The security of data communication in Smart Grids (SGs) is traditionally reliant on cryptosystems based on the computational difficulty of certain mathematical problems. However, the advent of quantum computers, with their unparalleled computational power, threatens the robustness of classical cryptographic methods. Despite significant research into quantum-secure solutions, limited attention has been given to quantum-based security in SGs. To address these emerging security challenges, this paper proposes a quantum-based multifaceted secure communication model (Qu-MCM) for SGs, offering unconditional security by leveraging quantum mechanical principles. The key contributions include: quantum encryption of power consumption data using truly random keys, a quantum-secure key exchange protocol between power users and utility suppliers, and data authentication and integrity verification through quantum fingerprinting. The model is experimentally evaluated via simulations on classical computer and actual quantum hardware using the IBM Qiskit platform. The experimental results show that the encryption algorithm achieves an accuracy of 81.73%, while the authentication algorithm reaches 87.4% through a probability distribution graph where accuracy signifies the dominance of correct outputs. The results demonstrate the validity of the proposed model, with a comprehensive security analysis confirming its perfect security, where perfect security is defined as the maximally mixed states achieved after encryption that is impossible to break for an eavesdropper equipped with quantum resources.

The intermittent communication of power usage information in smart grids (SGs) is highly susceptible to potential cyberattacks, which is protected by classical public-key cryptosystems. However, recent advancements in the field of quantum computing have rendered these cryptosystems trivially insecure, triggering the immediate requirement for a highly resilient data communication scheme. This paper addresses the above-mentioned issue by designing a Quantum Encryption and Quantum Fourier Transformation (QFT) based secure data communication and aggregation model (QC-EAM) for SG environments. QC-EAM enables the power consumption data of the users to be encrypted using truly random encryption keys, ensuring unconditional security, while group homomorphism of Clifford Gates is utilized to achieve homomorphic evaluation of the encrypted quantum states. Moreover, a quantum-based data aggregation circuit is developed that performs QFT over the encrypted quantum states, yielding a secure and aggregated state. Furthermore, entanglement swaps-based quantum networking is considered as an enabling infrastructure for the proposed scenario, ensuring preservation of highly susceptible quantum states. The experimental evaluation of QC-EAM is achieved through classical computer-based simulations and tested on actual quantum system, provisioned through the IBM Qiskit platform. Statistical measurements of quantum circuits yield significantly accurate results, proving the validity of QC-EAM. Moreover, a thorough security analysis is also provided that confirms the perfect security achieved through maximally mixed states.

Cloud-based digital twin (DT) platforms enable real-time monitoring, simulation, and collaborative decision-making across distributed clients. However, ensuring secure and trustworthy communication remains a critical challenge due to heterogeneous client behavior, resource contention, and evolving adversarial threats. This article proposes themultifactor trust-driven secure communication(MT-SeCom) framework to enforce resilient and intelligent collaboration in DT-enabled cloud environments. MT-SeCom operates through four coordinated phases: First,multifactor trust monitoring, capturing temporal, contextual, and federated trust signals; second,adaptive trust evaluation, adjusting trust weights based on network dynamics and threat intensity; third,Transformer-based trusted client classification, combining anomaly detection with supervised learning to accurately identify malicious or unreliable nodes; and finally,resilient communication management, optimizing routing, isolating compromised clients, and ensuring service continuity. A real-world testbed and comprehensive experiments demonstrate that MT-SeCom significantly enhances secure communication, mitigates cascading adversarial effects, and maintains high resilience under fluctuating attack conditions. MT-SeCom achieves an average18.7%improvement in threat detection accuracy and a24.3%reduction in anomaly occurrences compared to existing methods, confirming its robustness, scalability, and practical suitability for heterogeneous cloud-based DT ecosystems.

