Designing an Enhanced LSTM – XGBoost Architecture for Context-Oriented Anomaly Detection in Event Logs (CPU-based)

Cloud Computing IT infrastructure has the potential to be particularly suitable for collaborative commerce (c-commerce) applications; because it generally requires less efforts and interferences for development, customization, integration, operation, and maintenance than other traditional IT infrastructures (e.g., on-premises and data centers). However, upgrading c-commerce applications running on traditional IT infrastructures, to run efficiently on cloud computing infrastructure, faces a number of challenges, mainly, lack of effective and reliable architectural model. This paper presents a description of a new architectural model for developing cloud computing based c-commerce applications; which is denoted as cc-commerce model. The model is an basically based on the standard cloud computing model, and it consists of six main components; these are: client, provider, auditor, broker, security and privacy, and communications network. The new model is implemented in a simple and flexible Web-based test tool, namely, the cc-commerce test (3CT) tool, which is used to evaluate the performance of the model through measuring the response times for four different configurations. The analysis of the obtained results demonstrates that the cc-commerce model can provide better response time than equivalent c-commerce models.

The trend of merging telecommunication infrastructures with traditional IT infrastructures is becoming increasingly more common. The driver behind this development is partly the strong need for enhanced services from the telecom operator?s side aiming for value added services provision to the customer. The effect of this new trend is that existing value chains in the Telco infrastructure will disappear and the merge between the Telco infrastructure and the IT infrastructure can bring added value to the Telco?s network, which is needed in order to increase the willingness to pay for the services. Thus, Telecom operators are very keen on participating in the overall service delivery chain being placed on top of their transport infrastructure. This paper proposes a method, to help to propel the previously mentioned trend by enabling the user to query for aggregated composed services directly from the network edge. A network selection is therefore achived based on the services provided by the access network and their capabilities and costs, parallel to other traditional pure network-related parameters such as signal strength and network QoS.

The increasing proliferation of independent application service providers is making traditional IT infrastructure insufficient when dealing with new issues that appear in a dynamic outsourcing business model. Quality of service (QoS) gradually becomes an essential benchmark to differentiate diverse service providers during service selection process. In this paper, we argue service selection can be deemed as a decision making process -to decide which services providers should be selected within the specified service provision context during a definitive timeslot. Thus, existing decision support approaches can be leveraged if applicable. Hence, we propose a service selection solution which utilizes the decision support systems module (DSS Module) to select the most appropriate service. In DSS module we introduce AHP model to carry out the service QoS measurement based on the Context-specific Quality Aspects. The contributions of this paper are two folds. Firstly, we provide a novel and feasible solution for QoS-based service selection and secondly, we apply DSS module into web services, thus opening a new, fertile ground for DSS research in service ecosystem literature.

Data analytics is the science of extracting patterns, trends, and actionable information from large sets of data. The growing nature of data in from different servers with in consistent data formats like structured, semi-structured and unstructured data. Traditional IT infrastructure is simply not able to meet the demands of this new “Data Analytics” landscape. The secondary problem for data analytics is security, the rapid increase in usage of Internet, and consequent applications that allow users to create contents freely, amplify the already huge web volume. In today's data world, there are some vital things to keep in mind while beginning big data and analytics innovation projects. Hence the need of secured data analytics tool is mandatory.

Cloud is a large pool of easily usable and accessible virtualized resources (such as hardware, development platforms and/or services). It provides an on-demand, pay-as-you-go computing resources and had become an alternative to traditional IT Infrastructure. As more and more consumers delegate their task to cloud providers, Service Level Agreement (SLA) between consumer and provider becomes an important aspect. Due to the dynamic nature of cloud the matching of SLA templates need to be dynamic and continuous monitoring of Quality of Service (QoS) is necessary to enforce SLAs. SLA template contains many parameters like cloud's resources (physical memory, main memory, processor speed etc.) and properties (availability, response time etc.). This work addresses the issue of matching SLA parameters to find suitable cloud provider for particular application.

Advanced manufacturing such as aerospace, semi-conductor, and flat display device often involves complex production processes, and generates large volume of production data. In general, the production data comes from products with different levels of quality, assembly line with complex flows and equipments, and processing craft with massive controlling parameters. The scale and complexity of data is beyond the analytic power of traditional IT infrastructures. To achieve better manufacturing performance, it is imperative to explore the underlying dependencies of the production data and exploit analytic insights to improve the production process. However, few research and industrial efforts have been reported on providing manufacturers with integrated data analytical solutions to reveal potentials and optimize the production process from data-driven perspectives.

