Showing papers on "Resource management published in 2021"

Smart Resource Allocation for Mobile Edge Computing: A Deep Reinforcement Learning Approach

Abstract: The development of mobile devices with improving communication and perceptual capabilities has brought about a proliferation of numerous complex and computation-intensive mobile applications. Mobile devices with limited resources face more severe capacity constraints than ever before. As a new concept of network architecture and an extension of cloud computing, Mobile Edge Computing (MEC) seems to be a promising solution to meet this emerging challenge. However, MEC also has some limitations, such as the high cost of infrastructure deployment and maintenance, as well as the severe pressure that the complex and mutative edge computing environment brings to MEC servers. At this point, how to allocate computing resources and network resources rationally to satisfy the requirements of mobile devices under the changeable MEC conditions has become a great aporia. To combat this issue, we propose a smart, Deep Reinforcement Learning based Resource Allocation (DRLRA) scheme, which can allocate computing and network resources adaptively, reduce the average service time and balance the use of resources under varying MEC environment. Experimental results show that the proposed DRLRA performs better than the traditional OSPF algorithm in the mutative MEC conditions.

Federated Learning Over Wireless Networks: Convergence Analysis and Resource Allocation

Abstract: There is an increasing interest in a fast-growing machine learning technique called Federated Learning (FL), in which the model training is distributed over mobile user equipment (UEs), exploiting UEs’ local computation and training data. Despite its advantages such as preserving data privacy, FL still has challenges of heterogeneity across UEs’ data and physical resources. To address these challenges, we first propose FEDL , a FL algorithm which can handle heterogeneous UE data without further assumptions except strongly convex and smooth loss functions. We provide a convergence rate characterizing the trade-off between local computation rounds of each UE to update its local model and global communication rounds to update the FL global model. We then employ FEDL in wireless networks as a resource allocation optimization problem that captures the trade-off between FEDL convergence wall clock time and energy consumption of UEs with heterogeneous computing and power resources. Even though the wireless resource allocation problem of FEDL is non-convex, we exploit this problem’s structure to decompose it into three sub-problems and analyze their closed-form solutions as well as insights into problem design. Finally, we empirically evaluate the convergence of FEDL with PyTorch experiments, and provide extensive numerical results for the wireless resource allocation sub-problems. Experimental results show that FEDL outperforms the vanilla FedAvg algorithm in terms of convergence rate and test accuracy in various settings.

Multi-Agent Reinforcement Learning Based Resource Management in MEC- and UAV-Assisted Vehicular Networks

Abstract: In this paper, we investigate multi-dimensional resource management for unmanned aerial vehicles (UAVs) assisted vehicular networks. To efficiently provide on-demand resource access, the macro eNodeB and UAV, both mounted with multi-access edge computing (MEC) servers, cooperatively make association decisions and allocate proper amounts of resources to vehicles. Since there is no central controller, we formulate the resource allocation at the MEC servers as a distributive optimization problem to maximize the number of offloaded tasks while satisfying their heterogeneous quality-of-service (QoS) requirements, and then solve it with a multi-agent deep deterministic policy gradient (MADDPG)-based method. Through centrally training the MADDPG model offline, the MEC servers, acting as learning agents, then can rapidly make vehicle association and resource allocation decisions during the online execution stage. From our simulation results, the MADDPG-based method can converge within 200 training episodes, comparable to the single-agent DDPG (SADDPG)-based one. Moreover, the proposed MADDPG-based resource management scheme can achieve higher delay/QoS satisfaction ratios than the SADDPG-based and random schemes.

User-Oriented Virtual Mobile Network Resource Management for Vehicle Communications

Abstract: Currently, advanced communications and networks greatly enhance user experiences and have a major impact on all aspects of people’s lifestyles in terms of work, society, and the economy. However improving competitiveness and sustainable vehicle network services, such as higher user experience, considerable resource utilization and effective personalized services, is a great challenge. Addressing these issues, this paper proposes a virtual network resource management based on user behavior to further optimize the existing vehicle communications. In particular, ensemble learning is implemented in the proposed scheme to predict the user’s voice call duration and traffic usage for supporting user-centric mobile services optimization. Sufficient experiments show that the proposed scheme can significantly improve the quality of services and experiences and that it provides a novel idea for optimizing vehicle networks.

