Conventional Cloud Computing Research Articles

Edge-centric energy efficient LSTM with federated learning model based computation offloading for IoT applications

A more recent innovation to support cloud computing is edge computing that can address the deficiency of the existing centralised cloud computing paradigm and bring compute and storage resources closer to devices. Edge computing isn’t always the same as conventional cloud computing. Edge computing isn’t always the same as conventional cloud computing. It is a new computational model that performs computation at the network edge. Its crucial idea is to bring computing in the way of the information’s source. Task scheduling is the process allocating incoming requests (tasks) using a specific method to make the best use of the resources for the needed process. Users of services must submit their requests online because cloud computing is the technology used to deliver services through the internet. This paper aims to provide an Edge centric LSTM model with Federated learning for Data storage and model training that will take place on powerful edge servers in distributed ML methods. a massively distributed tasks requiring Processing on-site, coordinating the task remotely and execution are carried out in collaboration with number of multiple edge nodes and the distant cloud infrastructure. As a result, improved computation offloading and networking tradeoffs are possible to achieve low latency, large bandwidth take place on powerful edge servers.

Distributed Cloud Computing: Architecture, Enabling Technologies, and Open Challenges

Conventional cloud computing, where compute, storage, and networking resources reside in one or a few centralized data centers, has become unable to meet the stringent latency requirements of new applications. Along with that, the rapid development of 5 G network introduces the trend of network cloudification and network service provisioning according to cloud service models. Therefore, the emerging distributed cloud model represents an evolution from conventional centralized cloud into geographically dispersed cloud computing services located as per application needs. In this article, we attempt to sketch a big picture of distributed cloud. We first interpret the concept of distributed cloud computing. Then, we describe an architecture of the distributed cloud along with the enabling technologies. We also carry out a case study on service deployment and discovery in a 3-layer distributed cloud prototype and provide a preliminary assessment of service discovery time. Finally, we discuss open research challenges towards distributed cloud.

A Socially-Aware Radio Map Framework for Improving QoS of UAV-Assisted MEC Networks

The expeditious growth of the Internet of Things (IoT) has accelerated the evolution of multi-access edge computing (MEC). MEC alleviates the challenges of conventional cloud computing, such as high data latency, poor data gathering reliability, increased network cost, and lack of network robustness. The primary objective of MEC is to facilitate a hierarchy of edge servers to address these quality-of-service (QoS) challenges, especially the information propagation issue due to the mobility of IoT devices (IoD). Further, social-relationship among mobile IoD is a critical parameter used to reduce the data transmission delay and queue size at the MEC. Specifically, in this work, a novel socially-aware radio map generation method is proposed to compute the fine-grained and accurate locations of QoS-deprived areas. Firstly, a novel method to compute the social relationship index (SRI) factor is proposed on the basis of current and future encounters among moving IoDs. Then the obtained SRI factor is used to form clusters of mobile IoD. The clusters’ signal to interference plus noise ratio (SINR) is then used to generate the socially-aware radio map. Following that, unmanned aerial vehicles (UAV) use this radio map, which contains rich and serviceable channel information, for 3D beamforming towards the mobile clusters. Using the obtained radio map, Kalman filter-based offline path planning of UAVs is proposed to minimize the UAVs flying distance from the initial to final locations. Furthermore, an optimization problem is formulated to assess the performance of the proposed method. Finally, the performance of the proposed method is compared with the existing methods, taking into account various network parameters such as optimum number of UAVs needed to cover the deployed area, data transmission delay, and received SINR.

Privacy-Preserving Federated Learning for Industrial Edge Computing via Hybrid Differential Privacy and Adaptive Compression

With the continuous improvement of hardware computing power, edge computing of industrial data has been gradually applied. In the past decade, the promotion of edge computing has also greatly improved the efficiency of industrial production. Compared with the conventional cloud computing, it not only saves the bandwidth consumption of data transmission, but also ensures the terminal data security to a certain extent. However, the continuous update of attack types also put forward new requirements for the privacy protection of industrial edge computing. So it should fundamentally solve the risk of industrial data leakage in the process of deep model training in edge terminal. In this article, we propose a new federated edge learning framework based on hybrid differential privacy and adaptive compression for industrial data processing. Specifically, it first completes the adaptive gradient compression preparation, then constructs the industrial federated learning model, and finally makes use of adaptive differential privacy model to optimize, so as to complete the privacy protection towards the transmission of gradient parameters in industrial environment. By optimizing the hybrid differential privacy and adaptive compression, we can better prevent the terminal data privacy against inference attacks. The experimental results show that this method is very effective in the industrial edge computing situation, and it also opens up a new direction for the effect of differential privacy in federated learning.

