Computational Power Research Articles

Efficient virtual machine placement in cloud computing environment using BSO-ANN based hybrid technique

Cloud computing has revolutionized the way businesses and individuals access and utilize computing resources. Efficient virtual machine placement is a critical aspect of optimizing resource utilization, reducing operational costs, energy consumption, service level agreement and minimum virtual machine migrations, execution time, and ensuring the overall performance of cloud services. This manuscript introduces a novel approach that combines the creative problem-solving capabilities of brainstorming with the computational power of Artificial Neural Networks (ANN) to address the virtual machine placement problem in cloud environments. In this study, we propose a hybrid technique that leverages the collective intelligence of human brainstorming to generate a diverse set of placement strategies. These strategies are then evaluated, refined, and optimized using an ANN model trained on historical cloud resource allocation workload logs. By integrating the human creative process with the data-driven predictive capabilities of ANN, our approach aims to overcome the limitations of traditional virtual machine placement algorithms, which often struggle to adapt to dynamic workloads and changing resource requirements. The manuscript provides a detailed description of the hybrid technique, including the process of brainstorming for generating placement strategies, data collection and preprocessing, ANN model development, and the integration of these components into an efficient placement system. We present experimental results demonstrating the effectiveness of our approach in optimizing resource allocation, improving service performance, and optimizing resource utilization, reducing energy consumption, service level agreement and minimum virtual machine migrations, reducing execution time compared to existing static, and meta-heuristic methods. The proposed Brain Storming with ANN based Hybrid Technique offers a promising solution for enhancing the efficiency of virtual machine placement in cloud computing environments. BSO-ANN outperforms the existing techniques using performance metrics (energy consumption(Kwh), execution time(ms), SLA violations, and number of migrations). It combines human ingenuity with data-driven insights to adapt to the ever-changing dynamics of cloud workloads. This manuscript contributes to the ongoing research in cloud resource management, offering a practical approach for cloud service providers and organizations to better utilize their resources and enhance the overall quality of cloud-based services. © 2012 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Global Science and Technology Forum Pte Ltd.

Predicting the sample size of randomized controlled trials using natural language processing.

Extracting the sample size from randomized controlled trials (RCTs) remains a challenge to developing better search functionalities or automating systematic reviews. Most current approaches rely on the sample size being explicitly mentioned in the abstract. The objective of this study was, therefore, to develop and validate additional approaches. 847 RCTs from high-impact medical journals were tagged with 6 different entities that could indicate the sample size. A named entity recognition (NER) model was trained to extract the entities and then deployed on a test set of 150 RCTs. The entities' performance in predicting the actual number of trial participants who were randomized was assessed and possible combinations of the entities were evaluated to create predictive models. The test set was also used to evaluate the performance of GPT-4o on the same task. The most accurate model could make predictions for 64.7% of trials in the test set, and the resulting predictions were equal to the ground truth in 93.8%. GPT-4o was able to make a prediction on 94.7% of trials and the resulting predictions were equal to the ground truth in 90.8%. This study presents an NER model that can extract different entities that can be used to predict the sample size from the abstract of an RCT. The entities can be combined in different ways to obtain models with different characteristics. Training an NER model to predict the sample size from RCTs is feasible. Large language models can deliver similar performance without the need for prior training on the task although at a higher cost due to proprietary technology and/or required computational power.

Piezoelectric Shunt Damping for a Planar Motor Application under Cryogenic Conditions

For several decades, Moore’s law has driven the semiconductor industry, with computational power and production costs as the main drivers. Such drivers have enabled several technological innovations in the mechatronics and dynamics architecture of photolithography machines, used for semiconductor circuits manufacturing. Among current investigations, the use of superconductive magnets would enable higher accelerating stages and, thus, higher throughput and lower manufacturing costs. However, this involves a complex magnet structure that needs to operate at cryogenic temperatures and mechanical resonances at relatively low frequencies as a result of the thermal architecture of the system. The damping options are also limited due to the very low temperature. This paper explores the use of shunted piezoelectric transducers for damping the internal modes of the magnet mass. A classical resistive and inductive RL shunt is considered. The study was conducted both numerically and experimentally on a demonstrator of a superconductive magnet plate concept, where piezoelectric transducers are incorporated to support the superconducting coils. The study demonstrates the effectiveness of piezoelectric shunts as a damping solution at very low temperatures, with limited impact of the temperature variation on the performance.

