GAIN-QoS: A Novel QoS Prediction Model for Edge Computing

With recent increases in the number of network-connected devices, the number of edge computing services that provide similar functions has increased. Therefore, it is important to recommend an optimal edge computing service, based on quality-of-service (QoS). However, in the real world, there is a cold-start problem in QoS data: highly sparse invocation. Therefore, it is difficult to recommend a suitable service to the user. Deep learning techniques were applied to address this problem, or context information was used to extract deep features between users and services. However, edge computing environment has not been considered in previous studies. Our goal is to predict the QoS values in real edge computing environments with improved accuracy. To this end, we propose a GAIN-QoS technique. It clusters services based on their location information, calculates the distance between services and users in each cluster, and brings the QoS values of users within a certain distance. We apply a Generative Adversarial Imputation Nets (GAIN) model and perform QoS prediction based on this reconstructed user service invocation matrix. When the density is low, GAIN-QoS shows superior performance to other techniques. In addition, the distance between the service and user slightly affects performance. Thus, compared to other methods, the proposed method can significantly improve the accuracy of QoS prediction for edge computing, which suffers from cold-start problem.

A HIGH-CURRENCY GEO-SPATIAL SERVICE GATEWAY FOR NATIONAL GEO-INFORMATION SERVICE PLATFORM

Today, more and more geospatial services are provided by the governments and enterprises to share various geographic information data and functions, and services-based application integration has become a trend. However, many problems existed in the geo-platform for Geographic information sharing while providing services in the form of API, such as the coexistence of different versions of the same service, similar service routes of different APIs, cluttered service protocols, and complex authority management, that makes the integration among different geographic information services difficult and reduces the development efficiency. There are already some API gateway technologies to solve the problem, but the characteristics of geospatial services are not considered in the existing product. To address these problems, this paper proposed a high-currency geospatial service gateway system for National Geo-Information Service Platform based on the opensource framework of Kong for realizing the unified management and authorized open. The system provides the whole lifecycle management and fine-grained control for the service, and the functions such as unified geospatial service access, protocol conversion, service management, authorization verification, rate limiting, and security protection are also equipped. The system has been released and integrated in the National Geo-Information Service Platform, supporting hundreds of millions of service invocation every day. The result proves it simplifies geospatial services management, deployment, and application, and benefits the exchanging and sharing of geographic information.

Automatic definition of web service call zones based on the classification of context of the mobile device

Предложен метод автоматизации активации устройств Интернета вещей на основе классификации геопозиции мобильного устройства. В отличие от других методов пользователь обучает систему активации устройств с помощью примеров и контрпримеров, что значительно снижает требования к квалификации пользователя. Проведено тестирование метода на таких двух устройствах, как шлагбаум и электромеханический замок двери. Полученные результаты тестирования позволяют судить о работоспособности метода и возможности его использования в системах умного дома и города. Most IoT devices provide an application programming interface such as web service that allows controlling these IoT devices over Internet using a mobile phone. Activation of IoT devices is performed according to the status of user behavior. Both user behavior and activation of IoT devices are periodical. An activation of IoT device is often related with a user geolocation which can be defined by sensors of the mobile device. A method for automated activation of IoT devices based on classification of geolocation of mobile device is proposed. The method implements a supervised learning that simplifies automate activation of IoT devices for the end users. Existing methods demand appropriate end user qualification and require long time to automate activation. For indoor geolocation of the mobile device information from Wi-Fi access points and geolocation GPS sensor is utilized. Data of Wi-Fi and GPS sensors is used to form context of a mobile device. Based on context examples of invoking/not invoking web services the spatial areas are formed. When the mobile device context is within the web service invocation area, the web service is invoked and the associated IoT device is activated. To implement the method, an Android application was developed. The method was tested on a training set that contained 100 training examples of calling two web services: opening an electromechanical door lock and opening a barrier. As a result of testing, the accuracy of classifying the context of a mobile device was 98 percent. The results obtained can be used in the development of smart home and smart city systems.

Service Discovery and Selection Based on Dynamic QoS in the Internet of Things

Web services are self-describing and self-contained modular applications based on the network. With the deepening of web service applications, service consumers have gradually increased their requirements for service functions and service quality. Aiming at how to select the optimal plan from a large number of execution plans with the same function and different QoS characteristics, this paper proposes a web service selection algorithm that supports QoS global optimization and dynamic replanning. The algorithm uses position matrix coding to represent all execution paths and replanning information of the service combination. By calculating the Hamming distance of the service quality between individuals, the quality of the service portfolio is improved. By specifying the total user time limit and implementing a good solution retention strategy, the problem of the impact of algorithm running time on service quality is solved. The experimental results show that the method proposed in this paper is effectively integrated into the development trend of QoS and close to the requester’s needs and can better meet user needs. This algorithm improves the user’s satisfaction with the returned service to a certain extent and improves the efficiency of service invocation.

