PyTorchKR Papers

최신 논문

총 561편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.14244공식 코드 · Papers with Code

Federated Prompt Learning for Weather Foundation Models on Devices

On-device intelligence for weather forecasting uses local deep learning models to analyze weather patterns without centralized cloud computing, holds significance for supporting human activates. Federated Learning is a promising solution for such forecasting by enabling collaborative model training without sharing raw data. However, it faces three main challenges that hinder its reliability: (1) data heterogeneity among devices due to geographic differences; (2) data homogeneity within individual devices and (3) communication overload from sending large model parameters for collaboration. To address these challenges, this paper propose Federated Prompt Learning for Weather Foundation Models on Devices (FedPoD), which enables devices to obtain highly customized models while maintaining communication efficiency. Concretely, our Adaptive Prompt Tuning leverages lightweight prompts guide frozen foundation model to generate more precise predictions, also conducts prompt-based multi-level communication to encourage multi-source knowledge fusion and regulate optimization. Additionally, Dynamic Graph Modeling constructs graphs from prompts, prioritizing collaborative training among devices with similar data distributions to against heterogeneity. Extensive experiments demonstrates FedPoD leads the performance among state-of-the-art baselines across various setting in real-world on-device weather forecasting datasets.

arXiv:2305.07440

Optimizing Memory Mapping Using Deep Reinforcement Learning

Resource scheduling and allocation is a critical component of many high impact systems ranging from congestion control to cloud computing. Finding more optimal solutions to these problems often has significant impact on resource and time savings, reducing device wear-and-tear, and even potentially improving carbon emissions. In this paper, we focus on a specific instance of a scheduling problem, namely the memory mapping problem that occurs during compilation of machine learning programs: That is, mapping tensors to different memory layers to optimize execution time. We introduce an approach for solving the memory mapping problem using Reinforcement Learning. RL is a solution paradigm well-suited for sequential decision making problems that are amenable to planning, and combinatorial search spaces with high-dimensional data inputs. We formulate the problem as a single-player game, which we call the mallocGame, such that high-reward trajectories of the game correspond to efficient memory mappings on the target hardware. We also introduce a Reinforcement Learning agent, mallocMuZero, and show that it is capable of playing this game to discover new and improved memory mapping solutions that lead to faster execution times on real ML workloads on ML accelerators. We compare the performance of mallocMuZero to the default solver used by the Accelerated Linear Algebra (XLA) compiler on a benchmark of realistic ML workloads. In addition, we show that mallocMuZero is capable of improving the execution time of the recently published AlphaTensor matrix multiplication model.

arXiv:2305.06249

Deep Reinforcement Learning Based Resource Allocation for Cloud Native Wireless Network

Cloud native technology has revolutionized 5G beyond and 6G communication networks, offering unprecedented levels of operational automation, flexibility, and adaptability. However, the vast array of cloud native services and applications presents a new challenge in resource allocation for dynamic cloud computing environments. To tackle this challenge, we investigate a cloud native wireless architecture that employs container-based virtualization to enable flexible service deployment. We then study two representative use cases: network slicing and Multi-Access Edge Computing. To optimize resource allocation in these scenarios, we leverage deep reinforcement learning techniques and introduce two model-free algorithms capable of monitoring the network state and dynamically training allocation policies. We validate the effectiveness of our algorithms in a testbed developed using Free5gc. Our findings demonstrate significant improvements in network efficiency, underscoring the potential of our proposed techniques in unlocking the full potential of cloud native wireless networks.

arXiv:2305.05423

High-throughput Cotton Phenotyping Big Data Pipeline Lambda Architecture Computer Vision Deep Neural Networks

