Loading...
Search for:
nabavinejad--hossein
0.182 seconds
Total 1303 records
Energy efficiency in cloud-based mapReduce applications through better performance estimation
, Article Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016, 14 March 2016 through 18 March 2016 ; 2016 , Pages 1339-1344 ; 9783981537062 (ISBN) ; Goudarzi, M ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2016
Abstract
An important issue for efficient execution of MapReduce jobs on a cloud platform is selecting the best fitting virtual machine (VM) configuration(s) among the miscellany of choices that cloud providers offer. Wise selection of VM configurations can lead to better performance, cost and energy consumption. Therefore, it is crucial to explore the available configurations and choose the best one for each given MapReduce application. Executing the given application on all the configurations for comparison is a costly, time and energy consuming process. An alternative is to run the application on a subset of configurations (sample configurations) and estimate its performance on other...
Communication-awareness for energy-efficiency in datacenters
, Article Energy Efficiency in Data Centers and Clouds, 2016 ; Volume 100 , 2016 , Pages 201-254 ; 00652458 (ISSN) ; 9780128047781 (ISBN) ; Goudarzi, M ; Sharif University of Technology
Academic Press Inc
2016
Abstract
With the proliferation of cloud computing concept, the datacenters, as the basic infrastructure for cloud computing, have gained an ever-growing attention during the last decade. Energy consumption in datacenters is one of the several features of them that have been the target of various researches. Two major consumers of energy in datacenters are the cooling system and IT equipment. Computing resources, such as servers, and communicating ones, such as switches, constitute the main portion of IT equipment. Among these two major players, the servers have been considered more than networking equipment. Making servers energy proportional as well as server consolidation are the two essential...
Profit maximization of big data jobs in cloud using stochastic optimization
, Article IEEE Transactions on Cloud Computing ; Volume 9, Issue 4 , 2021 , Pages 1563-1574 ; 21687161 (ISSN) ; Goudarzi, M ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2021
Abstract
Reserved instances offered by cloud providers make it possible to reserve resources and computing capacity for a specific period of time. One should pay for all the hours of that time interval; in exchange, the hourly rate is significantly lower than on-demand instances. Reserved Instances can significantly reduce the monetary cost of resources needed to process big data applications in cloud. However, purchases of these instances are non-refundable, and hence, one should be able to estimate the required resources prior to purchase to avoid over-payment. It becomes important especially when the results obtained by big data job has monetary value, such as business intelligence applications....
Resource Allocation for Big Data Analysis in Clouds
, Ph.D. Dissertation Sharif University of Technology ; Goudarzi, Maziar (Supervisor)
Abstract
Forecasts predict that the volume of digital data will increase by 300 times in 2020 compared with 2005. This significant growth further emphasizes the importance of Big Data as well as Big Data Processing. MapReduce and its open source implementation Hadoop are prevailing frameworks for implementing Big Data Analytics and applications. Because of inherently huge amount of data and computational requirements of Big Data applications, acquisition of large amount of computational resources is necessary. However, managing in-house clusters to respond the computational requirements is costly such that small- and middle-sized companies either cannot afford it, or find cloud-based solutions...
Dispersed Drops Coalition Studi By CFD
, M.Sc. Thesis Sharif University of Technology ; Farhadi, Fatollah (Supervisor)
Abstract
Investigation of particles (bubbles or droplets) behavior in two phase flow is widely studied in many chemical engineering processes. This thesis describes CFD simulation for study of dispersed droplets behavior in two phase flow. For this purpose, in population balance equation which is coupled with mass balance equation, Lou and Svendsen model is used for breakage and Prince and Blanch model for coalescence with Eulerian-Eulerian approach for multiphase flow, in conjunction with turbulence model. Then the effect of gas velocity on the coalescence and break up phenomena studied and the results obtained here showed that by increasing gas flow rate, which increased , leads to increase...
MapReduce service provisioning for frequent big data jobs on clouds considering data transfers
, Article Computers and Electrical Engineering ; Volume 71 , 2018 , Pages 594-610 ; 00457906 (ISSN) ; Goudarzi, M ; Abedi, S ; Sharif University of Technology
Elsevier Ltd
2018
Abstract
Many companies regularly run Big Data analysis, and need to optimize their resource usage considering cost, deadline, and environmental impact simultaneously. The cloud allows choosing from various virtual machines (VM) where the number and type of VMs affect the outcome such as the time for data placement and data shuffle phases, a task's energy consumption and execution time, and the makespan of jobs. We provide provisioning and scheduling algorithms to minimize environmental impact, considering the above factors, for frequently executed MapReduce jobs. To mathematically model the problem and obtain the optimal solution, we present an Integer Linear Programming (ILP) model and then...
