Physical Machines Research Articles

New methods to increasing efficiency for durability design of elastomeric bushings

The use of elastomers in modern road vehicles can solve many design conflicts in the development process. The prerequisite for this is a detailed calculability of the component properties, which are dependent on the geometric shape, the choice of material and the parameters of the manufacturing process. A robust method for calculating parameter-property relationships of elastomer bushings based on physical models and machine learning approaches allows these relationships to be calculated in the early phases of vehicle development. Viscoelastic material properties represent a major challenge for the durability design of elastomer components in load data acquisition. With the help of the modeling approaches developed here for load data analysis, load paths with elastomer bushings in the vehicle can be calculated much more accurately for high loads. A new method for experimental component validation is presented, which reduces the costly testing time for operational load tests by up to 85%. This method uses multi-axis block programs and achieves damage patterns comparable to the operational load test.

Towards a container-based architecture for CMS data acquisition

The CMS data acquisition (DAQ) is implemented as a service-oriented architecture where DAQ applications, as well as general applications such as monitoring and error reporting, are run as self-contained services. The task of deployment and operation of services is achieved by using several heterogeneous facilities, custom configuration data and scripts in several languages. In this work, we restructure the existing system into a homogeneous, scalable cloud architecture adopting a uniform paradigm, where all applications are orchestrated in a uniform environment with standardized facilities. In this new paradigm DAQ applications are organized as groups of containers and the required software is packaged into container images. Automation of all aspects of coordinating and managing containers is provided by the Kubernetes environment, where a set of physical and virtual machines is unified in a single pool of compute resources. We demonstrate that a container-based cloud architecture provides an acrossthe-board solution that can be applied for DAQ in CMS. We show strengths and advantages of running DAQ applications in a container infrastructure as compared to a traditional application model.

Comparative analysis of cloud resources forecasting using deep learning techniques based on VM workload traces

AbstractThe major cost of running a cloud is power consumption. Under‐utilization of resources that are kept idly on, over‐allocation of resources, and so on, are a few reasons for excessive power utilization by the data centers. So, to optimize the power consumption, future resource usage of virtual machines (VM) can be forecasted using their trace logs. Based on this prediction, excessively allocated VM resources can be freed thereby reducing the number of physical machines as well as the carbon footprint. In this work, we present a comparative study of some deep learning techniques such as multilayer perceptron (MLP), autoregressive neural network (ARNN), convolutional neural network (CNN), long short‐term memory (LSTM) network in forecasting the CPU, memory usage of many VMs. The GWA‐T‐12 Bitbrains data center dataset consisting of 1250 VMs' workload traces is used in this work. The main goal is to avoid underload/overload in VMs which occurs sometimes while trying to optimize resource allocation. We achieved a maximum of 98% accuracy in future resource requirement forecasting. Among all models, MLP attained the highest accuracy.

Dynamic Cloud Resource Allocation: A Broker-Based Multi-Criteria Approach for Optimal Task Assignment

Cloud brokers and service providers are concerned with utilizing available resources to maximize their profits. On the other hand, customers seek the best service provider/resource to provide them with maximum satisfaction. One of the main concerns is the variability of available service providers on the cloud, their capabilities, and the availability of their resources. Furthermore, various criteria influence the effective assignment of a task to a virtual machine (VM) before it is, in turn, submitted to the physical machine (PM). To bring cloud service providers (CSPs) and customers together, this study proposes a broker-based mechanism that measures the tendency of each customer’s task. Then, the proposed mechanism assigns all tasks—in prioritized order of importance—to the best available service provider/resource. The model acquires the importance of each task, CSP, or resource by extracting and manipulating the evaluations provided by decision makers and by adopting a multi-criteria decision-making (MCDM) method. Thus, a partial result of the proposed mechanism is a defined and prioritized pool for each of the tasks, CSPs, and resources. Various MCDM methods are examined and compared to validate the proposed model, and experiments show the applicability of the various methods within the model. Furthermore, the results of the experiments verify the suitability and applicability of the proposed model within the cloud environment.