Research on electrical power quality disturbance recognition method based on edge computing and LightGBM

In conventional cloud computing, method that data is transmitted and calculated on the cloud cannot satisfy the real-time demand for energy quality disturbance recognition. This paper proposed a power quality disturbance recognition method based on edge computing and LightGBM classification algorithm. Our main idea is that the feature of disturbance is extracted on the edge sides and used to classified on the cloud. Firstly, a multi-group feature set was extracted at the edge side intelligent fusion terminal by wavelet transform. Secondly, we used feature training accuracy to select the optimal feature collection. Finally, the optimal feature set was selected to determine the disturbance recognition method of this paper. Experiments had shown that the proposed method meets demand on data transmission by 99.5%, and achieves 97.53% recognition accuracy. Our method not only guarantees high accuracy of the power quality disturbance recognition but also alleviates the bandwidth load pressure brought by large amounts of data transmission.

MULTIMEDIA CLOUD COMPUTING IN VEHICLES

Intelligent Transportation Systems (ITSs) means services to improve safety and traffic efficiency. For example, vehicle-to-vehicle communication for road safety. In ITSs, vehicles are equipped with a number of sensors which provide different functions like weather forecast, temperature, GPS etc. All these features make the drive better and smooth. As a result, these vehicles produce a large amount of multimedia related data, which is critical and delay-sensitive, and requires on-time processing. The standalone devices embedded in the vehicles cannot do the required fast-processing due to their limited computation facilities. Cost minimisation, Quality of Experience, and resource allocation are some more problems related to multimedia related content processing, which have arrived in recent times. Thus, the concept of merging cloud computing with vehicles has emerged. Still conventional cloud computing is not suitable for this critical and delaysensitive multimedia related data. So a new computing paradigm called Multimedia Cloud Computing (MCC) has emerged. Thus, in this paper, a Dynamic Priority-based Efficient Resource Allocation and Computing scheme is proposed to overcome the above-mentioned issues.

A revocable and outsourced multi-authority attribute-based encryption scheme in fog computing

Fog computing is a revolutionary technology for the next generation to bridge the gap between cloud data centers and end-users. Fog computing is not a counterfeit for cloud computing but a persuasive counterpart. It also accredits by utilizing the network edge while still rendering the possibility to interact with the cloud. Nevertheless, the features of fog computing are encountering several security challenges. The security of end-users and/or fog servers brings a significant dilemma in implementing fog computing. Moreover, in conventional cloud computing, the attribute-based encryption (ABE) technology is not appropriate for end-users due to restricted computing resources, i.e., limited resources, high end-to-end delay, and transmission capability. Hence, the revocation and outsourcing mechanisms become inappropriate between end-users and cloud servers. In this regard, this paper recommends a multi-authority attribute-based encryption (MA-ABE) technique to support revocation and outsource the attributes to fog computation. We present an attribute revocation scheme based on cipher-text attribute-based encryption by introducing the attribute group keys. In this process, the secret keys are dynamically altered and realized the requirement of immediate attribute revocations. Hence, we provide the complete encryption and decryption process for end-users and fog servers based on multi-authority, attribute revocation, and outsourcing computation, while most of the existing scheme lack to incorporate all these parameters. Our scheme also outsources the complicated encryption and decryption tasks to the fog server that significantly improves the overall computation efficiency compared to the state-of-the-art work.

Experimental Assessment of Automatic Optical Metro Edge Computing Network for Beyond 5G Applications and Network Service Composition

The upcoming 5G and beyond 5G heterogeneous applications with different quality of service (QoS) will impose strict latency, bandwidth, and flexibility requirements on optical metro access networks. Conventional cloud computing is gradually unable to fulfill the application requirements, especially on latency due to the distance causing propagation and networking delay. Therefore, the edge computing that distributed in metro access networks is promising to serve the applications with the requirements of ultra-low latency. As the resources of edge computing nodes are restricted and light compared with cloud data centers (DC), it is significant to manage across multiple edge computing nodes to enable joint allocation of the distributed resources. To address this issue, the optical metro network infrastructure should be flexible on the data plane and able to interact with the control and orchestration plane to automatically adapt to the communication requirements of multiple edge computing nodes. Related works have been focused on the simulation and numerical study. In this paper, an experimental testbed of a flexible optical metro access network including hardware and software components is built, and the performance is validated with real server traffic. The presented network system is based on the field-programmable gate array (FPGA), and hardware adapted open source network management and telemetry tools. Different from the commercial electrical switches, FPGA is fully programmable making it able to flexibly forward and monitor the traffic, in the meantime, to dynamically control the optical devices according to the feedback from the control plane. By exploiting dynamic software defined networking (SDN) control and network service orchestration, the proposed network is able to establish capacity adapted network slices for edge computing connections. Successful telemetry-assisted dynamic network service chain (NSC) generation, automatic bandwidth resources assignment, and QoS protection are demonstrated.