SOD‐YOLO: Small Object Detection Network for UAV Aerial Images

With the rapid development of the UAV industry, object detection using UAV has become a research hotspot. However, most current object detection models based on deep learning have large parameter counts and are difficult to deploy on embedded devices with limited memory and computational power. To address this problem, a Small Object Detection network for UAV aerial images SOD‐YOLO based on YOLOv8 is proposed, which can meet the application requirements of resource‐constrained devices while ensuring the detection accuracy. First, cross‐domain fusion attention (CDFA) mechanism is proposed to build the C2f‐Attention module in this paper, which is embedded in the backbone network in order to improve the extraction capability of key object features. Meanwhile, the AIFI_LSPE feature fusion module with improved RT‐DETR and the IoU‐aware query selection mechanism are added to the path aggregation network to improve the accuracy of multi‐scale object detection. In addition, in order to balance the sample size ratio and improve the robustness of the network model, we make a new UAV image dataset named VisDrone2019 Extended Edition (VDEE) using images from the VisDrone2019 and UAVDT public datasets. Finally, Shape‐IoU is used as a loss function to reduce the difference between the object GT frame and the detection frame. Experiments show that SOD‐YOLO has a mAP@0.5 of 42.8% in the VDEE dataset, which is increased by 5.1% over YOLOv8. In the VisDrone2019 dataset mAP@0.5 is 39.2%, an improvement of 5.8% over YOLOv8. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

The Evolution of Data Centers in the Age of AI

This article explores the evolving landscape of data centers in the era of artificial intelligence (AI). It examines the exponential growth of the global data center market, driven by increasing data generation and AI adoption. The article discusses key technological developments in data centers, including enhanced operational efficiency through AI-powered systems, specialized hardware for AI workloads, advanced cooling technologies, and sustainability initiatives. It also delves into future prospects, such as increased capacity for complex AI tasks, real-time processing of massive datasets, and further improvements in energy efficiency. The symbiotic relationship between AI and data centers is highlighted, emphasizing how this transformation is reshaping digital infrastructure to meet unprecedented demands for computational power and data processing while striving for sustainability.

Pan-genome-scale metabolic modeling of Bacillus subtilis reveals functionally distinct groups.

As the volume of genomic data and computational power have increased, so has the number of genome-scale metabolic models. These models encapsulate the totality of metabolic functions for a given organism. Bacillus subtilis strain 168 is one of the first bacteria for which a metabolic network was reconstructed. Since then, several updated reconstructions have been generated for this model microorganism. Here, we expand the metabolic model for a single strain into a pan-genome-scale model, which consists of individual models for 481 B. subtilis strains. By evaluating differences between these strains, we identified five distinct groups of strains, allowing for the rapid classification of any particular strain. Furthermore, this classification into five groups aids the rapid identification of suitable strains for any application.

GPU implementation of a fast active noise control algorithm with multiple reference signals

Traditional active noise control (ANC) systems are mostly implemented on digital signal processor (DSP). Due to the inadequate computational power of the DSP, especially in applications with multiple reference signals, the DSP is unable to update the optimal control filter for different types of noise. Hence, Graphics Processing Unit (GPU) has been incorporated to the ANC system to enhance its computational power. In this work, a DSP-CPU-GPU computing architecture is adopted to improve the computational performance of the ANC system and ensure the real-time signal processing. In addition, a fast ANC algorithm on the GPU is employed to update the control filters to handle different reference signals. Finally, the effectiveness of the method is verified by experiments in the condition of multiple reference signals.

Accelerated iterative DG finite element solvers for large-scale time-harmonic acoustic problems

Finite element methods are widely used to solve time-harmonic wave propagation problems, but solving large cases can be extremely difficult even with the computational power of parallel computers. In this work, the linear system resulting from the finite element discretization is solved with iterative solution methods, which are efficient in parallel but can require a large number of iterations. In standard discontinuous Galerkin (DG) methods, the numerical solution is discontinuous at the interfaces between the elements. In hybridizable DG methods, additional unknowns are introduced at the interfaces between the finite elements, and the physical unknowns are eliminated from the global system, resulting in a hybridized system. We have recently proposed a new strategy, called CHDG, where the additional unknowns correspond to transmission variables, whereas in the standard approach they are numerical fluxes. This strategy improves the properties of the hybridized system for faster iterative solution procedures. In this talk, we present and study a 3D CHDG implementation with nodal finite element basis functions. The resulting scheme has properties amenable to efficient parallel computing. Numerical results are presented to validate the method, and preliminary 3D computational results are proposed.