The rapid growth of geographically distributed cloud data centers has intensified the demand for secure, privacy-preserving, and resource-efficient collaboration among mutually untrusted cloud environments. This paper presents BlockFed, a blockchain-empowered federated learning framework designed to enable cyber-threat-resilient collaboration across geographically distributed data centers. In BlockFed, each data center independently trains local models using private workload data and shares only the computed gradients rather than raw data, with a centralized aggregation server through a secure blockchain layer. A Proof-of-Work consensus mechanism is employed to validate gradient transactions and maintain an immutable, tamper-resistant ledger, ensuring trust and integrity among participating entities. The centralized server aggregates blockchain-verified updates to construct a global model, which is iteratively redistributed to support collaborative learning. This integrated learning process enhances task-level resource demand prediction while simultaneously improving system security and operational efficiency across all participating data centers. Extensive simulations on the Google Cluster Dataset show that BlockFed outperforms state-of-the-art baselines, including ISTM, ETP-WE, First-Fit, Best-Fit, and Random-Fit, in resource utilization, power consumption, and active server reduction. BlockFed achieves up to 7-81% higher resource utilization, 41-58% lower power consumption, and 31-65% fewer active servers, while attaining a cyber-threat estimation accuracy of 93.19%.

Accurate workload prediction and proactive resource reservation are crucial for industry clouds. However, the conventional machine learning (CML) models with limited learning capabilities often fail to predict diverse, high-dimensional workloads with sudden changes in resource demand, leading to excessive power consumption and resource management issues. In this context, this article proposes a novel Hadamard neural network with quantum blackhole (QB-HNN) optimization. This model combines the computational efficiency of quantum mechanics with the persuasive learning capability of neural networks (NNs). The workload information is transformed into qubits and propagated via a deep network of qubit neurons comprising a Hadamard-gated activation function to fetch superposition within the QB-HNN model for intuitive pattern learning. Furthermore, a novel quantum blackhole biphase optimization (QB-BiO) algorithm is introduced to train and optimize qubit neural weights. The performance of the proposed model is comprehensively evaluated and compared with five state-of-the-art approaches using six benchmark datasets of three heterogeneous varieties of cloud workloads. The prediction accuracy achieved for an extensive range of workloads confirms its influential performance by minimizing the prediction error up to 36.36% and 22.83% over existing LSTM-and EQNN-based prediction approaches, respectively.

Digital healthcare is essential to facilitate consumers to access and disseminate their medical data easily for enhanced medical care services. However, the significant concern with digitalization across healthcare systems necessitates for a prompt, productive, and secure storage facility along with a vigorous communication strategy, to stimulate sensitive digital healthcare data sharing and proactive estimation of malicious entities. In this context, this paper introduces a comprehensive quantum-based framework to overwhelm the potential security and privacy issues for secure healthcare data management. It equips quantum encryption for the secured storage and dispersal of healthcare data over the shared cloud platform by employing quantum encryption. Also, the framework furnishes a quantum feed-forward neural network unit to examine the intention behind the data request before granting access, for proactive estimation of potential data breach. In this way, the proposed framework delivers overall healthcare data management by coupling the advanced and more competent quantum approach with machine learning to safeguard the data storage, access, and prediction of malicious entities in an automated manner. Thus, the proposed IQ-HDM leads to more cooperative and effective healthcare delivery and empowers individuals with adequate custody of their health data. The experimental evaluation and comparison of the proposed IQ-HDM framework with state-of-the-art methods outline a considerable improvement up to 67.6%, in tackling cyber threats related to healthcare data security. Note to Practitioners—This paper aims to address the issue of digital healthcare data access, which requires both ease and security. Existing research either focuses solely on safe access or on high security, which often comes with high computational challenges. In this paper, we present a comprehensive approach that takes into account various challenges such as secure data storage, efficient data communication, and the prediction of malicious entities. We have developed a mathematical system to portray the overall management of healthcare data. All techniques proposed in this paper have been implemented using quantum computing and have been tested on four healthcare datasets. Initial experimental results suggest that the proposed approach is feasible. Our techniques can be applied to discover malicious entities and understand the behavior of real-life users in healthcare processes.