Guest Editorial Special Issue on Vehicular Clouds

Cloud Computing, a catchy metaphor for utility computing, implemented through the provisioning of various types of hosted services over the Internet, has seen phenomenal growth and quasi-universal adoption in the past two decades. The underlying business model of cloud computing is the familiar “pay-as-you-go” model of metered services, where a user pays for whatever he/she uses and no more, and where additional demand for service can be met in real time. This powerful idea was suggested, at least in part, by the pervasive low-cost high-speed Internet, a good handle on virtualization, and advances in parallel and distributed computing. Three aspects are novel in conventional cloud computing: First, it gives users the illusion of infinite computing resources available to them on demand. Second, it eliminates the up-front financial commitment by cloud users, allowing them to increase hardware/software resources as needed. Third, it gives users the ability to pay for resources on a short-term basis and release them when they are no longer needed.

Toward Approximating Job Completion Time in Vehicular Clouds

Motivated by the phenomenal success of conventional cloud computing, vehicular clouds (VCs) were introduced as a group of vehicles whose corporate computing, sensing, communication, and physical resources can be coordinated and dynamically allocated to authorized users. Just as in conventional clouds, job completion time ranks high among the fundamental quantitative performance figures of merit. Recently, the authors have analytically investigated the effect of a redundancy-based job assignment on job completion time in VCs. However, these analytical expressions require full knowledge of the distribution functions of various random variables contributing to job completion time. In a practical context, the data center manager does not know these distribution functions. Instead, using accumulated empirical data, they may be able to estimate the first and, perhaps, the second moments of these random variables. Yet, getting a handle on the expected job completion time is a very important problem that must be addressed. Consequently, it is of great theoretical interest and practical relevance to be able to approximate the expression of job completion time. With this in mind, the main contribution of this paper is to offer easy-to-compute approximations of job completion time when estimates of the first or the first two moments of the intervening random variables are available. A comprehensive set of simulations have shown that our approximations are very close to the analytical predictions.

Short-Term Traffic Prediction for Edge Computing-Enhanced Autonomous and Connected Cars

Autonomous and connected cars (ACCs), together with edge computing (EC), have been recognized as a promising solution to achieve green intelligent transportation for smart cities. This paper aims to address short-term traffic prediction, a fundamental enabler for the success of ACC applications, under the European Telecommunications Standards Institute multi-access EC (MEC) architecture that exhibits constraints different from conventional cloud computing. First, a data-centric experiment platform is designed and implemented to facilitate traffic prediction algorithm development. This paper further proposes a novel short-term traffic prediction model that integrates a traffic light model and a vehicle velocity model, considering limited computing resources of MEC servers. We note that the effects of traffic lights are complicated and have not been rigorously examined in most, if not all, of the related work. This work models the queueing time when a driver arrives at a road intersection and faces a red light. Moreover, to forecast the vehicle velocity, we propose a novel low-complexity semiparametric prediction model considering periodic features and spatial/temporal correlations of dynamic road events. The experiment results demonstrate that our vehicle-velocity prediction model achieves almost equivalent accuracy to the well-known Long Short-Term Memory Neural Network model, requiring much lower computational complexity. Our experiment results also confirm that since our integrated model pays attention to the traffic-light effects and the individual driver behavior, it can more effectively capture the real-time changes of traffic conditions.

Mobility Support for Fog Computing: An SDN Approach

The emerging real-time and computation-intensive services driven by the Internet of Things, augmented reality, automatic driving, and so on, have tight quality of service and quality of experience requirements, which can hardly be supported by conventional cloud computing. Fog computing, which migrates the features of cloud computing to the network edge, guarantees low latency for location-aware services. However, due to the locality feature of fog computing, maintaining service continuity when mobile users travel across different access networks has become a challenging issue. In this article, we propose a novel software-defined-networking-based fog computing architecture by decoupling mobility control and data forwarding. Under the proposed architecture, we design efficient signaling operations to provide seamless and transparent mobility support to mobile users, and present an efficient route optimization algorithm by considering the performance gain in data communications and system overhead in mobile fog computing. Numerical results from extensive simulations have demonstrated that the proposed scheme can not only guarantee service continuity, but also greatly improve handover performance and achieve high data communication efficiency in mobile fog computing.

