Adaptive Management of Volatile Edge Systems at Runtime With Satisfiability

Edge computing offers the possibility of deploying applications at the edge of the network. To take advantage of available devices’ distributed resources, applications often are structured as microservices, often having stringent requirements of low latency and high availability. However, a decentralized edge system that the application may be intended for is characterized by high volatility, due to devices making up the system being unreliable or leaving the network unexpectedly. This makes application deployment and assurance that it will continue to operate under volatility challenging. We propose an adaptive framework capable of deploying and efficiently maintaining a microservice-based application at runtime, by tackling two intertwined problems: (i) finding a microservice placement across device hosts and (ii) deriving invocation paths that serve it. Our objective is to maintain correct functionality by satisfying given requirements in terms of end-to-end latency and availability, in a volatile edge environment. We evaluate our solution quantitatively by considering performance and failure recovery.

Efficient Resources Allocation and Energy Reduction with Virtual Machines for Cloud Computing

Cloud computing is an internet provisioned method for sharing the resources on demand by network management, storage, services, applications and the serves that necessitate management optimal effort. VMM (virtual machine migration) plays a major role in enhancing the resource utilization, application isolation, processing nodes, fault tolerance in VMs for enhancing nodes portability and for maximizing the efficiency of physical server. For balancing the clouds with resources for the enhanced performance, varied users are served with application deployment in the cloud environment is considered as the major task. The user can rent or request the resources when it becomes significant. The emphasis of this paper is on different energy VM energy efficient module as per machine learning methods. While allocating the VMs to the host machines, MBFD (Modified Best Fit Decreasing) is considered and the classification of host machine capability such as overloaded, normal loaded and underloaded is executed according to SVM (Support vector machine). SVM is utilized as a classifier for analyzing the MBFD algorithm and for the classification of the host as per the job properties. In this procedure, the numbers of jobs that are not allocated are examined via simulation which is computed by means of time consumption, energy consumption and a total number of migrations.

Energy-effective artificial internet-of-things application deployment in edge-cloud systems

Recently, the Internet-of-Things technique is believed to play an important role as the foundation of the coming Artificial Intelligence age for its capability to sense and collect real-time context information of the world, and the concept Artificial Intelligence of Things (AIoT) is developed to summarize this vision. However, in typical centralized architecture, the increasing of device links and massive data will bring huge congestion to the network, so that the latency brought by unstable and time-consuming long-distance network transmission limits its development. The multi-access edge computing (MEC) technique is now regarded as the key tool to solve this problem. By establishing a MEC-based AIoT service system at the edge of the network, the latency can be reduced with the help of corresponding AIoT services deployed on nearby edge servers. However, as the edge servers are resource-constrained and energy-intensive, we should be more careful in deploying the related AIoT services, especially when they can be composed to make complex applications. In this paper, we modeled complex AIoT applications using directed acyclic graphs (DAGs), and investigated the relationship between the AIoT application performance and the energy cost in the MEC-based service system by translating it into a multi-objective optimization problem, namely the CA$$^3$$ 3 D problem — the optimization problem was efficiently solved with the help of heuristic algorithm. Besides, with the actual simple or complex workflow data set like the Alibaba Cloud and the Montage project, we conducted comprehensive experiments to evaluate the results of our approach. The results showed that the proposed approach can effectively obtain balanced solutions, and the factors that may impact the results were also adequately explored.

Implementation of Google Cloud in Business to Business Tanda Tukar Faktur Application

Alfamart is a company engaged in retail. Companies involved in the retail sector are certainly inseparable from buying and selling products, and every transaction that occurs will be detailed in the invoice exchange. The problem that arises is because Alfamart wants to accommodate the electronic invoice exchange process. Therefore, Alfamart built a B2B TTF application that can accommodate the electronic invoice exchange process and help its accounting management. The application is made using the Research and Development method because it can address urgent needs and has a high validation value. It is built using the Flask framework and is integrated with Google Cloud to overcome application deployment speed problems and be more flexible. In addition, the implementation of Optical Character Recognition using Google Vision is used to validate uploaded invoice files. This study's results are in the form of a B2B TTF application that can make it easier for users to exchange invoices. The results of using Google Vision have a relatively high percentage of 77%. The B2B TTF application uses the Flask framework and is integrated with Google Cloud, which can assist users in the process of exchanging invoices electronically.

