The Experts below are selected from a list of 114 Experts worldwide ranked by ideXlab platform
T. Eugene S. Ng - One of the best experts on this subject based on the ideXlab platform.
-
Weaver: Efficient Coflow Scheduling in Heterogeneous Parallel Networks
2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2020Co-Authors: Xin Sunny Huang, T. Eugene S. NgAbstract:Leveraging application-level requirements expressed in Coflows has been shown to improve application-level communication efficiency. However, most existing works assume all application traffic is serviced by one monolithic network. This over-Simplified Assumption is no longer sufficient in a modern, evolving data center which operates on multiple generations of network fabrics, an architecture that we define as Heterogeneous Parallel Networks (HPNs). In this paper, we present the first scheduler, called Weaver, that addresses the Coflow management problem in HPNs. To exploit HPNs fully, achieving high communication efficiency for applications is crucial, yet it is also challenging because of the complex traffic patterns in applications and the heterogeneous bandwidth distribution in HPNs. Weaver addresses these challenges at two levels. At the microscopic level, for each application, Weaver leverages an efficient algorithm to exploit the distributed bandwidth in HPNs, which we proved to be within a constant factor of the optimal. At the macroscopic level involving multiple applications, Weaver can adopt a range of application traffic scheduling policies as desired by the system operator. Under realistic traffic, Weaver enables HPNs to service Coflows as efficiently as a monolithic network with equivalent aggregated capacity.
Sushanta K. Mitra - One of the best experts on this subject based on the ideXlab platform.
-
A comprehensive theoretical model of capillary transport in rectangular microchannels
Microfluidics and Nanofluidics, 2012Co-Authors: Prashant R. Waghmare, Sushanta K. MitraAbstract:A detailed theoretical model of capillary transport in rectangular microchannels is proposed. Two important aspects of capillary transport are revisited, which are considered with Simplified Assumption in the literature. The capillary flow is assumed as a low Reynolds number flow and hence creeping flow Assumptions are considered for majority of analyses. The velocity profile used with this Assumption results into a steady state fully developed velocity profile. The capillary flow is inherently a transient process. In this study, the capillary flow analysis is performed with transient velocity profile. The pressure field expression at the entrance of the microchannel is another aspect which is not often accurately represented in the literature. The approximated pressure field expression at the entrance of the rectangular microchannel is widely used in the literature. An appropriate entrance pressure field expression for a rectangular microchannel is proposed. For both analyses, the governing equation of the capillary transport in rectangular microchannel is derived by applying the momentum equation to the fluid control volume along the microchannel. The non-dimensional governing equations are obtained, each for a transient velocity profile and a newly proposed pressure field, for analyzing the importance of such velocity profile and pressure field expression.
Pierre Baptiste - One of the best experts on this subject based on the ideXlab platform.
-
customized scoring and weighting approaches for quantifying and aggregating results in social life cycle impact assessment
International Journal of Life Cycle Assessment, 2017Co-Authors: Breno Barros Telles Do Carmo, Manuele Margni, Pierre BaptisteAbstract:In social life cycle assessment (SLCA), to measure the social performance, it is necessary to consider the subcategory indicators related to each stakeholder dimension, such as workers, local community, society, consumers and value chain participants. Current methods in SLCA scientific literature consider a standard arbitrary linear score set to translate qualitative performances into a quantitative assessment for all subcategory indicators, i.e., it translate a A, B, C, D scoring into a 4, 3, 2, 1 ordinal scale. This Assumption does not cover the complexity of the subcategory indicators in the social life cycle assessment phase. The aim of this paper is to set out a customized scoring and weighting approach for impact assessment in SLCA beyond the Assumption of arbitrary linearity and equal weighting. This method overcomes the linearity Assumption and develops specific value functions for each subcategory indicator and an approach to establish the weighting factors between the indicators for each social dimension (workers, local community, and society). The value function and weighting factors are based on the considered opinions of SLCA experts in Quebec. The results show that value functions with different shapes used to score the performance of the product within each subcategory indicator influence SLCA results and have the potential to reverse the conclusions. The customized score is more realistic than the linear score because it can better capture the complexity of the subcategory indicators based on SLCA expert judgment. Our approach addresses a methodological weakness of the impact assessment phase of SLCA through a more representative performance of the potential social impacts based on the judgment of the SLCA expert rather than a Simplified Assumption of linearity and equal weighting among indicators. This approach may be applied to all types of product systems. The value functions and weighting factors cannot be generalized for all cases and the proposed approach must be adapted for each study. We stopped at the aggregation of the subcategory indicators based on expert judgment at the stakeholder level. If a complete aggregation in a single score is required, we recommend developing a framework that accounts for the value judgment of the decision-maker rather than the SLCA expert.
Scott Bonk - One of the best experts on this subject based on the ideXlab platform.
-
Sensory-Based Failure Threshold Estimation for Remaining Useful Life Prediction
IEEE Transactions on Reliability, 2017Co-Authors: Abdallah Chehade, Scott BonkAbstract:The rapid development of sensor and computing technology has created an unprecedented opportunity for condition monitoring and prognostic analysis in various manufacturing and healthcare industries. With the massive amount of sensor information available, important research efforts have been made in modeling the degradation signals of a unit and estimating its remaining useful life distribution. In particular, a unit is often considered to have failed when its degradation signal crosses a predefined failure threshold, which is assumed to be known a priori. Unfortunately, such a Simplified Assumption may not be valid in many applications given the stochastic nature of the underlying degradation mechanism. While there are some extended studies considering the variability in the estimated failure threshold via data-driven approaches, they focus on the failure threshold distribution of the population instead of that of an individual unit. Currently, the existing literature still lacks an effective approach to accurately estimate the failure threshold distribution of an operating unit based on its in-situ sensory data during condition monitoring. To fill this literature gap, this paper develops a convex quadratic formulation that combines the information from the degradation profiles of historical units and the in-situ sensory data from an operating unit to online estimate the failure threshold of this particular unit in the field. With a more accurate estimation of the failure threshold of the operating unit in real time, a better remaining useful life prediction is expected. Simulations as well as a case study involving a degradation dataset of aircraft turbine engines were used to numerically evaluate and compare the performance of the proposed methodology with the existing literature in the context of failure threshold estimation and remaining useful life prediction.
Xin Sunny Huang - One of the best experts on this subject based on the ideXlab platform.
-
Weaver: Efficient Coflow Scheduling in Heterogeneous Parallel Networks
2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS), 2020Co-Authors: Xin Sunny Huang, T. Eugene S. NgAbstract:Leveraging application-level requirements expressed in Coflows has been shown to improve application-level communication efficiency. However, most existing works assume all application traffic is serviced by one monolithic network. This over-Simplified Assumption is no longer sufficient in a modern, evolving data center which operates on multiple generations of network fabrics, an architecture that we define as Heterogeneous Parallel Networks (HPNs). In this paper, we present the first scheduler, called Weaver, that addresses the Coflow management problem in HPNs. To exploit HPNs fully, achieving high communication efficiency for applications is crucial, yet it is also challenging because of the complex traffic patterns in applications and the heterogeneous bandwidth distribution in HPNs. Weaver addresses these challenges at two levels. At the microscopic level, for each application, Weaver leverages an efficient algorithm to exploit the distributed bandwidth in HPNs, which we proved to be within a constant factor of the optimal. At the macroscopic level involving multiple applications, Weaver can adopt a range of application traffic scheduling policies as desired by the system operator. Under realistic traffic, Weaver enables HPNs to service Coflows as efficiently as a monolithic network with equivalent aggregated capacity.
