, decomposing time series into trend and multiple period components. This reduces noise interference from wireless channels, enhancing the overall transmission quality. For effective training and collaborative inference, we propose a Federated Mixture of period Routers (FedMoR) architecture. Within each channel encoder, period routers are divided into private and public ones. Private routers extract specialized features from individually collected data, mitigating accuracy degradation. Public routers share knowledge across all transmitters, enhancing temporal analysis robustness. Simulation results demonstrate that the proposed system outperforms two traditional technique-based and two semantic communication-based baselines under three common channels. The system achieves low mean square errors on five widely-used real-world time series forecasting datasets, particularly in the low signal-to-noise ratio regime.

Non-orthogonal multiple access (NOMA)-aided mobile edge computing (MEC) system can enhance the spectral-efficiency with massive tasks offloading. However, with more dynamic devices and the uncontrollable stochastic channel environment, it is even desirable to deploy appealing technique, i.e., intelligent reflecting surfaces (IRS), in the MEC system to flexibly adjust the communication environment and improve the system energy-efficiency. In this paper, we investigate the joint offloading, communication and computation resource allocation for IRS-assisted NOMA-aided MEC system. We firstly formulate a mixed integer energy-efficiency maximization problem with the system queue stability constraint. We then propose a Het-erogeneous Multi-agent Lyapunov-function-based Mixed Integer Deep Deterministic Policy Gradient (HMA-LMIDDPG) algorithm which is based on the multi-agent reinforcement learning (MARL) framework with homogeneous edge devices (EDs) and heterogeneous base station (BS) as heterogeneous multi-agent. Numerical results show that our proposed algorithms can achieve superior energy-efficiency performance to the benchmark algorithms while maintaining the queue stability.

Federated learning (FL) has been considered as a promising paradigm for enabling distributed machine learning (ML) in wireless networks. To address the limited energy capacity of wireless devices, we propose a simultaneous wireless information and power transfer (SWIPT) aided FL, in which one FL server (FLS) co-located at a cellular base station (BS) uses SWIPT to simultaneously broadcast the global model to wireless user-devices (UDs) and provide wireless power transfer to them. The UDs then use the harvested energy to train their local models and further transmit the local models to the FLS for aggregation. To improve the spectrum efficiency, we consider that the UDs form a non-orthogonal multiple access (NOMA) group for simultaneously sending their local models over the same spectrum channel. Taking the UDs’ time-varying available energy and channel conditions into account, we propose a dynamic optimization of the UDs-scheduling, the BS's transmit-power allocation, and the UDs’ power-splitting factors for SWIPT, with the objective of minimizing the long-term energy consumption while ensuring the FL convergence. The optimization problem, however, is challenging to solve since it is a finite-horizon dynamic programming problem but with an unknown stopping time, and moreover, the action space covers both discrete and continuous variables. To address these difficulties, we first execute a series of equivalent transformations to reduce the number of decision variables and then formulate the problem as a stochastic shortest path problem, based on which we propose an actor-critic deep reinforcement learning algorithm with the proximal policy optimization to efficiently learn the policy that dynamically adjusts the UDs-scheduling for FL as well as the BS's transmit-power for SWIPT. Numerical results validate the effectiveness and performance of our proposed algorithm. The results demonstrate that our proposed algorithm can effectively reduce the long-term energy consumption in comparison with two baseline algorithms.

By employing powerful edge servers for data processing, mobile edge computing (MEC) has been recognized as a promising technology to support emerging computation-intensive applications. Besides, non-orthogonal multiple access (NOMA)-aided MEC system can further enhance the spectral efficiency with massive tasks offloading. However, with more dynamic devices brought online and the uncontrollable stochastic channel environment, it is even desirable to deploy appealing technique, i.e., intelligent reflecting surfaces (IRS), in the MEC system to flexibly tune the communication environment and improve the system energy efficiency. In this paper, we investigate the joint offloading, communication and computation resource allocation for the IRS-assisted NOMA MEC system. We first formulate a mixed integer energy efficiency maximization problem with system queue stability constraint. We then propose the Lyapunov-function-based Mixed Integer Deep Deterministic Policy Gradient (LMIDDPG) algorithm which is based on the centralized reinforcement learning (RL) framework. To be specific, we design the mixed integer action space mapping which contains both continuous mapping and integer mapping. Moreover, the award function is defined as the upper-bound of the Lyapunov drift-plus-penalty function. To enable end devices (EDs) to choose actions independently at the execution stage, we further propose the Heterogeneous Multi-agent LMIDDPG (HMA-LMIDDPG) algorithm based on distributed RL framework with homogeneous EDs and heterogeneous base station (BS) as heterogeneous multi-agent. Numerical results show that our proposed algorithms can achieve superior energy efficiency performance to the benchmark algorithms while maintaining the queue stability. Specially, the distributed structure HMA-LMIDDPG can acquire more energy efficiency gain than the centralized structure LMIDDPG.