Diversity of workload demands lays a critical impact on efficient resource allocation and management of cloud services. The existing literature has either weakly considered or overlooked the heterogeneous feature of job requests received from wide range of internet services users. To address this context, the proposed approach namedReliable andEnergyEfficientTrafficManagement (REE-TM) has exploited the diversity of internet traffic in terms of variation in resource demands and expected complexity. Specifically, REE-TM incorporates categorization of heterogeneous job requests and executes them by selecting the most admissiblevirtual node(a software-defined instance such as a virtual machine or container) andphysical node(an actual hardware server or compute host) within the cloud infrastructure. To deal with resource-contention-based resource failures and performance degradation, a novel workload estimator ‘Toffoli Gate-based Quantum Neural Network’ (TG-QNN) is proposed, wherein learning process or interconnection weights optimization is achieved using Quantum version of BlackHole (QBHO) algorithm. The proactively estimated workload is used to compute entropy of the upcoming internet traffic with various traffic states analysis for detection of probable resource-congestion. REE-TM is extensively evaluated through simulations using a benchmark dataset and compared with optimal and without REE-TM versions. The performance evaluation and comparison of REE-TM with measured significant metrics reveal its effectiveness in assuring higher reliability by up to 30.25% and energy-efficiency by up to 23% as compared without REE-TM.

The increasing dependence on cloud-based data processing for industrial applications, smart devices, and CyberPhysical Systems (CPS) emphasizes the necessity to address the inherent vulnerabilities of multi-tenant cloud environments. The existing research have limited focus at the simultaneous handling of security and reliability in cloud workload management. This paper proposes a novel Quantum Toffoli Learning-based Service Management (QTL-SM) model to concurrently enhance both security and reliability during cloud applications processing. The model comprises two main components: (1) a reliability management unit composed of a novel Toffoli gate-embedded Quantum Adam neural network and (2) a security management unit for detecting and mitigating malicious virtual nodes. The former unit proactively estimates resource contention-based failures of physical nodes and manages them by analyzing reliability scores. It then allocates physical nodes to maximize these scores before executing client requests. The latter unit calculates vulnerability scores for each physical node by assessing multiple risk factors to identify potential malicious activities, mitigating their impact by preemptively terminating compromised nodes and connections. This integral approach ensures client requests are allocated to the most reliable and secure computation nodes, optimizing performance and service management. The QTL-SM model was implemented and evaluated using two real-world workloads. The comparative analysis with different model versions and state-ofthe-art methods demonstrated its effectiveness in failure analysis and management, resulting in a 59.7% improvement in reliability and a 51.4% reduction in malicious activities compared to models without QTL-SM.

Partial periodic patterns play a significant role in identifying regularities within temporal databases. However, most existing research has focused on discovering these patterns in binary datasets, overlooking the critical insights about the quantitative values associated with the items. This study utilizes the principles of fuzzy sets to propose a novel model for discovering Fuzzy Partial Periodic Frequent Patterns (FPPFPs) within a quantitative temporal database. A robust depth-first search algorithm has also been proposed to uncover all FPPFPs. The proposed algorithm incorporates a novel pruning strategy that effectively reduces the search space and the computational cost required for discovering the FPPFPs. The experimental findings on synthetic and real-world datasets demonstrate the efficiency of the proposed algorithm. Finally, a case study utilizing air pollution data is provided to showcase the practical applicability and significance of the identified patterns.

Industrial cross-cloud networks (ICCNs) combine services from multiple providers to support critical operations, but this diversity also creates major security challenges. Because each provider follows different protocols and safeguards, responses to cyber threats are often inconsistent and delayed, reducing the effectiveness of existing Cyber Threat Intelligence (CTI) systems. To address this gap, we propose a three-layered CTI framework that unifies learning and adaptation across heterogeneous clouds. The first layer implements a two-tier federated learning (FL) strategy, developing two global models:MLP-SimiFedandMLP-Non-SimiFed, within each industry cloud to manage scalability and heterogeneity. The second layer aggregates these models across distributed clouds into a Unified Global Model, strengthening collaborative defense. The third layer leverages transfer learning to produce theMeta Unified Global Cyber Threat Intelligence(MUG-CTI) model, which enables swift adaptation to emerging threats. Through test-bed simulation, MUG-CTI demonstrates superior threat management, achieving up to 20.7% and 43.06% higher accuracy, and reducing hamming loss by up to 73.8% and 98.3% compared to Federated Learning and SVM-driven methods, respectively.