Hybrid quantum annealing decomposition framework for unit commitment

Quantum computing is an emerging and promising technology that has overwhelming quantum advantages compared to its classical counterparts. Unit commitment (UC) is a critical issue in the power system, and it becomes more challenging with the integration of intermittent renewable energy. Therefore, this paper proposes an innovative decomposition and coordination optimization framework to accelerate the solution of UC, in which the interaction between an adiabatic quantum computer and a classical computer is designed to harness the immense computational power of quantum computers effectively. First, decomposition methods considering the requirements of quantum computers are introduced to decompose UC into small-scale models. Then, the paper presents a quadratic unconstrained binary optimization modeling method to transform UC problems into the form of quantum computing. Furthermore, due to the limitations of quantum computing resources, a reductive variable technique is proposed to reduce the number of slack variables in the optimization model and ensure that it remains feasible for quantum computers. Case studies conducted in test systems with a quantum annealing simulator and a real quantum annealing computer illustrate the feasibility and effectiveness of the method and demonstrate its potential in the era of quantum computing.

AN ANALYSIS OF APACHE SPARK AND GPU PERFORMANCES ON DATABASE SQL QUERIES FOR DISTRIBUTED NETWORKS

The use of GPU in different fields and its successful results initiate efforts to use GPU in database systems. It is also effective in distributed systems and computer networks in that accelerates computational tasks by leveraging parallel processing capabilities across multiple nodes and for tasks that require high computational power, such as network traffic analysis and real-time data processing. Digital transformation in all areas of life has led to the emergence of needs such as increased data diversity and faster data analysis. Upgrading the hardware capacity of the system or software-based studies are possible solutions to analyze this data for meeting the needs. In this study, Apache Spark and GPU performance differences are examined in commonly used SQL queries on big data. In this context, SQL queries such as grouping, sorting, and filtering, which are commonly used in data analysis, are used. While the queries performed with the GPU showed similar results in simple queries compared to the queries performed with Apache Spark, the GPU was completed 3x faster in queries requiring calculation.

A novel Real-time Control System for next generation gravitational-wave detectors

This contribution presents the INFN Pisa group research and development efforts aimed at defining and implementing a novel Real-time Control System (RCS) for next-generation interferometers, focusing on the initial phase of the Einstein Telescope (ET) gravitational wave detector. The RCS handles complex closed-loop systems, managing data collection from sensing elements, processing and actuator control within well defined time constraints. It integrates multiple spatially distributed control units, facilitating communications among them, with external systems as well as with users. Two distinct hardware approaches are explored: “Katane” and “Zancle”. These systems primarily differ in their core processing elements. The “Katane” system is built on powerful DSP processor boards, based on the Super-Attenuator control system, developed at INFN Pisa for Advanced Virgo detector. It uses the MicroTCA.4 architecture standard, ensuring flexibility, easy maintenance, and fast data exchange among the various custom modules, including several types of Front-End data converter boards, FPGA-based pre-processing boards, DSPs and standard processors. On the other hand, ”Zancle” explores GPU-based processing, aiming to use cost-effective consumer market systems and to leverage substantial computational power of these devices, also incorporating machine learning algorithms.

Collaborative resource allocation in computing power networks: A game-theoretic double auction perspective

The growth of global data is increasing exponentially, leading to a greater demand for computing power. To address this requirement, expanding computing power from the cloud to the edge is essential. However, this transformation presents two significant challenges: how to share computing resources more efficiently and how to optimize resource allocation. To tackle these challenges, we propose a three-layer Computing Power Network (CPN) framework that focuses on implementing the collaborative allocation of computing nodes and user tasks. We formulate the resource allocation problem in CPN as a double auction game and use an experience-weighted attraction algorithm that enables participants to adjust bidding strategies based on environmental interactions. We implemented a prototype of our proposed CPN framework and conducted extensive experiments to verify our algorithm’s convergence and evaluate the benefits obtained by buyers (users) and sellers (computing nodes) from the perspective of transaction prices, rewards, and average pricing. The comprehensive experimental results demonstrate the effectiveness of our proposed method. Compared with state-of-the-art pricing strategies, our approach achieves a 20% increase in convergence speed and an 88% increase in overall returns. Furthermore, it also exhibits a 2.5% increase in deal prices and a substantial 83% rise in the income of individual users. These outcomes convincingly prove the superiority of our method in achieving better convergence, improving overall returns, and benefiting both buyers and sellers in the CPN resource auction market.