Online Distributed Offloading and Computing Resource Management With Energy Harvesting for Heterogeneous MEC-Enabled IoT

Abstract: With the rapid development and convergence of the mobile Internet and the Internet of Things (IoT), computing-intensive and delay-sensitive IoT applications (APPs) are proliferating with an unprecedented speed in recent years. Mobile edge computing (MEC) and energy harvesting (EH) technologies can significantly improve the user experience by offloading computation tasks to edge-cloud servers as well as achieving green and durable operation. Traditional centralized strategies require precise information of system states, which may not be feasible in the era of big data and artificial intelligence. To this end, how to allocate limited edge-cloud computing resource on demand, and how to develop heterogeneous task offloading strategies with EH in a more flexible manner are remaining challenges. In this paper, we investigate an EH-enabled MEC offloading system, and propose an online distributed optimization algorithm based on game theory and perturbed Lyapunov optimization theory. The proposed algorithm works online and jointly determines heterogeneous task offloading, on-demand computing resource allocation, and battery energy management. Furthermore, to reduce the unnecessary communication overhead and improve the processing efficiency, an offloading pre-screening criterion is designed by balancing battery energy level, latency, and revenue. Extensive simulations are carried out to validate the effectiveness and rationality of the proposed approach.

When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multitimescale Resource Management for Multiaccess Edge Computing in 5G Ultradense Network

Abstract: Recently, smart cities, healthcare system, and smart vehicles have raised challenges on the capability and connectivity of state-of-the-art Internet-of-Things (IoT) devices, especially for the devices in hotspots area. Multiaccess edge computing (MEC) can enhance the ability of emerging resource-intensive IoT applications and has attracted much attention. However, due to the time-varying network environments, as well as the heterogeneous resources of network devices, it is hard to achieve stable, reliable, and real-time interactions between edge devices and their serving edge servers, especially in the 5G ultradense network (UDN) scenarios. Ultradense edge computing (UDEC) has the potential to fill this gap, especially in the 5G era, but it still faces challenges in its current solutions, such as the lack of: 1) efficient utilization of multiple 5G resources (e.g., computation, communication, storage, and service resources); 2) low overhead offloading decision making and resource allocation strategies; and 3) privacy and security protection schemes. Thus, we first propose an intelligent UDEC (I-UDEC) framework, which integrates blockchain and artificial intelligence (AI) into 5G UDEC networks. Then, in order to achieve real-time and low overhead computation offloading decisions and resource allocation strategies, we design a novel two-timescale deep reinforcement learning (2Ts-DRL) approach, consisting of a fast-timescale and a slow-timescale learning process, respectively. The primary objective is to minimize the total offloading delay and network resource usage by jointly optimizing computation offloading, resource allocation, and service caching placement. We also leverage federated learning (FL) to train the 2Ts-DRL model in a distributed manner, aiming to protect the edge devices’ data privacy. Simulation results corroborate the effectiveness of both the 2Ts-DRL and FL in the I-UDEC framework and prove that our proposed algorithm can reduce task execution time up to 31.87%.

Deep Reinforcement Learning-Based Dynamic Resource Management for Mobile Edge Computing in Industrial Internet of Things

Abstract: 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.

Resource Allocation for Energy-Efficient MEC in NOMA-Enabled Massive IoT Networks

Abstract: Integrating mobile edge computing (MEC) into the Internet of Things (IoT) enables the IoT devices of limited computation capabilities and energy to offload their computation-intensive and delay-sensitive tasks to the network edge, thereby providing high quality of service to the devices. In this article, we apply non-orthogonal multiple access (NOMA) technique to enable massive connectivity and investigate how it can be exploited to achieve energy-efficient MEC in IoT networks. In order to maximize the energy efficiency for offloading, while simultaneously satisfying the maximum tolerable delay constraints of IoT devices, a joint radio and computation resource allocation problem is formulated, which takes both intra- and inter-cell interference into consideration. To tackle this intractable mixed integer non-convex problem, we first decouple it into separated radio and computation resource allocation problems. Then, the radio resource allocation problem is further decomposed into a subchannel allocation problem and a power allocation problem, which can be solved by matching and sequential convex programming algorithms, respectively. Based on the obtained radio resource allocation solution, the computation resource allocation problem can be solved by utilizing the Knapsack method. Numerical results validate our analysis and show that our proposed scheme can significantly improve the energy efficiency of NOMA-enabled MEC in IoT networks compared to the existing baselines.

