CPU Utilization Research Articles

A Harris Hawk Optimisation system for energy and resource efficient virtual machine placement in cloud data centers.

Virtualisation is a major technology in cloud computing for optimising the cloud data centre's power usage. In the current scenario, most of the services are migrated to the cloud, putting more load on the cloud data centres. As a result, the data center's size expands resulting in increased energy usage. To address this problem, a resource allocation optimisation method that is both efficient and effective is necessary. The optimal utilisation of cloud infrastructure and optimisation algorithms plays a vital role. The cloud resources rely on the allocation policy of the virtual machine on cloud resources. A virtual machine placement technique, based on the Harris Hawk Optimisation (HHO) model for the cloud data centre is presented in this paper. The proposed HHO model aims to find the best place for virtual machines on suitable hosts with the least load and power consumption. PlanetLab's real-time workload traces are used for performance evaluation with existing PSO (Particle Swarm Optimisation) and PABFD (Best Fit Decreasing). The performance evaluation of the proposed method is done using power consumption, SLA, CPU utilisation, RAM utilisation, Execution time (ms) and the number of VM migrations. The performance evaluation is done using two simulation scenarios with scaling workload in scenario 1 and increasing resources for the virtual machine to study the performance in underloaded and overloaded conditions. Experimental results show that the proposed HHO algorithm improved execution time(ms) by 4%, had a 27% reduction in power consumption, a 16% reduction in SLA violation and an increase in resource utilisation by 17%. The HHO algorithm is also effective in handling dynamic and uncertain environments, making it suitable for real-world cloud infrastructures.

Deep Reinforcement Learning for Workload Prediction in Federated Cloud Environments.

The Federated Cloud Computing (FCC) paradigm provides scalability advantages to Cloud Service Providers (CSP) in preserving their Service Level Agreement (SLA) as opposed to single Data Centers (DC). However, existing research has primarily focused on Virtual Machine (VM) placement, with less emphasis on energy efficiency and SLA adherence. In this paper, we propose a novel solution, Federated Cloud Workload Prediction with Deep Q-Learning (FEDQWP). Our solution addresses the complex VM placement problem, energy efficiency, and SLA preservation, making it comprehensive and beneficial for CSPs. By leveraging the capabilities of deep learning, our FEDQWP model extracts underlying patterns and optimizes resource allocation. Real-world workloads are extensively evaluated to demonstrate the efficacy of our approach compared to existing solutions. The results show that our DQL model outperforms other algorithms in terms of CPU utilization, migration time, finished tasks, energy consumption, and SLA violations. Specifically, our QLearning model achieves efficient CPU utilization with a median value of 29.02, completes migrations in an average of 0.31 units, finishes an average of 699 tasks, consumes the least energy with an average of 1.85 kWh, and exhibits the lowest number of SLA violations with an average of 0.03 violations proportionally. These quantitative results highlight the superiority of our proposed method in optimizing performance in FCC environments.

FedCare: Federated Learning for Resource-Constrained Healthcare Devices in IoMT System

In social IoMT systems, resource-constrained devices face the challenges of limited computation, bandwidth, and privacy in the deployment of deep learning models. Federated learning (FL) is one of the solutions to user privacy and provides distributed training among several local devices. In addition, it reduces the computation and bandwidth of transferring videos to the central server in camera-based IoMT devices. In this work, we design an edge-based federated framework for such devices. In contrast to traditional methods that drop the resource-constrained stragglers in a federated round, our system provides a methodology to incorporate them. We propose a new phase in the FL algorithm, known as split learning. The stragglers train collaboratively with the nearest edge node using split learning. We test the implementation using heterogeneous computing devices that extract vital signs from videos. The results show a reduction of 3.6 h in the training time of videos using the split learning phase with respect to the traditional approach. We also evaluate the performance of the devices and system with key parameters, CPU utilization, memory consumption, and data rate. Furthermore, we achieve 87.29% and 60.26% test accuracy at the nonstragglers and stragglers, respectively, with a global accuracy of 90.32% at the server. Therefore, FedCare provides a straggler-resistant federated method for a heterogeneous system for social IoMT devices.

