Cloud Infrastructure Research Articles

Virtual Clouds, Real Threats: DDoS Attacks Reviewed and Mitigated

In today's digital world, companies and organizations rely heavily on cloud computing for their everyday needs. Ensuring availability, confidentiality, accessibility, and integrity in the cloud is crucial. Any attack on cloud services can lead to serious consequences, including downtime, reputational damage, and financial loss. Among these threats, Distributed Denial of Service (DDoS) attacks are particularly concerning as they target cloud infrastructure with overwhelming traffic. This review examines various studies on cloud architecture and DDoS attack scenarios, exploring how these attacks happen and their impact. It also discusses defensive measures like mitigation, detection, and prevention, while acknowledging the limitations of existing research in fully addressing DDoS threats.

Cloud Guardian: A Comprehensive Approach to Cloud Security Posture Management with Automated Multi-Cloud and Container Security

As organizations increasingly adopt multi-cloud environments and containerized applications to improve scalability and operational efficiency, managing security across these diverse platforms has become a critical challenge. Traditional security tools and manual processes are insufficient to handle the complexity and dynamic nature of modern cloud infrastructures. This research introduces Cloud Guardian, a cloud security posture management (CSPM) platform that automates security assessments, policy enforcement, and threat detection across multi-cloud platforms and containerized environments. Cloud Guardian addresses the key security challenges associated with multi-cloud and container environments, including misconfigurations, unpatched vulnerabilities, and inconsistent security policies. By integrating real-time threat intelligence and automated remediation capabilities, Cloud Guardian provides continuous protection, ensuring compliance with industry standards such as CIS and NIST. Additionally, the platform’s self-healing mechanisms and rollback capabilities allow for secure and uninterrupted operations by automatically fixing security issues and reverting changes if necessary. This study evaluates Cloud Guardian's effectiveness in securing complex cloud infrastructures through real-world case studies. The findings demonstrate significant improvements in operational efficiency, compliance, and security posture, reducing the risk of breaches and operational disruptions. Cloud Guardian offers a scalable and automated solution for organizations seeking to safeguard their cloud and container environments while minimizing manual intervention and ensuring continuous security and compliance.

IoT and Edge Computing for Smart Manufacturing: Architecture and Future Trends

The integration of the Internet of Things (IoT) and Edge Computing is revolutionizing the manufacturing industry, ushering in the era of smart manufacturing as part of Industry 4.0. This paper explores the synergy between IoT and Edge Computing, focusing on their combined architecture and the future trends driving innovation in smart factories. IoT enables the connection and communication of machines, sensors, and systems, allowing for real-time data collection and monitoring. However, traditional cloud-based approaches face challenges such as latency, bandwidth limitations, and security risks, which can hinder real-time decision-making in fast-paced manufacturing environments. Edge Computing addresses these issues by processing data closer to the source, minimizing latency and reducing dependence on cloud infrastructures. By combining IoT and edge solutions, smart manufacturing systems can make faster, data-driven decisions, leading to improved efficiency, reliability, and operational flexibility. This paper delves into the architectural design of IoT and edge computing in manufacturing, outlining how data flows from IoT devices to edge nodes and cloud services. Several real-world use cases and industry examples are analyzed to highlight the practical benefits of these technologies. Additionally, this research identifies key challenges such as security vulnerabilities, the need for robust network infrastructures (e.g., 5G), and issues related to data standardization. The future of smart manufacturing is also explored, emphasizing trends like the adoption of artificial intelligence (AI) and machine learning (ML) at the edge, digital twins for real-time monitoring, and the role of IoT and edge computing in fostering sustainability through energy-efficient production processes.This study provides a comprehensive overview of IoT and edge computing architectures in smart manufacturing and offers insights into future technological trends that will shape the industry.