Integrating physical model-based features and spatial contextual information to estimate building height in complex urban areas

Building height, as an essential measure of urban vertical structure, is key to understanding how urbanization is reshaping inner-city characteristics, particularly in developing countries. However, estimating building height in urban environments remains challenging. Building height estimation with physical model-based feature approaches and machine learning approaches are limited by a constrained large-scale application capability and the lack of physical significance, respectively. In this study, we proposed a two-step method to estimate building height in spatially heterogeneous urban areas by integrating the merits of machine learning approaches and physical model-based features, together with spatial contextual information. First, we trained a block-level machine learning model on Hangzhou block units to estimate average block-level building height as spatial contextual information. Second, we trained a building-level machine learning model to estimate the final building height of Hangzhou with the estimated spatial contextual information and additional physical model-based features, including radar look angle, building wall orientation, the length of the building, and dielectric constants of the building wall. Our results showed that the proposed method can largely improve the performance of building height estimation, with an overall R2 and RMSE of 0.76 and 6.64 m, respectively. Incorporating physical model-based features and spatial contextual information reduced model RMSE by 32 %. Compared with existing methods, our proposed model demonstrated a better accuracy performance and improved capability in addressing the prevailing overestimation of low-rise buildings and the underestimation of high-rise buildings in highly heterogeneous urban areas.

Unavailability-aware allocation of backup resources considering failures of virtual and physical machines

Cloud service providers widely use virtual machines and bring various benefits for customers and themselves. The unavailability of virtual machines is a crucial performance indicator for cloud service quality. However, no previous works studied the unavailability-aware backup allocation considering the failures of both virtual and physical machines. This paper proposes a backup allocation model considering these failures to minimize the maximum unavailability among virtual machines. We use a Markov chain and analyze the state transitions of the proposed model. We establish how to analytically compute the unavailability in the proposed model by solving the equilibrium-state equations formulated from the state transitions. We introduce a heuristic algorithm to solve the optimization problem of backup allocation. Numerical results show that the proposed model reduces the maximum unavailability by 7.5–28.2% compared to baseline models. Our study establishes a fundamental analytical way to calculate unavailability in the proposed model, which handles the failures of both virtual and physical machines.

Hybrid trust-based optimized virtual machine migration for dynamic load balancing and replica management in heterogeneous cloud

Cloud computing is an upcoming technology that has garnered interest from academic as well as commercial domains. Cloud offers the advantage of providing huge computing capability as well as resources that are positioned at multiple locations irrespective of time or location of the user. Cloud utilizes the concept of virtualization to dispatch the multiple tasks encountered simultaneously to the server. However, allocation of tasks to the heterogeneous servers requires that the load is balanced among the servers. To address this issue, a trust based dynamic load balancing algorithm in distributed file system is proposed. Load balancing is performed by predicting the loads in the physical machine with the help of the Rider optimization algorithm-based Neural Network (RideNN). Further, load balancing is carried out using the proposed Fractional Social Deer Optimization (FSDO) algorithm, where the virtual machine migration is performed based on the load condition in the physical machine. Later, replica management is accomplished for managing the replica in distributed file system with the help of the devised FSDO algorithm. Moreover, the proposed FSDO based dynamic load balancing algorithm is evaluated for its performance based on parameters, like predicted load, prediction error, trust, cost and energy consumption with values 0.051, 0.723, 0.390 and 0.431J correspondingly.

Vector Field-Based Volume Peeling for Multi-Axis Machining

Abstract This paper presents an easy-to-control volume peeling method for multi-axis machining based on the computation taken on vector fields. The current scalar field-based methods are not flexible and the vector field-based methods do not guarantee the satisfaction of the constraints in the final results. We first conduct an optimization formulation to compute an initial vector field that is well aligned with those anchor vectors specified by users according to different manufacturing requirements. The vector field is further optimized to be an irrotational field so that it can be completely realized by a scalar field’s gradients. Iso-surfaces of the scalar field will be employed as the layers of working surfaces for multi-axis volume peeling in the rough machining. Algorithms are also developed to remove and process singularities of the fields. Our method has been tested on a variety of models and verified by physical experimental machining.

Hotspot resolution in cloud computing: A Γ-robust knapsack approach for virtual machine migration

Cloud providers offer virtual machines (VMs) located on physical machines (PMs) to meet the increasing demand for computational services. When the instantaneous utilized capacities of VMs exceed a PM's threshold, hotspots form and degrade VM performance. To resolve hotspots, some VMs must be live migrated to other PMs, but selecting which VMs is challenging as their utilized capacities change continuously. We propose a Predicted Mixed Integer Linear Programming (MILP) Robust Solver (PMRS) that applies Γ-robustness theory to ensure PMs are hotspot-safe with a desired probability. PMRS uses a “prediction + optimization” framework that first predicts VMs' future behaviors and then formulates the problem as a Γ-robust knapsack problem (Γ-RKP) solvable with a novel MILP model. Experiments with real-trace and synthetic data demonstrate PMRS's effectiveness. Moreover, we apply PMRS in a real production environment in Huawei Cloud, and observe significant benefits in resolving existing hotspots and 94%+ potential future hotspots with minimal migration cost.