An Energy Efficient Particle Swarm Optimization based VM Allocation for Cloud Data Centre: EEVMPSO

Virtual Machine (VM) allocation are the crucial problems because cloud computing enables the rapid growth of data centres and compute centres. Power consumption and network expenses have increased as cloud computing becomes more and more prevalent. System instability may result from repeated requests for computing resources. One of the most important and difficulties facing virtualization technology is finding the best way to stack virtual machines on top of physical machines in cloud data centres. The host must move virtual machines from overloaded to underloaded hosts as part of load balancing, which has an impact on energy consumption. The proposed energy efficient particle swarm optimization algorithm (EEVMPSO) for Virtual Machine allocation to maximize the load balancing. System resources including CPU, storage, and memory are optimized using EEVMPSO. This research article suggests energy-aware virtual machine migration using the Particle Swarm Optimization Algorithm for dynamic VMs placement, energy efficient cloud data centres as a solution to this issue. The experimental result shown in the proposed method, consumption energy in comparison to the PAPSO, KHA, EALBPSO, and RACC-MDT algorithm by 10.86%, 18.22%, 25.8%, and 31.34% respectively, it demonstrated the improvements in the energy service level agreements violation 5.77%, 15.3%, 26.19%, and 30.4%, as well as the average CPU utilization 2.2%, 24%, 22.6%, and 14.6%.

Energy Efficient in Cloud Computing

Abstract: Today, both parallel and distributing computing have became ubiquitous in the forms of clouds and cyber physical systems, The size of cloud data center is growing rapidly. The larger the data center is, the more energy it consumes. Therefore, more and more researchers focus on energy efficient resource management techniques in the data center. In which manage the load factor and cpu utilization. we consider about cloud computing, its working, its problem definition, virtual machine requirements( executing VMs with similar execution time), objectives and future development of cloud computing. This has led to immense usage of energy, power consumption, usage of e-equipment’s and so on. To overcome this, efforts and techniques are reinforced to save energy, power consumption and the usage of equipment’s to save the planet. Energy efficiency is increasingly important for future ICT. To reduce the power consumption of cloud data centers we aim to reduce the efficient usage of power consumed by IT equipments. EEICC attainable by using eco-friendly computing resources.

Tigger: A Database Proxy That Bounces with User-Bypass

Developers often deploy database-specific network proxies whereby applications connect transparently to the proxy instead of directly connecting to the database management system (DBMS). This indirection improves system performance through connection pooling, load balancing, and other DBMS-specific optimizations. Instead of simply forwarding packets, these proxies implement DBMS protocol logic (i.e., at the application layer) to achieve this behavior. Consequently, existing proxies are user-space applications that process requests as they arrive on network sockets and forward them to the appropriate destinations. This approach incurs inefficiencies as the kernel repeatedly copies buffers between user-space and kernel-space, and the associated system calls add CPU overhead. This paper presents user-bypass, a technique to eliminate these overheads by leveraging modern operating system features that support custom code execution. User-bypass pushes application logic into kernel-space via Linux's eBPF infrastructure. To demonstrate its benefits, we implemented Tigger, a PostgreSQL-compatible DBMS proxy using user-bypass to eliminate the overheads of traditional proxy design. We compare Tigger's performance against other state-of-the-art proxies widely used in real-world deployments. Our experiments show that Tigger outperforms other proxies --- in one scenario achieving both the lowest transaction latencies (up to 29% reduction) and lowest CPU utilization (up to 42% reduction). The results show that user-bypass implementations like Tigger are well-suited to DBMS proxies' unique requirements.

