微服务架构的在线课程学习系统的研究与设计

随着互联网技术和数字化教育的发展,在线课程学习与线下课堂逐步融合互补。针对线下课堂时间和空间的限制,以及无法定制个性化学习的缺陷,设计一套SpringCloud微服务架构在线课程学习系统。系统包含账号登录、视频观看、课程学习、评论收藏、个性化分析、学习路线推荐等功能。该在线课程学习系统实现了资源共享,其灵活性、便捷性突破了时空的制约,同时其个性化分析可以对学员的学习情况和兴趣进行分析并针对性的进行推荐。     

A model-driven software engineering workflow and tool architecture for servitised manufacturing

Modern manufacturing businesses increasingly engage in servitisation, by offering advanced services along with physical products, and creating “product–service systems”. Information Technology infrastructures, and especially software, are a critical part of modern service provision. However, software development in this context has not been investigated and there are no development methods or tools specifically adapted to the task of creating software for servitised businesses in general, or manufacturing in particular. In this paper, we define the requirements for software engineering in servitised manufacturing. Based on these, we describe a model-driven software engineering workflow for servitised manufacturing, supporting both structural and behavioural modelling of the service system. Furthermore, we elaborate on the architecture of an appropriate model-driven Integrated Development Environment (IDE). The proposed workflow and a prototype implementation of the IDE were evaluated in a set of industrial pilots, demonstrating improved communication and collaboration between participants in the software engineering process.     

ModelSet: a dataset for machine learning in model-driven engineering

The application of machine learning (ML) algorithms to address problems related to model-driven engineering (MDE) is currently hindered by the lack of curated datasets of software models. There are several reasons for this, including the lack of large collections of good quality models, the difficulty to label models due to the required domain expertise, and the relative immaturity of the application of ML to MDE. In this work, we present ModelSet, a labelled dataset of software models intended to enable the application of ML to address software modelling problems. To create it we have devised a method designed to facilitate the exploration and labelling of model datasets by interactively grouping similar models using off-the-shelf technologies like a search engine. We have built an Eclipse plug-in to support the labelling process, which we have used to label 5,466 Ecore meta-models and 5,120 UML models with its category as the main label plus additional secondary labels of interest. We have evaluated the ability of our labelling method to create meaningful groups of models in order to speed up the process, improving the effectiveness of classical clustering methods. We showcase the usefulness of the dataset by applying it in a real scenario: enhancing the MAR search engine. We use ModelSet to train models able to infer useful metadata to navigate search results. The dataset and the tooling are available at https://figshare.com/s/5a6c02fa8ed20782935c and a live version at http://modelset.github.io.

     

Simplifying autonomic enterprise Java Bean applications via model-driven engineering and simulation

The goal of autonomic computing is to reduce the configuration, operational, and maintenance costs of distributed applications by enabling them to self-manage, self-heal, and self-optimize. This paper provides two contributions to the Model-Driven Engineering (MDE) of autonomic computing systems using Enterprise Java Beans (EJBs). First, we describe the structure and functionality of an MDE tool that visually captures the design of EJB applications, their quality of service (QoS) requirements, and the adaptations applied to their EJBs. Second, the paper describes how MDE tools can be used to generate code to simulate adaptive systems for verification and plug EJBs into a Java component framework that provides runtime adaptation capabilities.     

Platform ontologies for the model-driven architecture

The model-driven architecture enables the deployment of software applications on different platforms. It is based on a pattern in which a platform-independent model is transformed into a platform-specific model, given a platform model (PM). Currently, the model transformations used for this task implicitly assume this PM, which makes it unclear whether a model transformation can be used for platforms other than the one assumed. In order to target very specific platforms and platform variants, model transformations must be reusable beyond their assumed platform. We propose an explicit PM that can be used to reason about platform dependencies of model transformations and their applicability to specific platforms. In addition, we show how PMs can be integrated in a model-driven configuration management framework.     

