With the widespread application of the Internet of Things (IoT), computing tasks on the terminal side have surged. Traditional cloud computing models, constrained by high network latency and overloaded central servers, can no longer effectively meet the dual requirements of real-time responsiveness and energy efficiency. The cloud–edge–device collaborative architecture, by enabling distributed resource scheduling, offers a promising solution to reduce both latency and energy consumption. However, optimizing carbon emissions under dynamic operating conditions remains a pressing and unresolved challenge. This paper proposes a carbon-aware dynamic scheduling framework for cloud–edge–device systems, which accounts for the stochastic nature of task arrivals, heterogeneous computing capabilities, and varying carbon intensity across devices and locations. A multi-layer carbon emission model is developed, and the long-term carbon minimization objective is formulated as a stochastic optimization problem. Using the Lyapunov drift-plus-penalty method, the problem is transformed into a tractable deterministic optimization framework, upon which a Carbon-Efficient Computation Offloading (CECO) algorithm is designed. CECO jointly optimizes local computation frequency, data transmission rate, and edge resource allocation to dynamically balance task queue stability and carbon emission intensity. Theoretical analysis and simulation results validate that the proposed algorithm significantly reduces system-level carbon emissions while maintaining quality of service, demonstrating strong potential for enabling green computing in intelligent distributed environments.

Mobile multimedia applications such as real-time video processing, augmented reality, and mobile gaming have raised high requirements for low latency and high efficiency. Edge-based autonomous systems have become a key technology for processing these application tasks. This article focuses on joint resource allocation and task slicing for mobile multimedia computing in edge-based autonomous systems. We propose an efficient resource allocation and task slicing strategy, aiming at the optimization of the overall utility of both edge servers and mobile devices simultaneously. We transform the resource allocation problem into resource pricing and purchasing behaviors. We present a Stackelberg game model and prove theorems for the existence of equilibrium and optimality. Based on the theorems, we design an algorithm namely G-RPTSS for resource purchasing and computation task slicing. Then, we employ Deep Reinforcement Learning (DRL) techniques in resource pricing and propose the DRL-ESRP algorithm which is capable of adaptively responding to dynamic computational scenarios in edge-based autonomous systems. Our scheme leverages the DRL technique for autonomous learning and policy adjustment. Simulation experiments, based on real-world scenario data, demonstrate the superior of our approach in learning efficiency and performance advantages to existing both non-DRL and other DRL algorithms.

Multi-access Edge Computing (MEC) can effectively process Internet of Things (IoT) data by transferring computing intensive tasks to edge servers, and has become an effective mechanism to meet the growing demand for computing. The flexible Unmanned Aerial Vehicle (UAV) and High-Altitude Platform (HAP) with powerful resources working together can significantly improve the efficiency of edge computing system. This paper investigates the resource allocation and trajectory optimization problems in HAP-UAV-MEC system with a Non-Orthogonal Multiple Access (NOMA) communication scenario. By utilizing Wireless Power Transfer (WPT) technology to provide energy support for UAV, we jointly optimize UAV trajectories, resource allocation, and offloading decisions to minimize the energy cost of IoT devices and the energy cost of UAV. This problem is described as a multi-stage Mixed Integer Nonlinear Program ming (MINLP) problem. A Deep Deterministic Policy Gradient (DDPG)-Attention-based Resource Allocation and Trajectory Optimization (DART) algorithm combining Deep Reinforcement Learning (DRL) and Lyapunov optimization techniques is proposed to address this issue. DART algorithm utilizes the Lyapunov technique to transform the multi-stage MINLP problem into a deterministic optimization problem, and decomposes the original problem into four parallel subproblems. Through DDPG-attention algorithm based on reinforcement learning and deep learning attention mechanisms, we solve the problems of trajectory optimization and offloading decision. Meanwhile, for remaining subproblems related to resource allocation, convex optimization is used to solve them. The experimental results verify that the DART algorithm can significantly reduce the total cost while ensuring system stability and performance.

With the popularization of mobile devices, mobile crowdsensing (MCS) has become a paradigm with broad application prospects. However, traditional MCS face numerous challenges, such as surges in network traffic and infrastructure failures. To address these issues, we leverage flexible and low-cost Unmanned Aerial Vehicles (UAVs) in the MCS framework. UAV-assisted crowdsensing (UCS) provides an innovative approach to data collection that effectively addresses problems such as insufficient network coverage and congestion. In the UCS framework, UAVs can serve not only as temporary base stations (BSs) but also participate in collecting data and processing tasks. Nevertheless, the lack of adequate incentive mechanisms may lead both UAVs and mobile users to be reluctant to participate in sensing tasks. Therefore, this paper aims to investigate hierarchical incentive mechanisms for UCS. Considering the freshness of the collected data and the benefits of the platform, we adopt the Age of Information (AoI) metric to measure the quality of data. To ensure AoI of data, we model the incentive mechanisms from both the UAV and user perspectives, and we formulate them as single-dimensional and multi-dimensional contract-based incentives under scenarios of information asymmetry. Furthermore, we derive the optimal contract scheme under the constraints of individual rationality and incentive compatibility. Finally, experimental results confirm the effectiveness of the proposed contract design and maximize the utility of the model owner.

In light of the frequent disaster events worldwide, the risk of communication network disruptions is increasingly prominent. Unmanned Aerial Vehicle (UAV) with flexibility and maneuverability is considered an effective solution for rapid service provisioning. Meanwhile, Non-Orthogonal Multiple Access (NOMA) enables simultaneous access for multiple User Equipments (UEs) on the same frequency band, enhancing spectral efficiency. This paper investigates a system that integrates NOMA with UAV-assisted Mobile Edge Computing (MEC) to provide efficient computational services. First, we construct a system model of UE task offloading and UAV deployment to reduce the overall service cost. Each UE and UAV strive to minimize their own cost. Then, the problem is modeled as the User Task Offloading and UAV Deployment Game (UTUD Game), and it is theoretically proven that at least one Nash equilibrium strategy exists for the offloading and deployment selection. Further, a decentralized algorithm based on game theory named Distributed Iterative Co-optimization for Offloading and Deployment (DICOD) algorithm is proposed to achieve this strategy. The performance of the algorithm is analyzed theoretically. Finally, we conduct experiments to analyze the upper bound of convergence time and evaluate the algorithm's performance in comparison with some other benchmarks.

Federated Learning (FL) is an emerging distributed learning model that enables multiple devices to collaboratively train a shared model. However, in practical scenarios, device heterogeneity can cause outdated model parameters in synchronous FL. To address this issue, asynchronous updates are introduced to mitigate delays in parameter updates. However, asynchronous updates can lead to imbalanced updates, resulting in excessive energy consumption and reduced model accuracy. To tackle these challenges and ensure both parameter freshness and efficient resource utilization, this paper introduces Age of Information (AoI) as a metric to measure model freshness and optimizes AoI to ensure parameter freshness. Additionally, we consider Age of Peak (AoP) and impose a constraint on peak age to prevent prolonged periods of stale parameters, which lead to inaccurate models. Based on this, we formulate an optimization problem involving update decisions and resource allocation, aiming to optimize AoI and energy consumption while imposing a constraint on AoP. Since asynchronous updates and training delays are both stochastic and dynamic, we employ stochastic optimization techniques to decompose the problem into two subproblems and design a low-complexity algorithm using optimization theory. Extensive experimental results demonstrate the proposed framework's effectiveness in improving parameter freshness and energy efficiency.