Cb-WoFS: Migrating the Warn-on-Forecast System to the Cloud

Abstract This article provides a brief, technical narrative of the WoFS journey to a cloud-based high-performance computing (HPC) system, including some of the technological challenges encountered and solutions found. Also, discussed are a few new components that are in development for cloud-based Warn-on-Forecast System (cb-WoFS), such as the cloud infrastructure project for managing resources, as well as a new web application that manages cb-WoFS runs. An important initial step in our cloud journey is containerizing all of the compiled applications, such as WRF, GSI, and EnKF and their dependencies like netCDF and MPI. With these applications compiled within an Apptainer container, WoFS can run on any local or cloud-based HPC cluster that supports MPI. Furthermore, an additional software layer was developed that creates and manages cloud vendor resources. This layer, which is referred to as the WoFS framework, contains the workflow required to run cb-WoFS, as well as management for other aspects of cb-WoFS (including but not limited to creation of HPC pools in the end-to-end workflow, runtime notifications, and database management). This additional layer was developed to separate the WoFS business logic from vendor-specific API calls. The WoFS framework exposes features through its service library, which is then referenced by the newly developed cb-WoFS web application and other cloud applications. This makes WoFS a complete end-to-end cloud-based application, where an administrator can launch a model run, manage resources, and view output all within a single web app.

RETORCH*: A Cost and Resource aware Model for E2E Testing in the Cloud

Moving testing to the Cloud overcomes time/resource constraints by leveraging an unlimited and elastic infrastructure, especially for testing levels like End-to-End (E2E) that require a high number of resources and/or execution time. However, it introduces new challenges to those already faced on-premises, like selecting the most suitable Cloud infrastructure and billing scheme. We propose the RETORCH* test execution model that estimates and compares the monetary cost of executing an E2E test suite with different Cloud alternatives, billing schemes, and test configurations. RETORCH* goes beyond the mere cost billed, and selects the solution that best aligns with the test team strategy using the data of on-premises prior executions and the tester's experience. This cost is broken down into the cost incurred to execute the test suite (testing cost) and possible unused infrastructure (overprovisioning cost). Based on these distinct costs, the test team can compare different Cloud and test configurations. RETORCH* has been evaluated using a real-world application's E2E test suite. We analyze how the different decisions taken when the suite is migrated to the Cloud impact the cost, highlighting how RETORCH* can help the tester during Cloud and test configuration to make a more informed decision.

Secure Efficiency: Navigating Performance Challenges in Multi-Tenant Cloud Security Implementations

Multi-tenant cloud environments offer significant advantages in terms of cost-efficiency and scalability, but they also present unique challenges in balancing robust security measures with optimal performance. This article examines the intricate relationship between security implementations and system performance in shared cloud infrastructures. Through a comprehensive analysis of data isolation techniques, access control mechanisms, network security protocols, and threat detection systems, we identify key areas where security measures can impact performance metrics such as latency, throughput, and resource utilization. Our article employs a mixed-methods approach, combining quantitative performance measurements with qualitative case studies from industry-leading cloud service providers. The findings reveal that while stringent security measures often introduce performance overhead, strategic implementation and optimization can significantly mitigate these effects. We propose a framework for dynamically balancing security and performance requirements, incorporating emerging technologies such as AI-driven threat detection and automated resource allocation. This article contributes to the growing body of knowledge on cloud computing optimization and provides practical insights for cloud architects and security professionals seeking to enhance both the security posture and performance efficiency of multi-tenant cloud environments.

Analysis on addressing the threats to cloud computing on the basis of security safeguards for sap cloud services

Cloud computing has become an integral part of combination/multi-cloud infrastructures due to its many benefits, including quick deployment, flexibility, cheap costs, and scalability, which have attracted businesses of all sizes. New possibilities and threats in terms of security flaws are cropping up in this field, even if cloud storage provides substantial advantages and inexpensive choices for IT administration and growth. When we talk about safeguarding cloud infrastructure systems, we're referring to a set of rules, regulations, and systematic procedures. This is also known as cloud computing security. The purpose of implementing these security measures is to safeguard cloud-based data, facilitate the enforcement of legislation, ensure the privacy of consumer information, and set standards for encryption in specific devices and applications. Modern cloud computing and security concerns throughout the cloud's many layers are addressed in this study. Within this context, the current study would make a substantial contribution to lowering the frequency of security breaches in cloud computing, paving the way for the continued provision of safe and reliable services. Storage of databases on the cloud is expanding rapidly in the IT industry, including SAP networks. Because enterprises are ultimately responsible for the security of their data, migrating databases to cloud computing environments brings with it a plethora of security risks. To guarantee data integrity, availability, and secrecy, appropriate security measures should be put in place before a company migrates its sensitive data to the cloud. When data is at rest, it is most vulnerable to unauthorized access; when it is in transit, it must be subject to strict supervision.