Copyright: © 2013 Deka GC. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. As governments around the world continue to grapple with slow-moving economies, cloud computing is emerging as a viable and valuable answer to the persistent demands for reducing public sector spending. Recent attention has shifted to a new initiative called Cloud Government (G-Cloud) incorporating cloud computing into e-Government services, particularly aimed at communicating directly with citizens and implementing cloud computing services in order to cut costs and improve upon the IT services infrastructure. G-Cloud is an Internet based communications which enable public bodies to host, select and use computing services from secure, resilient and cost-effective IT service environment. The ambition of the journey from traditional IT infrastructures towards cloud computing and IaaS is a trusted Cloud with the network as the logical platform to bring the existing assets in the Datacenter and new Cloud computing approaches with Virtualization, Governance, Security, Information and Application. The G-Cloud program’s core benefits are cost reduction, improved services, faster delivery and progressive sustainability agenda. The citizen-centric data, services and applications will be stored, maintained and delivered from G-Cloud and a comprehensive government portal will be a part and parcel of this cloud-based service delivery. Government applications store will provide a “portal” to purchase G-Cloud services. The latest trend on G-Cloud is following the agency-by-agency implementation scenario. Various Ministries/Departments may use cloud services provided by various Cloud Service Provider (CSP) based on the availability in a particular locality as well as the specific requirement of the particular Department/Ministry. It is a fact that all the CSPs are not equally competent in all types of services like accounting, ERP, CRM etc. But for the smooth function of the Government machinery these clouds must be interoperable. Current cloud frameworks are not designed to interact with each other, which make it more difficult for organizations to consolidate their applications and fully realize the savings and productivity benefits of cloud solutions. The dynamic location of service facilities, Virtualization of hardware and software elements is stressing the communication network & protocols, when datacenters are interconnected through the Internet. Although the “Computing” aspects of Cloud have been largely investigated, lower attention has been devoted to the “Networking of Clouds”.

Recent years have shown an increase in the number and complexity of cyberattacks not only on traditional IT infrastructures, but also on smart energy supply networks. Cybercriminals and cyberspies are becoming more sophisticated and persistent in their actions, which requires increased cyber security measures and the development of new technologies to protect infrastructure. In this work we present a framework for detection of Man-in-the-Middle cyberattacks in smart grids based on the application of the ensemble process for feature selection. The workflow of the framework consists of two main stages: model creation and performance evaluation. To create the model, a study was carried out, which involved the selection of the optimal set of features by applying various methods of feature selection. In addition to the sets of features that were formed by feature selection methods, another set of features was formed, which is the result of the process of assembling features that were formed by feature selection methods. A feature score was proposed, which allows weighting of each feature depending on its frequency of selection in all selection methods and the relative number of selected features in the entire set. To check the effectiveness of detecting MitM cyberattacks, SVM and Decision Tree classifiers were used, the test data for which were generated according to the obtained sets of features.

Hybrid cloud is an integrated cloud computing environment utilizing a mix of public cloud, private cloud, and on-premise traditional IT infrastructures. Workload awareness, defined as a detailed full range understanding of each individual workload, is essential in implementing the hybrid cloud. While it is critical to perform an accurate analysis to determine which workloads are appropriate for on-premise deployment versus which workloads can be migrated to a cloud off-premise, the assessment is mainly performed by rule or policy based approaches. In this paper, we introduce StackInsights, a novel cognitive system to automatically analyze and predict the cloud readiness of workloads for an enterprise. Our system harnesses the critical metrics across the entire stack: 1) infrastructure metrics, 2) data relevance metrics, and 3) application taxonomy, to identify workloads that have characteristics of a) low sensitivity with respect to business security, criticality and compliance, and b) low response time requirements and access patterns. Since the capture of the data relevance metrics involves an intrusive and in-depth scanning of the content of storage objects, a machine learning model is applied to perform the business relevance classification by learning from the meta level metrics harnessed across stack. In contrast to traditional methods, StackInsights significantly reduces the total time for hybrid cloud readiness assessment by orders of magnitude.

The rapid adoption of cloud computing technologies has transformed the way organizations design, develop, and manage complex projects. Cloud-based environments, characterized by their distributed architectures, dynamic scaling, and multi-tenancy features, offer enhanced flexibility and scalability. However, these benefits also introduce new layers of complexity and vulnerability, making risk assessment and mitigation more challenging than in traditional IT infrastructures. This explores the latest advances in risk assessment and mitigation strategies specifically tailored for complex cloud-based project environments. Modern risk landscapes in the cloud are shaped by evolving cybersecurity threats, compliance demands, integration challenges, and operational uncertainties. Traditional risk assessment models often fall short in capturing the dynamic and interconnected nature of cloud ecosystems. In response, recent developments have introduced advanced techniques such as AI-driven threat detection, real-time risk monitoring, and scenario-based probabilistic modeling. These innovations enable proactive identification and prioritization of risks, allowing for more agile and adaptive mitigation responses. Mitigation strategies have also evolved significantly, with the rise of cloud-native security controls, DevSecOps practices, and resilience engineering methods like chaos testing. Organizations are increasingly adopting Zero Trust architectures and automated incident response frameworks to enhance their defensive posture. Additionally, there is a growing focus on vendor risk management and compliance automation to address regulatory requirements across jurisdictions. This highlights several case studies that demonstrate the practical application of these advanced methodologies in various sectors, including healthcare, finance, and enterprise IT. Despite these advancements, challenges such as data sensitivity, high implementation costs, and skill gaps persist. This concludes by outlining future directions for research and practice, emphasizing the need for continuous innovation, cross-disciplinary collaboration, and the integration of emerging technologies like quantum-safe cryptography to ensure robust risk management in cloud environments. These efforts are essential to sustaining the security, resilience, and trustworthiness of modern cloud-based project infrastructures.