With the arrival of the 6G era, there is a rapid increase in computational demands, and multiaccess edge computing (MEC) has emerged as an effective mechanism to satisfy these needs. In disaster-affected or remote areas where ground base stations may struggle to provide service, unmanned aerial vehicle (UAV), and high-altitude platforms (HAPs) can leverage their flexible deployment capabilities to offer MEC services. In this article, we design a layered aerial computing framework comprising user equipments (UEs), UAV, and HAP. Building upon this, we establish a hierarchical offloading computation model and formulate an optimization problem to maximize resource utilization and task scheduling within the model. Specifically, the objective is to minimize task computation delay and maximize the remaining energy of the UAV, i.e., minimize energy consumption, subject to constraints on the total task quantity, delay requirements and UAV energy limitations. Due to the nonconvex and highly complex nature of this objective problem, we propose a deep reinforcement learning-based trajectory optimization and task offloading (DTOTO) algorithm that enables the agent, the UAV, to make correct decisions in complex environments and high-dimensional action spaces. The algorithm is capable of optimizing the UAV’s trajectory to obtain the correct offloading decisions. Additionally, we employ state normalization to improve training efficiency. Simulation experiment results validate the effectiveness of the computing framework and the DTOTO algorithm, and numerical results analyze to evaluate system performance.

Autonomous aerial vehicles (AAV) are regarded as a promising technology to provide additional computing capabilities and wide coverage for Internet of Things (IoT) devices, particularly in cases where these devices are situated beyond the reach of traditional communication infrastructure. This study investigates an AAV-assisted multiaccess edge computing (MEC) network comprising multiple AAVs with edge servers and several IoT Devices (IoTDs). IoTDs with a substantial number of computation tasks can select to offload their tasks to AAV-assisted edge servers to alleviate pressure and costs, while the AAV-assisted edge servers can profit from selling computing resources. The interaction between AAV-assisted edge servers and IoTDs is modeled as a Stackelberg game, where both entities aim to maximize their utility. Employing backward induction, the existence of a unique Nash equilibrium is proved. Subsequently, a Stackelberg game-based distributed computation offloading (SDCO) algorithm is designed to approximate the optimal solution. Finally, extensive simulations validate the effectiveness of the SDCO algorithm, demonstrating superior performance compared to other benchmark methods across diverse scenarios.

Due to the limitations of computing resources and battery capacity, the computation tasks of ground devices can be offloaded to edge servers for processing. Moreover, with the development of the low earth orbit (LEO) satellite technology, LEO satellite-terrestrial edge computing can realize a global coverage network to provide seamless computing services beyond the regional restrictions compared to the conventional terrestrial edge computing networks. In this paper, we study the computation offloading problem in the LEO satellite-terrestrial edge computing systems. Ground devices can offload their computation tasks to terrestrial base stations (BSs) or LEO satellites deployed on edge servers for remote processing. We formulate the computation offloading problem to minimize the cost of devices while satisfying resource and LEO satellite communication time constraints. Since each ground device competes for transmission and computing resources to reduce its own offloading cost, we reformulate this problem as the LEO satellite-terrestrial computation offloading game (LSTCO-Game). It is derived that there is an upper bound on transmission interference and computing resource competition among devices. Then, we theoretically prove that at least one Nash equilibrium (NE) offloading strategy exists in the LSTCO-Game. We propose the game-theoretical distributed computation offloading (GDCO) algorithm to find the NE offloading strategy. Next, we analyze the cost obtained by GDCO's NE offloading strategy in the worst case. Experiments are conducted by comparing the proposed GDCO algorithm with other computation offloading methods. The results show that the GDCO algorithm can effectively reduce the offloading cost.

Unmanned Aerial Vehicle (UAV)-assisted Low Earth Orbit (LEO) satellite edge computing (ULSE) networks can address the challenge communications issues in areas with harsh terrain and achieve global wireless coverage to provide services for mobile user devices (MUDs). This paper studies the LEO-UAV task offloading problem where MUDs compete for limited resources in the ULSE networks. We formulate the optimization problem with the goal of minimizing the cost of all MUDs while meeting resource constraint and satellite coverage time constraint. We first theoretically prove that this problem is NP-hard. We then reformulate the problem as a LEO-UAV task offloading game (LUTO-Game), and show that there is at least one Nash equilibrium solution for the LUTO-Game. We propose a joint UAV and LEO satellite task offloading (JULTO) algorithm to obtain the Nash equilibrium offloading strategy, and analyze the performance of the worst-case offloading strategy obtained by the JULTO algorithm. Finally, extensive experiments, including convergence analysis and comparison experiments, are carried out to validate the effectiveness of our JULTO algorithm.

Mobile Edge Computing (MEC), as a highly promising technology, effectively processes computation-intensive tasks by offloading them to edge servers. Utilizing the advantages of Unmanned Aerial Vehicles (UAVs) in deployment flexibility and broad coverage, UAV-assisted edge computing can significantly enhance system efficiency. This paper studies a scenario where a UAV-MEC system serves multiple Mobile Users (MUs) with random task arrivals and movements. We minimize the energy consumption of MUs by jointly optimizing UAV trajectory and resource allocation for MUs subjected to the UAV energy limit. The problem is formulated as a multi-stage Mixed-Integer Nonlinear Programming (MINLP) problem. To address this, we propose an algorithm called JTORA integrated Deep Reinforcement Learning (DRL) and Lyapunov optimization techniques. Specifically, we initially transform the multi-stage MINLP problem into a deterministic optimization problem utilizing Lyapunov techniques and decompose the original problem into two sub-problems in parallel. Through DRL, we solve the first sub-problem of trajectory and communication resources optimization. For the second sub-problem involving computing resource allocation, convex optimization is employed to get the optimal solution. Theoretical analysis and experimental results demonstrate that the JTORA algorithm can effectively reduce the energy consumption of MUs while ensuring UAV endurance.

Due to the limited battery capacity and computational resources of mobile devices, computation-intensive tasks generated by mobile devices can be offloaded to edge servers for processing. This paper investigates the multi-user task offloading and resource pricing issues in Autonomous aerial vehicle (AAV)-assisted Multi-Access Edge Computing (MEC) systems. The optimization objectives is optimizing the utility of the server and the utility of the Edge Users (EUs), with decision variables encompassing the offloading strategies of EUs and the pricing strategies of the server. We divide the entire optimization problem into two parts. When optimizing the server's utility, server energy consumption is a crucial metric; hence, in the first part, we formulate the user allocation problem with the goal of minimizing the server's overall energy consumption. Utilizing game theory, we transform the user allocation problem into a multi-user non-cooperative game and prove the existence of a Nash Equilibrium (NE). The Game-based User Allocation (GBUA) algorithm is proposed to obtain the user allocation strategy. After addressing the user allocation problem, we consider the simultaneous optimization of both server and EUs utility. Therefore, in the second part, we model the server and EUs's engagement using the Stackelberg game model and employ backward induction to verify the presence of a Stackelberg Equilibrium (SE). Additionally, we propose the Resource Pricing and Task Offloading (RPATO) algorithm, based on game theory, to obtain the SE solution. Finally, extensive experiments are conducted to validate the effectiveness of the proposed algorithms, and numerous comparative algorithms are tested to prove the advancement and innovation of our proposed algorithms.