A scheduling algorithm to maximize storm throughput in heterogeneous cluster

In the most popular distributed stream processing frameworks (DSPFs), programs are modeled as a directed acyclic graph. Using this model, a DSPF can benefit from the parallelism capabilities of distributed clusters. Choosing a reasonable number of vertices for each operator and mapping the vertices to the appropriate processing resources significantly affect the overall system performance. Due to the simplicity of the current DSPF schedulers, these frameworks perform poorly on large-scale clusters. In this paper, we present a heterogeneity-aware scheduling algorithm that finds the proper number of the vertices of an application graph and maps them to the most suitable cluster node. We begin with a pre-processing step which allocates the vertices to the given cluster nodes using profiling data. Then, we gradually increase the topology input rate in order to scale up the application graph. Finally, using a CPU utilization model which predicts the CPU workload based on the input rate to vertices and the processing node’s CPU characteristics, we identify the bottlenecked vertices and allocate new instances derived from them to the least utilized processing resource. Our experimental results on Storm Micro-Benchmark show that (1) the prediction model estimate CPU utilization with 92% accuracy. (2) Compared to the default scheduler of Storm, our scheduler provides 7 to 44% throughput enhancement. (3) The proposed method can find the solution within 4% (worst case) of the optimal scheduler, which obtains the best scheduling scenario using an exhaustive search over problem design space.

Performance Analysis of Microservices Behavior in Cloud vs Containerized Domain based on CPU Utilization

Enterprise application development is rapidly moving towards a microservices-based approach. Microservices development makes application deployment more reliable and responsive based on their architecture and the way of deployment. Still, the performance of microservices is different in all environments based on resources provided by the respective cloud and services provided in the backend such as auto-scaling, load balancer, and multiple monitoring parameters. So, it is strenuous to identify Scaling and monitoring of microservice-based applications are quick as compared to monolithic applications [1]. In this paper, we deployed microservice applications in cloud and containerized environments to analyze their CPU utilization over multiple network input requests. Monolithic applications are tightly coupled while microservices applications are loosely coupled which help the API gateway to easily interact with each service module. With reference to monitoring parameters, CPU utilization is 23 percent in cloud environment. Additionally, we deployed the equivalent microservice in a containerized environment with extended resources to minimize CPU utilization to 17 percent. Furthermore, we have shown the performance of the application with “Network IN” and “Network Out” requests.

SGA Model for Prediction in Cloud Environment

With virtual information, cloud computing has made applications available to users everywhere. Efficient asset workload forecasting could help the cloud achieve maximum resource utilisation. The effective utilization of resources and the reduction of datacentres power both depend heavily on load forecasting. The allocation of resources and task scheduling issues in clouds and virtualized systems are significantly impacted by CPU utilisation forecast. A resource manager uses utilisation projection to distribute workload between physical nodes, improving resource consumption effectiveness. When performing a virtual machine distribution job, a good estimation of CPU utilization enables the migration of one or more virtual servers, preventing the overflow of the real machineries. In a cloud system, scalability and flexibility are crucial characteristics. Predicting workload and demands would aid in optimal resource utilisation in a cloud setting. To improve allocation of resources and the effectiveness of the cloud service, workload assessment and future workload forecasting could be performed. The creation of an appropriate statistical method has begun. In this study, a simulation approach and a genetic algorithm were used to forecast workloads. In comparison to the earlier techniques, it is anticipated to produce results that are superior by having a lower error rate and higher forecasting reliability. The suggested method is examined utilizing statistics from the Bit brains datacentres. The study then analyses, summarises, and suggests future study paths in cloud environments.

Inquisitive Genetic-Based Wolf Optimization for Load Balancing in Cloud Computing