Cloud computing has transformed traditional IT infrastructure, offering dynamic, configurable resources on demand.On the other hand, it brings unique cybersecurity challenges, particularly in protecting sensitive data from unauthorized access.Traditional single factor authentication does not address these risks.By implementing multi-factor authentication (MFA), which combines several factors for verification including password, tokens, and biometrics, this cloud security method has become increasingly popular.Existing authentication methods fall short in the cloud environment, so this paper presents a novel multi-factor, multi-layered cloud access authentication framework.The methodology for MFA implementation uses risk-adaptive authentication based on real-time risk assessment, adaptive policy for MFA selection, and seamless verification workflows for end-users.Moreover, the implementation of the advanced technologies that cover all aspects such as encryption, SSO, and adaptive authentication further safeguards it against evolving threats.Through experimental analyses, we show that the framework is effective to substantially reduce the vulnerabilities without compromising usability and scalability.This will help cloud service providers and organizations alike better equip themselves with an effective and agile security environment through the adoption of next generation MFA strategies.

Event logging and log files are playing an important role in system and network security. Log files record computer system activities, are used to provide requirements of reliability, security and accountability applications. Information stored in log files can be obtained from different devices, not necessarily clock synchronized, and they do not arrive in the same order they are generated. Nevertheless, log information has to be coherent in time to be useful. To support the events we propose to use Lamport's logic clocks, originated at different sources, in a causal relationship. As a result the administrator will count all the events involved general idea in a computer incident. A model implementation is also presented.

Process mining is based on event logs. Traditionally, an event log is a sequence of events. Yet, there is a growing amount of work in the literature that suggests we should extend the notion of an event log and use partially ordered logs as a basis for process mining. Thus, the need for algorithms able to handle these partially ordered logs will grow in the upcoming years. In this paper, we adapt an existing, classical process discovery algorithm to be able to handle partially ordered logs. We use the ILP Miner [1] as a basis and replace its region theory part by compact tokenflow regions [2] to introduce the ILP2 Miner. This ILP2 Miner handles sequential event logs just like the ILP Miner but, in addition, is able to directly process partially ordered logs. We prove that the ILP2 Miner provides the same guarantees regarding structural and behavioral properties of the discovered process models as the ILP Miner. We implement the ILP2 Miner and show experimental results of its runtime using three well-known example log files from the process mining community literature.

Event log files are the most common source of information for the characterization of events in large scale systems. However the large size of these files makes the task of manual analysing log messages to be difficult and error prone. This is the reason why recent research has been focusing on creating algorithms for automatically analysing these log files. In this paper we present a novel methodology for extracting templates that describe event formats from large datasets presenting an intuitive and user-friendly output to system administrators. Our algorithm is able to keep up with the rapidly changing environments by adapting the clusters to the incoming stream of events. For testing our tool, we have chosen 5 log files that have different formats and that challenge different aspects in the clustering task. The experiments show that our tool outperforms all other algorithms in all tested scenarios achieving an average precision and recall of 0.9, increasing the correct number of groups by a factor of 1.5 and decreasing the number of false positives and negatives by an average factor of 4.

Log files contain valuable information about the execution of a system. This information is often used for debugging, operational profiling, finding anomalies, detecting security threats, measuring performance etc. The log files are usually too big for extracting this valuable information manually, even though manual perusal is still one of the more widely used techniques. Recently a variety of data mining and machine learning algorithms are being used to analyze the information in the log files. A major road block for the efficient use of these algorithms is the inherent variability present in every log line of a log file. Each log line is a combination of a static message type field and a variable parameter field. Even though both these fields are required, the analyses algorithm often requires that these be separated out, in order to find correlations in the repeating log event types. This disentangling of the message and parameter fields to find the event types is called abstraction of log lines. Each log line is abstracted to a unique ID or event type and the dynamic parameter value is extracted to give an insight on the current state of the system. In this paper we present a technique based on a clustering technique used in the Simple Log file Clustering Tool for log file abstraction. This solution is especially useful when we don't have access to the source code of the application or when the lines in the log file do not conform to a rigid structure. We evaluated our implementation on log files from the Virtual Computing Lab, a cloud computer management system at North Carolina State University, and abstracted it to 727 unique event types.