Coordinated DVFS and Precision Control for Deep Neural Networks
, Article IEEE Computer Architecture Letters ; Volume 18, Issue 2 , 2019 , Pages 136-140 ; 15566056 (ISSN) ; Hafez Kolahi, H ; Reda, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2019
Abstract
Traditionally, DVFS has been the main mechanism to trade-off performance and power. We observe that Deep Neural Network (DNN) applications offer the possibility to trade-off performance, power, and accuracy using both DVFS and numerical precision levels. Our proposed approach, Power-Inference accuracy Trading (PIT), monitors the server's load, and accordingly adjusts the precision of the DNN model and the DVFS setting of GPU to trade-off the accuracy and power consumption with response time. At high loads and tight request arrivals, PIT leverages INT8-precision instructions of GPU to dynamically change the precision of deployed DNN models and boosts GPU frequency to execute the requests...
QoR-aware power capping for approximate big data processing
, Article Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018 ; Volume 2018-January , 19 April , 2018 , Pages 253-256 ; 9783981926316 (ISBN) ; Zhan, X ; Azimi, R ; Goudarzi, M ; Reda, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2018
Abstract
To limit the peak power consumption of a cluster, a centralized power capping system typically assigns power caps to the individual servers, which are then enforced using local capping controllers. Consequently, the performance and throughput of the servers are affected, and the runtime of jobs is extended as a result. We observe that servers in big data processing clusters often execute big data applications that have different tolerance for approximate results. To mitigate the impact of power capping, we propose a new power-Capping aware resource manager for Approximate Big data processing (CAB) that takes into consideration the minimum Quality-of-Result (QoR) of the jobs. We use...
Data locality and VM interference aware mitigation of data skew in hadoop leveraging modern portfolio theory
, Article 33rd Annual ACM Symposium on Applied Computing, SAC 2018, 9 April 2018 through 13 April 2018 ; 2018 , Pages 175-182 ; 9781450351911 (ISBN) ; Goudarzi, M ; ACM Special Interest Group on Applied Computing (SIGAPP) ; Sharif University of Technology
Association for Computing Machinery
2018
Abstract
Data skew, which is the result of uneven distribution of data among tasks in big data processing frameworks such as MapReduce, causes significant variation in the execution time of tasks and makes their placement on computing resources more challenging. Moreover, with the proliferation of big data processing in the cloud, the interference among virtual machines co-located on the same physical machine exacerbates the aforementioned variation. To tackle this challenge, we propose Locality and Interference aware Portfolio-based Task Assignment (LIPTA) approach. LIPTA leverages the modern portfolio theory to mitigate the variation in execution time of tasks while considering the interference of...
Calculation of the Energy Release Rate of Nano-Cracks in FCC Materials Via the Many Body Atomic Scale FEM
, M.Sc. Thesis Sharif University of Technology ; Mohammadi Shodja, Hossein (Supervisor)
Abstract
Since the classical continuum theory fails to deal with the problems associated with defects, stress concentrators, and relevant deformation phenomena in solids, alternative approaches that can detect the atomistic nature of materials' fracture are required. The deficiency of the capture the size effect which yields delusively high values for some components of the stress field right on the edge of the stress concentrators, and its weakness in describing the complex interaction between small inhomogeneities, cracks and the like when they are only a few nanometers apart, are among some of the disadvantages of the classical approach. In recent years, however, atomistic methods are emerging to...
Semisolid Stir Joining of As-Cast Silicon-Aluminum Bronze
, M.Sc. Thesis Sharif University of Technology ; Kokabi, Amir Hossein (Supervisor) ; Ashuri, Hossein (Supervisor)
Abstract
Aluminum Bronzes have many applications in marine environments. These alloys suffer from both hot cracking and cold cracking. In order to overcome the hot cracking and cold cracking, Semisolid Stir Joining method and a proper thermal cycle was used respectively. Effects of temperature, stirring rate, and tool type were investigated in Semisolid Stir joining method. In this method, butt joint design was used in order to place specimens, and the specimens were heated up to specific temperatures (920, 925, 930°C). A stirrer (Cylindrical and Grooved tool) with three rotational speeds (800, 1200, 1600 RPM) was introduced into the stir weld seam. Welded specimens were cooled to the 900°C...