Overhead-Aware Design of Reconfigurable Intelligent Surfaces in Smart Radio Environments

Abstract: Reconfigurable intelligent surfaces have emerged as a promising technology for future wireless networks. Given that a large number of reflecting elements is typically used and that the surface has no signal processing capabilities, a major challenge is to cope with the overhead that is required to estimate the channel state information and to report the optimized phase shifts to the surface. This issue has not been addressed by previous works, which do not explicitly consider the overhead during the resource allocation phase. This work aims at filling this gap, by developing an overhead-aware resource allocation framework for wireless networks where reconfigurable intelligent surfaces are used to improve the communication performance. An overhead model is proposed and incorporated in the expressions of the system rate and energy efficiency, which are then optimized with respect to the phase shifts of the reconfigurable intelligent surface, the transmit and receive filters, the power and bandwidth used for the communication and feedback phases. The bi-objective maximization of the rate and energy efficiency is investigated, too. The proposed framework characterizes the trade-off between optimized radio resource allocation policies and the related overhead in networks with reconfigurable intelligent surfaces.

Toward Resource-Efficient Federated Learning in Mobile Edge Computing

Abstract: Federated learning is a newly emerged distributed deep learning paradigm, where the clients separately train their local neural network models with private data and then jointly aggregate a global model at the central server. Mobile edge computing is aimed at deploying mobile applications at the edge of wireless networks. Federated learning in mobile edge computing is a prospective distributed framework to deploy deep learning algorithms in many application scenarios. The bottleneck of federated learning in mobile edge computing is the intensive resources of mobile clients in computation, bandwidth, energy, and data. This article first illustrates the typical use cases of federated learning in mobile edge computing, and then investigates the state-of-the-art resource optimization approaches in federated learning. The resource-effi-cient techniques for federated learning are broadly divided into two classes: the black-box and white-box approaches. For black-box approaches, the techniques of training tricks, client selection, data compensation, and hierarchical aggregation are reviewed. For white-box approaches, the techniques of model compression, knowledge distillation, feature fusion, and asynchronous update are discussed. After that, a neural-structure-aware resource management approach with mod-ule-based federated learning is proposed, where mobile clients are assigned with different subnetworks of the global model according to the status of their local resources. Experiments demonstrate the superiority of our approach in elastic and efficient resource utilization.

SmartBlock-SDN: An Optimized Blockchain-SDN Framework for Resource Management in IoT

Abstract: Software-Defined Networking (SDN) and Blockchain are leading technologies used worldwide to establish safe network communication as well as build secure network infrastructures They provide a robust and reliable platform to address threats and face challenges such as security, privacy, flexibility, scalability, and confidentiality Driven by these assumptions, this paper presents an optimized energy-efficient and secure Blockchain-based software-defined IoT framework for smart networks Indeed, SDN and Blockchain technologies have proven to be able to suitably manage resource utilization and to develop secure network communication across the IoT ecosystem However, there is a lack of research works that present a comprehensive definition of such a framework that can meet the requirements of the IoT ecosystem (ie efficient energy utilization and reduced end-to-end delay) Therefore, in this research, we present a layered hierarchical architecture for the deployment of a distributed yet efficient Blockchain-enabled SDN-IoT framework that ensures efficient cluster-head selection and secure network communication via the identification and isolation of rouge switches Besides, the Blockchain-enabled flow-rules record keeps track of the rules enforced in the switches and maintains the consistency within the controller cluster Finally, we assess the performance of the proposed framework in a simulation environment and show that it can achieve optimized energy-utilization, end-to-end delay, and throughput compared to considered baselines, thus being able to achieve efficiency and security in the smart network

Radio Resource Management in Joint Radar and Communication: A Comprehensive Survey