Performance analysis and evaluation of postquantum secure blockchained federated learning

As the field of quantum computing progresses, traditional cryptographic algorithms such as RSA and ECDSA are becoming increasingly vulnerable to quantum-based attacks, underscoring the need for robust post-quantum security in critical systems like Federated Learning (FL) and Blockchain. In light of this, we propose a novel hybrid approach for blockchain-based FL (BFL) that integrates a stateless signature scheme, such as Dilithium or Falcon, with a stateful hash-based scheme like XMSS. This combination leverages the complementary strengths of both schemes to provide enhanced security. To further optimize performance, we introduce a linear formula-based device role selection method that takes into account key factors such as computational power and stake accumulation. This selection process is reinforced by a verifiable random function (VRF), which strengthens the blockchain consensus mechanism. Our extensive experimental results demonstrate that this hybrid approach significantly enhances both the security and efficiency of BFL systems, establishing a robust framework for the integration of post-quantum cryptography as we transition into the quantum computing era.

SWQC: Efficient sequencing data quality control on the next-generation sunway platform

Sequencing data quality control can significantly prevent low-quality data from impacting downstream applications in bioinformatics. The enormous growth of biological sequencing data in recent years introduces new challenges to the efficiency of quality control processes and motivates the need for fast implementations on modern compute systems. The powerful next-generation heterogeneous Sunway platform holds significant potential for addressing this challenge. However, there are currently no dedicated quality control applications that can fully utilize its computational power. To bridge this gap, we introduce SWQC, a novel quality control application specifically designed for the Sunway platform. We present an efficient distributed FASTQ I/O framework for Sunway-based workstations and supercomputers to take advantage of fast SSDs and the parallel file system. In order to support both process-level and thread-level (CPE-level) parallelism to leverage the computational power, we refactor and optimize all standard quality control modules for the heterogeneous Sunway architecture. When using a single node, SWQC achieves speedups between 2 and 40 over highly optimized quality control applications executed on a high-end 48-core AMD server. Additionally, when using 16 nodes, SWQC achieves parallel efficiencies of 70% (for reading and writing a single file) and 95% (for reading one file and writing split files) compared to a single node. Overall, SWQC is able to perform quality control operations for a 140GB FASTQ file within only 70 s using a single Sunway node. It is publicly available at https://github.com/RabbitBio/SWQC.

Model risk management in stress testing: The road up to here

This paper reviews the historical evolution of the quantitative models, model usage and model risk management (MRM) in large US banks since the 1980s. It comments on the most significant model-related events through this period. Some of these events were associated with contexts of great stress to the financial system. The paper identifies the main features of modelling in finance and economics that distinguish it from its application in the natural sciences. Then it presents the different types of models used in the large banks' stress testing programmes, the specific characteristics and risks of each type of model and the best practices for the implementation of sound model risk management, and it suggests a proper way to interpret the results of stress testing and capital assessment in the presence of model risks. The paper discusses the future evolution of MRM towards the implementation of a `fully fledged risk management framework` along the lines of other risk management disciplines, including risk identification, measurement, monitoring, reporting, limiting and capitalisation. It acknowledges the enhancements and opportunities offered by advances in the use of artificial intelligence and machine learning as well as increases in computational power. The paper concludes by noting that the model risk management framework that has been enforced by the Federal Reserve's stress testing and capital planning programmes has substantially strengthened the capital position, profitability and resilience of the large banks in the US.

ScRNAbox: empowering single-cell RNA sequencing on high performance computing systems

BackgroundSingle-cell RNA sequencing (scRNAseq) offers powerful insights, but the surge in sample sizes demands more computational power than local workstations can provide. Consequently, high-performance computing (HPC) systems have become imperative. Existing web apps designed to analyze scRNAseq data lack scalability and integration capabilities, while analysis packages demand coding expertise, hindering accessibility.ResultsIn response, we introduce scRNAbox, an innovative scRNAseq analysis pipeline meticulously crafted for HPC systems. This end-to-end solution, executed via the SLURM workload manager, efficiently processes raw data from standard and Hashtag samples. It incorporates quality control filtering, sample integration, clustering, cluster annotation tools, and facilitates cell type-specific differential gene expression analysis between two groups. We demonstrate the application of scRNAbox by analyzing two publicly available datasets.ConclusionScRNAbox is a comprehensive end-to-end pipeline designed to streamline the processing and analysis of scRNAseq data. By responding to the pressing demand for a user-friendly, HPC solution, scRNAbox bridges the gap between the growing computational demands of scRNAseq analysis and the coding expertise required to meet them.