The Cloud-edge-based Dynamic Reconfiguration to Service Workflow for Mobile Ecommerce Environments

The emergence of mobile service composition meets the current needs for real-time eCommerce. However, the requirements for eCommerce, such as safety and timeliness, are becoming increasingly strict. Thus, the cloud-edge hybrid computing model has been introduced to accelerate information processing, especially in a mobile scenario. However, the mobile environment is characterized by limited resource storage and users who frequently move, and these characteristics strongly affect the reliability of service composition running in this environment. Consequently, applications are likely to fail if inappropriate services are invoked. To ensure that the composite service can operate normally, traditional dynamic reconfiguration methods tend to focus on cloud services scheduling. Unfortunately, most of these approaches cannot support timely responses to dynamic changes. In this article, the cloud-edge based dynamic reconfiguration to service workflow for mobile eCommerce environments is proposed. First, the service quality concept is extended. Specifically, the value and cost attributes of a service are considered. The value attribute is used to assess the stability of the service for some time to come, and the cost attribute is the cost of a service invocation. Second, a long short-term memory (LSTM) neural network is used to predict the stability of services, which is related to the calculation of the value attribute. Then, in view of the limited available equipment resources, a method for calculating the cost of calling a service is introduced. Third, candidate services are selected by considering both service stability and the cost of service invocation, thus yielding a dynamic reconfiguration scheme that is more suitable for the cloud-edge environment. Finally, a series of comparative experiments were carried out, and the experimental results prove that the method proposed in this article offers higher stability, less energy consumption, and more accurate service prediction.

A Novel Coevolutionary Approach to Reliability Guaranteed Multi-Workflow Scheduling upon Edge Computing Infrastructures

Recently, mobile edge computing (MEC) is widely believed to be a promising and powerful paradigm for bringing enterprise applications closer to data sources such as IoT devices or local edge servers. It is capable of energizing novel mobile applications, especially the ultra-latency-sensitive ones, by providing powerful local computing capabilities and lower end-to-end delays. Nevertheless, various challenges, especially the reliability-guaranteed scheduling of multitask business processes in terms of, e.g., workflows, upon distributed edge resources and servers, are yet to be carefully addressed. In this paper, we propose a novel edge-environment-based multi-workflow scheduling method, which incorporates a reliability estimation model for edge-workflows and a coevolutionary algorithm for yielding scheduling decisions. The proposed approach aims at maximizing the reliability, in terms of success rates, of services deployed upon edge infrastructures while minimizing service invocation cost for users. We conduct simulative experimental case studies based on multiple well-known scientific workflow templates and a well-known dataset of edge resource locations as well. Simulative results clearly suggest that our proposed approach outperforms traditional ones in terms of workflow success rate and monetary cost.

Performance Analysis of a Clustering Model for QoS-Aware Service Recommendation

The numbers of web services are growing rapidly in recent years. One of the most challenging issues in service computing is the personalized recommendation of Web services. Most of the current research recommends services based on Quality of Service (QoS)-aware data with few considerations of service-side factors, such as service functions. In this paper, a new QoS-aware Web service recommendation model based on user and service clustering (RMUSC) is proposed to gain an advance in recommended accuracy. Firstly, similar users are clustered together by a Top-N similarity algorithm through the user QoS records. Secondly, a K-means++ based filtering service cluster is established. Finally, a user and services collaborative scheme is exploited and obtains potential user QoS preferences to generate recommendations. The experimental results show that when the density of the service invocation matrix is 5%, 10% and 20%. the average absolute error (MAE) and root mean square error (RMSE) of RMUSC are lower than those of other methods.

An Approach to Analyze Vulnerability of Information Flow in Software Architecture

Current research on software vulnerability analysis mostly focus on source codes or executable programs. But these methods can only be applied after software is completely developed when source codes are available. This may lead to high costs and tremendous difficulties in software revision. On the other hand, as an important product of software design phase, architecture can depict not only the static structure of software, but also the information flow due to interaction of components. Architecture is crucial in determining the quality of software. As a result, by locating the architecture-level information flow that violates security policies, vulnerabilities can be found and fixed in the early phase of software development cycle when revision is easier with lower cost. In this paper, an approach for analyzing information flow vulnerability in software architecture is proposed. First, the concept of information flow vulnerability in software architecture is elaborated. Corresponding security policies are proposed. Then, a method for constructing service invocation diagrams based on graph theory is proposed, which can depict information flow in software architecture. Moreover, an algorithm for vulnerability determination is designed to locate architecture-level vulnerabilities. Finally, a case study is provided, which verifies the effectiveness and feasibility of the proposed methods.