Comparison of software architecture reverse engineering methods

Problems related to interactions between components is a sign of problems with the software architecture of the system and are often costly to fix. Thus it is very desirable to identify potential architectural problems and track them across releases to see whether some relationships between components are repeatedly change-prone.This paper shows a study of combining two technologies for software architecture: architecture recovery and change dependency analysis based on version control information. More specifically, it describes a reverse engineering method to derive a change architecture from Revision Control System (RCS) change history. It compares this method to other reverse engineering methods used to derive software architectures using other types of data. These techniques are illustrated in a case study on a large commercial system consisting of over 800 KLOC of C, C++, and microcode. The results show identifiable problems with a subset of the components and relationships between them, indicating systemic problems with the underlying architecture.     

Introduction to the theme section on Agile model-driven engineering

Software and Systems Modeling -     

Server-side QUIC connection migration to support microservice deployment at the edge

In edge computing environments, microservices are typically deployed in the form of containers. To maintain proximity between edge computing services and mobile users, containers need to be migrated between nodes. When migrating containers, however, it is important to consider that they typically have ongoing communications with client endpoints. Moreover, in case of connection-oriented protocols, communicating endpoints share a state (i.e., the connection), which needs to be migrated as well. Connection-oriented protocols like TCP were not designed having connection migration in mind, thus their connections cannot survive a change of IP address or port number. On the other hand, QUIC, a transport protocol recently standardised by IETF, provides a mechanism for client-side connection migration, whereas a server-side connection migration is not yet implemented nor investigated. In this work, we propose an extension of QUIC to support server-side connection migration when a container is migrated between servers. We designed three different strategies, fitting a diverse set of scenarios, wherein the migration procedure is either or not supported by a centralised entity, e.g., an orchestrator. We implemented and verified the proposed extension. Besides, we evaluated it on a real testbed, showing how each of the three strategies is impacted by different container migration techniques and container sizes. To conclude, we compared our solution against two alternatives based on TCP+DNS and MPTCP respectively, demonstrating performance improvements in terms service-migration time.     

Supporting the verification of compliance to safety standards via model-driven engineering: Approach,tool-support and empirical validation

ContextMany safety–critical systems are subject to safety certification as a way to provide assurance that these systems cannot unduly harm people, property or the environment. Creating the requisite evidence for certification can be a challenging task due to the sheer size of the textual standards based on which certification is performed and the amenability of these standards to subjective interpretation.ObjectiveThis paper proposes a novel approach to aid suppliers in creating the evidence necessary for certification according to standards. The approach is based on Model-Driven Engineering (MDE) and addresses the challenges of using certification standards while providing assistance with compliance.MethodGiven a safety standard, a conceptual model is built that provides a succinct and explicit interpretation of the standard. This model is then used to create a UML profile that helps system suppliers in relating the concepts of the safety standard to those of the application domain, in turn enabling the suppliers to demonstrate how their system development artifacts comply with the standard.ResultsWe provide a generalizable and tool-supported solution to support the verification of compliance to safety standards. Empirical validation of the work is presented via an industrial case study that shows how the concepts of a sub-sea production control system can be aligned with the evidence requirements of the IEC61508 standard. A subsequent survey examines the perceptions of practitioners about the solution.ConclusionThe case study indicates that the supplier company where the study was performed found the approach useful in helping them prepare for certification of their software. The survey indicates that practitioners found our approach easy to understand and that they would be willing to adopt it in practice. Since the IEC61508 standard applies to multiple domains, these results suggest wider applicability and usefulness of our work.     

Guest editorial to the theme section on AI-enhanced model-driven engineering

Software and Systems Modeling - This theme section brings together the latest research at the intersection of artificial intelligence (AI) and model-driven engineering (MDE). Over the past years,...     

Rich-text document styling restoration via reinforcement learning

Richly formatted documents, such as financial disclosures, scientific articles, government regulations, widely exist on Web. However, since most of these documents are only for public reading, the styling information inside them is usually missing, making them improper or even burdensome to be displayed and edited in different formats and platforms. In this study we formulate the task of document styling restoration as an optimization problem, which aims to identify the styling settings on the document elements, e.g., lines, table cells, text, so that rendering with the output styling settings results in a document, where each element inside it holds the (closely) exact position with the one in the original document. Considering that each styling setting is a decision, this problem can be transformed as a multi-step decision-making task over all the document elements, and then be solved by reinforcement learning. Specifically, Monte-Carlo Tree Search (MCTS) is leveraged to explore the different styling settings, and the policy function is learnt under the supervision of the delayed rewards. As a case study, we restore the styling information inside tables, where structural and functional data in the documents are usually presented. Experiment shows that, our best reinforcement method successfully restores the stylings in 87.65% of the tables, with 25.75% absolute improvement over the greedymethod.We also discuss the tradeoff between the inference time and restoration success rate, and argue that although the reinforcement methods cannot be used in real-time scenarios, it is suitable for the offline tasks with high-quality requirement. Finally, this model has been applied in a PDF parser to support cross-format display.     

