The rapid deployment of Internet of Things (IoT) applications leads to massive data that need to be processed. These IoT applications have specific communication requirements on latency and bandwidth, and present new features on their generated data such as time-dependency. Therefore, it is desirable to reshape the current IoT architectures by exploring their inherent nature of communication and computing to support smart IoT data process and analysis. We introduce in this paper features of IoT data, trends of IoT network architectures, some problems in IoT data analysis, and their solutions. Specifically, we view that software-defined edge computing is a promising architecture to support the unique needs of IoT data analysis. We further present an experiment on data anomaly detection in this architecture, and the comparison between two architectures for ECG diagnosis. Results show that our method is effective and feasible.
Federated learning (FL) brings collaborative intelligence into industries without centralized training data to accelerate the process of Industry 4.0 on the edge computing level. FL solves the dilemma in which enterprises wish to make the use of data intelligence with security concerns. To accelerate industrial Internet of things with the further leverage of FL, existing achievements on FL are developed from three aspects: 1) define terminologies and elaborate a general framework of FL for accommodating various scenarios; 2) discuss the state-of-the-art of FL on fundamental researches including data partitioning, privacy preservation, model optimization, local model transportation, personalization, motivation mechanism, platform & tools, and benchmark; 3) discuss the impacts of FL from the economic perspective. To attract more attention from industrial academia and practice, a FL-transformed manufacturing paradigm is presented, and future research directions of FL are given and possible immediate applications in Industry 4.0 domain are also proposed.
Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time. Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy. To mitigate this cost, in this paper we introduce a novel method called Multi-Exit Curriculum Learning that utilizes curriculum learning, a training strategy for neural networks that imitates human learning by sorting the training samples based on their difficulty and gradually introducing them to the network. Experiments on CIFAR-10 and CIFAR-100 datasets and various configurations of multi-exit architectures show that our method consistently improves the accuracy of early exits compared to the standard training approach.
As a promising solution to achieve efficient learning among isolated data owners and solve data privacy issues, federated learning is receiving wide attention. Using the edge server as an intermediary can effectively collect sensor data, perform local model training, and upload model parameters for global aggregation. So this paper proposes a new framework for resource allocation in a hierarchical network supported by edge computing. In this framework, we minimize the weighted sum of system cost and learning cost by optimizing bandwidth, computing frequency, power allocation and subcarrier assignment. To solve this challenging mixed-integer non-linear problem, we first decouple the bandwidth optimization problem(P1) from the whole problem and obtain a closed-form solution. The remaining computational frequency, power, and subcarrier joint optimization problem(P2) can be further decomposed into two sub-problems: latency and computational frequency optimization problem(P3) and transmission power and subcarrier optimization problem(P4). P3 is a convex optimization problem that is easy to solve. In the joint optimization problem(P4), the optimal power under each subcarrier selection can be obtained first through the successive convex approximation(SCA) algorithm. Substituting the optimal power value obtained back to P4, the subproblem can be regarded as an assignment problem, so the Hungarian algorithm can be effectively used to solve it. The solution of problem P2 is accomplished by solving P3 and P4 iteratively. To verify the performance of the algorithm, we compare the proposed algorithm with five algorithms; namely Equal bandwidth allocation, Learning cost guaranteed, Greedy subcarrier allocation, System cost guaranteed and Time-biased algorithm. Numerical results show the significant performance gain and the robustness of the proposed algorithm in the face of parameter changes.
We propose a novel strategy for energy-efficient dynamic computation offloading, in the context of edge-computing-aided beyond 5G networks. The goal is to minimize the energy consumption of the overall system, comprising multiple User Equipment (UE), an access point (AP), and an edge server (ES), under constraints on the end-to-end service delay and the packet error rate performance over the wireless interface. To reduce the energy consumption, we exploit low-power sleep operation modes for the users, the AP and the ES, shifting the edge computing paradigm from an always on to an always available architecture, capable of guaranteeing an on-demand target service quality with the minimum energy consumption. To this aim, we propose an online algorithm for dynamic and optimal orchestration of radio and computational resources called Discontinuous Computation Offloading (DisCO). In such a framework, end-to-end delay constraints translate into constraints on overall queueing delays, including both the communication and the computation phases of the offloading service. DisCO hinges on Lyapunov stochastic optimization, does not require any prior knowledge on the statistics of the offloading traffic or the radio channels, and satisfies the long-term performance constraints imposed by the users. Several numerical results illustrate the advantages of the proposed method.