Agile digital machine development

In mechatronic machine design and development, it is no longer enough to think about machine functionality and integration as machines are increasingly digitalized. Virtual upgrades are being made to manufacturing systems to keep up with the need for faster product cycles, higher quality, and the introduction of Industry 4.0 technologies. The design and development of new mechatronic discrete manufacturing machines (MDMM) should thus include these characteristics in their design. However, most machine builders do not have the capabilities and resources to do virtual engineering (VE) at the required level, which means these machines are made with limitations or sometimes without their virtual counterparts. Reusable VE MDMM modularization allows machine builders to obtain these competencies quickly and with fewer resources. This research proposes developing adaptable digital twins (DT) by modularizing all virtual and physical mechatronic machine aspects. DTs are well-explored in literature, but re-engineering them requires massive resources and is often unviable. We introduce a new DT-based approach that allows machine builders to quickly re-engineer, adapt, and test machines, given its modular confined approach. Although VE on different abstraction levels still must be developed, confined modularization allows hiding the complexity into modules rather than addressing the entire machine simultaneously. Building machines through modularization is thus an investment, as machine builders and other stakeholders will be able to use and reuse them later for other machines, reducing the overall resources that go into the development. The paper shows how to develop adaptable DT machines using Siemens tools related to virtual engineering.

VT-IO: A Virtual Time System Enabling High-fidelity Container-based Network Emulation for I/O Intensive Applications

Network emulation allows unmodified code execution on lightweight containers to enable accurate and scalable networked application testing. However, such testbeds cannot guarantee fidelity under high workloads, especially when many processes concurrently request resources (e.g., CPU, disk I/O, GPU, and network bandwidth) that are more than the underlying physical machine can offer. A virtual time system enables the emulated hosts to maintain their own notion of virtual time. A container can stop advancing its time when not running (e.g., in an idle or suspended state). The existing virtual time systems focus on precise time management for CPU-intensive applications but are not designed to handle other operations, such as disk I/O, network I/O, and GPU computation. In this paper, we develop a lightweight virtual time system that integrates precise I/O time for container-based network emulation. We model and analyze the temporal error during I/O operations and develop a barrier-based time compensation mechanism in the Linux kernel. We also design and implement Dynamic Load Monitor (DLM) to mitigate the temporal error during I/O resource contention. VT-IO enables accurate virtual time advancement with precise I/O time measurement and compensation. The experimental results demonstrate a significant improvement in temporal error with the introduction of DLM. The temporal error is reduced from 7.889 seconds to 0.074 seconds when utilizing the DLM in the virtual time system. Remarkably, this improvement is achieved with an overall overhead of only 1.36% of the total execution time.

Backup Resource Allocation of Virtual Machines With Two-Stage Probabilistic Protection

In a cloud, protection through backup of virtual machines contained in physical machines (PMs) reduces damage to users due to failure of PMs, such as hardware malfunctions. However, from a resource cost perspective, it is necessary to reduce the amount of capacity for backup while limiting the probability of unsuccessful protection. Existing studies suggest the method of sharing backup capacity among primary resources, but the amount of capacity reduction required to protect is limited. This paper proposes a backup resource allocation model with two-stage probabilistic protection to minimize the total required backup capacity for multiple simultaneous failures of PMs. In probabilistic protection, backup resources are allocated so that the probability of backup failure does not exceed a given survivability parameter which represents the acceptable probability of backup failure. Probabilistic protection which achieves efficient sharing of backup capacity enables flexible allocation and reduces the required backup capacity. In order to increase the flexibility of backup capacity allocation, the proposed model extends the probabilistic protection to two stages. By dividing the protection into two stages, the weight of probability between stages can be adjusted, enabling more effective capacity sharing. Since it is uncertain which primary PMs fail, we apply robust optimization to the probabilistic protection. By using a table that takes into account the survivability parameter and the failure probability of PMs, the proposed model is formulated as a mixed integer linear programming problem. We prove the NP-hardness of considered problem. A heuristic is introduced to solve the optimization problem. The proposed model can reduce the total required backup capacity compared to the models with dedicated protection and one-stage probabilistic protection. The model can also provide protection in a range of survivability parameters that the model with one-stage probabilistic protection cannot satisfy.