Abstract: Joint radar and communication (JRC) has recently attracted substantial attention. The first reason is that JRC allows individual radar and communication systems to share spectrum bands and thus improves the spectrum utilization. The second reason is that JRC enables a single hardware platform, e.g., an autonomous vehicle or a UAV, to simultaneously perform the communication function and the radar function. As a result, JRC is able to improve the efficiency of resources, i.e., spectrum and energy, reduce the system size, and minimize the system cost. However, there are several challenges to be solved for the JRC design. In particular, sharing the spectrum imposes the interference caused by the systems, and sharing the hardware platform and energy resource complicates the design of the JRC transmitter and compromises the performance of each function. To address the challenges, several resource management approaches have been recently proposed, and this paper presents a comprehensive literature review on resource management for JRC. First, we give fundamental concepts of JRC, important performance metrics used in JRC systems, and applications of the JRC systems. Then, we review and analyze resource management approaches, i.e., spectrum sharing, power allocation, and interference management, for JRC. In addition, we present security issues to JRC and provide a discussion of countermeasures to the security issues. Finally, we highlight important challenges in the JRC design and discuss future research directions related to JRC.

Edge Caching and Computation Management for Real-Time Internet of Vehicles: An Online and Distributed Approach

Abstract: Vehicular Edge Computing (VEC) is expected to be an effective solution to meet the ultra-low delay requirements of many emerging Internet of Vehicles (IoV) services by shifting the service caching and the computation capacities to the network edge. However, due to the constraints of the multidimensional (storage-computing-communication) resources capacities and the cost budgets of vehicles, there are two main issues need to be addressed: 1) How to collaboratively optimize the service caching decision among edge nodes to better reap the benefits of the storage resource and save the time-correlated service reconfiguration cost? 2) How to allocate resources among various vehicles and where vehicular requests are scheduled to improve the efficiency of the computing and communication resources utilization? In this paper, we formulate an edge caching and computation management problem that jointly optimizes the service caching, the request scheduling, and the resource allocation strategies. Our focus is to minimize the time-average service response delay of the random arriving service requests in a cost-efficient way. To cope with the dynamic and unpredictable challenges of IoVs, we leverage the combined power of Lyapunov optimization, matching theory, and consensus alternating direction method of multipliers to solve the problem in an online and distributed manner. Theoretical analysis shows that the developed approach achieves a close-to-optimal delay performance without relying on any prior knowledge of the future network information. Moreover, simulation results validate the theoretical analysis and demonstrate that our algorithm outperforms the baselines substantially.

Dynamic Resource Allocation and Computation Offloading for IoT Fog Computing System

Abstract: Fog computing system is able to facilitate computation-intensive applications and emerges as one of the promising technology for realizing the Internet of Things (IoT). By offloading the computational tasks to the fog node (FN) at the network edge, both the service latency and energy consumption can be improved, which is significant for industrial IoT applications. However, the dynamics of computational resource usages in the FN, the radio environment and the energy in the battery of IoT devices make the offloading mechanism design become challenging. Therefore, in this article, we propose a dynamic optimization scheme for the IoT fog computing system with multiple mobile devices (MDs), where the radio and computational resources, and offloading decisions, can be dynamically coordinated and allocated with the variation of radio resources and computation demands. Specifically, with the objective to minimize the system cost related to latency, energy consumption, and weights of MDs, we propose a joint computation offloading and radio resource allocation algorithm based on Lyapunov optimization. Through minimizing the derived upper bound of the Lyapunov drift-plus-penalty function, we divide the main problem into several subproblems at each time slot and address them accordingly. Through performance evaluation, the effectiveness of the proposed scheme can be verified.

Price-Based Resource Allocation for Edge Computing: A Market Equilibrium Approach

Abstract: The emerging edge computing paradigm promises to deliver superior user experience and enable a wide range of Internet of Things (IoT) applications. In this paper, we propose a new market-based framework for efficiently allocating resources of heterogeneous capacity-limited edge nodes (EN) to multiple competing services at the network edge. By properly pricing the geographically distributed ENs, the proposed framework generates a market equilibrium (ME) solution that not only maximizes the edge computing resource utilization but also allocates optimal resource bundles to the services given their budget constraints. When the utility of a service is defined as the maximum revenue that the service can achieve from its resource allotment, the equilibrium can be computed centrally by solving the Eisenberg-Gale (EG) convex program. We further show that the equilibrium allocation is Pareto-optimal and satisfies desired fairness properties including sharing incentive, proportionality, and envy-freeness. Also, two distributed algorithms, which efficiently converge to an ME, are introduced. When each service aims to maximize its net profit (i.e., revenue minus cost) instead of the revenue, we derive a novel convex optimization problem and rigorously prove that its solution is exactly an ME. Extensive numerical results are presented to validate the effectiveness of the proposed techniques.