Digital twins (DTs), integral to cloud platforms, bridge physical and virtual worlds, fostering collaboration among stakeholders in manufacturing and processing. However, the cloud platforms face challenges such as service outages, vulnerabilities, and resource contention, hindering critical DT application development. The existing research works have limited focus on reliability and fault tolerance in DT processing. In this context, this article proposed a novel self-healing and fault-tolerant cloud-based digital twin processing management (SF-DTM) model. It employs collaborative DT tasks resource requirement estimation unit that utilizes newly devised federated learning with cosine similarity integration. Furthermore, SF-DTM incorporates a self-healing fault-tolerance strategy employing a frequent sequence fault-prone pattern analytics unit for deciding the most admissible virtual machine (VM) allocation. The implementation and evaluation of the SF-DTM model using real traces demonstrates its effectiveness and resilience, revealing improved availability, higher mean time between failure, and lower mean time to repair compared with non-SF-DTM approaches, enhancing collaborative DT application management. SF-DTM improved the services availability up to 13.2% over non-SF-DTM-based DT processing.

In the era of crowd delivery vehicle routing and traffic management in smart cities, a complex challenge appears indistinctly, affecting both developed and developing nations worldwide. This challenging problem involves optimizing multi-depot routes while addressing various hurdles: minimizing travel time, distance, fuel consumption, and carbon emissions, all while navigating dynamic traffic congestion across diverse pathways. Existing approaches often focus on isolated aspects like shortest paths, carbon emissions, or traffic prediction, leaving the comprehensive multi-depot traffic management problem unaddressed. In response, this research work proposes an Intelligent Multi-Depot Vehicle Routing and Management (IM-VRM) model which provides a comprehensive and holistic solution. It employs a Graph Neural Network (GNN) learning-based routing with a greedy optimization to establish initial optimal pathways for multi-depot journeys. Subsequently, the IM-VRM model integrates traffic congestion prediction with green parameter computation, engaging the Dijkstra algorithm to select the most admissible routes. This consecutive steps-based travel route guidance process optimizes routing for heterogeneous vehicles, including both heavy-duty and light-duty types. It accounts for load-dependent fuel consumption, velocity, and carbon emissions. By doing so, it simplifies the complexities of multi-depot traffic routing and management. The proposed model has been rigorously evaluated using a real-world multi-depot traffic dataset, demonstrating its practical viability. Notably, IM-VRM model achieves a remarkable improvement in fuel savings, reduced carbon emissions, and shorter travel time outperforming previous state-of-the-art methods in both efficiency and precision.

Accurate workload prediction and advanced resource reservation are indispensably crucial for managing dynamic cloud services. Traditional neural networks and deep learning models frequently encounter challenges with diverse, high-dimensional workloads, especially during sudden resource demand changes, leading to inefficiencies. This issue arises from their limited optimization during training, relying only on parametric (interconnection weights) adjustments using conventional algorithms. To address this issue, this work proposes a novel comprehensively adaptive architectural optimization-based variable quantum neural network (CA-QNN), which combines the efficiency of quantum computing with complete structural and qubit vector parametric learning. The model converts workload data into qubits, processed through qubit neurons with controlled not-gated activation functions for intuitive pattern recognition. In addition, a comprehensive architecture optimization algorithm for networks is introduced to facilitate the learning and propagation of the structure and parametric values in variable-sized quantum neural networks (VQNNs). This algorithm incorporates quantum adaptive modulation (QAM) and size-adaptive recombination during the training process. The performance of the CA-QNN model is thoroughly investigated against seven state-of-the-art methods across four benchmark datasets of heterogeneous cloud workloads. The proposed model demonstrates superior prediction accuracy, reducing prediction errors by up to 93.40% and 91.27% compared to existing deep learning and QNN-based approaches.