Federated learning: A cutting-edge survey of the latest advancements and applications

Robust machine learning (ML) models can be developed by leveraging large volumes of data and distributing the computational tasks across numerous devices or servers. Federated learning (FL) is a technique in the realm of ML that facilitates this goal by utilizing cloud infrastructure to enable collaborative model training among a network of decentralized devices. Beyond distributing the computational load, FL targets the resolution of privacy issues and the reduction of communication costs simultaneously. To protect user privacy, FL requires users to send model updates rather than transmitting large quantities of raw and potentially confidential data. Specifically, individuals train ML models locally using their own data and then upload the results in the form of weights and gradients to the cloud for aggregation into the global model. This strategy is also advantageous in environments with limited bandwidth or high communication costs, as it prevents the transmission of large data volumes. With the increasing volume of data and rising privacy concerns, alongside the emergence of large-scale ML models like Large Language Models (LLMs), FL presents itself as a timely and relevant solution. It is therefore essential to review current FL algorithms to guide future research that meets the rapidly evolving ML demands. This survey provides a comprehensive analysis and comparison of the most recent FL algorithms, evaluating them on various fronts including mathematical frameworks, privacy protection, resource allocation, and applications. Beyond summarizing existing FL methods, this survey identifies potential gaps, open areas, and future challenges based on the performance reports and algorithms used in recent studies. This survey enables researchers to readily identify existing limitations in the FL field for further exploration.

HYBRID CLOUD DATABASES FOR BIG DATA ANALYTICS: A REVIEW OF ARCHITECTURE, PERFORMANCE, AND COST EFFICIENCY

The increasing reliance on big data analytics has driven organizations to seek more flexible, scalable, and cost-effective data management solutions, with hybrid cloud databases emerging as a prominent option. Hybrid cloud databases integrate both public and private cloud environments, allowing businesses to balance the scalability and cost advantages of public clouds with the security and control provided by private clouds. This systematic review, conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, examines the architecture, performance, cost efficiency, security, and technological advancements of hybrid cloud databases. The study synthesizes findings from 40 peer-reviewed articles published between 2015 and 2024, focusing on key factors that affect the performance of hybrid cloud databases, such as workload distribution, network latency, and the use of advanced data analytics tools like Hadoop and Spark. The review also explores cost-saving mechanisms, including dynamic resource scaling and pay-as-you-go pricing models, which help organizations reduce infrastructure costs by up to 28%. Additionally, it discusses the security risks and privacy concerns associated with hybrid cloud environments, highlighting the effectiveness of encryption protocols and identity access management systems in mitigating data breaches by as much as 40%. Furthermore, the review identifies emerging trends in the integration of machine learning and artificial intelligence (AI), which have significantly enhanced system automation and resource optimization in hybrid cloud infrastructures, leading to performance improvements of up to 45%.

MANAGEMENT OF SCALABILITY IN CLOUD-BASED APPLICATIONS

The following is an abstract of the article. The article presents an analysis of the challenges associated with monitoring and managing the scalability of a cloud application. To this end, a module for monitoring and managing the scalability of a cloud application has been developed as part of this study. The development process included the introduction of automatic scaling, and monitoring using Prometheus and Grafana, which allows for a high level of availability and resource efficiency. The study comprised a series of phases, including requirements analysis, system design, development, testing, and evaluation. Consequently, the system's performance, stability, and capacity to scale in response to fluctuating workloads were enhanced. The module exhibits a high degree of adaptability to changes in system requirements and load, which is a crucial attribute for the dynamic development of business applications. This solution assists in optimizing the allocation of resources and reducing infrastructure costs. The project has been found to fully meet the set goals and objectives, as well as the requirements for effective resource management of the Amazon Web Services cloud platform using Terraform, Prometheus, and Grafana. The practical value of the developed module is evidenced by a significant improvement in resource efficiency, service stability and cost optimisation. The module design has been subjected to rigorous testing and has been successfully implemented in a test environment, thereby demonstrating the sustainability and efficiency of the developed solution. The experience gained in the implementation and operation of this solution may prove useful for further expansion and optimization of cloud solutions in other projects and companies specializing in the provision of cloud solutions. The findings of this study were validated in a test environment at an IT company with a specialization in cloud technologies. The objective was to ascertain the functionality and efficiency of the developed module in a real-world context of cloud infrastructure operation. The testing process entailed the configuration of the module on pre-existing cloud infrastructure systems, its integration with Prometheus and Grafana for monitoring purposes, and the execution of a series of stress tests designed to assess the module's scalability. As a result of this testing, a number of critical points were identified that required further optimization. The results of the study and the issues identified during the project testing have enabled the identification of several areas for further improvement and development of the system. First and foremost, the optimization of automatic scaling algorithms represents a crucial avenue for improvement. The development of these algorithms should be oriented towards utilizing historical monitoring data to anticipate potential shifts in system load. Another pivotal area for enhancement is the precision of monitoring systems. The integration of supplementary tools and the expansion of existing monitoring systems' functionality will facilitate the acquisition of more comprehensive insights into the system's condition. This, in turn, will facilitate the expedient identification and eradication of potential issues.