Abstract Cloud remains an active and dominant player in the field of information technology. Hence, to meet the rapidly growing requirement of computational processes and storage resources, the cloud provider deploys efficient data centres globally that comprise thousands of IT servers. Because of tremendous energy and resource utilization, a reliable cloud platform has to be necessarily optimized. Effective load balancing is a great option to overcome these issues. However, loading balancing difficulties, such as increased computational complexity, the chance of losing the client data during task rescheduling, and consuming huge memory of the host, and new VM (Virtual Machine), need appropriate optimization. Hence, the study aims to create a newly developed IG-WA (Inquisitive Genetic–Wolf Optimization) framework that meritoriously detects the optimized virtual machine in an environment. For this purpose, the system utilises the GWO (Grey Wolf Optimization) method with an evolutionary mechanism for achieving a proper compromise between exploitation and exploration, thereby accelerating the convergence and achieving optimized accuracy. Furthermore, the fitness function evaluated with an inquisitive genetic algorithm adds value to the overall efficacy. Performance evaluation brings forward the outperformance of the proposed IGWO system in terms of energy consumption, execution time and cost, makespan, CPU utilization, and memory utilization. Further, the system attains more comprehensive and better results when compared to the state of art methods.

GPU Based High Definition Parallel Video Codec Optimization in Mobile Device

The main challenges when using video codec technology on mobile devices are: 1) the explosive growth of multimedia applications renders the computing resource allocation a problem of major importance; 2) high power consumption and limited battery power; 3) high cpu utilization causes the system to be unresponsive. In this paper, a GPU based High Definition Parallel Video Codec (GHPVC) is proposed, which is a low energy consumption and high efficient video codec on mobile devices. First, Frame Data Management model and Prediction Model Selector model are proposed in order to get higher data transmission efficiency and parallel execution efficiency. Second, a GPU based Parallel ME module is proposed because the ME module is the most compute-intensive part and most time consuming module in video codec. The GHPVC is proposed on the basis of conforming to the H.264 standard. Moreover and experimentally evaluated for different GPU devices on different mobile devices. Experimental results show that compared with the existing H.264 scheme, the proposed GHPVC not only has significant improvement in codec performance, but also effectively reduces energy consumption and CPU utilization.

A Multivariate KPIs Anomaly Detection Framework With Dynamic Balancing Loss Training

Anomaly detection on multivariate KPIs (Key Performance Indicators, such as CPU utilization, sockets status, and HTTP requests per second) is of utmost importance to the systems’ reliability. Unsupervised methods have been of considerable interests and have significantly progressed due to their superior effectiveness. However, the state-of-art unsupervised anomaly detection methods still suffer from high false or missed alarm rates. To this end, in this paper, we propose MM, a practical Multivariate KPIs anomaly detection framework following the principles of Multi-task learning with the proposed dynamic balancing loss function. To capture KPIs’ characteristics to the most extent, we simultaneously train multiple sequential autoencoders with different connections based on a designed semi-Random Connection Recurrent Neural Network (sRC-RNN). These autoencoders can be treated as different reconstruction tasks while training. Furthermore, we propose a dynamic loss function to adaptively balance the tasks’ weights. Extensive experiments show that MM outperforms the state-of-art unsupervised multivariate KPIs anomaly detection algorithms and achieves an average F1-score of 0.95 on two public machine-level KPIs datasets and 0.96 on an internal container-level KPIs dataset.

KEdge: Fuzzy-Based Multi-AI Model Coalescence Solution for Mobile Healthcare System

In this work, we propose a condition-aware analytical framework—KEdge—for health condition recommendation in Internet of Things (IoT) based mobile healthcare systems. Procuring data from multiple sensors and making a singular assessment from them is a challenging task. KEdge overcomes such an issue by determining the severity of the patient by determining a condition index (CI) using a two-step analytical framework and a multiple rule fuzzy inference system (FIS). In the first step, KEdge detects the heart severity condition using a convolutional neural network model and, in the second step, it detects the respiratory condition using a random forest classification model. KEdge also utilizes auscultation sounds from SkopEdge (a digital stethoscope) for assessing the heartbeats. Through extensive experiments, we observe that KEdge identifies the arrhythmia condition with an accuracy of 98.53% and respiratory condition by 98.68%. KEdge considers the analytical predictions and analysis from SkopEdge to evaluate the CI for recommending the overall health condition using Mamdani FIS. We observe that KEdge is suitable for resource-constrained IoT devices providing memory consumption of 6.6%. On offloading the same to the fog nodes, we observe improved CPU utilization with data upload rates in the order of 25 kb/s (KEdge) and 5 Mb/s (SkopEdge).