In UAV-assisted Multi-access Edge Computing (MEC) systems, UAV trajectories and resource pricing directly determine system utility - improper UAV positioning will lead to increased delay and energy costs for users, while inappropriate pricing will result in insufficient task offloading or UAV overload. This paper aims to optimize UAVs' trajectories, pricing strategies and users' offloading decisions, enabling UAVs to move to suitable locations and provide computing offloading services at appropriate prices, thereby reducing delay and energy, and enhancing the utilities of both UAV and users. The user utility specifically consist of throughput, energy consumption, delay penalties, and expenditures on purchasing computing resources. The UAV's utility consists of computing energy consumption, delay penalties, and revenue from selling computing resources as incentives. We formulate the pre-offloading problem to solve users' offloading selection, and transform the problem into a multi-user non-cooperative game using game theory while proving the existence of Nash equilibrium. Then we model the interaction between UAV and users using Stackelberg game model and prove the existence of Stackelberg equilibrium. We use multi-agent deep reinforcement learning (MADRL) and propose DRL and Game Theory-based Trajectory Optimization and Task Offloading (DGTT) algorithm to solve UAVs' trajectories and obtain the Stackelberg equilibrium solution. We sequentially solve for the pricing strategy and offloading decisions, thereby obtaining the optimized utilities of both UAV and users. Finally, we conduct simulation experiments to verify the feasibility of DGTT algorithm, along with comparative experiments that demonstrate our proposed DGTT algorithm's excellent performance in optimizing UAV and user utilities, while reducing system energy consumption and delay.

With the rapid development of 5G technology, the service demand in various application scenarios is continuously increasing. Mobile edge computing (MEC) has become a popular computing paradigm by placing services and corresponding computing resources to edge servers to satisfy the low latency demands of users. However, edge servers lack a stable infrastructure for protection and limited storage space and computing power. Considering the reliability and stability of the edge system, efficiently placing resources and offloading tasks to the edge servers has become an urgent challenge. In this paper, we consider resource placement and task offloading strategies under different time scales to optimize the service response time in a dynamic edge system environment. We established the Markov model to obtain a quantitative relationship between system reliability and latency, and analyze the time required for resource and task offloading. Then, we propose the resource placement and task offloading (RPTO) algorithms under different time scales based on deep reinforcement learning (DRL) techniques with the aim of minimizing the cost of service providers in the long term. The experimental results demonstrate that our approach effectively tackles the challenges of joint resource placement and task offloading in the MEC.

In the evolving landscape of federated learning (FL), ensuring the active participation of local model owners (LMOs) while safeguarding data privacy and service security presents a formidable challenge. Our investigation focuses on two different information scenarios: the weakly incomplete information scenario and the strongly incomplete information scenario, which pose unique challenges to the integrity and efficiency of FL systems. In the weakly incomplete information scenario, LMOs have motivations to hide their true types. We use contract theory and exploit its self-revealing properties to ensure LMOs truthfully report their types. In the strongly incomplete information scenario, We present the Contract-based Deep Reinforcement Learning (CDRL) algorithm, which combines the strategic framework of contract theory with the adaptive capabilities of DRL. The CDRL algorithm is designed to perform real-time contract design in dynamic environments, enabling the system to respond effectively to FL participation and ensure continuous alignment of incentives with system security and learning objectives. Through extensive experimentation on a real-world dataset, our proposed mechanism has demonstrated superiority in motivating LMOs to actively participate in FL, thereby significantly improving system performance.

With the swift progress of Internet of Things (IoT) technologies, the number of IoT devices has grown exponentially, leading to an increasing demand for computational power and system stability. Mobile edge computing (MEC) is a powerful solution that allows IoT devices to offload data to the edge for computing. In situations involving disasters or complex terrains, establishing ground-based stations may be challenging in providing computational services. Edge computing frameworks built with unmanned aerial vehicles (UAVs) and high-altitude platforms (HAPs) can provide airborne computational services for IoT devices situated in environments with disasters or complex terrains. In this article, we design a three-tier framework consisting of ground users (GUs), UAVs, and HAP, offering MEC services for GUs. Considering the randomness and dynamism of task arrivals and the wireless communication quality of devices, we propose an algorithm supporting nonorthogonal multiple access (NOMA) communication in aerial access networks. The objective of the algorithm is to reduce the overall energy consumption of the system while ensuring system stability. Employing stochastic optimization techniques, we convert the task offloading and resource allocation problem into several parallel solvable subproblems. We also provide a theoretical analysis of the algorithm. Through a series of comparative experiments, we demonstrate the feasibility and effectiveness of our proposed dynamic energy-efficient computation offloading (DEECO) algorithm.

Edge caching is crucial in the Internet of Things (IoT) by accelerating content delivery and reducing latency, offering significant advantages. However, inappropriate incentive mechanisms may prevent third-party edge caching nodes from caching data. To address the incentive challenges in edge caching, this paper proposes a contract theory approach to resolve the incentive issues between content providers (Google and Microsoft) and edge caching nodes. Initially, utilizing the framework of contract theory, the security service quality of edge caching nodes is classified into a finite number of types, and transactions between content providers and edge caching nodes are modelled. Subsequently, contract packages containing popular data content and corresponding rewards are designed for different types of edge caching nodes. Utilizing the revelation principle of contract theory addresses the problem of incomplete information in the system, enabling content providers to maximize revenue. A blockchain-based reputation mechanism is employed to identify abnormal nodes within edge caching nodes. Numerical results demonstrate that, compared to other mechanisms, our proposed contracts can effectively incentivize the participation of edge caching nodes, significantly enhance content providers’ revenue, and improve content delivery efficiency and effectiveness.

As the Internet of Things (IoT) becomes ubiquitous and the demand for high-quality services increases, the limitations of traditional network models are starting to show due to endpoint resource constraints. Edge Computing, as an emerging computing paradigm, can significantly improve data processing efficiency and quality of experience by deploying edge servers with computing resources near terminal devices. However, the computing process can generate a lot of carbon emissions due to energy consumption. How to reduce energy consumption and therefore reduce carbon emissions while ensuring service latency is still a pressing issue to resolve. This article focuses on how to reasonably utilize technologies, such as mobile edge computing (MEC), nonorthogonal multiple access (NOMA), and small cell networks (SCNs) in the IoT environment, while considering service latency and energy-saving carbon reduction requirements. We model the problem as a stochastic problem involving local devices, small base stations (SBS), and macro base stations (MBSs), aiming to simultaneously ensure service latency and minimize carbon dioxide emissions. Due to uncertainties, such as task arrival rates and channel conditions, we convert the stochastic problem into a deterministic problem using mathematical optimization theory. Then, we propose an online algorithm called Carbon-aware dynamic task offloading (CADTO) which can solve the problem brought by NOMA and obtain a dynamic offloading strategy. Through theoretical analysis and simulation experiments, we prove that the CADTO algorithm can effectively reduce energy consumption and carbon emissions while ensuring service quality.

Abstract As machine learning (ML) technologies continue to evolve, there is an increasing demand for data. Mobile crowd sensing (MCS) can motivate more users in the data collection process through reasonable compensation, which can enrich the data scale and coverage. However, nowadays, users are increasingly concerned about their privacy and are unwilling to easily share their personal data. Therefore, protecting privacy has become a crucial issue. In ML, federated learning (FL) is a widely known privacy‐preserving technique where the model training process is performed locally by the data owner, which can protect privacy to a large extent. However, as the model size grows, the weak computing power and battery life of user devices are not sufficient to support training a large number of models locally. With mobile edge computing (MEC), user can offload some of the model training tasks to the edge server for collaborative computation, allowing the edge server to participate in the model training process to improve training efficiency. However, edge servers are not fully trusted, and there is still a risk of privacy leakage if data is directly uploaded to the edge server. To address this issue, we design a local differential privacy (LDP) based data privacy‐preserving algorithm and a deep reinforcement learning (DRL) based task offloading algorithm. We also propose a privacy‐preserving distributed ML framework for MEC and model the cloud‐edge‐mobile collaborative training process. These algorithms not only enable effective utilization of edge computing to accelerate machine learning model training but also significantly enhance user privacy and save device battery power. We have conducted experiments to verify the effectiveness of the framework and algorithms.

