Machine Learning (ML) is extensively used for predicting transfer times for general purpose Wide Area Networks (WANs) or public Internet applications, but for Research and Education Networks (RENs) two major gaps exis...
详细信息
ISBN:
(纸本)9798350369588;9798350369595
Machine Learning (ML) is extensively used for predicting transfer times for general purpose Wide Area Networks (WANs) or public Internet applications, but for Research and Education Networks (RENs) two major gaps exist in literature. First, RENs i.e. networks carrying large data flows have received limited attention by the networking community. RENs behave differently compared to the general purpose Internet applications and other network types. Hence, ML models from other network types cannot be used interchangeably for large data transfers. Second, the ML models are used as blackboxes to train on measured network values and then used to predict transfer times or other runtime network parameters. In this paper, we present a dynamical systems model of the large data transfers typical of RENs in the form of a system of Ordinary Differential Equations (ODEs) inspired by the Lotka-Volterra competition model. We present a transfer time prediction component called Dynamic Transfer time Predictor (DTTP) which solves the ODEs and predicts the future transfer times. Second we formulate a loss function based on Lyapunov function called Lyapunov Drift Correction (LDC) that self-corrects the transfer time prediction errors dynamically. To design and develop our model, we studied real-world datasets consisting of over 100 million transfer records collected from platforms such as Open Science Grid (OSG), Large Hadron Collider Optical Private Network (LHCOPN), Worldwide LHC Grid (WLCG), as well as the RENs of Internet2 and ESNet. We integrate our model into well-known neural network models and regressors and present evaluation results.
Simultaneous localization and mapping, as the basic methods for autonomous motion of mobile robots, have been widely developed and applied in conventional structured environments. But it is more difficult to collect a...
详细信息
This study explores cloud-based data mining algorithm integration in elevating smart city infrastructure management and decision support systems. Specifically, the authors focus on optimizing traffic management throug...
详细信息
Using digital twins for the healthcare industry has picked up pace with the various advances in technologies and capabilities that support creating digital twins and with the increased awareness of digital twins benef...
详细信息
ISBN:
(纸本)9798350385328;9798350385335
Using digital twins for the healthcare industry has picked up pace with the various advances in technologies and capabilities that support creating digital twins and with the increased awareness of digital twins benefits for the industry. At a more specialized level, healthcare facilities management is an important and very critical component contributing to the effective and efficient planning and use of the facilities. Some work has been going on exploring how digital twins can be applied in some areas of healthcare facilities management such as maintenance and building management. However, there is very little exploring the use of digital twins in other areas of healthcare facilities management such as capacity planning, disaster recovery planning and facilities and resource scheduling. These areas can benefit tremendously from digital twins. In this paper we discuss the different aspects of healthcare facilities management where digital twins can be of great benefit. In addition, we show how using the digital twins and their accurate representations of the real healthcare systems can be integrated with other advanced tools like simulation, analytics and visualization to create more value-added capabilities to help enhance healthcare facilities management processes and outcomes. In particular, we believe that using the digital twin models and real-time operational data can be used as inputs for various simulation processes to help in the decision-making processes and to make better and more informed decisions regarding the various activities in healthcare facilities management.
Application of blockchain in financial services has opened new ways of efficiency in transaction processing, assets management and security. The application of parallel, distributed, and grid computing with blockchain...
详细信息
Autonomous vehicles are well-known for automated tasks that are difficult or dangerous to be performed by human. However, the environment in which those Autonomous Vehicle (AV) are evolving is generally hard to predic...
详细信息
ISBN:
(纸本)9798350325430
Autonomous vehicles are well-known for automated tasks that are difficult or dangerous to be performed by human. However, the environment in which those Autonomous Vehicle (AV) are evolving is generally hard to predict. Thus, the challenge is to achieve a predefined mission while adapting AVs to their shifting environment in realtime as efficiently as possible. The mission often includes path planning problems, where self-adaptation to terrain modifications is required while maintaining contradictory objectives, such as safety, risk assessment, travelling time or distance or consumed energy. We choose to focus on supervision missions (covering area with a lidar, with pictures, searching, etc) with two objectives: travelled distance (that could later be modeled into time or energy consumption) and covered area. We propose a multi-objective optimization (MOO) framework for a self adaptation of autonomous vehicles, with an offline/online approach, in order to solve covering/monitoring missions. The offline process will predict a initial path for the AV and the online process will be useful for the dynamic path re-planning when obstacles are detected. Our results demonstrate the benefits of reusing the offline pre-computed solutions for the online phase and for dynamic path re-planning.
The avionics system in safety critical aerospace systems plays an extremely important role in ensuring proper performance as well as safety of the mission. The Onboard Computer (OBC) that functions as the master in th...
详细信息
Human-action recognition attempts to determine which deed occurs by people. Owing to the wide spectrum of human activities, action recognition spans a wide range. Among all, falls the conduct gathering special interes...
详细信息
The integration of Internet of Things (IoT) technology into transportation systems holds immense potential to transform the way we move people and goods, offering benefits such as increased efficiency, reduced emissio...
详细信息
Edge computing is poised to greatly boost Industry 5.0 by providing a computing substrate that can run highly specialized applications with minimal latency, reducing the requirements on computational resources at the ...
详细信息
暂无评论