To empower the management of smart meters’ demand load within a smart grid environment, this paper presents a Feed-forward Neural Network with ADaptive Evolutionary Learning Approach (ADELA). In this model, the load forecasting information is propagated via neurons of input and multiple hidden layers and the final estimated output is achieved with the help of the sigmoid activation function. An improved evolutionary algorithm is proposed for training and adjusting the interconnecting weights among the layers of the intended neural network. This model is capable of addressing the critical challenges of high volatility, uncertainty, missing smart meters data, and sudden upsurge and plunge in electricity demand. The proposed algorithm is able to learn the best suitable evolutionary operators from a given pool of operators and the probabilities associated with them. The proposed load forecasting approach is simulated over three real-world smart meter datasets, including the Australian Smart Grid Smart City project, the Irish Commission for Energy Regulation, and UMass Smart. The performance evaluation and comparison of the proposed approach with the existing state-of-the-art approaches revealed a relative improvement of up to 46.93%, 5.05%, and 2.20% in forecast accuracy over the Smart Grid Smart City, UMass Smart and the Irish Commission for Energy Regulation datasets, respectively.

Secure resource management (SRM) within a cloud computing environment is a critical yet infrequently studied research topic. This article provides a comprehensive survey and comparative performance evaluation of potential cyber threat countermeasure strategies that address security challenges during cloud workload execution and resource management. Cybersecurity is explored specifically in the context of cloud resource management, with an emphasis on identifying the associated challenges. The cyber threat countermeasure methods are categorized into three classes: defensive strategies, mitigating strategies, and hybrid strategies. The existing countermeasure strategies belonging to each class are thoroughly discussed and compared. In addition to conceptual and theoretical analysis, the leading countermeasure strategies within these categories are implemented on a common platform and examined using two real-world virtual machine (VM) data traces. Based on this comprehensive study and performance evaluation, this article discusses the tradeoffs among these countermeasure strategies and their utility, providing imperative concluding remarks on the holistic study of cloud cyber threat countermeasures and SRM. Furthermore, the study suggests future methodologies that could effectively address the emerging challenges of secure cloud resource management.

Workload pattern learning-based resource management is crucial for cloud computing environments for achieving higher performance, sustainability, fault-tolerance, and quality of service. The existing literature lacks a comprehensive discussion and meta-analysis of workload pattern learning centered cloud resource management. In this context, this paper presents a first comprehensive study about five pattern learning and analysis-driven techniques applied for achieving higher efficiency and performance during multi-constrained cloud resource management. The paper manifests utility and significance of workload pattern learning-based resource management as compared with traditional resource management. The five principle techniques are thoroughly discussed with coherent depiction of intended concept alongwith numerical illustration. The most prominent state-of-the-art models belonging to each technique are further distinguished based on distinct objectives conferring an extensive survey and comparison. Besides, conceptual and theoretical analysis, the leading models underlying the major resource management techniques are implemented on a common platform and thoroughly examined using real-world Google Cluster workload traces. Based on the all-inclusive study and performance evaluation, trade-off discussion among these techniques are capsuled to put forward imperative concluding remarks with concrete open issues and insightful future research directions.

Large-scale computing systems in the modern era distribute tasks into smaller units that can be executed simultaneously to speed up job completion and decrease energy usage. However, cloud computing systems encounter a significant challenge called the Long Tail problem, where a small subset of slow-performing tasks hinders the overall progress of parallel job execution. This behavior leads to longer service response times and reduced system efficiency. This paper introduces a novel approach called Stochastic Gradient Descent with Momentum-driven Neural Network to analyze and classify heterogeneous tasks as either stragglers or non-stragglers. The straggler tasks are further categorized into Resource Hunter and Long-Tail stragglers based on their specific resource requirements. A traffic management policy is implemented to schedule and assign resources among user job requests, considering the task category, to achieve parallelism and improve sustainability within the cloud infrastructure. Extensive simulations are conducted using the Google Cluster Dataset (GCD) to assess the effectiveness of the proposed framework. The results obtained from these simulations are then compared to state-of-the-art techniques. The experimental findings demonstrate significant reductions in power consumption, carbon emissions, active servers, conflicting servers, and VM migration up to 55.16%, 49.76%, 35%, 25.7%, and 87.29%, respectively. Moreover, there has been an enhancement in resource utilization by up to 78.31%, accompanied by a decrease in execution time of up to 67.74%.