Machine Learning-Driven RUL Prediction and Uncertainty Quantification for Ball Screw Drives in a Cloud-Ready Maintenance Framework

In today's rapidly evolving industrial landscape, efficient predictive maintenance solutions are essential for minimizing downtime and enhancing productivity. This research introduces an adaptive cloud-based model pipeline for predicting the Remaining Useful Life (RUL) of machine components, specifically ball screws. The pipeline integrates local preprocessing, edge computing, and cloud-based adaptive model training, ensuring data privacy and reducing data transmission volumes. The system classifies wear states using various machine learning mod-els and predicts RUL through regression analysis, incorporating uncertainty quantification for robust maintenance scheduling. The experimental setup includes accelerated degradation of ball screws, with data collected via a three-dimensional accelerometer. Feature extraction and data augmentation techniques are employed to enhance prediction accuracy. Random Forest and Gradient Boosting models demonstrate superior performance, with Random Forest selected for its robustness and uncertainty quantification capabilities. Empirical results indicate high prediction accuracy, with Random Forest achieving up to 91% accuracy in Phase 2. This cloud-ready predictive maintenance framework leverages scalable cloud infrastructure for efficient data processing and real-time updates, offering a practical solution for industrial applications. The proposed approach significantly advances the adoption of digital business models within the manufacturing industry, providing a reliable and efficient tool for predictive maintenance.

Banking in the cloud: mapping big tech’s global digital technology networks

ABSTRACT Witnessing the inroads of big tech into finance, this paper maps the growing dependence of incumbent banks on public cloud infrastructures. Although ‘cloud interfacing’ has become crucial amid platform finance, the intersections between what we conceptualise as global digital technology networks and global financial networks have received little attention. We mobilise social network analysis to map: (1) the geographically variegated patterns of public cloud adoption in banking and their geopolitical implications; (2) the corporate networks supporting banks’ cloud migration; and (3) the urban networks of command and control undergirding cloud banking, connecting established financial centres with tech valleys old and new.

Zero Trust Architecture: Enhancing Cybersecurity in Enterprise Networks

Zero Trust Architecture (ZTA) offers a robust approach to enhancing cybersecurity in enterprise networks, replacing the traditional perimeter-based security models. This paper examines the application, challenges, and effectiveness of ZTA in contemporary corporate environments, with a focus on hybrid and cloud infrastructures. By emphasizing key principles such as least-privileged access, continuous authentication, and network segmentation, ZTA directly addresses the security risks that organizations face today. This research includes a review of relevant literature and an analysis of case studies to explore the difficulties companies encounter when adopting ZTA, including financial costs, integration complexities, and resistance to change. The study also identifies strategies that organizations have successfully employed to overcome these obstacles, leading to improved security and operational efficiency. The findings highlight ZTA’s ability to reduce security incidents through automation and enhanced monitoring. While there are technical challenges to implementing Zero Trust, the research concludes that the framework is essential for maintaining a strong security posture. Future areas for exploration include the role of technologies like artificial intelligence and machine learning in further improving ZTA.

Design And Implementation of Blockchain-Based Security Solutions for Electronic Health Records (EHRS): Enhancing Data Integrity and Privacy

A block chain-based electronic health record (EHR) system is the primary focus of this study. To improve data security and interoperability, healthcare is increasingly looking to cloud-based electronic health record (EHR) systems and block chain technology. It delves into the topic of choosing the right cloud infrastructure, data management methodologies, and block chain technology to guarantee the availability, integrity, and security of patient data. We go over every detail of the system's design and implementation, from the block chain network and cloud storage layer to the user interface. By comparing it to more conventional EHR systems, the pilot research finds that the new system is more capable of protecting, exchanging, and managing patient data. We take a look at the pros, cons, and obstacles that might prevent a cloud EHR system based on block chain from being widely used. Insights and suggestions from this study address the obstacles, give direction for effective adoption, and are of great value to healthcare organisations thinking about implementing such systems. Keywords: Block chain, Security, Solutions, Electronic Health Records (Ehrs) And Privacy