An adaptive auto-scaling framework for cloud resource provisioning

Cloud computing emerged as a technology that offers scalable access to computing resources in conjunction with low maintenance costs. In this domain, cloud users utilize virtualized resources to benefit from on-demand and long-term pricing strategies. Although the latter consists of a more cost-efficient solution, it requires accurate estimations of future workload demands, which is a challenging task. Furthermore, clouds offer threshold-based auto-scaling rules that need to be manually controlled by the users according to application requirements. Still, tuning scaling parameters is not trivial, since it is mainly based on static scaling rules that may lead to unreasonable costs and quality of service violations. In this work we introduce ADA-RP, an adaptive auto-scaling framework for reliable resource provisioning in the cloud. ADA-RP uses historical time series data for training K-means and convolutional neural networks (CNN) to categorize future workload demands as High, Medium or Low based on CPU utilization. We auto-scale cloud resources in real-time based on the predicted workload demand to reduce costs and improve application performance. The experimental analysis is based on TPC-C runs on MySQL containers deployed on the Google Cloud Platform. Experimental results are prosperous, demonstrating the ability of ADA-RP (i) to reduce MySQL deployment costs by 48% in a single-tenant environment, and (ii) to double the executed queries per second in a multi-tenant environment considering user’s budget requirements.

Advanced data analytics using three-stage intelligent model pipelining for containerized microservices in 5G networks and beyond

The recent rapid advancement of cloud-native networking infrastructure has leveraged the resource virtualization technology of containers to realize diverse microservice-based applications in 5G/6G networks and clouds. Containers drastically enhance the efficiency of computational resource allocation and utilization as compared to the related virtualization technology of Virtual Machines (VMs). The networking environment leveraging both VM and container mixed virtualization technologies makes the most use of them to realize a computational platform whose resources can be dynamically adjusted to a fine granularity. To continuously meet the required levels of quality of services in 5G/6G networks and clouds in that platform, an agile and autonomous data analytics system in the control plane is essential for the accurate prediction of server workloads and dynamic allocation of enough amount of computational resource. In this paper, we introduce a framework, which complies with Recommendation ITU-T Y.3177, for autonomous computational resource control and management. The framework consists of an advanced data analytics system and a resource control system. We propose an architecture for the advanced data analytics system consisting of learning and prediction components. The learning component includes a three-stage intelligent model pipelining with three cascaded machine learning models, nonlinear regression, clustering, and multiple regression. These models determine the fluctuation trends in CPU utilization, classify services with similarities in the trends, and predict the peak CPU utilization of each containerized microservice. We evaluate the proposed models through experiments and numerical analysis. The results prove that the models support agile data analytics, which can complete data processing in the time granularity of seconds and achieve higher prediction accuracy of CPU utilization.

Productive Asset Management Methodology Technique in Virtual Machines to Increase CPU Utilization

One of the technologies with the quickest growth is cloud computing, which is utilized in many applications where customers can access virtual machines (VMs) that are offered by cloud service providers in data centers. The ideal distribution should meet both the needs of users and service providers. A2OA, an adaptive Archimedes optimization algorithm, is the suggested mechanism for allocating resources in cloud computing. The optimization problem will be solved and user tasks will be distributed using this adaptive approach. The adaptive approach will combine the Seagull Optimization Algorithm with the Archimedes Optimization Algorithm (AOA) (SOA). The update procedure in the AOA will be improved. in cooperation with the SOA. The tasks will be distributed to the user optimally based on the proposed A2OA. In MATLAB, the suggested methodology will be put into practice, and results will be examined. Performance metrics such make span, load standard deviation, load ratio, user provider satisfaction level, response time, and convergence analysis will be used to assess how well the suggested methodology performs. The suggested approach will be contrasted with the traditional approaches, including the Genetic Algorithm (GA), Particle Swarm Algorithm (PSO), and Whale Optimization Algorithm (WOA), respectively. Key Word: Virtual machines, adaptive Archimedes optimization algorithm (A2OA), Seagull Optimization Algorithm (SOA), Genetic Algorithm (GA), maximum power, load ratio