Determinants of Effective Change Management for Software Deployment Projects

Software application deployment change management is one of the emerging research themes that is gaining increased focus day by day. Our study examined the factors that affect software application deployment change management in Agile software development settings. Our study provided a systematic review and synthesized the approaches, practices, and challenges reported for adopting and implementing deployment change management. The prime objective of our study was to systematically synthesize the data extracted and formulate evidence-based practical recommendations that are influential in software deployment change management. Six research themes are proposed to evaluate the rationale of the research question. This qualitative study and systematic review explored the pertinent research articles and key findings from prominent academic databases. Based on the selected criteria, the final screening revealed 25 articles from an immense set of publications. Key findings that emerged from these publications are correlated with the six research themes: (a) timely communication with all stakeholders; (b) the reliance of deployment approaches on past experience; (c) the importance of collaboration among team members having adequate knowledge of DevOps tools; (d) the ramification of the differences among development, test, and production environments; (e) the influential areas that reap the benefits of continuous delivery and deployment; and (f) the challenges of the effective use of containerization. We also found indications of the significance of Lewin’s three-step change process model in the Agile development and deployment environment. Overall, our study deepens understanding of this thriving research area and contributes to the literature on Agile deployment and the software change management process.

VerificationTalk: A Verification and Security Mechanism for IoT Applications

An Internet of Things (IoT) application typically involves implementations in both the device domain and the network domain. In this two-domain environment, it is possible that application developers implement the wrong network functions and/or connect some IoT devices that should never be linked, which result in the execution of wrong operations on network functions. To resolve these issues, we propose the VerificationTalk mechanism to prevent inappropriate IoT application deployment. VerificationTalk consists of two subsystems: the BigraphTalk subsystem which verifies IoT device configuration; and AFLtalk which validates the network functions. VerificationTalk provides mechanisms to conduct online anomaly detection by using a runtime monitor and offline by using American Fuzzy Lop (AFL). The runtime monitor is capable of intercepting potentially harmful data targeting IoT devices. When VerificationTalk detects errors, it provides feedback for debugging. VerificationTalk also assists in building secure IoT applications by identifying security loopholes in network applications. By the appropriate design of the IoTtalk execution engine, the testing capacity of AFLtalk is three times that of traditional AFL approaches.

A Novel Automate Python Edge-to-Edge: From Automated Generation on Cloud to User Application Deployment on Edge of Deep Neural Networks for Low Power IoT Systems FPGA-Based Acceleration

Deep Neural Networks (DNNs) deployment for IoT Edge applications requires strong skills in hardware and software. In this paper, a novel design framework fully automated for Edge applications is proposed to perform such a deployment on System-on-Chips. Based on a high-level Python interface that mimics the leading Deep Learning software frameworks, it offers an easy way to implement a hardware-accelerated DNN on an FPGA. To do this, our design methodology covers the three main phases: (a) customization: where the user specifies the optimizations needed on each DNN layer, (b) generation: the framework generates on the Cloud the necessary binaries for both FPGA and software parts, and (c) deployment: the SoC on the Edge receives the resulting files serving to program the FPGA and related Python libraries for user applications. Among the study cases, an optimized DNN for the MNIST database can speed up more than 60× a software version on the ZYNQ 7020 SoC and still consume less than 0.43W. A comparison with the state-of-the-art frameworks demonstrates that our methodology offers the best trade-off between throughput, power consumption, and system cost.