VNF and CNF Placement in 5G: Recent Advances and Future Trends

With the growing demand for openness, scalability, and granularity, mobile network function virtualization (NFV) has emerged as a key enabler for the most of mobile network operators. NFV decouples network functions from hardware devices. This decoupling allows network services, called Virtualized Network Functions (VNFs), to be hosted on commodity hardware which simplifies and enhances service deployment and management for providers, improves flexibility, and leads to efficient and scalable resource usage, and lower costs. The proper placement of VNFs in the hosting infrastructures is one of the main technical challenges. This placement significantly influences the network’s performance, reliability, and operating costs. The VNF placement is NP-Hard. Therefore, there is a need for placement methods that can cope with the complexity of the problem and find appropriate solutions in a reasonable duration. The primary purpose of this study is to provide a taxonomy of optimization techniques used to tackle the VNF placement problems. We classify the studied papers based on performance metrics, methods, algorithms, and environment. Virtualization is not limited to simply replacing physical machines with virtual machines or VNFs, but may also include micro-services, containers, and cloud-native systems. In this context, the second part of our article focuses on the placement of Containers Network Functions (CNFs) in edge/fog computing. Many issues have been considered as traffic congestion, resource utilization, energy consumption, performance degradation, etc. For each matter, various solutions are proposed through different surveys and research papers in which each one addresses the placement problem in a specific manner by suggesting single objective or multi-objective methods based on different types of algorithms such as heuristic, meta-heuristic, and machine learning algorithms.

Improving the Scalability of Distributed Network Emulations: An Algorithmic Perspective

By deploying virtualized network elements (hosts, switches, routers, links, etc.) on clusters of commodity machines, distributed network emulations (DNE) closely mimic the behaviors of network systems and provide real-time interactions and analysis for network service management. However, DNE encounters scalability challenges when faced with large network topologies. These challenges can be boiled down to the assignment problem: to which physical machine each virtualized network element should be assigned so that the largest possible network topology can be emulated? In this paper, we tackle this problem from an algorithmic perspective. We first propose TBR (topology balancing relaxation) as the relaxation of the assignment problem. TBR tries to maintain a balance of the hardware resource consumption, by minimizing the maximum inter-machine bandwidth. We further develop TBS (topology balancing solver), which combines mathematical techniques with multi-level algorithms to solve TBR efficiently. We integrate TBR and TBS into MaxiNet, a famous distributed network emulator. Experimental results show that with the same available physical resources, TBR and TBS can improve emulation scalability by up to 4.7× compared to baselines.

A Utilization Based Genetic Algorithm for virtual machine placement in cloud systems

Due to the increasing demand for cloud computing and related services, cloud providers need to come up with methods and mechanisms that increase the performance, availability and reliability of data centers and cloud systems. Server virtualization is a key component to achieve this, which enables sharing of resources of a single physical machine among multiple virtual machines in a totally isolated manner. Optimizing virtualization has a very significant effect on the overall performance of a cloud computing system. This requires efficient and effective placement of virtual machines into physical machines. Since this is an optimization problem that involves multiple constraints and objectives, we propose a method based on genetic algorithms to place virtual machines into physical servers of a data center. By considering the utilization of machines and node distances, our method, called Utilization Based Genetic Algorithm (UBGA), aims at reducing resource waste, network load, and energy consumption at the same time. We compared our method against several other placement methods in terms of utilization achieved, networking bandwidth consumed, and energy costs incurred, using an open-source, publicly available CloudSim simulator. The results show that our method provides better performance compared to other placement approaches.

Multi-objective secure aware workflow scheduling algorithm in cloud computing based on hybrid optimization algorithm

Cloud computing provides the on-demand service of the user with the use of distributed physical machines, in which security has become a challenging factor while performing various tasks. Several methods were developed for the cloud computing workflow scheduling based on optimal resource allocation; still, the security consideration and efficient allocation of the workflow are challenging. Hence, this research introduces a hybrid optimization algorithm based on multi-objective workflow scheduling in the cloud computing environment. The Regressive Whale Water Tasmanian Devil Optimization (RWWTDO) is proposed for the optimal workflow scheduling based on the multi-objective fitness function with nine various factors, like Predicted energy, Quality of service (QoS), Resource utilization, Actual task running time, Bandwidth utilization, Memory capacity, Make span equivalent of the total cost, Task priority, and Trust. Besides, secure data transmission is employed using the triple data encryption standard (3DES) to acquire enhanced security for workflow scheduling. The method’s performance is evaluated using the resource utilization, predicted energy, task scheduling cost, and task scheduling time and acquired the values of 1.00000, 0.16587, 0.00041, and 0.00314, respectively.