As the computing resources and the battery capacity of mobile devices are usually limited, it is a feasible solution to offload the computation-intensive tasks generated by mobile devices to edge servers (ESs) in mobile edge computing (MEC) . In this article, we study the multi-user multi-server task offloading problem in MEC systems, where all users compete for the limited communication resources and computing resources. We formulate the offloading problem with the goal of minimizing the cost of the users and maximizing the profits of the ESs. We propose a hierarchical EETORP (Economic and Efficient Task Offloading and Resource Purchasing) framework that includes a two-stage joint optimization process. Then we prove that the problem is NP-complete. For the first stage, we formulate the offloading problem as a multi-channel access game (MCA-Game) and prove theoretically the existence of at least one Nash equilibrium strategy in MCA-Game. Next, we propose a game-based multi-channel access (GMCA) algorithm to obtain the Nash equilibrium strategy and analyze the performance guarantee of the obtained offloading strategy in the worst case. For the second stage, we model the computing resource allocation between the users and ESs by Stackelberg game theory, and reformulate the problem as a resource pricing and purchasing game (PAP-Game). We prove theoretically the property of incentive compatibility and the existence of Stackelberg equilibrium. A game-based pricing and purchasing (GPAP) algorithm is proposed. Finally, a series of both parameter analysis and comparison experiments are carried out, which validate the convergence and effectiveness of the GMCA algorithm and GPAP algorithm.

In many remote areas lacking ground communication infrastructure support, such as wilderness, desert, ocean, etc., an integrated edge computing network in the air with edge computing nodes is an effective solution. It can provide over-the-air computing services for ground devices (GDs) with limited computing resources and battery life. In this paper, we study task offloading and resource allocation in the aerial-based mobile edge computing (MEC) system supported by a high altitude platform (HAP) and unmanned aerial vehicles (UAVs), with the goal of minimizing the GD's energy consumption. Considering that the task arrival of GDs and wireless communication quality are both stochastic and dynamic, we apply stochastic optimization techniques to transform this task offloading and resource allocation problem into two subproblems, i.e., 1) a subproblem for local computation resource allocation, and 2) a subproblem for offloading resource allocation. For the first subproblem, we use convex optimization methods to address it. For the second subproblem, we use game theory to formulate the competition of offloading resources among GDs and propose the Distributed Game-theoretical Multi-server Selection (DGMS) algorithm and the Transmission Power Allocation (TPA) algorithm. Finally, we propose a Distributed Online Task Offloading and Resource Allocation (DOTORA) algorithm and give the theoretical performance analysis of the algorithm. We perform extensive experiments, including the comparison experiments with the UAV-Only and HAP-Only framework, and the comparison experiments with other algorithms under our HAP-UAV framework. The experimental results validate our proposed framework and the DOTORA algorithm.

Due to the limited computing resource and battery capability at the mobile devices, the computation-intensive tasks generated by mobile devices can be offloaded to edge servers or cloud for processing. In this paper, we study the multi-user task offloading problem in an end-edge-cloud system, in which all user devices compete for the limited communication and computing resources. Particularly, we first formulate the offloading problem with the goal of maximizing the Quality of Experience (QoE) of the users subject to resource constraints. Since each user focuses on maximizing its own QoE, we reformulate the problem as a Multi-User Task Offloading Game (MUTO-Game). We then identify an important property that for any device, both the communication interference and the degree of computing resource competition can be upper bounded. Based on the property, we further theoretically prove that there exists at least one Nash Equilibrium offloading strategy in the MUTO-Game. We propose the Game-based Decentralized Task Offloading (GDTO) approach to obtain the Nash Equilibrium offloading strategy. Finally, we analyze the upper bound for the convergence time and characterize the performance guarantee of the obtained offloading strategy for the worst case. A series of experimental results are presented, in comparison with both the centralized optimal approach and the approximate approaches.

With the explosive development of mobile computing, federated learning (FL) has been considered as a promising distributed training framework for addressing the shortage of conventional cloud based centralized training. In FL, local model owners (LMOs) individually train their respective local models and then upload the trained local models to the task publisher (TP) for aggregation to obtain the global model. When the data provided by LMOs do not meet the requirements for model training, they can recruit workers to collect data. In this paper, by considering the interactions among the TP, LMOs and workers, we propose a three-layer hierarchical game framework. However, there are two challenges. First, information asymmetry between workers and LMOs may result in that the workers hide their types. Second, incentive mismatch between TP and LMOs may result in a lack of LMOs’ willingness to participate in FL. Therefore, we decompose the hierarchical-based framework into two layers to address these challenges. For the lower-layer, we leverage the contract theory to ensure truthful reporting of the workers’ types, based on which we simplify the feasible conditions of the contract and design the optimal contract. For the upper-layer, the Stackelberg game is adopted to model the interactions between the TP and LMOs, and we derive the Nash equilibrium and Stackelberg equilibrium solutions. Moreover, we develop an iterativeHierarchical-basedUtilityMaximizationAlgorithm (HUMA) to solve the coupling problem between upper-layer and lower-layer games. Extensive numerical experimental results verify the effectiveness of HUMA, and the comparison results illustrate the performance gain of HUMA.

The prosperous development of the Internet of Things (IoT) and wireless communication technologies has led to explosive growth in the number of IoT sensor devices. However, some sensor devices are inevitably deployed in remote and inaccessible areas. How to continuously and reliably power sensor devices is a critical problem that needs to be addressed. Deploying self-powered modules on sensor devices by adopting self-powered technology is an effective solution to the energy shortage of sensor devices. Besides, Mobile Edge Computing (MEC) as a promising paradigm has provoked widespread popularity. With the help of MEC, devices can offload computing tasks to edge servers for processing, which greatly alleviates the limitations on energy, storage, and computation capability of devices. In this paper, we jointly study task scheduling and resource allocation in the MEC scenario where the sensor devices are with self-powered modules. Our goal is to minimize the long-term average energy consumption of self-powered sensor devices while ensuring system performance. We adopt stochastic optimization techniques to transform the modeled stochastic problem into a deterministic problem. Then, the deterministic problem is decomposed into four sub-problems, and we propose a task scheduling and resource allocation (TSRA) algorithm to solve these problems. Finally, we carry out a series of parameter analysis and comparison experiments to verify the TSRA algorithm. The experimental results show that our TSRA algorithm can make a dynamic tradeoff between energy consumption and system performance. It also demonstrates the effectiveness of our TSRA algorithm compared with other baseline algorithms.

In recent years, the Internet of Things (IoT) and mobile communication technologies have developed rapidly. Meanwhile, many delay-sensitive and computation-intensive IoT services have been widely applied. Because of the limited computing resources, storage, and battery capacity of IoT devices, mobile edge computing (MEC) is emerging as a promising paradigm to help process the tasks of IoT devices. Furthermore, non-orthogonal multiple access (NOMA) has evolved as a practical approach to meeting the requirement of massive connectivity. In this paper, we study the NOMA-aided dynamic task offloading problem for the IoT, which combines task scheduling and computing resource allocation decisions. We model and formulate the problem as a stochastic optimization problem, and our goal is to minimize the system energy consumption while satisfying performance requirements. We transform the original problem into a deterministic optimization problem through stochastic optimization technology. Then, we decompose it into four sub-problems and propose the energy efficient task offloading (EETO) algorithm to solve these four sub-problems. Our proposed EETO algorithm does not rely on prior statistical knowledge related to task arrival or wireless channel conditions. Through theoretical analysis and experiment results, we demonstrate that our EETO algorithm can make a flexible trade-off between system energy consumption and performance. Additionally, the EETO algorithm can effectively decrease the system energy consumption while ensuring system performance.