The heterogeneous and multi-structured data within datalakes environment stored at distributed geographical locations raises the difficulty of user query processing. Caching is a technique that can help reduce the latency by facilitating the required web pages within cache memory for faster query processing. The dynamic demands of heterogeneous web content are entangled with critical challenges of adjusting cache size dynamically and scaling processing requirements with elastic resource capacity. However, the existing caching schemes based on duration of web page stay within cache are insufficient to provision dynamic caching of heterogeneous web content automatically. In this context, this paper proposes a novel dynamic and self-adaptive cache management model named latency aware dynamic caching (LAD-Caching). It incorporates deep learning capability of Long Short-term Memory (LSTM) algorithm for proactive estimation of caching contents with an automated cache admission and eviction scheme. The innovative idea of engaging two different LSTM-based units for dynamic cache size prediction and cache content eviction is proposed for the first time which captures all-inclusive dynamic cache management in diverse datalake environment. The simulation and performance evaluation of the proposed LAD-Caching using a benchmark dataset confirms its efficiency in terms of reduced average data access time up to 100.826 nsec as compared with optimal case and minimizing average delay up to 99% over without LAD-Caching. Further, the number of cache hits are improved up to 52.7% and 51.2% over existing caching.

The key challenges in cloud computing encompass dynamic resource scaling, load balancing, and power consumption. Accurate workload prediction is identified as a crucial strategy to address these challenges. Despite numerous methods proposed to tackle this issue, existing approaches fall short of capturing the high-variance nature of volatile and dynamic cloud workloads. Consequently, this paper introduces a novel model aimed at addressing this limitation. This paper presents a novel Multiple Controlled Toffoli-driven Adaptive Quantum Neural Network (MCT-AQNN) model to establish an empirical solution to complex, elastic as well as challenging workload prediction problems by optimizing the exploration, adaption, and exploitation proficiencies through quantum learning. The computational adaptability of quantum computing is ingrained with machine learning algorithms to derive more precise correlations from dynamic and complex workloads. The furnished input data point and hatched neural weights are refitted in the form of qubits while the controlling effects of Multiple Controlled Toffoli (MCT) gates are operated at the hidden and output layers of Quantum Neural Network (QNN) for enhancing learning capabilities. Complimentarily, a Uniformly Adaptive Quantum Machine Learning (UAQL) algorithm has evolved to functionally and effectually train the QNN. The extensive experiments are conducted and the comparisons are performed with state-of-the-art methods using four real-world benchmark datasets. Experimental results evince that MCT-AQNN has up to 32%-96% higher accuracy than the existing approaches.

The inefficient sharing of industrial cloud resour-ces among multiple users and vulnerabilities of virtual machines (VM)s and servers prompt unauthorized access to users’ sensitive data along with excess consumption of power and resource wastage. To address these entangled issues, this paper proposes a novelEmerging VMThreatPrediction and DynamicWorkloadEstimation based Resource Allocation (ETP-WE) framework that predicts VM threats and resource usage proactively in real-time. The proposed framework contributes by introducing a Risk-Score Matrix that analyses multiple risks for each VM; utilizing knowledge of proposed security and workload analyzers for efficient VM Placement (VMP), and estimating resource utilization by developing an ensemble predictor for prior mitigation of over-/under-load on servers. ETP-WE framework collaborates machine-learning-based security and workload analysis for secure and resource-efficient VMP, thereby reducing the number of security threats, optimizing resource utilization, power-consumption, and adapting to the changes in application demands. The performance of the proposed framework is evaluated using two benchmark datasets OpenNebula and Google Cluster. The simulation-based comparison with state-of-the-arts validates the efficacy of ETP-WE in terms of reduction of security threats, power consumption, and number of active servers up to 86.9%, 66.67% and 30%-80%, respectively with an improved resource utilization up to 60%-75% over existing approachesNote to Practitioners—Industry clouds serve the precise needs and provide the service features and tools as per the industry’s needs to help organizations meet their workloads processing and storage demands. For instance, healthcare and financial organizations have to comply with extended security to meet specific service requirements. To this context, we have proposed a novel ETP-WE framework for prediction and mitigation of cyberthreats on virtual resources in real-time for secure execution of industrial applications on third-party servers. ETP-WE collaborates machine-learning based security and workload analysis for secure and resource efficient VM allocation, thereby reducing number of security threats, optimizing resource utilization, power-consumption and adaptating to the changes in application demands. During the processing of any sensitive transaction such as medical data, bank transactions, ETP-WE framework will induce improved data protection by mitigating potential data breaches. ETP-WE framework will be deployed at Resource Scheduler to boost security performance by estimating the multiple risks score status of VMs engaged in execution of industrial transactions or workloads. It will help to predict and analyze the probable security threats or breaches proactively and facilitate their mitigation. The performance evaluation and comparison with state-of-the-arts validate potency of ETP-WE in terms of reduction of cybersecurity threats and number of active servers with an improved resource utilization over existing approaches.