With the advancement in drone technology, in just a few years, drones will be assisting humans in every domain. But there are many challenges to be tackled, communication being the chief one. This paper aims at providing insights into the latest UAV (Unmanned Aerial Vehicle) communication technologies through investigation of suitable task modules, antennas, resource handling platforms, and network architectures. Additionally, we explore techniques such as machine learning and path planning to enhance existing drone communication methods. Encryption and optimization techniques for ensuring long lasting and secure communications, as well as for power management, are discussed. Moreover, applications of UAV networks for different contextual uses ranging from navigation to surveillance, URLLC (Ultra reliable and low latency communications), edge computing and work related to artificial intelligence are examined. In particular, the intricate interplay between UAV, advanced cellular communication, and internet of things constitutes one of the focal points of this paper. The survey encompasses lessons learned, insights, challenges, open issues, and future directions in UAV communications. Our literature review reveals the need for more research work on drone to drone and drone to device communications.
Wireless charging coupled with computation offloading in edge networks offers a promising solution for realizing power-hungry and computation intensive applications on user devices. We consider a multi-access edge computing (MEC) system with collocated MEC server and base-station/access point, each equipped with a massive MIMO antenna array, supporting multiple users requesting data computation and wireless charging. The goal is to minimize the energy consumption for computation offloading and maximize the received energy at the user from wireless charging. The proposed solution is a novel two-stage algorithm employing nested primal-dual and linear programming techniques to perform data partitioning and time allocation for computation offloading and design the optimal energy beamforming for wireless charging, all within MEC-AP transmit power and latency constraints. Algorithm results show that optimal energy beamforming significantly outperforms other schemes such as isotropic or directed charging without beam power allocation. Compared to binary offloading, data partition in partial offloading leads to lower energy consumption and more charging time, and hence offers better wireless charging performance. The charged energy over an extended period of time both with and without computation offloading can be substantial. Opportunistic wireless charging from MEC-AP thus offers a viable untethered approach for supplying energy to user-devices.
In this paper, we explore optimization-based and data-driven solutions in a reconfigurable intelligent surface (RIS)-aided multi-user mobile edge computing (MEC) system, where the user equipment (UEs) can partially offload their computation tasks to the access point (AP). We aim at maximizing the total completed task-input bits (TCTB) of all UEs with limited energy budgets during a given time slot, through jointly optimizing the RIS reflecting coefficients, the AP's receive beamforming vectors, and the UEs' energy partition strategies for local computing and offloading. A three-step block coordinate descending (BCD) algorithm is first proposed to effectively solve the non-convex TCTB maximization problem with guaranteed convergence. In order to reduce the computational complexity and facilitate lightweight online implementation of the optimization algorithm, we further construct two deep learning architectures. The first one takes channel state information (CSI) as input, while the second one exploits the UEs' locations only for online inference. The two data-driven approaches are trained using data samples generated by the BCD algorithm via supervised learning. Our simulation results reveal a close match between the performance of the optimization-based BCD algorithm and the low-complexity learning-based architectures, all with superior performance to existing schemes in both cases with perfect and imperfect input features. Importantly, the location-only deep learning method is shown to offer a particularly practical and robust solution alleviating the need for CSI estimation and feedback when line-of-sight (LoS) direct links exist between UEs and the AP.
Driven by the unprecedented high throughput and low latency requirements in next-generation wireless networks, this paper introduces an artificial intelligence (AI) enabled framework in which unmanned aerial vehicles (UAVs) use non-orthogonal multiple access (NOMA) and mobile edge computing (MEC) techniques to service terrestrial mobile users (MUs). The proposed framework enables the terrestrial MUs to offload their computational tasks simultaneously, intelligently, and flexibly, thus enhancing their connectivity as well as reducing their transmission latency and their energy consumption. To this end, the fundamentals of this framework are first introduced. Then, a number of communication and AI techniques are proposed to improve the quality of experiences of terrestrial MUs. To this end, federated learning and reinforcement learning are introduced for intelligent task offloading and computing resource allocation. For each learning technique, motivations, challenges, and representative results are introduced. Finally, several key technical challenges and open research issues of the proposed framework are summarized.