Resource Scheduling in Edge Computing: A Survey

Abstract: With the proliferation of the Internet of Things (IoT) and the wide penetration of wireless networks, the surging demand for data communications and computing calls for the emerging edge computing paradigm. By moving the services and functions located in the cloud to the proximity of users, edge computing can provide powerful communication, storage, networking, and communication capacity. The resource scheduling in edge computing, which is the key to the success of edge computing systems, has attracted increasing research interests. In this paper, we survey the state-of-the-art research findings to know the research progress in this field. Specifically, we present the architecture of edge computing, under which different collaborative manners for resource scheduling are discussed. Particularly, we introduce a unified model before summarizing the current works on resource scheduling from three research issues, including computation offloading, resource allocation, and resource provisioning. Based on two modes of operation, i.e., centralized and distributed modes, different techniques for resource scheduling are discussed and compared. Also, we summarize the main performance indicators based on the surveyed literature. To shed light on the significance of resource scheduling in real-world scenarios, we discuss several typical application scenarios involved in the research of resource scheduling in edge computing. Finally, we highlight some open research challenges yet to be addressed and outline several open issues as the future research direction.

A Survey on 4G-5G Dual Connectivity: Road to 5G Implementation

Abstract: Rising popularity of 5G communications is making tremendous demands on the cellular network operators for providing true 5G services to the users. With limited numbers of 5G users initially, the investments for 5G services can be very high. In the early stage of 5G deployments, the 5G cells would not be lavishly spread and there would be 5G coverage holes. The operators can provide seamless services to the 5G users by inter working with the existing 4G Long-Term Evolution (LTE) network. The 5G inter working with fully deployed LTE would not only provide fast and seamless coverage but would also provide economic viability to the network operators. In this paper we survey and consolidate the 4G-5G inter working solutions that can assist in attaining the insight about various inter working possibilities and their challenges. It is important that a network operator is able to optimize its deployed infrastructure while being able to guarantee fast and seamless transition to 5G for its subscribers. To this regard, we evaluate the performance and radio resource management challenges for different 4G-5G dual connectivity options proposed by 3rd Generation Partnership Project (3GPP) standardization. We also discuss spectrum sharing possibilities between 4G and 5G wireless networks. Finally, various research challenges and discussions on path for migration to 5G standalone networks are also presented.

Privacy-Preserving Federated Learning for UAV-Enabled Networks: Learning-Based Joint Scheduling and Resource Management

Abstract: Unmanned aerial vehicles (UAVs) are capable of serving as flying base stations (BSs) for supporting data collection, machine learning (ML) model training, and wireless communications. However, due to the privacy concerns of devices and limited computation or communication resource of UAVs, it is impractical to send raw data of devices to UAV servers for model training. Moreover, due to the dynamic channel condition and heterogeneous computing capacity of devices in UAV-enabled networks, the reliability and efficiency of data sharing require to be further improved. In this paper, we develop an asynchronous federated learning (AFL) framework for multi-UAV-enabled networks, which can provide asynchronous distributed computing by enabling model training locally without transmitting raw sensitive data to UAV servers. The device selection strategy is also introduced into the AFL framework to keep the low-quality devices from affecting the learning efficiency and accuracy. Moreover, we propose an asynchronous advantage actor-critic (A3C) based joint device selection, UAVs placement, and resource management algorithm to enhance the federated convergence speed and accuracy. Simulation results demonstrate that our proposed framework and algorithm achieve higher learning accuracy and faster federated execution time compared to other existing solutions.

