Towards the Automatic Detection of Efficient Computing Assets in a Heterogeneous Cloud Environment

This paper is concerned with the study and implementation of effective Data Emplacement Algorithm in large set of databases called Big Data and proposes a model for improving the efficiency of data processing and storage utilization for dynamic load imbalance among nodes in a heterogeneous cloud environment. With the era of explosive information and data receiving, more and more fields need to deal with massive, large scale of data. A method has been proposed with an improved Data Placement algorithm called Effective Data Emplacement Algorithm with computing capacity of each node as a predominant factor that promotes and improves the efficiency in data processing in a short duration time from large set of data. The adaptability of the proposed model can be obtained by minimizing the time with processing efficiency through the computing capacity of each node in the cluster. The proposed solution improves the performance of the heterogeneous cluster environment by effectively distributing data based on the performance oriented sampling as the experimental results made with word count applications.

Cloud computing is growing massively in the world of information technology. As a result of which the number of servers and virtual machines is increasing day by day. It leads to huge energy consumption and carbon emission. In this regard, task scheduling has drawn the attention of cloud service providers to reduce energy consumption and increase cloud utilization. This is a crucial issue in a heterogeneous cloud environment. In this paper, energy consumption issues of cloud datacenters are addressed and an Energy-Aware Cloud Task Scheduling (EACTS) algorithm is proposed. It is taking the concept from traditional min-min, max-min, and sufferage heuristics and merge with the energy model. These heuristics are implemented on the heterogeneous cloud environment. EACTS energy model focuses on the estimation of energy consumption in cloud datacenters. The proposed algorithms estimated the makespan, cloud utilization, and energy consumption for a benchmark dataset. The experimental results obtained from EACTS algorithm provides a valid arbitration between energy efficiency and makespan. It has shown the comparison between above mentioned algorithms for various scheduling parameters.

To avoid the drawbacks of a pricing mechanism in heterogeneous cloud environments that considers only single resources, we propose a multi-resource combinatorial pricing mechanism in this paper. This approach jointly considers the principal resources (i.e., CPU, memory, storage, and bandwidth) with the goal of minimizing the total cost. Then, a cost-optimized resource provisioning policy (CORPP) based on game theory is applied to this mechanism that considers the Nash equilibrium between cloud users as well as the Stackelberg equilibrium between users and the cloud provider. The experimental results show that the proposed combinatorial pricing mechanism is more suitable in a heterogeneous cloud environment when running various types of cloudlets. Moreover, CORPP is effective in reducing users' total costs when using both random cloudlets and PlanetLab cloudlets.

Well organized datacentres with interconnected servers constitute the cloud computing infrastructure. User requests are submitted through an interface to these servers that provide service to them in an on-demand basis. The scientific applications that get executed at cloud by making use of the heterogeneous resources being allocated to them in a dynamic manner are grouped under NP hard problem category. Task scheduling in cloud poses numerous challenges impacting the cloud performance. If not handled properly, user satisfaction becomes questionable. More recently researchers had come up with meta-heuristic type of solutions for enriching the task scheduling activity in the cloud environment. The prime aim of task scheduling is to utilize the resources available in an optimal manner and reduce the time span of task execution. An improvised seagull optimization algorithm which combines the features of the Cuckoo search (CS) and seagull optimization algorithm (SOA) had been proposed in this work to enhance the performance of the scheduling activity inside the cloud computing environment. The proposed algorithm aims to minimize the cost and time parameters that are spent during task scheduling in the heterogeneous cloud environment. Performance evaluation of the proposed algorithm had been performed using the Cloudsim 3.0 toolkit by comparing it with Multi objective-Ant Colony Optimization (MO-ACO), ACO and Min-Min algorithms. The proposed SOA-CS technique had produced an improvement of 1.06%, 4.2%, and 2.4% for makespan and had reduced the overall cost to the extent of 1.74%, 3.93% and 2.77% when compared with PSO, ACO, IDEA algorithms respectively when 300 vms are considered. The comparative simulation results obtained had shown that the proposed improvised seagull optimization algorithm fares better than other contemporaries.