Research on Network Security and Privacy Protection Technology of Autonomous Vehicle

With the rapid development of information technology and the increasing maturity of intelligent transportation systems, autonomous vehicles, as an important carrier of future travel, are gradually moving from concept to commercial application. However, the highly connected and intelligent nature of autonomous vehicles also makes them face unprecedented cybersecurity and privacy protection challenges. This paper deeply discusses the security threats and privacy disclosure risks of autonomous vehicles in network architecture, data transmission, data processing and other links, and systematically reviews the current technical means and research progress to address these challenges. This paper Outlines the data collection and transmission mechanism of autonomous vehicles, including the collection and processing of sensor data as well as the communication process between vehicles and the cloud, other vehicles and transportation infrastructure, and analyzes in detail the network security threats faced by autonomous vehicles, including remote control attacks, malware attacks, communication hijacking, etc. These threats can lead to serious consequences such as vehicle failure, data breach, or system crash. At the same time, the paper also points out the challenges faced by autonomous vehicles in terms of privacy protection, such as the risk of leakage of sensitive data such as personal location information and driving habits, as well as the risk of data abuse and sharing. In order to address the above challenges, this paper focuses on the technical research progress of cybersecurity and privacy protection of autonomous vehicles. In the aspect of network security, this paper discusses the key technical means such as data encryption, access control, intrusion detection and response system, and emphasizes the importance of security hardware and software in improving the overall security of the system. In terms of privacy protection, this paper proposes strategies such as anonymization and desensitization technology, privacy protection protocols and standards to protect users' privacy from invasion.

CLOUD SECURITY POSTURE MANAGEMENT AUTOMATING RISK IDENTIFICATION AND RESPONSE IN CLOUD INFRASTRUCTURES

Cloud Security Posture Management (CSPM) tools have become essential in addressing the growing security challenges faced by organizations as they migrate to cloud environments. This study explores the effectiveness of CSPM tools in automating the identification and response to security risks within cloud infrastructures, highlighting their role in reducing misconfigurations, improving compliance, and enhancing overall security posture. Through a mixed-method approach, combining a comprehensive literature review, a survey of IT security professionals, and detailed case study analyses, this research provides a robust evaluation of CSPM tools' capabilities and the challenges associated with their implementation. The findings reveal that organizations utilizing CSPM tools experience significant reductions in security incidents and operational inefficiencies, with automation playing a crucial role in enabling real-time threat detection and response. However, the study also identifies critical barriers to CSPM adoption, including integration complexities, cost concerns, and organizational resistance to automated security solutions. These challenges suggest that while CSPM tools offer substantial benefits, their successful deployment requires careful planning, adequate resource allocation, and strategic change management to address both technical and human factors. This study contributes to the existing literature by providing detailed insights into the practical applications and limitations of CSPM tools, offering valuable guidance for organizations seeking to enhance their cloud security strategies through automation.

DuCFF: A Dual-Channel Feature-Fusion Network for Workload Prediction in a Cloud Infrastructure

Cloud infrastructures are designed to provide highly scalable, pay-as-per-use services to meet the performance requirements of users. The workload prediction of the cloud plays a crucial role in proactive auto-scaling and the dynamic management of resources to move toward fine-grained load balancing and job scheduling due to its ability to estimate upcoming workloads. However, due to users’ diverse usage demands, the changing characteristics of workloads have become more and more complex, including not only short-term irregular fluctuation characteristics but also long-term dynamic variations. This prevents existing workload-prediction methods from fully capturing the above characteristics, leading to degradation of prediction accuracy. To deal with the above problems, this paper proposes a framework based on a dual-channel temporal convolutional network and transformer (referred to as DuCFF) to perform workload prediction. Firstly, DuCFF introduces data preprocessing technology to decouple different components implied by workload data and combine the original workload to form new model inputs. Then, in a parallel manner, DuCFF adopts the temporal convolution network (TCN) channel to capture local irregular fluctuations in workload time series and the transformer channel to capture long-term dynamic variations. Finally, the features extracted from the above two channels are further fused, and workload prediction is achieved. The performance of the proposed DuCFF’s was verified on various workload benchmark datasets (i.e., ClarkNet and Google) and compared to its nine competitors. Experimental results show that the proposed DuCFF can achieve average performance improvements of 65.2%, 70%, 64.37%, and 15%, respectively, in terms of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and R-squared (R2) compared to the baseline model CNN-LSTM.