Sinan: ML-based and QoS-aware resource management for cloud microservices

Abstract: Cloud applications are increasingly shifting from large monolithic services, to large numbers of loosely-coupled, specialized microservices. Despite their advantages in terms of facilitating development, deployment, modularity, and isolation, microservices complicate resource management, as dependencies between them introduce backpressure effects and cascading QoS violations. We present Sinan, a data-driven cluster manager for interactive cloud microservices that is online and QoS-aware. Sinan leverages a set of scalable and validated machine learning models to determine the performance impact of dependencies between microservices, and allocate appropriate resources per tier in a way that preserves the end-to-end tail latency target. We evaluate Sinan both on dedicated local clusters and large-scale deployments on Google Compute Engine (GCE) across representative end-to-end applications built with microservices, such as social networks and hotel reservation sites. We show that Sinan always meets QoS, while also maintaining cluster utilization high, in contrast to prior work which leads to unpredictable performance or sacrifices resource efficiency. Furthermore, the techniques in Sinan are explainable, meaning that cloud operators can yield insights from the ML models on how to better deploy and design their applications to reduce unpredictable performance.

Recent Advances of Resource Allocation in Network Function Virtualization

Abstract: Network Function Virtualization (NFV) has been emerging as an appealing solution that transforms complex network functions from dedicated hardware implementations to software instances running in a virtualized environment. Due to the numerous advantages such as flexibility, efficiency, scalability, short deployment cycles, and service upgrade, NFV has been widely recognized as the next-generation network service provisioning paradigm. In NFV, the requested service is implemented by a sequence of Virtual Network Functions (VNF) that can run on generic servers by leveraging the virtualization technology. These VNFs are pitched with a predefined order through which data flows traverse, and it is also known as the Service Function Chaining (SFC). In this article, we provide an overview of recent advances of resource allocation in NFV. We generalize and analyze four representative resource allocation problems, namely, (1) the VNF Placement and Traffic Routing problem, (2) VNF Placement problem, (3) Traffic Routing problem in NFV, and (4) the VNF Redeployment and Consolidation problem. After that, we study the delay calculation models and VNF protection (availability) models in NFV resource allocation, which are two important Quality of Service (QoS) parameters. Subsequently, we classify and summarize the representative work for solving the generalized problems by considering various QoS parameters (e.g., cost, delay, reliability, and energy) and different scenarios (e.g., edge cloud, online provisioning, and distributed provisioning). Finally, we conclude our article with a short discussion on the state-of-the-art and emerging topics in the related fields, and highlight areas where we expect high potential for future research.

Energy-Efficient Resource Management in UAV-Assisted Mobile Edge Computing

Abstract: Unmanned aerial vehicles (UAVs) have been deployed to enhance the network capacity and provide services to mobile users with or without infrastructure coverage. At the same time, we have observed the exponential growth in Internet of Things (IoTs) devices and applications. However, as IoT devices have limited computation capacity and battery lifetime, it is challenging to process data locally on the devices. To this end, in this letter, a UAV-aided mobile edge computing system is proposed. The problem to jointly minimize the energy consumption at the IoT devices and the UAVs during task execution is studied by optimizing the task offloading decision, resource allocation mechanism and UAV’s trajectory while considering the communication and computation latency requirements. A non-convex structure of the formulated problem is revealed and shown to be challenging to solve. To address this challenge, a block successive upper-bound minimization (BSUM) algorithm is introduced. Finally, simulation results are provided to show the efficiency of our proposed algorithm.

Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis

Abstract: Deep learning has recently emerged as a disruptive technology to solve challenging radio resource management problems in wireless networks. However, the neural network architectures adopted by existing works suffer from poor scalability and generalization, and lack of interpretability. A long-standing approach to improve scalability and generalization is to incorporate the structures of the target task into the neural network architecture. In this paper, we propose to apply graph neural networks (GNNs) to solve large-scale radio resource management problems, supported by effective neural network architecture design and theoretical analysis. Specifically, we first demonstrate that radio resource management problems can be formulated as graph optimization problems that enjoy a universal permutation equivariance property. We then identify a family of neural networks, named message passing graph neural networks (MPGNNs). It is demonstrated that they not only satisfy the permutation equivariance property, but also can generalize to large-scale problems, while enjoying a high computational efficiency. For interpretablity and theoretical guarantees, we prove the equivalence between MPGNNs and a family of distributed optimization algorithms, which is then used to analyze the performance and generalization of MPGNN-based methods. Extensive simulations, with power control and beamforming as two examples, demonstrate that the proposed method, trained in an unsupervised manner with unlabeled samples, matches or even outperforms classic optimization-based algorithms without domain-specific knowledge. Remarkably, the proposed method is highly scalable and can solve the beamforming problem in an interference channel with 1000 transceiver pairs within 6 milliseconds on a single GPU.