The ever-increasing web application programming interfaces (APIs) in various service-sharing communities (e.g., ProgrammableWeb.com and Mashape.com) have enabled software developers to quickly create their interested mashups conveniently and economically. However, the big volume of candidate web APIs and their differences often make it hard for software developers to discover a set of appropriate web APIs for mashup creation by considering API functions and API quality performances (e.g., popularity, compatibility, and diversity) simultaneously. These decrease the mashup development success rate and the mashup developers’ satisfaction significantly. In view of these challenges, a novel web APIs’ recommendation method named the popularity-aware and diverse method of web API compositions’ recommendation (PD-WACR) is proposed in this article. In concrete, we model web APIs’ functions, popularity, and compatibility with an API correlation graph. Afterward, correlation graph-based web APIs’ recommendation is performed with popularity and compatibility guarantee. Moreover, a top-$k$strategy is adopted in the recommendation process, so as to diversify the final recommended web APIs’ results. Finally, massive experiments are carried out on a real-world web API dataset crawled from ProgrammeableWeb.com. Experimental comparisons with related methods show the advantages and innovations of the proposed PD-WACR method.

With the maturity of 5G cellular communication systems and mobile-edge computing (MEC), a large number of base stations (BSs) with edge-computing servers are densely deployed. There are extensive overlapping coverage areas among the BSs in which some heavy computational tasks from Internet of Things (IoT) devices can be divided and offloaded to multiple BSs via the coordinated multipoint (CoMP) technique for parallel processing. However, it is a challenging issue about how to make proper task offloading decisions among multiple connected BSs while satisfying delay requirements of multiple devices. To address this challenge, this article presents an efficient multidevice and multi-BSs task offloading scheme with the goal of minimizing the delay for completing the tasks of the devices. By conducting quantitative analysis of local delay and offloading delay, a nonlinear and nonconvex delay optimization offloading problem, which is based on the theory of noncooperative game, is formulated. We prove the existence of Nash equilibrium by analyzing the feature of the proposed offloading problem and further propose a distributed task offloading algorithm called DOLA. Finally, simulation experiments based on real-world data set from the Melbourne CBD area of Australia are conducted to validate the efficacy of our DOLA algorithm. Comparison experiments are also carried out to demonstrate the superiority of DOLA in comparison with some existing schemes.

Computation offloading is a hot research topic in mobile edge computing (MEC). Computation offloading among multiedge nodes in heterogeneous networks can help reduce offloading cost. In addition, the unmanned aerial vehicles (UAVs) play a key role in MEC, where UAVs in the air communicate with ground base stations to improve the network performance. However, limited channel resources can lead to the increase of transmission delay and the decline of communication quality. Effective channel selection mechanisms can help address those issues by improving transmission rate and ensuring communication quality. In this paper, we study channel selection during communication between multiple UAVs and base stations in an MEC system with heterogeneous networks. To maximize the transmission rate of each UAV user, we formulate a channel selection problem and model it as a noncooperative game. Then, we prove the existence of Nash equilibrium (NE). In addition, we design a multiple UAV-enabled transmission channel selection (UTCS) algorithm to obtain the equilibrium strategy profile of all the UAV users. Experimental results validate that UTCS algorithm can converge after a finite number of iterations and it outperforms random transmission algorithm (RTA) and sequential transmission algorithm (STA).

With the development of 5G communication technologies and smart mobile devices, various computation-intensive and delay-sensitive tasks continue to increase. The combination of Mobile Edge Computing (MEC) and Ultra-Dense Networks (UDN) increases the network capacity and improves the computing capability of mobile devices, which effectively meets the transmission and computing demands of tasks. However, the ultra-dense deployment of network infrastructures causes energy shortage and channel interference, making it challenging to reduce the system cost. In this paper, we investigate the task offloading and resources scheduling problem in UDN with MEC. In order to minimize the total system cost including delay and energy consumption in the intensive deployment environment of edge servers and base stations (BSs) simultaneously, we design the strategy of task offloading, BS selection and resources scheduling of mobile devices. Because of the complex coupling of decision variables, the original problem is decomposed into two sub-problems. We propose Newton-IPM based Computing Resource Allocation (NICRA) algorithm and Genetic Algorithm based BS Selection and Resources Scheduling (GABSRS) algorithm to solve these two sub-problems, respectively. Then, we prove the number of iterations can be reduced effectively by the GABSRS algorithm while reaching the optimal solution through mathematical analysis. Through experiments analysis, the effectiveness of the GABSRS algorithm is validated.

With the development of Internet of Things (IoT) and network technologies, traditional networks cannot cope with the growth of network traffic and the changes in service requirements. The 5-th Generation Mobile Communication (5G) technology improves network transmission performance. In the communication network, 5G combines Software Defined Network (SDN) and Network Function Virtualization (NFV), through the deployment of end-to-end network slicing, to meet the challenge of differentiated service requirements in the complex environment. In the mobile network, users need to choose appropriate slices for access. Its performance is related to the quality of service and determines the efficiency of system resources utilization. We research the problem of slice re-access and slice resource scheduling caused by user mobility in 5G network slicing architecture and propose a slice access mechanism based on maximum throughput. A slice access selection algorithm based on genetic algorithm (GA) is proposed. Related simulations and comparative tests are carried out to prove the effectiveness and superiority of the algorithm.

In recent years, driven by the commercialization of the 6th Generation Communication Technology (6G), an increasing number of 6G devices connected to mobile networks produces computation-intensive tasks such as ultra-high-resolution video streaming, inter-active visual reality (VR) gaming, augmented reality (AR). However, the computing capacity and the capacity of battery of the 6G devices are limited. The technology of computation offloading would offload the tasks from the IoT devices to the edge network in the scenario of mobile edge computing (MEC). Not only can solve the shortage of mobile user device in energy effciency, but also deal with the tasks in low latency. IoT devices can offload computing tasks or execute them locally to finish the work. In order to find the optimal allocation rate of local computing tasks and offloading tasks, a resource allocation policy gradient (RAPG) based DDPG is considered. Finally we analyze the performance of RAPG by contrasts with different resource allocation algorithms. Numerial simulation results showed that the RAPG can achieve the best allocate rate between the BS and local, also can reduce the overall system delay of task combination with minimum energy consumption.

With the rapid development of 5G technologies, Internet-of-Vehicles (IoV) has become a promising and important research hotspot. The high-speed mobility of vehicles brings great challenges for services with low delay and high stability requirements. To address these challenges, this paper takes the relative movement between vehicles into account and analyzes the mobility in detail based on probability distribution. We propose a proactive caching and multi-link cooperative communication scheme to cope with mobility. According to the driving and content request information of vehicle users, the requested content is cached in the road side units (RSUs) and neighboring vehicles in advance. Furthermore, the optimal bandwidth is allocated for each communication link in order to improve the stability of vehicle communication and data transmission efficiency. We propose a Deep Reinforcement Learning-based Proactive Caching and Bandwidth Allocation Algorithm (DPCBA) by considering the high-dimensional continuity of the state and action space. The extensive simulation results demonstrate that our DPCBA scheme can effectively improve the Quality-of-Experience (QoE) of vehicle users in various situations, and outperforms traditional benchmark algorithms.