In the upcoming sixth-generation (6G) era, the demand for constructing a wide-area time-sensitive Internet of Things (IoT) keeps increasing. As conventional cellular technologies are hard to be directly used for wide-area time-sensitive IoT, it is beneficial to use non-terrestrial infrastructures including satellites and unmanned aerial vehicles (UAVs), where a non-terrestrial network (NTN) can be built under the cell-free architecture. Driven by the time-sensitive requirements and uneven distribution of IoT devices, the NTN is required to be empowered by mobile edge computing (MEC) while providing oasis-oriented on-demand coverage for the devices. Nevertheless, communication and MEC systems are coupled with each other under the influence of complex propagation environment in the MEC-empowered NTN, which makes it hard to orchestrate the resources. In this paper, we propose a process-oriented framework to design the communication and MEC systems in a time-division manner. Under this framework, the large-scale channel state information (CSI) is used to characterize the complex propagation environment with an affordable cost, where a non-convex latency minimization problem is formulated. After that, the approximated problem is given and it can be decomposed into subproblems. These subproblems are further solved in an iterative way. Simulation results demonstrate the superiority of the proposed process-oriented scheme over other algorithms. These results also indicate that the payload deployments of UAVs should be appropriately predesigned to improve the efficiency of resource use. Furthermore, the results imply that it is advantageous to integrate NTN with MEC for wide-area time-sensitive IoT.
In recent years, Graph Neural Networks (GNNs) appear to be state-of-the-art algorithms for analyzing non-euclidean graph data. By applying deep-learning to extract high-level representations from graph structures, GNNs achieve extraordinary accuracy and great generalization ability in various tasks. However, with the ever-increasing graph sizes, more and more complicated GNN layers, and higher feature dimensions, the computational complexity of GNNs grows exponentially. How to inference GNNs in real time has become a challenging problem, especially for some resource-limited edge-computing platforms. To tackle this challenge, we propose BlockGNN, a software-hardware co-design approach to realize efficient GNN acceleration. At the algorithm level, we propose to leverage block-circulant weight matrices to greatly reduce the complexity of various GNN models. At the hardware design level, we propose a pipelined CirCore architecture, which supports efficient block-circulant matrices computation. Basing on CirCore, we present a novel BlockGNN accelerator to compute various GNNs with low latency. Moreover, to determine the optimal configurations for diverse deployed tasks, we also introduce a performance and resource model that helps choose the optimal hardware parameters automatically. Comprehensive experiments on the ZC706 FPGA platform demonstrate that on various GNN tasks, BlockGNN achieves up to $8.3\times$ speedup compared to the baseline HyGCN architecture and $111.9\times$ energy reduction compared to the Intel Xeon CPU platform.
Spiking neural networks have shown great promise for the design of low-power sensory-processing and edge-computing hardware platforms. However, implementing on-chip learning algorithms on such architectures is still an open challenge, especially for multi-layer networks that rely on the back-propagation algorithm. In this paper, we present a spike-based learning method that approximates back-propagation using local weight update mechanisms and which is compatible with mixed-signal analog/digital neuromorphic circuits. We introduce a network architecture that enables synaptic weight update mechanisms to back-propagate error signals across layers and present a network that can be trained to distinguish between two spike-based patterns that have identical mean firing rates, but different spike-timings. This work represents a first step towards the design of ultra-low power mixed-signal neuromorphic processing systems with on-chip learning circuits that can be trained to recognize different spatio-temporal patterns of spiking activity (e.g. produced by event-based vision or auditory sensors).