In this study, we propose a big data pipeline for cotton bloom detection using a Lambda architecture, which enables real-time and batch processing of data. Our proposed approach leverages Azure resources such as Data Factory, Event Grids, Rest APIs, and Databricks. This work is the first to develop and demonstrate the implementation of such a pipeline for plant phenotyping through Azure's cloud computing service. The proposed pipeline consists of data preprocessing, object detection using a YOLOv5 neural network model trained through Azure AutoML, and visualization of object detection bounding boxes on output images. The trained model achieves a mean Average Precision (mAP) score of 0.96, demonstrating its high performance for cotton bloom classification. We evaluate our Lambda architecture pipeline using 9000 images yielding an optimized runtime of 34 minutes. The results illustrate the scalability of the proposed pipeline as a solution for deep learning object detection, with the potential for further expansion through additional Azure processing cores. This work advances the scientific research field by providing a new method for cotton bloom detection on a large dataset and demonstrates the potential of utilizing cloud computing resources, specifically Azure, for efficient and accurate big data processing in precision agriculture.

arXiv:2305.00706공식 코드 · Papers with Code

Full Scaling Automation for Sustainable Development of Green Data Centers

The rapid rise in cloud computing has resulted in an alarming increase in data centers' carbon emissions, which now accounts for >3% of global greenhouse gas emissions, necessitating immediate steps to combat their mounting strain on the global climate. An important focus of this effort is to improve resource utilization in order to save electricity usage. Our proposed Full Scaling Automation (FSA) mechanism is an effective method of dynamically adapting resources to accommodate changing workloads in large-scale cloud computing clusters, enabling the clusters in data centers to maintain their desired CPU utilization target and thus improve energy efficiency. FSA harnesses the power of deep representation learning to accurately predict the future workload of each service and automatically stabilize the corresponding target CPU usage level, unlike the previous autoscaling methods, such as Autopilot or FIRM, that need to adjust computing resources with statistical models and expert knowledge. Our approach achieves significant performance improvement compared to the existing work in real-world datasets. We also deployed FSA on large-scale cloud computing clusters in industrial data centers, and according to the certification of the China Environmental United Certification Center (CEC), a reduction of 947 tons of carbon dioxide, equivalent to a saving of 1538,000 kWh of electricity, was achieved during the Double 11 shopping festival of 2022, marking a critical step for our company's strategic goal towards carbon neutrality by 2030.

arXiv:2304.13738

Scalable, Distributed AI Frameworks: Leveraging Cloud Computing for Enhanced Deep Learning Performance and Efficiency

In recent years, the integration of artificial intelligence (AI) and cloud computing has emerged as a promising avenue for addressing the growing computational demands of AI applications. This paper presents a comprehensive study of scalable, distributed AI frameworks leveraging cloud computing for enhanced deep learning performance and efficiency. We first provide an overview of popular AI frameworks and cloud services, highlighting their respective strengths and weaknesses. Next, we delve into the critical aspects of data storage and management in cloud-based AI systems, discussing data preprocessing, feature engineering, privacy, and security. We then explore parallel and distributed training techniques for AI models, focusing on model partitioning, communication strategies, and cloud-based training architectures. In subsequent chapters, we discuss optimization strategies for AI workloads in the cloud, covering load balancing, resource allocation, auto-scaling, and performance benchmarking. We also examine AI model deployment and serving in the cloud, outlining containerization, serverless deployment options, and monitoring best practices. To ensure the cost-effectiveness of cloud-based AI solutions, we present a thorough analysis of costs, optimization strategies, and case studies showcasing successful deployments. Finally, we summarize the key findings of this study, discuss the challenges and limitations of cloud-based AI, and identify emerging trends and future research opportunities in the field.

arXiv:2304.13379

Blockchain-based Access Control for Secure Smart Industry Management Systems

Smart manufacturing systems involve a large number of interconnected devices resulting in massive data generation. Cloud computing technology has recently gained increasing attention in smart manufacturing systems for facilitating cost-effective service provisioning and massive data management. In a cloud-based manufacturing system, ensuring authorized access to the data is crucial. A cloud platform is operated under a single authority. Hence, a cloud platform is prone to a single point of failure and vulnerable to adversaries. An internal or external adversary can easily modify users' access to allow unauthorized users to access the data. This paper proposes a role-based access control to prevent modification attacks by leveraging blockchain and smart contracts in a cloud-based smart manufacturing system. The role-based access control is developed to determine users' roles and rights in smart contracts. The smart contracts are then deployed to the private blockchain network. We evaluate our solution by utilizing Ethereum private blockchain network to deploy the smart contract. The experimental results demonstrate the feasibility and evaluation of the proposed framework's performance.