EC-SAGINs: Edge Computing-enhanced Space-Air-Ground Integrated Networks for Internet of Vehicles

Abstract: Edge computing-enhanced Internet of Vehicles (EC-IoV) enables ubiquitous data processing and content sharing among vehicles and terrestrial edge computing (TEC) infrastructures (e.g., 5G base stations and roadside units) with little or no human intervention, plays a key role in the intelligent transportation systems. However, EC-IoV is heavily dependent on the connections and interactions between vehicles and TEC infrastructures, thus will break down in some remote areas where TEC infrastructures are unavailable (e.g., desert, isolated islands and disaster-stricken areas). Driven by the ubiquitous connections and global-area coverage, space-air-ground integrated networks (SAGINs) efficiently support seamless coverage and efficient resource management, represent the next frontier for edge computing. In light of this, we first review the state-of-the-art edge computing research for SAGINs in this article. After discussing several existing orbital and aerial edge computing architectures, we propose a framework of edge computing-enabled space-air-ground integrated networks (EC-SAGINs) to support various IoV services for the vehicles in remote areas. The main objective of the framework is to minimize the task completion time and satellite resource usage. To this end, a pre-classification scheme is presented to reduce the size of action space, and a deep imitation learning (DIL) driven offloading and caching algorithm is proposed to achieve real-time decision making. Simulation results show the effectiveness of our proposed scheme. At last, we also discuss some technology challenges and future directions.

Deep Reinforcement Learning Based Resource Management for DNN Inference in Industrial IoT

Abstract: Performing deep neural network (DNN) inference in real time requires excessive network resources, which poses a big challenge to the resource-limited industrial Internet of things (IIoT) networks. To address the challenge, in this paper, we introduce an end-edge-cloud orchestration architecture, in which the inference task assignment and DNN model placement are flexibly coordinated. Specifically, the DNN models, trained and pre-stored in the cloud, are properly placed at the end and edge to perform DNN inference. To achieve efficient DNN inference, a multi-dimensional resource management problem is formulated to maximize the average inference accuracy while satisfying the strict delay requirements of inference tasks. Due to the mix-integer decision variables, it is difficult to solve the formulated problem directly. Thus, we transform the formulated problem into a Markov decision process which can be solved efficiently. Furthermore, a deep reinforcement learning based resource management scheme is proposed to make real-time optimal resource allocation decisions. Simulation results are provided to demonstrate that the proposed scheme can efficiently allocate the available spectrum, caching, and computing resources, and improve average inference accuracy by 31.4 $\%$ compared with the deep deterministic policy gradient benchmark.

Design, Resource Management, and Evaluation of Fog Computing Systems: A Survey

Abstract: A steady increase in Internet-of-Things (IoT) applications needing large-scale computation and long-term storage has lead to an overreliance on cloud computing. The resulting network congestion in the cloud, coupled with the distance of cloud data centers from IoT, contributes to unreliable end-to-end response delay. Fog computing has been introduced as an alternative to cloud, providing low-latency service by bringing processing and storage resources to the network edge. In this survey, we sequentially present the phases required in the implementation and realization of practical fog computing systems: 1) design and dimensioning of a fog infrastructure; 2) fog resource provisioning for IoT application use and IoT resource allocation to fog; 3) installation of fog frameworks for fog resource management; and 4) evaluation of fog infrastructure through simulation and emulation. Our focus is on determining the implementation aspects required to build a practical large-scale fog computing infrastructure to support the general IoT landscape.