As the complexity of Deep Neural Network (DNN) models increases, their deployment on mobile devices becomes increasingly challenging, especially in complex vision tasks such as image classification. Many of recent contributions aim either to produce compact models matching the limited computing capabilities of mobile devices or to offload the execution of such burdensome models to a compute-capable device at the network edge - the edge servers. In this paper, we propose to modify the structure and training process of DNN models for complex image classification tasks to achieve in-network compression in the early network layers. Our training process stems from knowledge distillation, a technique that has been traditionally used to build small - student - models mimicking the output of larger - teacher - models. Here, we adopt this idea to obtain aggressive compression while preserving accuracy. Our results demonstrate that our approach is effective for state-of-the-art models trained over complex datasets, and can extend the parameter region in which edge computing is a viable and advantageous option. Additionally, we demonstrate that in many settings of practical interest we reduce the inference time with respect to specialized models such as MobileNet v2 executed at the mobile device, while improving accuracy.
Offloading the execution of complex Deep Neural Networks (DNNs) models to compute-capable devices at the network edge, that is, edge servers, can significantly reduce capture-to-output delay. However, the communication link between the mobile devices and edge servers can become the bottleneck when channel conditions are poor. We propose a framework to split DNNs for image processing and minimize capture-to-output delay in a wide range of network conditions and computing parameters. The core idea is to split the DNN models into head and tail models, where the two sections are deployed at the mobile device and edge server, respectively. Different from prior literature presenting DNN splitting frameworks, we distill the architecture of the head DNN to reduce its computational complexity and introduce a bottleneck, thus minimizing processing load at the mobile device as well as the amount of wirelessly transferred data. Our results show 98% reduction in used bandwidth and 85% in computation load compared to straightforward splitting.
Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, the poor efficiency of GNN inference and frequent Out-Of-Memory (OOM) problem limit the successful application of GNN on edge computing platforms. To tackle these problems, a feature decomposition approach is proposed for memory efficiency optimization of GNN inference. The proposed approach could achieve outstanding optimization on various GNN models, covering a wide range of datasets, which speeds up the inference by up to 3x. Furthermore, the proposed feature decomposition could significantly reduce the peak memory usage (up to 5x in memory efficiency improvement) and mitigate OOM problems during GNN inference.
With the development of virtual reality (VR) technology, the future of VR systems is evolving from single-user wired connections to multi-user wireless connections. However, wireless online rendering and transmission incur extra processing and transmission latency, as well as higher bandwidth requirements. To meet the requirements of wireless VR applications and enhance the quality of the VR user experience, this paper designs a view synthesis-based 360° VR caching system over Cloud Radio Access Network (C-RAN), where both mobile edge computing (MEC) and hierarchical caching are supported. In the system, an MEC-Cache Server is deployed in the pooled Base band Units (BBU pool) and used for view synthesis and caching. In addition, the remote radio heads (RRHs) can also cache some video contents. If the requested content of a specific view is cached in the BBU pool or RRHs, or can be synthesized with the aid of the cached adjacent views, it is unnecessary to request the content from the remote VR video source server. Therefore, the transmission latency and backhaul traffic load for VR services can be decreased. We formulate a hierarchical collaborative caching problem aiming to minimize the transmission latency, which is proved NP-hard. To address the impractical expenses of the offline optimal method, an online MaxMinDistance caching algorithm with low complexity is proposed. Numerical simulation results demonstrate that the proposed caching strategy provides significantly improved cache hit rate, backhaul traffic load, transmission latency, and Quality of Experience (QoE) performances relative to conventional caching strategies
Several researches and evidence show the increasing likelihood of pandemics (large-scale outbreaks of infectious disease) which has far reaching sequels in all aspects of human lives ranging from rapid mortality rates to economic and social disruption across the world. In the recent time, COVID-19 (Coronavirus Disease 2019) pandemic disrupted normal human lives, and motivated by the urgent need of combating COVID-19, researchers have put significant efforts in modelling and analysing the disease spread patterns for effective preventive measures (in addition to developing pharmaceutical solutions, like vaccine). In this regards, it is absolutely necessary to develop an analytics framework by extracting and incorporating the knowledge of heterogeneous datasources to deliver insights in improving administrative policy and enhance the preparedness to combat the pandemic. Specifically, human mobility, travel history and other transport statistics have significant impacts on the spread of any infectious disease. In this direction, this paper proposes a spatio-temporal knowledge mining framework, named STOPPAGE to model the impact of human mobility and other contextual information over large geographic area in different temporal scales. The framework has two major modules: (i) Spatio-temporal data and computing infrastructure using fog/edge based architecture; and (ii) Spatio-temporal data analytics module to efficiently extract knowledge from heterogeneous data sources. Typically, we develop a Pandemic-knowledge graph to discover correlations among mobility information and disease spread, a deep learning architecture to predict the next hot-spot zones; and provide necessary support in home-health monitoring utilizing Femtolet and fog/edge based solutions. The experimental evaluations on real-life datasets related to COVID-19 in India illustrate the efficacy of the proposed methods.