arXiv:2304.11931

Automatisation de la structuration des logs pour le Cloud Computing

Logs are a fundamental component of modern computer systems. They enable the analysis and monitoring teams to understand any abnormal or malicious behavior that may have occurred. The continuous increase in the volume of logs generated by these systems made it unsuitable for manual inspection and represents a real challenge with regard to process automation. In order to process these data, several log-structuring solutions have been developed. In this article, we analyze the capabilities of two solutions in order to meet the challenges of Cloud Computing in terms of efficiency and effectiveness. Our work focuses on the impact of parameterization and preprocessing on the performance of these methods -- two important steps as they require human intervention, which is incompatible with with the automation of the log-structuring process.

arXiv:2304.11940

MoniLog: An Automated Log-Based Anomaly Detection System for Cloud Computing Infrastructures

Within today's large-scale systems, one anomaly can impact millions of users. Detecting such events in real-time is essential to maintain the quality of services. It allows the monitoring team to prevent or diminish the impact of a failure. Logs are a core part of software development and maintenance, by recording detailed information at runtime. Such log data are universally available in nearly all computer systems. They enable developers as well as system maintainers to monitor and dissect anomalous events. For Cloud computing companies and large online platforms in general, growth is linked to the scaling potential. Automatizing the anomaly detection process is a promising way to ensure the scalability of monitoring capacities regarding the increasing volume of logs generated by modern systems. In this paper, we will introduce MoniLog, a distributed approach to detect real-time anomalies within large-scale environments. It aims to detect sequential and quantitative anomalies within a multi-source log stream. MoniLog is designed to structure a log stream and perform the monitoring of anomalous sequences. Its output classifier learns from the administrator's actions to label and evaluate the criticality level of anomalies.

arXiv:2303.15490

Research on Efficiency Analysis of Microservices

With the maturity of web services, containers, and cloud computing technologies, large services in traditional systems (e.g. the computation services of machine learning and artificial intelligence) are gradually being broken down into many microservices to increase service reusability and flexibility. Therefore, this study proposes an efficiency analysis framework based on queuing models to analyze the efficiency difference of breaking down traditional large services into n microservices. For generalization, this study considers different service time distributions (e.g. exponential distribution of service time and fixed service time) and explores the system efficiency in the worst-case and best-case scenarios through queuing models (i.e. M/M/1 queuing model and M/D/1 queuing model). In each experiment, it was shown that the total time required for the original large service was higher than that required for breaking it down into multiple microservices, so breaking it down into multiple microservices can improve system efficiency. It can also be observed that in the best-case scenario, the improvement effect becomes more significant with an increase in arrival rate. However, in the worst-case scenario, only slight improvement was achieved. This study found that breaking down into multiple microservices can effectively improve system efficiency and proved that when the computation time of the large service is evenly distributed among multiple microservices, the best improvement effect can be achieved. Therefore, this study's findings can serve as a reference guide for future development of microservice architecture.

arXiv:2303.14329

Edge-Based Video Analytics: A Survey

Edge computing has been getting a momentum with ever-increasing data at the edge of the network. In particular, huge amounts of video data and their real-time processing requirements have been increasingly hindering the traditional cloud computing approach due to high bandwidth consumption and high latency. Edge computing in essence aims to overcome this hindrance by processing most video data making use of edge servers, such as small-scale on-premises server clusters, server-grade computing resources at mobile base stations and even mobile devices like smartphones and tablets; hence, the term edge-based video analytics. However, the actual realization of such analytics requires more than the simple, collective use of edge servers. In this paper, we survey state-of-the-art works on edge-based video analytics with respect to applications, architectures, techniques, resource management, security and privacy. We provide a comprehensive and detailed review on what works, what doesn't work and why. These findings give insights and suggestions for next generation edge-based video analytics. We also identify open issues and research directions.