The amount of data that human activities generate poses a challenge to current computer systems. Big data processing techniques are evolving to address this challenge, with analysis increasingly being performed using cloud-based systems. Emerging services, however, require additional enhancements in order to ensure their applicability to highly dynamic and heterogeneous environments and facilitate their use by Small a Medium-sized Enterprises (SMEs). Observing this landscape in emerging computing system development, this work presents Small a Medium-sized Enterprise Data Analytic in Real Time (SMART) for addressing some of the issues in providing compute service solutions for SMEs. SMART offers a framework for efficient development of Big Data analysis services suitable to small and medium-sized organizations, considering very heterogeneous data sources, from wireless sensor networks to data warehouses, focusing on service composability for a number of domains. This paper presents the basis of this proposal and preliminary results on exploring application deployment on hybrid infrastructure.

External geometric factors obtained from three-dimensional (3D) log scanners can be used to sort logs according to different quality standards. This study evaluated the possibilities of automatic grading of logs according to current Swedish grading standard for pricing. The accuracy of the automatic method was compared with the accuracy of conventional manual grading. Models were developed from a training set using variables enhanced from a 3D log scanner and linear discriminate analysis. The models were tested on a large test set for which the grades set from both conventional manual grading and a grading inspector were known before the study; the latter was considered the true grade. The test set consisted of pine and spruce logs from five sawmills in different parts of Sweden. The accuracy of the grading was evaluated with Cohen's kappa. The evaluation compared the accuracy of manual versus automatic grading: this comparison was conducted in various ways. Automatic grading was determined as less accurate than manual grading for all logs. Although the accuracy of automatic grading was lower, advantages such as reduced costs could make automatic grading a preferable method of grading logs.

Security of cloud computing is one of the challenges to be addressed before the novel pas-as-you-go business model is widely applied, and dependability is one of the most important means to improve security of current heterogeneous cloud platforms. Previous research on dependability in computing systems only uses qualitative approaches and there are few systematic works on dependability in cloud systems. In this paper, the definition of dependability in cloud systems is given and a series of quantitative indicators are presented to evaluate the dependability. A novel cloud dependability model CDSV is established to enhance the security of heterogeneous cloud environments. System-level virtualization techniques are used to enhance the dependability of cloud environments. Systematic analysis shows that this model can enhance the system dependability and security. Experimental results show that the dependability model CDSV can efficiently and safely construct dependability relationship in heterogeneous cloud environments.

<p>As we approach the limits of Moore’s law the Cloud computing landscape is becoming ever more heterogeneous in order to extract more performance from available resources. Meanwhile, the container-based cloud is of growing importance as a lightweight way to deploy applications. A unified heterogeneous systems framework for use with container-based applications in the heterogeneous cloud is required. We present a bytecode-based framework and it’s implementation called Man O’ War, which allows for the creation of novel, portable LLVM bitcode-based containers for use in the heterogeneous cloud. Containers in Man O’ War enabled systems can be efficiently specialized for the available hardware within the Cloud and expand the frontiers for optimization in heterogeneous cloud environments. We demonstrate that a framework utilizing portable bytecode-based containers eases optimizations such as heterogeneous scaling which have the potential to improve resource utilization and significantly lower costs for users of the public cloud.</p>

As cloud adoption accelerates, organizations increasingly face challenges in managing and optimizing operational costs across multiple providers such as Microsoft Azure, AWS, and Google Cloud. Traditional FinOps (Financial Operations) practices rely heavily on manual analysis and static thresholds, often leading to inefficiencies and reactive decision-making. This paper presents an AI-driven FinOps model that integrates predictive analytics, automation, and intelligent workload optimization to manage costs across heterogeneous cloud environments. Leveraging tools such as Azure Cost Management, Machine Learning, and cross-cloud APIs, the proposed architecture enables real-time visibility, anomaly detection, and automated budget governance. Experimental analysis demonstrates that AI-driven FinOps reduces cloud cost variance and improves forecasting accuracy, providing a foundation for sustainable, data-driven financial governance.

Log anomaly detection in cloud computing environments is essential for maintaining system reliability and security. While sequence modeling architectures such as LSTMs and Transformers have been widely employed to capture temporal dependencies in log messages, their effectiveness deteriorates in zero-shot transfer scenarios due to distributional shifts in log structures, terminology, and event frequencies, as well as minimal token overlap across datasets. To address these challenges, we propose an effective detection approach integrating a domain-specific pre-trained language model (PLM) fine-tuned on cybersecurity-adjacent data with a novel loss function, Loss with Decaying Factor (LDF). LDF introduces an exponential time decay mechanism into the training objective, ensuring a dynamic balance between historical context and real-time relevance. Unlike traditional sequence models that often overemphasize outdated information and impose high computational overhead, LDF constrains the training process by dynamically weighing log messages based on their temporal proximity, thereby aligning with the rapidly evolving nature of cloud computing environments. Additionally, the domain-specific PLM mitigates semantic discrepancies by improving the representation of log data across heterogeneous datasets. Extensive empirical evaluations on two supercomputing log datasets demonstrate that this approach substantially enhances cross-dataset anomaly detection performance. The main contributions of this study include: (1) the introduction of a Loss with Decaying Factor (LDF) to dynamically balance historical context with real-time relevance; and (2) the integration of a domain-specific PLM for enhancing generalization in zero-shot log anomaly detection across heterogeneous cloud environments.