Ground segmentation of point clouds remains challenging because of the sparse and unordered data structure. This paper proposes the GSECnet - Ground Segmentation network for Edge Computing, an efficient ground segmentation framework of point clouds specifically designed to be deployable on a low-power edge computing unit. First, raw point clouds are converted into a discretization representation by pillarization. Afterward, features of points within pillars are fed into PointNet to get the corresponding pillars feature map. Then, a depthwise-separable U-Net with the attention module learns the classification from the pillars feature map with an enormously diminished model parameter size. Our proposed framework is evaluated on SemanticKITTI against both point-based and discretization-based state-of-the-art learning approaches, and achieves an excellent balance between high accuracy and low computing complexity. Remarkably, our framework achieves the inference runtime of 135.2 Hz on a desktop platform. Moreover, experiments verify that it is deployable on a low-power edge computing unit powered 10 watts only.
Virtual reality (VR) is promising to fundamentally transform a broad spectrum of industry sectors and the way humans interact with virtual content. However, despite unprecedented progress, current networking and computing infrastructures are incompetent to unlock VR's full potential. In this paper, we consider delivering the wireless multi-tile VR video service over a mobile edge computing (MEC) network. The primary goal is to minimize the system latency/energy consumption and to arrive at a tradeoff thereof. To this end, we first cast the time-varying view popularity as a model-free Markov chain to effectively capture its dynamic characteristics. After jointly assessing the caching and computing capacities on both the MEC server and the VR playback device, a hybrid policy is then implemented to coordinate the dynamic caching replacement and the deterministic offloading, so as to fully utilize the system resources. The underlying multi-objective problem is reformulated as a partially observable Markov decision process, and a deep deterministic policy gradient algorithm is proposed to iteratively learn its solution, where a long short-term memory neural network is embedded to continuously predict the dynamics of the unobservable popularity. Simulation results demonstrate the superiority of the proposed scheme in achieving a trade-off between the energy efficiency and the latency reduction over the baseline methods.
Intelligent Transportation Systems are thriving thanks to a wide range of technological advances, namely 5G communications, Internet of Things, artificial intelligence and edge computing. Central to this is the wide deployment of smart sensing devices and accordingly the large amount of harvested information to be processed for timely decision making. Robust network access is, hence, essential for offloading the collected data before a set deadline, beyond which the data loses its value. In environments where direct communication can be impaired by, for instance, blockages such as in urban cities, unmanned aerial vehicles (UAVs) can be considered as an alternative for providing and enhancing connectivity, particularly when IoT devices (IoTD) are constrained with their resources. Also, to conserve energy, IoTDs are assumed to alternate between their active and passive modes. This paper, therefore, considers a time-constrained data gathering problem from a network of sensing devices and with assistance from a UAV. A Reconfigurable Intelligent Surface (RIS) is deployed to further improve both the connectivity and energy efficiency of the UAV, particularly when multiple devices are served concurrently and experience different channel impairments. This integrated problem brings challenges related to the configuration of the phase shift elements of the RIS, the scheduling of IoTDs transmissions as well as the trajectory of the UAV. First, the problem is formulated with the objective of maximizing the total number of served devices each during its activation period. Owing to its complexity and the incomplete knowledge about the environment, we leverage deep reinforcement learning in our solution; the UAV trajectory planning is modeled as a Markov Decision Process, and Proximal Policy Optimization is invoked to solve it. Next, the RIS configuration is then handled via Block Coordinate Descent.