arXiv:2303.13525공식 코드 · Papers with Code

Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Transfer Learning

Predicting future resource demand in Cloud Computing is essential for optimizing the trade-off between serving customers' requests efficiently and minimizing the provisioning cost. Modelling prediction uncertainty is also desirable to better inform the resource decision-making process, but research in this field is under-investigated. In this paper, we propose univariate and bivariate Bayesian deep learning models that provide predictions of future workload demand and its uncertainty. We run extensive experiments on Google and Alibaba clusters, where we first train our models with datasets from different cloud providers and compare them with LSTM-based baselines. Results show that modelling the uncertainty of predictions has a positive impact on performance, especially on service level metrics, because uncertainty quantification can be tailored to desired target service levels that are critical in cloud applications. Moreover, we investigate whether our models benefit transfer learning capabilities across different domains, i.e. dataset distributions. Experiments on the same workload datasets reveal that acceptable transfer learning performance can be achieved within the same provider (because distributions are more similar). Also, domain knowledge does not transfer when the source and target domains are very different (e.g. from different providers), but this performance degradation can be mitigated by increasing the training set size of the source domain.

arXiv:2303.13493

Green Time-Critical Fog Communication and Computing

Fog computing allows computationally-heavy problems with tight time constraints to be solved even if end devices have limited computational resources and latency induced by cloud computing is too high. How can energy consumed by fog computing be saved while obeying latency constraints and considering not only computations but also transmission through wireless and wired links? This work examines the latency and energy consumption sources in fog networks and discusses models describing these costs for various technologies. Next, resource allocation strategies are discussed considering the various degrees of freedom available in such a complex system, and their influence on energy consumption and latency. Finally, a vision for a future distributed, AI-driven resources allocation strategy is presented and justified.

arXiv:2303.11198공식 코드 · Papers with Code

A set of semantic data flow diagrams and its security analysis based on ontologies and knowledge graphs

For a long time threat modeling was treated as a manual, complicated process. However modern agile development methodologies and cloud computing technologies require adding automatic threat modeling approaches. This work considers two challenges: creating a set of machine-readable data flow diagrams that represent real cloud based applications; and usage domain specific knowledge for automatic analysis of the security aspects of such applications. The set of 180 semantic diagrams (ontologies and knowledge graphs) is created based on cloud configurations (Docker Compose); the set includes a manual taxonomy that allows to define the design and functional aspects of the web based and data processing applications; the set can be used for various research in the threat modeling field. This work also evaluates how ontologies and knowledge graphs can be used to automatically recognize patterns (mapped to security threats) in diagrams. A pattern represents features of a diagram in form of a request to a knowledge base, what enables its recognition in a semantic representation of a diagram. In an experiment four groups of the patterns are created (web applications, data processing, network, and docker specific), and the diagrams are examined by the patterns. Automatic results, received for the web applications and data processing patterns, are compared with the manual taxonomy in order to study challenges of automatic threat modeling.

arXiv:2303.09045

Web and Mobile Platforms for Managing Elections based on IoT And Machine Learning Algorithms

The global pandemic situation has severely affected all countries. As a result, almost all countries had to adjust to online technologies to continue their processes. In addition, Sri Lanka is yearly spending ten billion on elections. We have examined a proper way of minimizing the cost of hosting these events online. To solve the existing problems and increase the time potency and cost reduction we have used IoT and ML-based technologies. IoT-based data will identify, register, and be used to secure from fraud, while ML algorithms manipulate the election data and produce winning predictions, weather-based voters attendance, and election violence. All the data will be saved in cloud computing and a standard database to store and access the data. This study mainly focuses on four aspects of an E-voting system. The most frequent problems across the world in E-voting are the security, accuracy, and reliability of the systems. E-government systems must be secured against various cyber-attacks and ensure that only authorized users can access valuable, and sometimes sensitive information. Being able to access a system without passwords but using biometric details has been there for a while now, however, our proposed system has a different approach to taking the credentials, processing, and combining the images, reformatting and producing the output, and tracking. In addition, we ensure to enhance e-voting safety. While ML-based algorithms use different data sets and provide predictions in advance.