Efficient and Secure Access Control Scheme in the Standard Model for Vehicular Cloud Computing

Vehicular networking involves the storage, compute, and analysis of massive vehicular data. Vehicular cloud computing, as a special cloud computing platform, seamlessly combines vehicular ad hoc networks and conventional cloud computing. However, in the vehicular cloud computing, there is still the problem of unauthorized users accessing and stealing data. In the traditional ciphertext-policy attribute-based encryption (CP-ABE) scheme, a trusted central authority is employed to manage attributes and distribute keys. Based on multi-authority (MA) CP-ABE, we propose a secure and revocable access control scheme for vehicular cloud computing in this paper, in which the requester can decrypt the ciphertext with only a small amount of computation. We show that our MA-CP-ABE scheme can prevent static corruption of authorities in the standard model under the decisional q-parallel bilinear Diffie–Hellman exponent assumption. Theoretical analysis and experimental simulation results show that our scheme has lower communication cost and lower computational complexity than other schemes.

Challenges of Future VANET and Cloud‐Based Approaches

Vehicular ad hoc networks (VANETs) have been studied intensively due to their wide variety of applications and services, such as passenger safety, enhanced traffic efficiency, and infotainment. With the evolution of technology and sudden growth in the number of smart vehicles, traditional VANETs face several technical challenges in deployment and management due to less flexibility, scalability, poor connectivity, and inadequate intelligence. Cloud computing is considered a way to satisfy these requirements in VANETs. However, next‐generation VANETs will have special requirements of autonomous vehicles with high mobility, low latency, real‐time applications, and connectivity, which may not be resolved by conventional cloud computing. Hence, merging of fog computing with the conventional cloud for VANETs is discussed as a potential solution for several issues in current and future VANETs. In addition, fog computing can be enhanced by integrating Software‐Defined Network (SDN), which provides flexibility, programmability, and global knowledge of the network. We present two example scenarios for timely dissemination of safety messages in future VANETs based on fog and a combination of fog and SDN. We also explained the issues that need to be resolved for the deployment of three different cloud‐based approaches.

An Adaptive Virtual Machine Location Selection Mechanism in Distributed Cloud

Mobile cloud computing has recently become a new paradigm for the utilization of a variety of shared mobile resources via wireless network environments. However, due to the inherent characteristics of mobile devices, a limited battery life, and a network access requirement, it is necessary for mobile servers to provide a dynamic approach for managing mobile resources efficiently in mobile cloud computing environments. Since on-demand job requests occur frequently and the number of mobile devices is drastically increased in mobile cloud computing environments, a different mobile resource management method is required to maximize the computational power. In this paper, we therefore propose a cooperative, mobile resource sharing method that considers both the inherent properties and the number of mobile devices in mobile cloud environments. The proposed method is composed of four main components: mobile resource monitor, job handler, resource handler, and results consolidator. In contrast with conventional mobile cloud computing, each mobile device under the proposed method can be either a service consumer or a service provider in the cloud. Even though each device is resource-poor when a job is processed independently, the computational power is dramatically increased under the proposed method, as the devices cooperate simultaneously for a job. Therefore, the mobile computing power throughput is dynamically increased, while the computation time for a given job is reduced. We conduct case-based experiments to validate the proposed method, whereby the feasibility of the method for the purpose of cooperative computation is shown.

Cloud-Sea Computing Systems: Towards Thousand-Fold Improvement in Performance per Watt for the Coming Zettabyte Era