Improving Responsiveness: Our Journey from Manual Yearly Updates to Automated Linkage for Near Real-Time Understanding of Outcomes and Modelling Future Service Demand

ObjectiveDemand for real-time data during the COVID-19 pandemic revealed a need to increase efficiencies in manual linkage processes to respond to events in near real-time. In response, our jurisdictional linkage agency transitioned from yearly to daily, weekly and monthly linkage practices through increasing automation and improving process flows. ApproachOur linkage agency transitioned to a fully automated process utilising scalable cloud infrastructure. Source data is now provided directly to a common data platform. This data is split into linkage and content, cleansed and quality assured in Python and set to automatically run via Azure data pipelines. The data is then linked via a combination of deterministic and probabilistic criteria, with data quality checks automatically performed along the way. Researchers can analyse this data in a secure virtual machine that only they can access and retrieve data from. Results This infrastructure expedites the data linkage process allowing daily linkage results to select datasets, and enables advanced research such as a predictive micro-simulation model, which leverages the platform to predict and intervene on outcomes influenced by governmental policies. This model relies on timely administrative data to build targeted interventions for groups with poor future outcomes, tests these interventions, and monitors outcomes in near real-time. ConclusionOur linkage agency has transitioned from manual to automated linkage processes in response to increasing need for timely data. By embracing cloud infrastructure and leveraging automation, we have streamlined our operations, enabling responsive linkage depending on need and expediting the provision of de-identified, linked data to researchers.

A succinct state-of-the-art survey on green cloud computing: Challenges, strategies, and future directions

Cloud computing is a method of providing various computing services, including software, hardware, databases, data storage, and infrastructure, to the public through the Internet. The rapid expansion of cloud computing services has raised significant concerns over their environmental impact. Cloud computing services should be designed in a green manner, efficient in energy consumption, virtualized, consolidated, and eco-friendly. Green Cloud Computing (GCC) is a significant field of study that focuses on minimizing the environmental impact and energy usage of cloud infrastructures. This survey provides a comprehensive overview of the current state of GCC, focusing on the challenges, strategies, and future directions. The review study begins by identifying important challenges in GCC from practical implementations, identifying GCC-introduced environmental protection and prevention initiatives, and expressing the demand for long-term technical progression. It then addresses GCC’s primary concerns, such as energy efficiency, resource management, operational costs, and carbon emissions, and categorizes implementations according to algorithms, architectures, frameworks, general issues, and models and methodologies. Furthermore, enhancements in virtualization, multi-tenancy, and consolidation have been identified, analyzed, and accurately portrayed to address the advancements in GCC. Finally, the survey outlines future research directions and opportunities for advancing the field of GCC, including the development of novel algorithms, technologies for energy harvesting, and energy-efficient and eco-friendly solutions. By providing a comprehensive overview of GCC, this survey aims to serve as documentation for further evolving new emerging technological approaches in the GCC environment.

Efficient resource allocation in cloud computing environments using AI-driven predictive analytics

This paper proposes an innovative AI-driven approach for efficient resource allocation in cloud computing environments using predictive analytics. The study addresses the critical challenge of optimizing resource utilization while maintaining high quality of service in dynamic cloud infrastructures. A hybrid predictive model combining XGBoost and LSTM networks is developed to forecast workload patterns across various time horizons. The model leverages historical data from a large-scale cloud environment, encompassing 1000 servers and over 52 million data points. A dynamic resource scaling algorithm is introduced, which integrates the predictive model outputs with real-time system state information to make proactive allocation decisions. The proposed framework incorporates advanced techniques such as workload consolidation, resource oversubscription, and elastic resource pools to maximize utilization efficiency. Experimental results demonstrate significant improvements in key performance indicators, including increasing resource utilization from 65% to 83%, reducing SLA violation rates from 2.5% to 0.8%, and enhancing energy efficiency, with PUE improving from 1.4 to 1.18. Comparative analysis shows that the proposed model outperforms existing prediction accuracy and resource allocation efficiency methods. The study contributes to the field by presenting a comprehensive, AI-driven solution that addresses the complexities of modern cloud environments and paves the way for more intelligent and autonomous cloud resource management systems.