Offloading tasks from computing intensive mobile devices (MDs) to neighboring edge servers in the form of incentive mechanism can effectively reduce latency and increase utility in mobile edge computing (MEC). In this paper, we design an auction mechanism for a MEC system, and the system consists of multiple MDs and one service provider (SP). As the auctioneer, SP receives the bidding information from MDs, making resource allocation strategies by optimizing social welfare. An exact algorithm to solve social welfare maximization problem and a perturbation-based randomized allocation algorithm to achieve (1 - α) optimal social welfare approximation rate are proposed. Furthermore, we prove that the truthful random auction mechanism can achieves the auction properties, including individual rationality, incentive compatibility, weakly budget balance and computational efficiency in theory. Finally, simulation results show the effectiveness of the auction mechanism.

Summary The proliferation of mobile phones and webcams has led to an exponential increase in video data. One of the key technologies of video surveillance systems is Person Re‐identification (Re‐ID). The Re‐ID is used to identify whether the target pedestrian is the same person, and through scene matching, cross‐field tracking and track prediction of suspected pedestrians can be achieved. The edge computing has become the first choice for video analysis and processing, because of shorter response time and more efficient processing. In this paper, we propose a deep square similarity learning (DSSL), which considers the difference correlation, first‐order correlation, and two‐order correlation of image pairs. The training data automatically adjusts the network parameters and the weights of the three correlations to minimize the loss of the training set. Moreover, we conducted experiments on the challenging Re‐ID databases CuHK03 and Male1501. Compared with algorithm IDLA and DHSL, the first recognition rate is increased by 18% and 40%, respectively, in CuHK03, and 22% and 80% in Male1501. Then, we propose an online deep square similarity learning (ODSSL) algorithm to solve problem of data updating after the model is established by DSSL strategy. Meanwhile, ODSSL shows shorter update time and more efficient processing.

With proliferation of computation-intensive Internet of Things (IoT) applications, the limited capacity of end devices can deteriorate service performance. To address this issue, computation tasks can be offloaded to the Mobile Edge Computing (MEC) for processing. However, it consumes considerable energy to transmit and process these tasks. In this paper, we study the energy efficient task offloading in MEC. Specifically, we formulate it as a stochastic optimization problem, with the objective of minimizing the energy consumption of task offloading while guaranteeing the average queue length. Solving this offloading optimization problem faces many technical challenges due to the uncertainty and dynamics of wireless channel state and task arrival process, and the large scale of solution space. To tackle these challenges, we apply stochastic optimization techniques to transform the original stochastic problem into a deterministic optimization problem, and propose an energy efficient dynamic offloading algorithm called EEDOA. EEDOA can be implemented in an online manner to make the task offloading decisions with polynomial time complexity. Theoretical analysis is provided to demonstrate that EEDOA can approximate the minimal transmission energy consumption while still bounding the queue length. Experiment results are presented which show the EEDOA’s effectiveness.

As an emerging computing paradigm, mobile edge computing (MEC) can improve users’ service experience by provisioning the cloud resources close to the mobile devices. With MEC, computation-intensive tasks can be processed on the MEC servers, which can greatly decrease the mobile devices’ energy consumption and prolong their battery lifetime. However, the highly dynamic task arrival and wireless channel states pose great challenges on the computation task allocation in MEC. This paper jointly investigates the task allocation and CPU-cycle frequency, to achieve the minimum energy consumption while guaranteeing that the queue length is upper bounded. We formulate it as a stochastic optimization problem, and with the aid of stochastic optimization methods, we decouple the original problem into two deterministic optimization subproblems. An online Task Offloading and Frequency Scaling for Energy Efficiency (TOFFEE) algorithm is proposed to obtain the optimal solutions of these subproblems concurrently. TOFFEE can obtain the close-to-optimal energy consumption while bounding the applications’ queue length. Performance evaluation is conducted which verifies TOFFEE’s effectiveness. Experiment results indicate that TOFFEE can decrease the energy consumption by about 15 percent compared with the RLE algorithm, and by about 38 percent compared with the RME algorithm.

Nowadays, driven by the rapid development of smart mobile equipments and 5G network technologies, the application scenarios of Internet of Things (IoT) technology are becoming increasingly widespread. The integration of IoT and industrial manufacturing systems forms the industrial IoT (IIoT). Because of the limitation of resources, such as the computation unit and battery capacity in the IIoT equipments (IIEs), computation-intensive tasks need to be executed in the mobile edge computing (MEC) server. However, the dynamics and continuity of task generation lead to a severe challenge to the management of limited resources in IIoT. In this article, we investigate the dynamic resource management problem of joint power control and computing resource allocation for MEC in IIoT. In order to minimize the long-term average delay of the tasks, the original problem is transformed into a Markov decision process (MDP). Considering the dynamics and continuity of task generation, we propose a deep reinforcement learning-based dynamic resource management (DDRM) algorithm to solve the formulated MDP problem. Our DDRM algorithm exploits the deep deterministic policy gradient and can deal with the high-dimensional continuity of the action and state spaces. Extensive simulation results demonstrate that the DDRM can reduce the long-term average delay of the tasks effectively.

Driven by Internet of Things (IoT) and 5G communication technologies, the paradigm of mobile computing has changed from centralized mobile cloud computing to distributed mobile edge computing (MEC). Narrowing the gap between high quality of service (QoS) requirements and limited computing resources, and improving the utilization of computing resources between IoT devices and edge servers have become key issues. In this paper, we formulate a stochastic optimization problem involving dynamic offloading and resource scheduling between the local devices, base station (BS) and the back-end cloud. The goal is to minimize the consumption of energy and computing resources in the MEC system with energy harvesting (EH) devices, while meeting the QoS requirements of IoT devices. In order to solve this stochastic optimization problem, we convert it into a deterministic optimization problem, and propose an online dynamic offloading and resource scheduling algorithm (DORS) based on Lyapunov optimization theory. It is proved that the DORS algorithm can effectively balance the relationship between scheduling cost and MEC system’s performance. The comparison experiments show the effectiveness of the DORS algorithm in reducing the energy consumption.

The emerging fifth generation (5G) wireless technologies support services with huge heterogeneous requirements. Network slicing technology can compose multiple logical networks and allocate wireless resources according to the needs of each user, which can reduce the cost of hardware and network resources. Nevertheless, considering how systems containing different types of users reduce the cost of resources remains challenging. In this paper, we study the system cost of two types of user groups requesting resource blocks (RBs) at the radio access network (RAN), which are the enhanced mobile broadband (eMBB) cellular user group and the cellular vehicle to everything (C-V2X) user group. In order to improve the rational utilization, we make dynamic resource pricing according to the needs of users. Then, we propose a Cooperative Resource Sharing (CRS) Algorithm, which makes two user groups jointly purchase and share resources. The simulation results show that the strategy used in this algorithm can effectively reduce the unit price of RB and minimize the total cost of the system.

Summary Narrow Band Internet of Things (NB‐IoT) is a cellular‐based low power wide area network (LPWAN) radio technology, which can provide highly reliable services and wide coverage for IoT devices. Software defined networking (SDN) as an emerging network architecture can realize flexible resource allocation and network management. We introduce SDN into NB‐IoT and investigate the traffic modeling and performance evaluation of SDN‐based NB‐IoT access network. To evaluate the network performance in different environments, we introduce the Beta/D/1, Uniform/D/1, and M/D/1 queuing models, respectively. The proposed queuing models are suitable for different scenarios, in which NB‐IoT devices access the network in a highly synchronized, unsynchronized, or stochastic manner. We use the general solution to the G/G/1 and the M/G/1 queuing model to solve the proposed modeling problems. Through simulations, we investigate the influence of different network parameters. The analysis and simulation results can be used in the SDN controller to dynamically allocate resources and make network management decisions to satisfy different performance requirements of NB‐IoT applications.

With the popularity of computationally intensive applications, more and more computing resources are required. Mobile edge computing (MEC) is widely applied as an effective method to meet the increasing computing demands. In a relatively stable state, MEC can provide computing services with low latency and energy consumption. However, in special cases such as communication traffic, the unmanned aerial vehicle (UAV), by taking advantage of its mobility and flexibility, can assist the edge server to cope with the challenge of instantaneous computing surge. In this study, the authors consider a UAV‐enabled edge computing system. In addition to delay and energy consumption, the authors also consider computing resources costs in the offloading model. Besides, in order to minimise the computing cost of each mobile user (MU), they apply the non‐cooperative game method to model the channel and computing resources competition among MUs. Then, the authors prove that the proposed game is an ordinal potential game and the existence of Nash equilibrium in the game. The authors propose the UAV‐enabled computation offloading (UECO) algorithm to obtain the equilibrium strategy. Finally, the authors show that the UECO algorithm can quickly converge through iterative experiments, and it can achieve lower computing cost through comparative experiments.

To satisfy the increasingly complex demands of the Internet of Things (IoT) applications, multiclouds are a promising solution that can provide scalable, various, and abundant resources. However, in multiclouds, each cloud has its specific virtual machine (VM) type and pricing scheme. In addition, the request arrival, network bandwidth, and VM's price all vary with time and are hardly predicted. In such cases, the request scheduling and resource provisioning (RSRP) for cost efficiency becomes a highly challenging work. In this article, to capture the dynamics in the multiclouds environment, we formulate a stochastic optimization problem where the aim is to minimize the system cost and guarantee the IoT applications' queueing delay. By applying stochastic optimization theory, the original problem is transformed into a deterministic optimization problem in each slot, and then the deterministic problem is further decomposed into three independent subproblems. An online RSRP algorithm is devised to obtain these subproblems' optimal solutions. Mathematical analysis shows that RSRP can approach the optimal system cost while bounding the queueing delay, and make an arbitrary tradeoff between system cost and queueing delay as well. Moreover, trace-driven simulation results show the effectiveness of RRSP.

Mobile edge computing (MEC) has recently become a promising paradigm to meet the increasing computing requirement of mobile devices, and hybrid energy supply has been considered as an effective approach for saving the energy consumption of the MEC system and making it environmentally friendly. In particular, the joint task scheduling and energy management (TSEM) scheme plays a crucial role in reaping the benefits of MEC with hybrid energy supply. In this article, we focus on jointly optimizing the TSEM decisions to maximize the utility of the MEC system which accounts for both the computation throughput and the fairness among different cells, by formulating a stochastic optimization problem subject to the constraints of queue stability and energy budget. We transform the formulated problem into a deterministic problem and then decouple it into four independent subproblems, which can be solved in a distributed manner without future system statistical information. An online TSEM algorithm is developed to derive the optimal solutions to these subproblems. Mathematical analysis shows that TSEM can achieve a close-to-optimal system utility and realize the utility-queue tradeoff. The experimental results validate the advantages of TSEM in improving the system utility and stabilizing the queue length.

The enhanced Mobile Broadband (eMBB) and ultra-Reliable Low Latency Communications (URLLC) are two main scenarios of 5G networks. There is an obvious difference in service requirements between the two different scenarios. When multiple heterogeneous services coexist in the network, it is important to explore optimal resource scheduling and allocation strategies. In this paper, we study the Quality of Service (QoS) optimization problem in eMBB and URLLC coexisting scenario. Considering the services' characteristics of heterogeneity and dynamics, we first introduce the flexible numerology structure which defines a set of flexible transmission time interval (TTI) to satisfy different QoS requirements of heterogeneous services, and then, we formulate a Markov decision process (MDP)-based dynamic resource optimization problem with the flexibilities of time and frequency domains. Next, we prove this optimization problem to be NP-hard and propose an innovative joint scheduling strategy DRSA based on flexible numerology and deep reinforcement learning method to allocate dynamic resources. Through experiments, the flexible numerology significantly outperforms the non-flexible ones. Comparison experiments with Sequence, Greedy and Random strategies show that the average throughput of DRSA is 7.1%, 14.8% and 23.9% higher than them, and DRSA can reduce URLLC services' loss rate by 43.7%, 28.6% and 53.8%.

With the rapid growth of Internet of Things (IoT), network slicing is regarded as an important technology to support the multi-users' needs for 5G mobile network. Network slicing allows network operators to provide services to different users, which can improve the rational utilization of network and hardware resources. In order to ensure the quality of service and build low-cost network infrastructure services, it is a challenging problem to find an appropriate resource allocation mechanism. In this paper, we discuss resource allocation in 5G radio access network (RAN). Considering the real-time resource request of the slice user, we propose a semi-Markov decision system model, which enables the virtual network provider to effectively satisfy the different user demands in real time. Then, we propose a resource slicing algorithm based on deep reinforcement learning (RS-DRL), which aims to improve the long-term benefits of virtual network providers and the utilization of slicing resources. We evaluate the performance of the RS-DRL through evaluations and comparisons. The results show that the proposed RS-DRL algorithm can effectively improve the performance and achieve the long-term benefits quickly.

Limited capacities in computation and battery of Internet of things (IoT) devices are two main bottlenecks for quality of service. Emerging mobile edge computing (MEC) and radio frequency based wireless power transfer (WPT) can help alleviate the issues. Incorporating WPT into MEC, IoT devices can get sustainable energy supply by WPT, and offload computation tasks to MEC to improve the computing ability. In this paper, we jointly consider the radio resource and task allocation for the wireless powered MEC system. To capture the high dynamics in task arrival and wireless network, a stochastic optimization problem which minimizes the energy consumption while guaranteeing queue stability is formulated. By exploiting the stochastic optimization theory, we transform the original problem into a deterministic optimization problem. A radio resource and task allocation (RRTA) algorithm is designed to acquire the optimal solutions of this problem. Theoretical analysis shows that RRTA can achieve arbitrary tradeoff between the energy consumption and queue length. Moreover, the close-to-optimal energy consumption can be reached by RRTA while bounding the queueing length. Experiment results reveal that RRTA can effectively decrease the energy consumption and maintain a small queue length.

Nowadays, billions of Internet of Things (IoT) devices arise around us running complex and computation-intensive applications. Due to the limited resources of the IoT devices, it is appealing to offload the application tasks from IoT devices to the remote cloud data centers. However, offloading all the tasks to the cloud can put a significant burden on the network. One promising way to solve this issue is edge computing, where edge servers are provisioned at the network edge. In edge computing for IoT, as the task generating process is highly dynamic and the statistical information can hardly be obtained or precisely predicted, it is of great importance yet very challenging to effectively offload application tasks to achieve the tradeoff between offloading cost and performance. In this paper, we formulate the computation offloading as an optimization problem to minimize offloading cost while providing performance guarantees. Based on stochastic optimization, we propose a dynamic computation offloading algorithm (DCOA), which decomposes the optimization problem into a series of subproblems, and solves these subproblems concurrently in an online and distributed way. Theoretical analysis is presented which demonstrates that DCOA can achieve the tradeoff between offloading cost and performance. Experiments are also carried out to evaluate the effectiveness of DCOA.

Service composition is popular for composing a set of existing services to provide complex services. With the increasing number of services deployed in cloud computing environments, many service providers have started to offer candidate services with equivalent functionality but different Quality of Service (QoS) levels. Therefore, QoS-aware service composition has drawn extensive attention. Most existing approaches for QoS-aware service composition assume a service's QoS values are not correlated to those of other services. However, QoS dependency exists in real life, and impacts the overall QoS values of the composite services. In this article, we study QoS dependency-aware service composition considering multiple QoS attributes. Based on the Pareto set model, we focus on searching for a set of Pareto optimal solutions. A candidate pruning algorithm for removing the unpromising candidates is proposed, and a service composition algorithm using Vector Ordinal Optimization techniques is designed. Simulation experiments are conducted to validate the efficiency and effectiveness of our algorithms. We are the first to take advantage of Vector Ordinal Optimization techniques to search for Pareto optimal composition solutions with QoS dependency involved. The capturing of QoS dependency enables us to find truly desirable solutions.