This article proposed a novel industry cloud resource management framework that exploits resource oversubscription and heterogeneous service pricing models to maximize profitability and operational efficiency for industry cloud providers. The framework proposes an adaptive ensemble machine learning driven prediction model for proactive estimation of resource utilization of Virtual Machines (VM)s-based on previous resource utilization of respective users’ VMs to minimize resource wastage due to oversubscription by them. Accordingly, the VMs having similar predicted resource usage are grouped using Fuzzy C-means clustering. This helps to determine the required number of VMs with specific configuration to be deployed before executing user requests. Concurrently, the framework incorporates two distinct categories of cloud service pricing models, namely theDelay Sensitive Modeland theBest-Effort Model. Accordingly, the user requests are classified and executed by selecting the most suitable VMs, with the goal of maximizing revenue and reducing electricity costs in cloud data centers ($\mathbb{C}\mathbb{D}\mathbb{C}$s). Experimental simulation and comparison against state-of-the-art methods, using two benchmark VM traces, validates the performance of proposed framework. It significantly reduces electricity bills by 55.56%, power consumption and active servers by up to 60.7% and 51%, respectively, while improving resource utilization and profits by up to 60% and 51.18%, respectively.

The precise estimation of resource usage is a complex and challenging issue due to the high variability and dimensionality of heterogeneous service types and dynamic workloads. Over the last few years, the prediction of resource usage and traffic has received ample attention from the research community. Many machine learning-based workload forecasting models have been developed by exploiting their computational power and learning capabilities. This paper presents the first systematic survey cum performance analysis-based comparative study of diversified machine learning-driven cloud workload prediction models. The discussion initiates with the significance of predictive resource management followed by a schematic description, operational design, motivation, and challenges concerning these workload prediction models. Classification and taxonomy of different prediction approaches into five distinct categories are presented focusing on the theoretical concepts and mathematical functioning of the existing state-of-the-art workload prediction methods. The most prominent prediction approaches belonging to a distinct class of machine learning models are thoroughly surveyed and compared. All five classified machine learning-based workload prediction models are implemented on a common platform for systematic investigation and comparison using three distinct benchmark cloud workload traces via experimental analysis. The essential key performance indicators of state-of-the-art approaches are evaluated for comparison and the paper is concluded by discussing the trade-offs and notable remarks.

Massive upsurge in cloud resource usage stave off service availability resulting into outages, resource contention, and excessive power-consumption. The existing approaches have addressed this challenge by providing multi-cloud, VM migration, and running multiple replicas of each VM which accounts for high expenses of cloud data centre (CDC). In this context, a novel VM Significance Ranking and Resource Estimation based High Availability Management (SRE-HM) Model is proposed to enhance service availability for users with optimized cost for CDC. The model estimates resource contention based server failure and organises needed resources beforehand for maintaining desired level of service availability. A significance ranking parameter is introduced and computed for each VM, executing critical or non-critical tasks followed by the selection of an admissible High Availability (HA) strategy respective to its significance and user specified constraints. It enables cost optimization for CDC by rendering failure tolerance strategies for significant VMs only instead of all the VMs. The proposed model is evaluated and compared against state-of-the-arts by executing experiments using Google Cluster dataset. SRE-HM improved the services availability up to 19.56% and scales down the number of active servers and power-consumption up to 26.67% and 19.1%, respectively over HA without SRE-HM.