Energy-Efficient Virtual Machine Migration Algorithm in Data Centers

The issue of data center power consumption is becoming increasingly serious. One of the most effective techniques for increasing resource utilization and lowering power consumption is virtual machine consolidation. This paper proposes a threshold-based energy-efficient and SLA-aware algorithm for virtual machine migration and consolidation. Based on statistics and analysis of historical virtual machine status, the algorithm dynamically obtains the upper CPU utilization threshold of the physical servers and identifies whether to perform the virtual machine migration, so as to reduce the number of active hosts to save energy. The experimental results demonstrate that the proposed algorithm has better comprehensive performance. When compared to the existing algorithm, our method can effectively decrease energy consumption and SLA violations.

Task Load and Work Property-Based Virtual Machine Dispatching Algorithm

This research proposes a virtual machine dispatching algorithm that takes into account the task load and work property of a virtual machine. The algorithm utilizes an interruption monitoring module to assess the interruption frequency of the virtual machine and determine whether it belongs to a CPU-dense or I/O-dense type. Additionally, a CPU monitoring module tracks the current CPU utilization rate to monitor the task load. By considering the historical information within a specified time range, the algorithm calculates a dispatching time segment for the virtual machine and notifies the dispatcher to update the time segment. The dispatcher module adjusts the credit value dispatcher based on inputs from the monitoring and CPU modules. It applies different dispatching time segments to virtual machines with varying work properties, aiming to reduce I/O request delays, provide sufficient time for I/O request handling, and minimize additional overhead. Notably, the modifications occur within the virtual machine monitor, ensuring practicality and adaptability.

F-FNC: Privacy concerned efficient federated approach for fake news classification

Fake news and manipulated information affect the social, economic and emotional growth of the world's population.For the identification of fake news, several classification systems are available, but no such system was found fast, secure and reliable as per the need of the hour. In this work, an efficient framework based on the federated architecture for the classification of fake news was proposed, while maintaining the data privacy constraints for sensitive text news datasets. The proposed federated-Fake New Classification (f-FNC) framework utilized the distributed client–server architecture with data privacy of all client or connected edge devices. For the testing and evaluation of the proposed f-FNC framework, the non-identical data was gathered from several online resources and was disseminated in a pre-processed format. To test the validity of federated deep learning models, the experiments were performed under various scenarios such as traditional learning, federated learning single client, and federated learning multi-clients. The performance of f-FNC framework was evaluated through various computational parameters such as accuracy and loss validation along with available resource parameters including CPU and RAM utilization. It was observed from the resultant outcome that the proposed f-FNC framework worked significantly well in both single-client and multi-client (N-clients) scenarios in comparison to traditional distributed deep learning based classifiers. The additional features of low cost and data-privacy of edge devices with limited resources made this proposed framework unique and the best alternative to existing fake news classifier tools.

A Countermeasure for Double Spending Attacks on Blockchain Technology in Smart Grid

As a distributed technology, blockchain has been applied in many fields. Much research has been done on its inherent security issues. Among these security issues, double spending is one of the most pernicious. Current countermeasures are not systematic, they either focus on monitoring or detection with no effective strategy to prevent future double spending. These countermeasures also have serious drawbacks, such as high network traffic, high CPU utilization, and heavy management overhead. In this paper, we present a systematic approach to address double spending attack on smart grid. A reputable node is selected, which constantly compares all transactions in current time window with previously validated block and current block. Upon discovering conflicting transactions, a warning message with the conflicting transaction and two penalty transactions are broadcasted to the network to stop the current attack and to prevent future attacks. Our experiment has demonstrated our design is highly effective to detect double spending, with short detection time and low CPU utilizations.