We are entering a new era of computing, characterized by the need to handle over one zettabyte (1021 bytes, or ZB) of data. The world’s capacities to sense, transmit, store, and process information need to grow three orders of magnitude, while maintain an energy consumption level similar to that of the year 2010. In other words, we need to produce thousand-fold improvement in performance per watt. To face this challenge, in 2012 the Chinese Academy of Sciences launched a 10-year strategic priority research initiative called the Next Generation Information and Communication Technology initiative (the NICT initiative). A research thrust of the NICT program is the Cloud-Sea Computing Systems project. The main idea is to augment conventional cloud computing by cooperation and integration of the cloud-side systems and the sea-side systems, where the "sea-side" refers to an augmented client side consisting of human facing and physical world facing devices and subsystems. The Cloud-Sea Computing Systems project consists of four research tasks: a new computing model called REST 2.0 which extends the REST (representational state transfer) architectural style of Web computing to cloud-sea computing, a three-tier storage system architecture capable of managing ZB of data, a billion-thread datacenter server with high energy efficiency, and an elastic processor aiming at energy efficiency of one trillion operations per second per watt. This special section contains 12 papers produced by the Cloud-Sea Computing Systems project team, presenting research results relating to sensing and REST 2.0, the elastic processor, the hyperparallel server, and the cloud-sea storage.

Security challenges in vehicular cloud computing

In a series of recent papers, Prof. Olariu and his co-workers have promoted the vision of vehicular clouds (VCs), a nontrivial extension, along several dimensions, of conventional cloud computing. In a VC, underutilized vehicular resources including computing power, storage, and Internet connectivity can be shared between drivers or rented out over the Internet to various customers. Clearly, if the VC concept is to see a wide adoption and to have significant societal impact, security and privacy issues need to be addressed. The main contribution of this work is to identify and analyze a number of security challenges and potential privacy threats in VCs. Although security issues have received attention in cloud computing and vehicular networks, we identify security challenges that are specific to VCs, e.g., challenges of authentication of high-mobility vehicles, scalability and single interface, tangled identities and locations, and the complexity of establishing trust relationships among multiple players caused by intermittent short-range communications. Additionally, we provide a security scheme that addresses several of the challenges discussed.

Inter-Cloud Computing

This catchword article presents the concept of “Inter-Cloud Computing” which introduces an additional management layer on top of conventional Cloud Computing Systems. Its goal is to reach a higher level of sustainability by autonomously shifting resources among the participating Cloud systems when unexpected load levels occur or disasters strike. Cloud systems are widely seen as a promising paradigm for an IT infrastructure that is capable of creating an added value for business, society, and administration. If Cloud systems are to be applied to critical areas, such as enterprises’ core businesses, governmental systems, medical applications, and other social infrastructure services, it is crucial to guarantee end-to-end service quality that covers the involved external networks, and to meet a set of requirements regarding reliability (including security), compliance, governance, and power efficiency. However, if services are provided by a single Cloud system – which is the usual case today – unexpected levels of overload traffic from the Internet or natural disasters may affect the system’s reliable functioning. The ability of a single Cloud to request reserved resources is usually fixed by limited bounds. Therefore, unexpected loads and failures can easily overburden a single Cloud system and lead to unreliable and interrupted services. In order to enable a Cloud system to continue the delivery of guaranteed service levels even in such cases, it is indispensable to introduce a super-ordinate layer of Cloud organization which manages multiple Cloud systems so that they complement each other. Thus single Cloud systems, which are interconnected via broadband networks, can mutually request required resources from their peers, or provide available capacity to them, respectively. This flavor of Cloud Computing is called Inter-Cloud Computing.

Inter-Cloud-Computing

This catchword article presents the concept of “Inter-Cloud Computing” which introduces an additional management layer on top of conventional Cloud Computing Systems. Its goal is to reach a higher level of sustainability by autonomously shifting resources among the participating Cloud systems when unexpected load levels occur or disasters strike. Cloud systems are widely seen as a promising paradigm for an IT infrastructure that is capable of creating an added value for business, society, and administration. If Cloud systems are to be applied to critical areas, such as enterprises’ core businesses, governmental systems, medical applications, and other social infrastructure services, it is crucial to guarantee end-to-end service quality that covers the involved external networks, and to meet a set of requirements regarding reliability (including security), compliance, governance, and power efficiency. However, if services are provided by a single Cloud system – which is the usual case today – unexpected levels of overload traffic from the Internet or natural disasters may affect the system’s reliable functioning. The ability of a single Cloud to request reserved resources is usually fixed by limited bounds. Therefore, unexpected loads and failures can easily overburden a single Cloud system and lead to unreliable and interrupted services. In order to enable a Cloud system to continue the delivery of guaranteed service levels even in such cases, it is indispensable to introduce a super-ordinate layer of Cloud organization which manages multiple Cloud systems so that they complement each other. Thus single Cloud systems, which are interconnected via broadband networks, can mutually request required resources from their peers, or provide available capacity to them, respectively. This flavor of Cloud Computing is called Inter-Cloud Computing.