Machine Learning and Physics: A Survey of Integrated Models

Predictive modeling of various systems around the world is extremely essential from the physics and engineering perspectives. The recognition of different systems and the capacity to predict their future behavior can lead to numerous significant applications. For the most part, physics is frequently used to model different systems. Using physical modeling can also very well help the resolution of complexity and achieve superior performance with the emerging field of novel artificial intelligence and the challenges associated with it. Physical modeling provides data and knowledge that offer a meaningful and complementary understanding about the system. So, by using enriched data and training phases, the overall general integrated model achieves enhanced accuracy. The effectiveness of hybrid physics-guided or machine learning-guided models has been validated by experimental results of diverse use cases. Increased accuracy, interpretability, and transparency are the results of such hybrid models. In this article, we provide a detailed overview of how machine learning and physics can be integrated into an interactive approach. Regarding this, we propose a classification of possible interactions between physical modeling and machine learning techniques. Our classification includes three types of approaches: (1) physics-guided machine learning (2) machine learning-guided physics, and (3) mutually-guided physics and ML. We studied the models and specifications for each of these three approaches in-depth for this survey.

Tweaked optimization based quality aware VM selection method for effectual placement strategy

Cloud computing has become a standard and promising distributed computing framework for the provision of on-demand computing resources and pay-per-use concepts. Operations of these computing resources result in maximum power consumption, enraged cost and high Co2 emission to the environment. The major difficulties faced when accessing cloud data center are SLA violations, increased time, less utilization of resources, high consumption of power and energy. Hence, considering these difficulties, a novel virtual machine (VM) selection approach is proposed to minimize the constraints while maintaining the SLA. First, based on the assumptions of VMs and physical machines (PMs), the overutilized hosts are detected using a static threshold approach, while underutilized hosts are identified based on the utilized resources. After load detection, the VMs that need to be migrated over other PMs are selected using the tweaked chimp optimization algorithm (TCOA). After selecting VMs without influencing the capacity of other VMs, the placement process is performed over other PMs using a power aware best fit decreasing approach. The proposed approach can greatly improve the QoS by selecting the optimal VMs that need to be migrated. Cloudsim is used as a simulation tool, and the results are compared with existing techniques in terms of migration time, energy consumption, SLA violation per host and so on to prove the superiority. The energy consumption of the proposed model is obtained to be 195.3 kWh, the overall SLA violation rate is attained to be 0.032%, and the migration time for 500 virtual machines is 8.72 s

A Novel Virtual Machine Placement Algorithm Using an Energy-Aware Meta-Heuristics Approach

The paramount concern associated with the Virtual Machine Placement (VMP) relates to the mapping of Virtual Machine (VMs) to the Physical Machine’s (PMs). This mapping goal is to utilize the PMs to their maximum potential. In order to attain the full proficiency from the mapping process it is required not to impede already active instances of Virtual machine. Incompetence in mapping process substantially results in resource wastage and increase in energy consumption and consequentially increasing the overall functional cost at the data canter. A meta-heuristic based algorithm for virtual machine placement is recommended to redress the aforementioned issues. A cr-Cuckoo algorithm is proposed which integrates the concept of correlation and Cuckoo Search. The work given here is contrasted with varied familiar algorithm of the domain. The acquired results exhibit a distinguished reduction in the consumption of power and count of migrations by VMs and violation in SLA.

HEPGA: A new effective hybrid algorithm for scientific workflow scheduling in cloud computing environment

Cloud data center comprises various physical and virtual machines, alongside storage datacenter services provided by cloud providers. Effectively mapping tasks to optimize resource utilization and load balance is essential for efficient task scheduling. This process, referred to as scheduling constraints, can significantly enhance overall efficiency. However, to harness the benefits of this scheduling, one must address the challenges arising during task execution. The interdependencies between tasks and the diverse resources available in the datacenter pose significant hurdles to efficient resource allocation. To address these challenges, this paper introduces the Hybrid HEFT-PSO-GA algorithm (HEPGA), aiming to efficiently allocate tasks to available resources across the datacenter. The HEPGA algorithm builds upon prior research by integrating the strengths of PSO (Particle Swarm Optimization) and GA (Genetic Algorithm) to optimize task scheduling in cloud computing environments. Through the fusion of PSO, GA, and HEFT-based Initialization, the algorithm strives to efficiently allocate tasks to processors, thereby minimizing the makespan. This approach capitalizes on parallel processing capabilities to further enhance resource utilization in the cloud environment. By varying the weights of the fitness function and considering the resources within the datacenter, we meticulously analyze the algorithm's performance concerning both makespan and Resource Utilization (RU). The results of these tests underscore the algorithm's consistent and robust resource utilization across diverse weight configurations, highlighting its adaptability to varying priorities. Moreover, the observed variations in makespan performance based on different weights emphasize the algorithm's potential for excellence when tailored to specific optimization goals.