arXiv:2303.01744

Next-generation Co-Packaged Optics for Future Disaggregated AI Systems

Co-packaged optics is poised to solve the interconnect bandwidth bottleneck for GPUs and AI accelerators in near future. This technology can immediately boost today's AI/ML compute power to train larger neural networks that can perform more complex tasks. More importantly, co-packaged optics unlocks new system-level opportunities to rethink our conventional supercomputing and datacenter architectures. Disaggregation of memory and compute units is one of such new paradigms that can greatly speed up AI/ML workloads by providing low-latency and high-throughput performance, while maintaining flexibility to support conventional cloud computing applications as well. This paper gives a brief overview of state-of-the-art of co-packaged optical I/O and requirements of its next generations. We also discuss ideas to exploit co-packaged optics in disaggregated AI systems and possible future directions.

arXiv:2302.13995

Architecting Peer-to-Peer Serverless Distributed Machine Learning Training for Improved Fault Tolerance

Distributed Machine Learning refers to the practice of training a model on multiple computers or devices that can be called nodes. Additionally, serverless computing is a new paradigm for cloud computing that uses functions as a computational unit. Serverless computing can be effective for distributed learning systems by enabling automated resource scaling, less manual intervention, and cost reduction. By distributing the workload, distributed machine learning can speed up the training process and allow more complex models to be trained. Several topologies of distributed machine learning have been established (centralized, parameter server, peer-to-peer). However, the parameter server architecture may have limitations in terms of fault tolerance, including a single point of failure and complex recovery processes. Moreover, training machine learning in a peer-to-peer (P2P) architecture can offer benefits in terms of fault tolerance by eliminating the single point of failure. In a P2P architecture, each node or worker can act as both a server and a client, which allows for more decentralized decision making and eliminates the need for a central coordinator. In this position paper, we propose exploring the use of serverless computing in distributed machine learning training and comparing the performance of P2P architecture with the parameter server architecture, focusing on cost reduction and fault tolerance.

arXiv:2302.05630공식 코드 · Papers with Code

CILP: Co-simulation based Imitation Learner for Dynamic Resource Provisioning in Cloud Computing Environments

Intelligent Virtual Machine (VM) provisioning is central to cost and resource efficient computation in cloud computing environments. As bootstrapping VMs is time-consuming, a key challenge for latency-critical tasks is to predict future workload demands to provision VMs proactively. However, existing AI-based solutions tend to not holistically consider all crucial aspects such as provisioning overheads, heterogeneous VM costs and Quality of Service (QoS) of the cloud system. To address this, we propose a novel method, called CILP, that formulates the VM provisioning problem as two sub-problems of prediction and optimization, where the provisioning plan is optimized based on predicted workload demands. CILP leverages a neural network as a surrogate model to predict future workload demands with a co-simulated digital-twin of the infrastructure to compute QoS scores. We extend the neural network to also act as an imitation learner that dynamically decides the optimal VM provisioning plan. A transformer based neural model reduces training and inference overheads while our novel two-phase decision making loop facilitates in making informed provisioning decisions. Crucially, we address limitations of prior work by including resource utilization, deployment costs and provisioning overheads to inform the provisioning decisions in our imitation learning framework. Experiments with three public benchmarks demonstrate that CILP gives up to 22% higher resource utilization, 14% higher QoS scores and 44% lower execution costs compared to the current online and offline optimization based state-of-the-art methods.

arXiv:2302.01749

Command Line Interface Risk Modeling

Protecting sensitive data is an essential part of security in cloud computing. However, only specific privileged individuals have access to view or interact with this data; therefore, it is unscalable to depend on these individuals also to maintain the software. A solution to this is to allow non-privileged individuals access to maintain these systems but mask sensitive information from egressing. To this end, we have created a machine-learning model to predict and redact fields with sensitive data. This work concentrates on Azure PowerShell, showing how it applies to other command-line interfaces and APIs. Using the F5-score as a weighted metric, we demonstrate different transformation techniques to map this problem from an unknown field to the well-researched area of natural language processing.

arXiv:2301.10450공식 코드 · Papers with Code

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud Computing System

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR.