Virtual Instances Research Articles

Unveiling Genetic Reinforcement Learning (GRLA) and Hybrid Attention-Enhanced Gated Recurrent Unit with Random Forest (HAGRU-RF) for Energy-Efficient Containerized Data Centers Empowered by Solar Energy and AI

The adoption of renewable energy sources has seen a significant rise in recent years across various industrial sectors, with solar energy standing out due to its eco-friendly characteristics. This shift from conventional fossil fuels to solar power is particularly noteworthy in energy-intensive environments such as cloud data centers. These centers, which operate continuously to support active servers via virtual instances, present a critical opportunity for the integration of sustainable energy solutions. In this study, we introduce two innovative approaches that substantially advance data center energy management. Firstly, we introduce the Genetic Reinforcement Learning Algorithm (GRLA) for energy-efficient container placement, representing a pioneering approach in data center management. Secondly, we propose the Hybrid Attention-enhanced GRU with Random Forest (HAGRU-RF) model for accurate solar energy prediction. This model combines GRU neural networks with Random Forest algorithms to forecast solar energy production reliably. Our primary focus is to evaluate the feasibility of solar energy in meeting the energy demands of cloud data centers that utilize containerization for virtualization, thereby promoting green cloud computing. Leveraging a robust German photovoltaic energy dataset, our study demonstrates the effectiveness and adaptability of these techniques across diverse environmental contexts. Furthermore, comparative analysis against traditional methods highlights the superior performance of our models, affirming the potential of solar-powered data centers as a sustainable and environmentally responsible solution.

Cooperative Knowledge Distillation: A Learner Agnostic Approach

Knowledge distillation is a simple but powerful way to transfer knowledge between a teacher model to a student model. Existing work suffers from at least one of the following key limitations in terms of direction and scope of transfer which restrict its use: all knowledge is transferred from teacher to student regardless of whether or not that knowledge is useful, the student is the only one learning in this exchange, and typically distillation transfers knowledge only from a single teacher to a single student. We formulate a novel form of knowledge distillation in which many models can act as both students and teachers which we call cooperative distillation. The models cooperate as follows: a model (the student) identifies specific deficiencies in it's performance and searches for another model (the teacher) who encodes learned knowledge into instructional virtual instances via counterfactual instance generation. Because different models may have different strengths and weaknesses, all models can act as either students or teachers (cooperation) when appropriate and only distill knowledge in areas specific to their strengths (focus). Since counterfactuals as a paradigm are not tied to any specific algorithm, we can use this method to distill knowledge between learners of different architectures, algorithms, and even feature spaces. We demonstrate our approach not only outperforms baselines such as transfer learning, self-supervised learning, and multiple knowledge distillation algorithms on several datasets, but it can also be used in settings where the aforementioned techniques cannot.

Development of a minimal PBPK-QSP modeling platform for LNP-mRNA based therapeutics to study tissue disposition and protein expression dynamics

Physiologically based pharmacokinetic models have gained significant recognition as effective mathematical models that enable deeper mechanistic investigation of drug delivery and tissue disposition. Here we describe the development of a platform PBPK-quantitative systems pharmacology (QSP) model to study tissue delivery of lipid nanoparticle (LNP) based mRNA therapeutics. The model is calibrated to published data in the context of Crigler-Najjar syndrome. Sensitivity analyses were performed to explore factors that influence protein expression and pharmacodynamic response following LNP-mRNA liver disposition. The most sensitive determinants of protein exposures were mRNA stability, translation, and cellular uptake rate, while the liver influx rate of lipid nanoparticle did not appreciably impact protein expression. Indeed, protein expression level may be tuned by modulation of mRNA degradation rate. However, simulations predicted that when the intrinsic half-life of the translated protein falls below a certain threshold, lowering mRNA degradation rate may not rescue protein exposure, a design feature that should be considered in optimal design of mRNA therapeutics. Additionally, interplay of LNP degradation rate and mRNA escape rate from endosomes was found to be crucial in modulation of protein expression. Simulations predicted that at a given LNP degradation rate, protein exposure varied linearly with mRNA escape rate. We further extended the model by incorporating LNP recycling to identify conditions necessary for observing a second peak in mRNA pharmacokinetics (PK). Simulations predict that with a fast recycling and slow tissue re-uptake rates, a robust second peak is observed in the plasma mRNA concentration curve. The amplitude and timing of the second peak could be tuned with recycling and re-uptake rates. Modeling results indicate that within the context of non-secreted mRNA mediated enzyme replacement therapy, recycling may depress or improve protein exposure depending on the re-uptake rate of the recycled LNP. The model is subsequently used to generate virtual animal cohorts to investigate optimal dosing and schedule of the compound. Virtual instances of the model were then employed to identify design principles that potentially reduce dosing frequency while maintaining efficacy. This study demonstrates the potential applications of coupled PBPK-QSP model for LNP based mRNA therapeutics as a translational platform.

Runtime unknown unsafe scenarios identification for SOTIF of autonomous vehicles

Safety is a critical concern for autonomous vehicles (AVs). Current testing approaches face challenges in simultaneously meeting the requirements of being valid, safe, and fast. To address these challenges, the silent testing approach that tests functions or systems in the background without interfering with driving is motivated. Building upon our previous research, this study first extends the method to specifically address the validation of AV perception, utilizing a lane marking detection algorithm (LMDA) as a case study. Second, field experiments were conducted to investigate the method’s effectiveness in validating AV systems. For both studies, an architecture for describing the working principle is presented. The efficacy of the method in evaluating the LMDA is demonstrated through the use of adversarial images generated from a dataset. Furthermore, various scenarios involving pedestrians crossing a road under different levels of criticality were constructed to gain practical insights into the method’s applicability for AV system validation. The results show that corner cases of the LMDA are successfully identified by the given evaluation metrics. Furthermore, the experiments highlight the benefits of employing multiple virtual instances with different initial states, enabling the expansion of the test space and the discovery of unknown unsafe scenarios, particularly those prone to false-positive objects. The practical implementation and systematic discussion of the method offer a significant contribution to AV safety validation.

HalfedgeCNN for Native and Flexible Deep Learning on Triangle Meshes

AbstractWe describe HalfedgeCNN, a collection of modules to build neural networks that operate on triangle meshes. Taking inspiration from the (edge‐based) MeshCNN, convolution, pooling, and unpooling layers are consistently defined on the basis of halfedges of the mesh, pairs of oppositely oriented virtual instances of each edge. This provides benefits over alternative definitions on the basis of vertices, edges, or faces. Additional interface layers enable support for feature data associated with such mesh entities in input and output as well. Due to being defined natively on mesh entities and their neighborhoods, lossy resampling or interpolation techniques (to enable the application of operators adopted from image domains) do not need to be employed. The operators have various degrees of freedom that can be exploited to adapt to application‐specific needs.

Locating Automated Parcel Lockers (APL) with known customers’ demand: a mixed approach proposal

Logistics Service Providers (LSP) are increasingly adopting Automated Parcel Lockers (APLs) to mitigate the operational pressure of last-mile logistics. The optimal location of APL stations is key for reaching customers’ demand while keeping the investment reasonable. Previous studies developed optimization algorithms and applied them to virtual instances of the problem, lacking applicability to real-life situations encountered by LSPs who aim to serve an urban area with such technology. This study proposes a novel solution to the APLs location problem by combining mixed-integer linear programming and greedy heuristics algorithms. The study tested the propose solution on real customers’ demand data related to Turin, Italy. Results show that covering 90% of the estimated potential demand requires 10 to 11 APLs, on average. The adopted approach enables finding an optimal solution grounded in a real geographical context without requiring time-consuming optimization.

Weight-Aware Cache for Application-Level Proportional I/O Sharing

Virtualization technology has enabled server consolidation where multiple servers are co-located on a single physical machine to improve resource utilization. In such systems, proportional I/O sharing is critical to meet the SLO (Service-Level Objectives) of the applications running in each virtual instance. However, previous studies focus on block-level I/O proportionality without considering the upper-layer I/O caches, which handle I/O requests on behalf of the underlying storage devices, thereby failing to achieve application-level proportional I/O sharing. To overcome this limitation, we propose a new cache management scheme, Weight-aware Cache (WaC), which reflects the I/O weights on cache allocation and reclamation. Specifically, WaC prioritizes higher-weighted applications in the lock acquisition process of cache allocation by re-ordering the lock waiting queue based on I/O weight. Additionally, WaC keeps the number of cache entries of each application proportional to its I/O weight, through weight-aware cache reclamation. To verify the efficacy of our scheme, we implement and evaluate WaC on both the page cache and bcache. The experimental results demonstrate that our scheme improves I/O proportionality with negligible overhead in various cases.

Comparison of the offer of selected cloud service providers from the point of view of implementing IT projects based on open code

The article presents a comparison of the offers of selected cloud computing providers in terms of their use in the process of developing and implementing IT services based on the idea of open source code. The conducted research concerns services provided according to the IaaS model in the form of a virtual machine lease and services provided according to the PaaS model in the form of database services. The presented analysis is both qualitative (subjective assessment) and quantitative, which consists in a series of measurements of the parameters of virtual instances. Based on this analysis, the best public cloud service provider for users starting to use cloud computing resources was selected.
 Keywords: cloud computing; IaaS service model; PaaS service model

Application of an Innovative Convolutional/LSTM Neural Network for Computing Resource Allocation in NFV Network Architectures

An innovative resource allocation framework for virtualized network environments and based on the application of Artificial Intelligence techniques is proposed and investigated. It integrates the needed processing capacity prediction procedure and the allocation one which determines the capacity under-allocation or over-allocation needed to minimize the resource allocation and Quality of Service degradation costs. The proposed solution is based on: i) a monitoring procedure in which the processing capacities required by virtual instances are periodically monitored; ii) an integrated allocation/prediction procedure in which the processing capacities to be allocated to the virtual instances are evaluated in time intervals successive to the monitoring periods. This second procedure uses a Convolutional/Long Short Term Memory neural network whose loss function is defined so as to minimize an overall cost dependent on both the cloud resource allocation and Quality of Service degradation costs. We evaluate the proposed solution in backbone and metropolitan traffic and network scenario. We show how in the traffic scenario of an Italian Mobile Operator in Milan zone, the proposed solution far outperforms the not integrated classical solution in which the capacity prediction and allocation procedures are separately performed. Furthermore its performance are very near to the one of an oracle that optimizes the capacity over/under dimensioning parameter.

Real-Time Analysis of Multiple Root Causes for Anomalies Assisted by Digital Twin in NFV Environment

Network Function Virtualization (NFV) is a promising paradigm that enables the employment of novel service types with lower deployment cost and faster time-to-value, but it introduces new fault management problems and challenges. In NFV environment, anomalies occurred in virtual machines (VMs) can be caused by faulty components of their hosting servers or anomaly propagation from other ones. If the performance of VMs degrades, we need to find out the root causes accurately, i.e., locate the exact faulty components, to recover the networks as soon as possible. In this paper, we first use digital twin to establish a virtual instance of the physical network to capture the real-time anomaly-fault dependency relationship. When the network environment changes, transfer learning is leveraged to utilize the learned knowledge of dependency relationship in historical periods to avoid huge time and computation cost of learning from scratch. Assisted by the learned dependency relationship, a dynamic set-covering (DSC) based root caused analysis problem is formulated and modeled with a set of parallel hidden Markov models to capture the dynamics of component states, which can best explain the sequence of anomalous VMs. We use alternating direction method of multipliers to decompose the DSC problem into a set of independent sub-problems and solve it in a distributed fashion. Since the state variables of each component in the DSC problem are coupled between any two successive time epochs, each sub-problem is solved by the Viterbi decoding and an incremental function is designed to construct the feasible solution that covers all anomalous VMs. Simulation results show the availability and superiority of the digital-twin assisted root cause analysis algorithm for NFV environment.

Architecting Digital Twins

In 2002, Grieves defined the concept of the digital twin as a virtual instance of physical assets capable of continuously mirroring them. Ever since then, driven by remarkable industrial attention, digital twins flourished and ripened in several sectors. The notable industrial adoption has been sided by a growing interest from the software engineering community in general and the software architecture community in particular as demonstrated by the growing number of published peer-reviewed publications and proposed software architectural solutions for digital twins. In this paper, we report on the planning, execution, and results of a systematic mapping study on architecting digital twins. The study captures crucial aspects of software architectures for digital twins as types of architectural solutions, quality attributes, and architectural patterns. It supports practitioners in creating digital twins tailored to their specific needs and researchers in identifying trends and open challenges. Starting from an initial set of potentially relevant 1630 peer-reviewed publications, we selected 140 primary studies. We analysed the set of primary studies using thorough data extraction, analysis, and synthesis process. To compensate for single method limitations and reduce possible threats to conclusion validity, we discussed the results of our study with experts in the software architecture community. Based on our results, the field of software architecture for digital twins is lively and an increasing number of architectural solutions are being proposed. Although there is a lack of widely accepted reference architectural solutions for digital twins, most of them are built using a combination of the layered and service-oriented patterns and address maintainability, performance efficiency, and compatibility quality attributes.

ELITE: An Intelligent Digital Twin-based Hierarchical Routing Scheme for Softwarized Vehicular Networks

Software-Defined Vehicular Network (SDVN) is a networking architecture that can provide centralized control for vehicular networks. However, the design for routing policies in SDVNs is generally influenced by several limitations, such as frequent topological changes, complex service requests, and long model training time. Intelligent Digital Twin-based Software-Defined Vehicular Networks (IDT-SDVN) can overcome these weaknesses and maximize the advantages of the conventional SDVN architecture by enabling the controller to construct virtual network spaces and provide virtual instances of corresponding physical objects within the Digital Twin (DT). In this paper, we propose a junction-based hierarchical routing scheme in IDT-SDVN, namely, intelligent digital twin hierarchical (ELITE) routing. The proposed scheme is conducted in four phases: policy training and generation in the virtual network, and deployment and relay selection in physical networks. First, the policy learning phase employs several parallel agents in DT networks and derives multiple single-target policies. Second, the generation phase combines the learned policies and generates new policies based on complex communication requirements. Third, the deployment phase selects the most suitable generated policy according to the real-time network status and message types. A road path is calculated by the controller based on the selected policy and then sent to the requester vehicle. Finally, the relay selection phase is utilized to determine relay vehicles in a hop-by-hop process along the selected path. Simulation results demonstrate that ELITE achieves substantial improvements in terms of packet delivery ratio, end-to-end delay, and communication overhead compared with its counterparts.

Deploying Multi-tenant FPGAs within Linux-based Cloud Infrastructure

Cloud deployments now increasingly exploit Field-Programmable Gate Array (FPGA) accelerators as part of virtual instances. While cloud FPGAs are still essentially single-tenant, the growing demand for efficient hardware acceleration paves the way to FPGA multi-tenancy. It then becomes necessary to explore architectures, design flows, and resource management features that aim at exposing multi-tenant FPGAs to the cloud users. In this article, we discuss a hardware/software architecture that supports provisioning space-shared FPGAs in Kernel-based Virtual Machine (KVM) clouds. The proposed hardware/software architecture introduces an FPGA organization that improves hardware consolidation and support hardware elasticity with minimal data movement overhead. It also relies on VirtIO to decrease communication latency between hardware and software domains. Prototyping the proposed architecture with a Virtex UltraScale+ FPGA demonstrated near specification maximum frequency for on-chip data movement and high throughput in virtual instance access to hardware accelerators. We demonstrate similar performance compared to single-tenant deployment while increasing FPGA utilization, which is one of the goals of virtualization. Overall, our FPGA design achieved about 2× higher maximum frequency than the state of the art and a bandwidth reaching up to 28 Gbps on 32-bit data width.

Virtualization-Based Digitization of a Retail Store: An Enhanced Implementation of Digital Transformation

The rise of neoteric technologies like Machine Learning, the Internet of Things, Cloud Services, etc has affected the life of a common man at various levels. Irrespective of the size or domain, almost all companies are now incorporating digitization to various degrees and thus progressing towards a new business model with little or no significance to geographical and physical barriers. This shift from traditional store models to automated entities is referred to as Digital Transformation. It is the simplified way of outlining how digital technologies are transforming and automating business operations across all organizations irrespective of their domain. This digital revolution relies on a whole range of machinery, networks, services, and operations to expand their power of communication, thus ensuring seamless integration with the technologies. At this juncture, there would be many challenges in both technical and non-technical aspects. To facilitate successful automation by resolving those issues, using the concept of virtualization can be very helpful. Virtualization is the process of creating a virtual instance of hardware resources like virtual applications, servers, or storage by logically separating them from the hardware. It enables multiple applications or operations to gain access to the hardware resources/ software resources of the host machine. In a sense, virtualization is always at the center of all this revolution providing a rock-solid foundation. For example, when digitizing an organization, machine learning algorithms are applied to the IoT data in addition to the organizational data. Given the huge size of data, companies adapting to this automation rely on cloud services for data management because of the reliability it provides. This issue is solved using the Edge Computing concept which is an advanced implementation of Virtualization. In this paper, we try to discuss such challenges and try to understand how virtualization can be useful in solving them. This can be exemplified using a hypothetical digitalization in a retail store scenario.

Effectiveness of Virtualization in the Process of Running a Virtual Instance of a Computer System in a Layer Abstracted from the Actual Hardware

Under this research paper many different kinds of viewpoints concept of Virtualizations, the use of visualization for security reasons, and the Importance of IoT in the virtualization process. Moreover, this paper will signify that Different virtual environments are offered through a virtualized IT firm, which has to be accepted and operated if technology evolves quickly. This research paper will highlight many different types of strong and sustainable viewpoints about the visualization process and its impacts. It can be a supportive way for the next researcher to understand the scope of this research paper in a proper manner. In order to conduct a proper understanding of the effect of virtualization in running a virtual instance of a computer system from actual hardware will be the main aim of this paper. On the other hand, virtualization may also be described as a technique that can theoretically divide a server's physical resources and use it as several, separated computers known as virtual machines.

An optimization method to design a skip–stop pattern for renovating operation schemes in urban railways

ABSTRACT This study deals with an optimization problem to design an A/B skip–stop pattern (A/B SSP) to renovate operation schemes in urban railways. The A/B SSP is especially useful for urban railways since the renovation does not require a restructuring of infrastructure. The renovation improves passengers’ travel time along with lost passengers owing to selective stops. This study aims to achieve two goals that are minimizing the lost passengers and the travel time during the renovation. To this end, we first present a mathematical model based on a network flow model. The model explicitly maximizes transportation volume and implicitly controls the travel time by the number of stop stations under operational constraints. As the model size is huge for railways in practice, we also propose a two-step approach to solve the model efficiently. The performance of the two-step approach is verified based on practical and virtual instances.

Orchestrating a stateful application using Operator

Containerization is a leading technological advancement in cloud-native developments. Virtualization isolates the running processes at the bare metal level but containerization isolates the processes at the operating system level. Virtualization encapsulates all the new virtual instances with a new operating system but containerization encapsulates the software only with its dependencies. Containerization avoids the problem of dependency missing between different operating systems and their distributions. The concept of containerization is old but the development of open-source tools like Docker, Kubernetes, and Openshift accelerated the adaption of this technology. Docker builds container images and Openshift or Kubernetes is an Orchestrating tool. For stateful applications, Kubernetes workload resources are not a better option to orchestrate the application, as each resource has its own identity. In such cases, the operator can be built to manage the entire life cycle of resources in the Kubernetes cluster. Operator combines human operational knowledge into software code in a systematic way. The paper discusses the default control mechanism in Kubernetes and then it explains the procedure to build the operator to orchestrate the stateful application.

A Secure File Transfer over Virtual Machine Instances using Hybrid Encryption Technique

Cloud Computing is used to share data, services, and resources via a network but this system is vulnerable to cyber-attacks by an unauthorized person denying the user privacy and confidentiality. The exponential growth in Information technology especially in the field of Cloud Computing has seen a rise in security attacks such as Interruption, Interception, Modification, Fabrication making it absolutely necessary to enhance cloud security as well as network security. To tackle the menace of security threats is to make use of the various encryption techniques and to ensure secure transmission of the data to ensure the user of his rights of Privacy, Confidentiality, Integrity, Authentication, and access controls of data. This can be achieved by Cryptographic techniques. In the former implementation, a new virtual instance is created and embedded with all the requested resources and allocated to the user whereas in the later implementation the size of the allotted VM is being altered to account for the extra requested resource or to free the unused resource to increase efficiency. To achieve Secure file transfer between instances Hypervisor tool Virtual Box developed by Oracle Corporation is used. To interface with Hypervisor via Host CLI commands provided by the Virtual Box is used. Thus, developing a model that mimics the cloud environment on small scale using the laptop/desktop which enacts a cloud with a limited resource pool.

Leveraging Data Augmentation for Service QoS Prediction in Cyber-physical Systems

With the fast-developing domain of cyber-physical systems (CPS), constructing the CPS with high-quality services becomes an imperative task. As one of the effective solutions for information overload in CPS construction, quality of service (QoS)-aware service recommendation has drawn much attention in academia and industry. However, the lack of most QoS values limits the recommendation performance and it is time-consuming for users to get the QoS values by invoking all the services. Therefore, a powerful prediction model is required to predict the unobserved QoS values. Considering the fact that most existing QoS prediction models are unable to effectively address the data-sparsity problem, a novel two-stage framework called AgQ is proposed for QoS prediction. Specifically, a data augmentation strategy is designed in the first stage to enlarge the training set by drawing additional virtual instances. In the second stage, a prediction model is applied that considers both virtual and factual instances during the training procedure. We conduct extensive experiments on the WSDream dataset to demonstrate the effectiveness of the our QoS prediction framework and verify that the data augmentation strategy can indeed alleviate the data-sparsity problem. In terms of mean absolute error, taking the Multilayer Perceptron model as an example, the maximum improvement achieves 5% under 5% sparsity.

Augmenting the Operations on Cloud Virtual Forensic Data by Employing Probabilistic Data Structures

Background: Gathering and scrutinizing the different types of logs are the vital steps in the forensic domain. Logs are commonly gathered by the cloud service providers or by some third party layers which are governed by the cloud service providers. Security of the logs is a crucial issue as the logs can be tampered accidentally or intentionally by an employee in the cloud service provider’s organization or by the forensic investigator. Objective: The algorithm designed assists in verifying the tampering of the virtual instance logs which can be accidental or intentional. Verification process confirms that the confidentiality and integrity of the logs remains intact. Verification of the potential evidence for past logs is normally carried out by the forensic investigator and the auditor. Methods: The uniqueness of the research conducted in this paper is a technique which employs the cuckoo filter, which is supportive in proving the integrity of the potential evidences for past logs at a faster pace. The probabilistic data structures cuckoo filter and the bloom filter also support the concealment of logs. Results: The implemented system and the results observed in it, are very promising in the cloud forensic domain. The performance of the algorithm is better than the earlier system implemented with the log chain and the database. Conclusion: The secure framework designed in this research paper aids in proving the integrity of the virtual instance logs. The evidence verification process supports concealment of data also.