Machine Learning-Based Scaling Management for Kubernetes Edge Clusters

Abstract: Kubernetes, the container orchestrator for cloud-deployed applications, offers automatic scaling for the application provider in order to meet the ever-changing intensity of processing demand. This auto-scaling feature can be customized with a parameter set, but those management parameters are static while incoming Web request dynamics often change, not to mention the fact that scaling decisions are inherently reactive, instead of being proactive. We set the ultimate goal of making cloud-based applications’ management easier and more effective. We propose a Kubernetes scaling engine that makes the auto-scaling decisions apt for handling the actual variability of incoming requests. In this engine various machine learning forecast methods compete with each other via a short-term evaluation loop in order to always give the lead to the method that suits best the actual request dynamics. We also introduce a compact management parameter for the cloud-tenant application provider to easily set their sweet spot in the resource over-provisioning vs. SLA violation trade-off. We motivate our scaling solution with analytical modeling and evaluation of the current Kubernetes behavior. The multi-forecast scaling engine and the proposed management parameter are evaluated both in simulations and with measurements on our collected Web traces to show the improved quality of fitting provisioned resources to service demand. We find that with just a few, but fundamentally different, and competing forecast methods, our auto-scaler engine, implemented in Kubernetes, results in significantly fewer lost requests with just slightly more provisioned resources compared to the default baseline.

Learning-Based Queue-Aware Task Offloading and Resource Allocation for Space–Air–Ground-Integrated Power IoT

Abstract: Space–air–ground-integrated power Internet of Things (SAG-PIoT) can provide ubiquitous communication and computing services for PIoT devices deployed in remote areas In SAG-PIoT, the tasks can be either processed locally by PIoT devices, offloaded to edge servers through unmanned aerial vehicles (UAVs), or offloaded to cloud servers through satellites However, the joint optimization of task offloading and computational resource allocation faces several challenges, such as incomplete information, dimensionality curse, and coupling between long-term constraints of queuing delay and short-term decision making In this article, we propose a learning-based queue-aware task offloading and resource allocation algorithm (QUARTER) Specifically, the joint optimization problem is decomposed into three deterministic subproblems: 1) device-side task splitting and resource allocation; 2) task offloading; and 3) server-side resource allocation The first subproblem is solved by the Lagrange dual decomposition For the second subproblem, we propose a queue-aware actor–critic-based task offloading algorithm to cope with dimensionality curse A greedy-based low-complexity algorithm is developed to solve the third subproblem Compared with existing algorithms, simulation results demonstrate that QUARTER has superior performances in energy consumption, queuing delay, and convergence

A Review of Internet of Things—Resource Allocation

Abstract: As one of emerging technologies, Internet of Things (IoT) has become popular. This article reviews the literature regarding resource allocation (RA) of the Internet of Things systematically. It identifies the key techniques, state-of-the-art, challenges, and trend associated with the IoT resource allocation, and its impact on the enterprise architecture.

Resource Allocation and Service Provisioning in Multi-Agent Cloud Robotics: A Comprehensive Survey

Abstract: Robotic applications nowadays are widely adopted to enhance operational automation and performance of real-world Cyber-Physical Systems (CPSs) including Industry 4.0, agriculture, healthcare, and disaster management. These applications are composed of latency-sensitive, data-heavy, and compute-intensive tasks. The robots, however, are constrained in the computational power and storage capacity. The concept of multi-agent cloud robotics enables robot-to-robot cooperation and creates a complementary environment for the robots in executing large-scale applications with the capability to utilize the edge and cloud resources. However, in such a collaborative environment, the optimal resource allocation for robotic tasks is challenging to achieve. Heterogeneous energy consumption rates and application of execution costs associated with the robots and computing instances make it even more complex. In addition, the data transmission delay between local robots, edge nodes, and cloud data centres adversely affects the real-time interactions and impedes service performance guarantee. Taking all these issues into account, this paper comprehensively surveys the state-of-the-art on resource allocation and service provisioning in multi-agent cloud robotics. The paper presents the application domains of multi-agent cloud robotics through explicit comparison with the contemporary computing paradigms and identifies the specific research challenges. A complete taxonomy on resource allocation is presented for the first time, together with the discussion of resource pooling, computation offloading, and task scheduling for efficient service provisioning. Furthermore, we highlight the research gaps from the learned lessons, and present future directions deemed beneficial to further advance this emerging field.