With the rapid development of Internet of Things (IoTs), various sensors are deployed to collect different physical information. Smart surveillance is one of applications by analyzing the real-time video generated by camera sensors. However, due to the limited computing capability of camera sensors, running video analysis models (e.g., AlexNet and YOLO3) on camera sensors directly consumes a lot of computing time. In addition, transferring video to the remote cloud suffers a long-distance transmission latency. Fortunately, edge computing has been considered as a promising solution for enabling computation-intensive yet latency-sensitive applications at resource-constrained devices. Thanks to edge computing, camera sensors can upload video to different edge servers employed at the edge of networks for processing. Moreover, the lightweight Kubernetes for edge computing, i.e., K3s, enable a fine-grained task division and parallel computing. In this paper, we consider a heterogeneous edge cooperative video analysis, i.e., face recognition, with the objective of minimizing the processing latency. Specifically, we use a Deep Q-Learning network (DQN) to dynamically adjust the size of pieces video allocated to different edge servers connected via wireless networks. In addition, to improve the resource utilization of edge servers and reduce the processing latency, each edge server further divides the received video into multiple segments that are processed by different containers in parallel. To validate the effectiveness of our scheme, we implement a small-scale prototype system and conduct numerous experiments. Experimental results show that our proposed algorithm outperforms the other four schedule schemes by testing on the tasks of face recognition and pose recognition.

Nowadays, sensor-cloud systems have received wide attention from both academia and industry. Sensor-cloud system not only improves performances of wireless sensor networks (WSNs), but also combines different functional WSNs together to provide comprehensive services. However, a variety of malicious attacks threaten the sensor-cloud security, such as integrity, authenticity, availability and so on. Traditional available security mechanisms (e.g., cryptography and authentication) are still vulnerable. Although there are schemes to provide security by trust evaluation, the evaluation considers whether or not a sensor is credible only by checking the communication behaviors. Furthermore, when mobile sensor sinks are employed to collect sensing data, there appears a type of attacks called replicated sink attacks that are often ignored in the previous work. These attacks may bring serious vulnerability to trustworthy data collection in sensor-cloud systems. In this paper, we propose a comprehensive trustworthy data collection (CTDC) approach for sensor-cloud systems. Three kinds of trust, i.e., direct trust, indirect trust, and functional trust are defined to evaluate the trustworthiness of both sensors and mobile sinks. Except for resisting malicious attacks, the performances of sensor-cloud, such as energy, transmission distance and network throughput are also considered. We also conduct extensive simulations to evaluate the efficiency of CTDC. The simulation results show that CTDC correctly identifies malicious nodes and offers an improved performance in the data collection.

Mobile edge computing (MEC) has been envisioned as an efficient solution to provide computation-intensive yet latency-sensitive services for terminal devices. In this paper, we investigate multi-user computation off loading in MEC and propose a joint optimization of off loading decisions, bandwidth and computation-resource allocations, with the objective of minimizing the total latency for completing all users' tasks. Due to the non-convexity of the formulated joint optimization problem, we identify its layer structure and decompose it into two problems, i.e·, a sub-problem and a top-problem. For the sub-problem, we propose a bisection-search based algorithm to efficiently find the optimal off loading solutions under a given feasible top-problem solution. Then, we use a linear-search based algorithm to obtain the optimal solution of the top-problem. Numerical results are provided to validate our proposed algorithm for minimizing the total latency in MEC-based multi-user computation off loading. We also demonstrate the advantage of our proposed algorithm in comparison with the conventional multi-user computation off loading schemes.

The development of cloud computing pours great vitality into traditional wireless sensor networks (WSNs). The integration of WSNs and cloud computing has received a lot of attention from both academia and industry. However, collecting data from WSNs to cloud is not sustainable. Due to the weak communication ability of WSNs, uploading big sensed data to the cloud within the limited time becomes a bottleneck. Moreover, the limited power of sensor usually results in a short lifetime of WSNs. To solve these problems, we propose to use multiple mobile sinks (MSs) to help with data collection. We formulate a new problem which focuses on collecting data from WSNs to cloud within a limited time and this problem is proved to be NP-hard. To reduce the delivery latency caused by unreasonable task allocation, a time adaptive schedule algorithm (TASA) for data collection via multiple MSs is designed, with several provable properties. In TASA, a non-overlapping and adjustable trajectory is projected for each MS. In addition, a minimum cost spanning tree (MST) based routing method is designed to save the transmission cost. We conduct extensive simulations to evaluate the performance of the proposed algorithm. The results show that the TASA can collect the data from WSNs to Cloud within the limited latency and optimize the energy consumption, which makes the sensor-cloud sustainable.