Caching the popular files in mobile terminal equipments and transferring those files via Device-to-Device (D2D) communication technology can offload the traffic from the Base Station(BS) over edge computing wierless network. The user equipments(UE) are mobile and the D2D communication links may drop any instant. In addition, UEs are carried by people with social attributes. Considering those information about mobile terminals when we study the D2D caching content deployment strategy can improve the caching efficiency. In order to reduce the probability of requesting files from BS, we design an efficient social-aware caching content deployment strategy, which includes the community discovery mechanism, the caching nodes selection algorithm and the file caching probability determination algorithm. Simulation experiments are provided to prove that our D2D caching content deployment strategy can improve the traffic offload rate in edge computing wireless networks.

With the rapid development of the mobile Internet and the Internet of Things, the number of mobile communication services has grown rapidly. When multiple different types of networks cover the same region, it is important to decide which one users connect to, known as the network selection problem. In this paper, we explore the optimal network selection problem in 5G ultra-dense network. We consider several different types of transmission data such as session, media, background and interactive, which conclude different QoS requirements. And then, we formulate the network selection problem as an MDP model in ultra-dense system, and propose NS-MDP algorithm which aims to obtain best target network by calculating the benefits of the utility function. NS-MDP algorithm takes into account user data requirements, current system status, and network load conditions. Comparison experiments with Best-Rate, Random and Greedy_AHP strategies, show that NS-MDP algorithm's average throughput is 8.6%, 17.8% and 20.5% higher than them, and NS-MDP can reduce blocking rate by 33.3%, 17.6%, and 37.7%.

Nowadays, mobile services (applications) running on terminal devices are becoming more and more computation‐intensive. Offloading the service requests from terminal devices to cloud computing can be a good solution, but it would put a high burden on the network. Edge computing is an emerging technology to solve this problem, which places servers at the edge of the network. Dynamic scheduling of offloaded service requests in mobile edge computing systems is a key issue. It faces challenges due to the dynamic nature and uncertainty of service request patterns. In this article, we propose a Dynamic Service Request Scheduling (DSRS) algorithm, which makes request scheduling decisions to optimize scheduling cost while providing performance guarantees. The DSRS algorithm can be implemented in an online and distributed way. We present mathematical analysis which shows that the DSRS algorithm can achieve arbitrary tradeoff between scheduling cost and performance. Experiments are also carried out to show the effectiveness of the DSRS algorithm.

With the increasing popularity of services published online, energy consumption of services computing systems is growing dramatically. Besides Quality of Service (QoS), energy efficiency has become an important issue and drawn significant attention. However, energy efficient request scheduling and service management for large-scale services computing systems face challenges because of the high dynamics and unpredictability of request arrivals. In this paper, we jointly consider the conflicting metrics of performance, queue congestion and energy consumption. We propose a distributed online scheduling and management algorithm which does not require any priori statistical knowledge of request arrivals. Mathematical analysis is conducted which demonstrates that our algorithm can achieve arbitrary tradeoff between performance and energy efficiency. Numerical and real trace data based experiments are carried out to validate the effectiveness of our algorithm in optimizing energy efficiency while stabilizing the system.

As web service has become a popular way for engineering software on the Internet, quality of service (QoS) which describes non-functional characteristics of web services is often employed in service composition. Since QoS is an aggregated concept consisting of several attributes, service composition on enormous candidate sets is a challenging multi-objective optimization problem. In this paper, we study the problem from a general Pareto optimal angle, seeking to reduce search space in service composition. Pareto set model for QoS-aware service composition is introduced, and its relationship with the widely used utility function model is theoretically studied, which proves the applicability of our model. QoS attributes are systematically studied according to their different types of aggregation patterns in service composition, and QoS-based dominance relationships between candidates and between workflows are defined. Taking advantage of pruning candidates by dominance relationships and constraint validations at candidate level, a service composition algorithm using partial selection techniques is proposed. Furthermore, a parallel approach is designed, which is able to significantly reduce search space and achieve great performance gains. A careful analysis of the optimality of our approach is provided, and its efficacy is further validated by both simulation experiments and real-world data based evaluations.

With the increasing presence of web services on the Internet, Quality of Service (QoS) is becoming important for describing non-functional characteristics of web services, and is often employed in web service composition. As QoS is an aggregated concept consisting of several attributes, service composition on enormous candidate sets is a challenging multi-objective optimization problem. In this paper, we study the problem from a general Pareto-optimal angle, seeking to reduce the search space in service composition. QoS attributes are systematically studied according to their different types of aggregation pattern in service composition, and QoS-based dominance relationships between candidates and between workflows are defined. Taking advantage of pruning candidates by dominance relationships and constraint validations at candidate level, a service composition algorithm using partial selection technique is proposed, which is able to significantly reduce the search space and achieve great performance gains. A careful analysis of the optimality of our approach is provided, and its efficacy is further validated by empirical evaluation.

With the increasing popularity of web services on the Internet, service selection has become an important issue in large-scale web service systems. In recent years, with the growing energy consumption associated with IT systems and services, energy efficiency has drawn extensive attention in service allocation and selection. However, existing approaches for energy efficient web service selection face great challenges, because of the high dynamics and unpredictability of task arrivals, and large scale of current web service systems. In this paper, we present a distributed online approach for web service selection that jointly considers the conflicting performance metrics including response time, queue congestion and energy consumption. Targeting at optimizing the long-term average system reward, our approach does not require any priori knowledge of the statistics or prediction on task arrivals. Mathematical analysis as well as simulation experiments demonstrate its effectiveness in optimizing energy efficiency while stabilizing the system.

With the increasing popularity of web services on the Internet, besides functionalities, Quality of Service (QoS) is becoming an important concern for describing characteristics of web services. QoS rankings provide valuable information for making optimal service selection and recommendation from a set of functionally similar or equivalent service candidates. However, in order to obtain such rankings, a huge number of invocations on the services are usually required, which is extremely expensive and even impractical in reality. To tackle this challenge, this paper proposes a scheme to derive the global ranking from observations of QoS rankings on subsets of the services, while the observations may also be contaminated by noise and errors. We introduce a pairwise comparison model to describe the relationships between services, and thus the ranking can be formulated as random walks over the services. A Markov chain based approach is proposed, and algorithms for deriving global rankings are designed. The efficacy of our approach is validated by both mathematical analysis and simulation experiments.

Reliability is a critical concern in the provision and placement of web services. A breakdown of service would seriously reduce customers' satisfaction, and thus harm the revenue of service providers. To maintain a high reliability, the common approach is deploying multiple service instances across different physical servers. This would inevitably raise another concern of energy consumption. Thus, greening web services also becomes an important issue. In this paper, we study the fundamental tradeoff between reliability and energy consumption, and propose an optimization framework that considers both factors. In specific, we build a continuous-time Markov model to analyze the steady-state reliability and mean time to failure (MTTF) from a service-oriented perspective, and obtain the minimum number of service instances to meet the given reliability requirement. Then, we show that deploying these instances in the server cluster to minimize energy consumption is NP-hard. To this end, we propose a heuristic algorithm to approximate the result. The analytical and experimental results show the effectiveness, and the approximation ratio is less than 1.25 for 90% of the data sets we use.