DIMA: Distributed cooperative microservice caching for internet of things in edge computing by deep reinforcement learning

World Wide Web - The ubiquitous Internet of Things (IoTs) devices spawn growing mobile services of applications with computationally-intensive and latency-sensitive features, which increases the...     

A hybrid agent architecture integrating desire,intention and reinforcement learning

This paper presents a hybrid agent architecture that integrates the behaviours of BDI agents, specifically desire and intention, with a neural network based reinforcement learner known as Temporal Difference-Fusion Architecture for Learning and COgNition (TD-FALCON). With the explicit maintenance of goals, the agent performs reinforcement learning with the awareness of its objectives instead of relying on external reinforcement signals. More importantly, the intention module equips the hybrid architecture with deliberative planning capabilities, enabling the agent to purposefully maintain an agenda of actions to perform and reducing the need of constantly sensing the environment. Through reinforcement learning, plans can also be learned and evaluated without the rigidity of user-defined plans as used in traditional BDI systems. For intention and reinforcement learning to work cooperatively, two strategies are presented for combining the intention module and the reactive learning module for decision making in a real time environment. Our case study based on a minefield navigation domain investigates how the desire and intention modules may cooperatively enhance the capability of a pure reinforcement learner. The empirical results show that the hybrid architecture is able to learn plans efficiently and tap both intentional and reactive action execution to yield a robust performance.     

基于RISC-V架构的强化学习容器化方法研究

RISC-V作为近年来最热门的开源指令集架构,被广泛应用于各个特定领域的微处理器,特别是机器学习领域的模块化定制.但是,现有的RISC-V应用需要将传统软件或模型在RISC-V指令集上重新编译或优化,故如何能快速地在RISC-V体系结构上部署、运行和测试机器学习框架是一个亟待解决的技术问题.使用虚拟化技术可以解决跨平台...     

A model-driven approach to machine learning and software modeling for the IoT

Software and Systems Modeling - Models are used in both Software Engineering (SE) and Artificial Intelligence (AI). SE models may specify the architecture at different levels of abstraction and for...     

A learning architecture based on reinforcement learning for adaptive control of the walking machine LAURON

The learning of complex control behaviour of autonomous mobile robots is one of the actual research topics. In this article an intelligent control architecture is presented which integrates learning methods and available domain knowledge. This control architecture is based on Reinforcement Learning and allows continuous input and output parameters, hierarchical learning, multiple goals, self-organized topology of the used networks and online learning. As a testbed this architecture is applied to the six-legged walking machine LAURON to learn leg control and leg coordination.     

VAnDroid: A framework for vulnerability analysis of Android applications using a model-driven reverse engineering technique

Android is extensively used worldwide by mobile application developers. Android provides applications with a message passing system to communicate within and between them. Due to the risks associated with this system, it is vital to detect its unsafe operations and potential vulnerabilities. To achieve this goal, a new framework, called VAnDroid, based on Model Driven Reverse Engineering (MDRE), is presented that identifies security risks and vulnerabilities related to the Android application communication model. In the proposed framework, some security-related information included in an Android app is automatically extracted and represented as a domain-specific model. Then, it is used for analyzing security configurations and identifying vulnerabilities in the corresponding application. The proposed framework is implemented as an Eclipse-based tool, which automatically identifies the Intent Spoofing and Unauthorized Intent Receipt as two attacks related to the Android application communication model. To evaluate the tool, it has been applied to several real-world Android applications, including 20 apps from Google Play and 110 apps from the F-Droid repository. VAnDroid is also compared with several existing analysis tools, and it is shown that it has a number of key advantages over those tools specifically regarding its high correctness, scalability, and usability in discovering vulnerabilities. The results well indicate the effectiveness and capacity of the VAnDroid as a promising approach in the field of Android security.