Post-quantum XML and SAML Single Sign-On

Extensible Markup Language (XML) is one of the most popular serialization languages. Since many security protocols are built using XML, it also provides cryptographic functionality. A central framework in this area is the Security Assertion Markup Language (SAML). This standard is one of the most widely used options for implementing Single Sign-On (SSO), which allows users to authenticate to different service providers using the credentials from a single identity provider. Like all other security protocols currently in use, the security and privacy of XML-based frameworks such as SAML is threatened by the development of increasingly powerful quantum computers. In fact, future attackers with access to scalable quantum computers will be able to break the currently used cryptographic building blocks and thus undermine the security of the SAML SSO to illegally access sensitive private information. Post-quantum cryptography algorithms have been developed to protect against such quantum attackers. While many security protocols have been migrated into the quantum age by using post-quantum cryptography, no such solutions for XML and the security protocols based on it have been developed, let alone tested. We make the following contributions to fill this gap. We have designed post-quantum solutions for the cryptographic building blocks in XML and integrated them into the SAML SSO protocol. We implemented our solutions in the OpenSAML, Apache Santuario, and BouncyCastle libraries and extensively tested their performance for various post-quantum instantiations. As a result, we have created a comprehensive and solid foundation for post-quantum XML and post-quantum SAML SSO migration.

Synthetic Image Generation Using Deep Learning: A Systematic Literature Review

ABSTRACTThe advent of deep neural networks and improved computational power have brought a revolutionary transformation in the fields of computer vision and image processing. Within the realm of computer vision, there has been a significant interest in the area of synthetic image generation, which is a creative side of AI. Many researchers have introduced innovative methods to identify deep neural network‐based architectures involved in image generation via different modes of input, like text, scene graph layouts and so forth to generate synthetic images. Computer‐generated images have been found to contribute a lot to the training of different machine and deep‐learning models. Nonetheless, we have observed an immediate need for a comprehensive and systematic literature review that encompasses a summary and critical evaluation of current primary studies' approaches toward image generation. To address this, we carried out a systematic literature review on synthetic image generation approaches published from 2018 to February 2023. Moreover, we have conducted a systematic review of various datasets, approaches to image generation, performance metrics for existing methods, and a brief experimental comparison of DCGAN (deep convolutional generative adversarial network) and cGAN (conditional generative adversarial network) in the context of image generation. Additionally, we have identified applications related to image generation models with critical evaluation of the primary studies on the subject matter. Finally, we present some future research directions to further contribute to the field of image generation using deep neural networks.

VG-CALF: A vision-guided cross-attention and late-fusion network for radiology images in Medical Visual Question Answering

Image and question matching is essential in Medical Visual Question Answering (MVQA) in order to accurately assess the visual-semantic correspondence between an image and a question. However, the recent state-of-the-art methods focus solely on the contrastive learning between an entire image and a question. Though contrastive learning successfully model the global relationship between an image and a question, it is less effective to capture the fine-grained alignments conveyed between image regions and question words. In contrast, large-scale pre-training poses significant drawbacks, including extended training times, handling substantial data volumes, and necessitating high computational power. To address these challenges, we propose the Vision-Guided Cross-Attention based Late Fusion (VG-CALF) network, which integrates image and question features into a unified deep model without relying on pre-training for MVQA tasks. In our proposed approach, we use self-attention to effectively leverage intra-modal relationships within each modality and implement vision-guided cross-attention to emphasize the inter-modal relationships between image regions and question words. By simultaneously considering intra-modal and inter-modal relationships, our proposed method significantly improves the overall performance of MVQA without the need for pre-training on extensive image-question pairs. Experimental results on benchmark datasets, such as, SLAKE and VQA-RAD demonstrate that our proposed approach performs competitively with existing state-of-the-art methods.

Neural Machine Translation Between English And Bangla: A Philosophical Survey Observing Architectures And Performances

Neural Machine Translation (NMT) is a state of the art of machine translations that uses neural network models to translate text from one language to another. Unlike traditional machine translation methods, which rely on statistical models and rule-based systems, NMT leverages the power of deep learning, specifically using techniques such as recurrent neural networks (RNNs), long short-term memory networks (LSTMs), or more recently, transformers. Neural Machine Translation represents a significant dive forward in the field of automatic translation, leveraging the latest advancements in deep learning to deliver more accurate and natural translations. The progress in NMT has been remarkable, driven by advancements in model architectures, multilingual training, pretraining techniques, increased computational power, and the availability of vast multilingual datasets and improved evaluation metrics. These developments have collectively enhanced the quality, efficiency, and applicability of NMT systems across various languages and domains. In this article we will explore the technologies and performances of NMT between English and Bangla Language pair from its launching periods to present.