Task scheduling in heterogeneous cloud environment using mean grey wolf optimization algorithm

As an extended cloud solution, the cloud federation is designed to address the highly increasing complexity of business needs by providing capabilities on demand, at a better service level agreement (SLA). In fact, Cloud federation could not only be an appropriate way for managing the intensive-resource requirements but also it may be a powerful coordination environment for meeting complex business needs by easily integrating different distributed SaaS systems. Building a SaaS system that could satisfy a more complex need, upon existing ones deployed in a federated cloud environment could be treated as a System of Systems (SoS). The individual SaaS systems behave independently and, cooperate with each other to emerge a new resulting behavior. Thus, building an overall SaaS system from a set of distributed SaaS systems, deployed on heterogeneous cloud environments may increase the overall delivery costs. In this paper, we focus on how building a large SaaS system from a set of existing ones, while maximizing the desirable resulting behavior and minimizing the total delivery costs. Thus, we propose a cost-efficient composition approach for building a federated cloud-based SoS, by considering both the functional and non-functional requirements to obtain the best composition in terms of delivery costs. We implement an agent based SoS composition simulator providing composition scenarios and their related QoS and evaluating the different special cloud criterion that can influence the overall SoS delivery cost.

To solve the problem of resource heterogeneity and the dynamic structure, loose coupling of integrated applications has brought a lot of benefits in clouds environment. Thus, the development of highly robust service-oriented applications has many challenges, especially for the autonomy of service resources over the system components to the end-user portal. In this paper, a proposed method for the business users can satisfy the service availability changes in the early warning and application for service relationship adjustment. Then, the designed mechanism can deal with exception not available for service in a real-time development application for a business user. Based on the heterogeneous model of service-oriented applications, an availability process with lifecycle analysis is proposed to ensure that service resources are available to integrate components at different levels.

Current financial systems are faced with unparalleled challenges in managing computational infrastructure throughout heterogeneous cloud environments at the same time as sustaining stringent overall performance necessities and regulatory compliance requirements. Asynchronous application programming interfaces represent essential architectural additives that permit economic institutions to decouple request processing from response transport, taking into account enhanced resource usage and machine resilience in distributed computing environments. Adaptive scaling mechanisms leverage event-driven architectures, box orchestration platforms, and sophisticated monitoring infrastructure to put into effect automated decision-making tactics governing aid provisioning sports with out manual intervention. The mixing of artificial intelligence and gadget learning techniques in scaling strategies fosters predictive talents expecting call for fluctuations based on historical patterns, temporal characteristics, and outside market indicators. Multi-cloud deployment techniques introduce architectural complexities related to move-company networking, information sovereignty necessities, and seller-specific service integration styles that necessitate cautious attention when distributing workloads across heterogeneous infrastructure companies. Box orchestration structures offer the important abstraction layers required to normalize workload deployment, service discovery, and traffic management across disparate cloud environments whilst remaining like-minded with issuer-specific optimization opportunities. The convergence of asynchronous conversation patterns, predictive scaling algorithms, and multi-cloud resource allocation strategies positions economic establishments to realize levels of operational performance that can not be achieved through greater conventional architectural paradigms, even while ensuring transaction integrity, regulatory compliance, and price optimization goals crucial to competitive gain in dynamic financial services markets.

In this paper we present a novel on-line NFV (Network Function Virtualization) orchestration algorithm for edge computing infrastructure providers that operate in a heterogeneous cloud environment. The goal of our algorithm is to minimize the usage of computing resources which are offered by a public cloud provider (e.g., Amazon Web Services), while fulfilling the required networking related constraints (latency, bandwidth) of the services to be deployed.We propose a reference network architecture which acts as a test environment for the evaluation of our algorithm. During the measurements, we compare our results to the optimal solution provided by an ILP-based solver.