Cloud virtualization technology, ingrained with physical resource sharing, prompts cybersecurity threats on users’ virtual machines (VMs) due to the presence of inevitable vulnerabilities on the offsite servers. Contrary to the existing works which concentrated on reducing resource sharing and encryption/decryption of data before transfer for improving cybersecurity which raises computational cost overhead, the proposed model operates diversely for efficiently serving the same purpose. This article proposes a novel multiple risks analysis-based VM threat prediction model (MR-TPM) to secure computational data and minimize adversary breaches by proactively estimating the VMs threats. It considers multiple cybersecurity risk factors associated with the configuration and management of VMs, along with analysis of users’ behavior. All these threat factors are quantified for the generation of respective risk score values and fed as input into a machine learning-based classifier to estimate the probability of threat for each VM. The performance of MR-TPM is evaluated using benchmark Google Cluster and OpenNebula VM threat traces. The experimental results demonstrate that the proposed model efficiently computes the cybersecurity risks and learns the VM threat patterns from historical and live data samples. The deployment of MR-TPM with existing VM allocation policies reduces cybersecurity threats up to 88.9%.

The elasticity of cloud resources allows cloud clients to expand and shrink their demand for resources dynamically over time. However, fluctuations in the resource demands and pre-defined size of virtual machines (VMs) lead to lack of resource utilization, load imbalance, and excessive power consumption. To address these issues and to improve the performance of data center, an efficient resource management framework is proposed, which anticipates resource utilization of the servers and balances the load accordingly. It facilitates power saving, by minimizing the number of active servers, VM migrations, and maximizing the resource utilization. An online resource prediction system, is developed and deployed at each VM to minimize the risk of Service Level Agreement (SLA) violations and performance degradation due to under/overloaded servers. In addition, multi-objective VM placement and migration algorithms are proposed to reduce the network traffic and power consumption within data center. The proposed framework is evaluated by executing experiments on three real world workload datasets namely, Google Cluster dataset, Planet Lab, and Bitbrains VM traces. The comparison of proposed framework with the state-of-the-art approaches reveals its superiority in terms of different performance metrics. The improvement in power saving achieved by OP-MLB framework is upto 85.3 percent over the Best-Fit approach.

Cloud computing has become inevitable for every digital service which has exponentially increased its usage. However, a tremendous surge in cloud resource demand stave off service availability resulting into outages, performance degradation, load imbalance, and excessive power-consumption. The existing approaches mainly attempt to address the problem by using multi-cloud and running multiple replicas of a virtual machine (VM) which accounts for high operational-cost. This paper proposes a Fault Tolerant Elastic Resource Management (FT-ERM) framework that addresses aforementioned problem from a different perspective by inducing high-availability in servers and VMs. Specifically,(1)an online failure predictor is developed to anticipate failure-prone VMs based on predicted resource contention;(2)the operational status of server is monitored with the help of power analyser, resource estimator and thermal analyser to identify any failure due to overloading and overheating of servers proactively; and(3)failure-prone VMs are assigned to proposed fault-tolerance unit composed of decision matrix and safe box to trigger VM migration and handle any outage beforehand while maintaining desired level of availability for cloud users. The proposed framework is evaluated and compared against state-of-the-arts by executing experiments using two real-world datasets. FT-ERM improved the availability of the services up to 34.47% and scales down VM-migration and power-consumption up to 88.6% and 62.4%, respectively over without FT-ERM approach.

This work presents a novel Evolutionary Quantum Neural Network (EQNN) based workload prediction model for Cloud datacenter. It exploits the computational efficiency of quantum computing by encoding workload information into qubits and propagating this information through the network to estimate the workload or resource demands with enhanced accuracy proactively. The rotation and reverse rotation effects of the Controlled-NOT (C-NOT) gate serve activation function at the hidden and output layers to adjust the qubit weights. In addition, a Self Balanced Adaptive Differential Evolution (SB-ADE) algorithm is developed to optimize qubit network weights. The accuracy of the EQNN prediction model is extensively evaluated and compared with seven state-of-the-art methods using eight real world benchmark datasets of three different categories. Experimental results reveal that the use of the quantum approach to evolutionary neural network substantially improves the prediction accuracy up to 91.6 percent over the existing approaches.