The Study of Eliminating Gender Gap in Iran Labor Market on Participation Rate of Married Urban Women
, M.Sc. Thesis Sharif University of Technology ; Rahmati, Mohammad Hossein (Supervisor) ; Joshaghani, Hossein (Supervisor)
Abstract
The low female labor force participation rate in the Iranian labor market relative to the global average and even to countries that do not differ significantly from the socio-economic characteristics of our country is one of the important questions of the Iranian labor market. In this study, we seek to answer the question of whether the economic participation rate of married women will increase if the gender gaps in wages, job findings and job losses among women and men are eliminated in the Iranian labor market. To answer this question using household expenditure and income data and labor force data, we show that between the two categories of occupations, in terms of the share of women's...
Graph homomorphisms through random walks [electronic resource]
, Article Journal of Graph Theory ; 2003, Volume 44, Issue 1, pages 15–38 ; Hajiabolhassan, Hossein ; Sharif University of Technology
Abstract
In this paper we introduce some general necessary conditions for the existence of graph homomorphisms, which hold in both directed and undirected cases. Our method is a combination of Diaconis and Saloff–Coste comparison technique for Markov chains and a generalization of Haemers interlacing theorem. As some applications, we obtain a necessary condition for the spanning subgraph problem, which also provides a generalization of a theorem of Mohar (1992) as a necessary condition for Hamiltonicity. In particular, in the case that the range is a Cayley graph or an edge-transitive graph, we obtain theorems with a corollary about the existence of homomorphisms to cycles. This, specially, provides...
Unique list-colourability and the fixing chromatic number of graphs [electronic resource]
, Article Discrete Applied Mathematics ; Volume 152, Issues 1–3, 1 November 2005, Pages 123–138 ; Hajiabolhassan, Hossein ; Sharif University of Technology
Abstract
In this paper we introduce a chromatic parameter, called the fixing chromatic number, which is related to unique colourability of graphs, in the sense that it measures how one can embed the given graph G in G∪Kt by adding edges between G and Kt to make the whole graph uniquely t-colourable. We study some basic properties of this parameter as well as its relationships to some other well-known chromatic numbers as the acyclic chromatic number. We compute the fixing chromatic number of some graph products by applying a modified version of the exponential graph construction
Circular colouring and algebraic no-homomorphism theorems
, Article European Journal of Combinatorics ; Volume 28, Issue 6, August 2007, Pages 1843–1853 ; Hajiabolhassan, Hossein ; Sharif University of Technology
Abstract
In this paper, we apply some new algebraic no-homomorphism theorems in conjunction with some new chromatic parameters to estimate the circular chromatic number of graphs. To show the applicability of the general results, as a couple of examples, we generalize a well known inequality for the fractional chromatic number of graphs and we also show that the circular chromatic number of the graph obtained from the Petersen graph by excluding one vertex is equal to 3. Also, we focus on the Johnson–Holroyd–Stahl conjecture about the circular chromatic number of Kneser graphs and we propose an approach to this conjecture. In this regard, we introduce a new related conjecture on Kneser graphs and we...
Density and power graphs in graph homomorphism problem
, Article Discrete Mathematics ; Volume 308, Issue 17, 6 September 2008, Pages 4027–4030 ; Hajiabolhassan, Hossein ; Sharif University of Technology
Abstract
We introduce two necessary conditions for the existence of graph homomorphisms based on the concepts of density and power graph. As corollaries, we obtain a lower bound for the fractional chromatic number, and we set forward elementary proofs of the facts that the circular chromatic number of the Petersen graph is equal to three and the fact that the Coxeter graph is a core
Temperature dependence study of nonocontact AFM images using molecular dynamics simulations [electronic resource]
, Article Int. Journal of Modern Physics ; 2012, Vol. 5, pp. 418-432 ; Meghdar, Ali ; Sharif University of Technology
Abstract
The effect of temperature on the noncontact atomic force microscopy (NC-AFM) surface imaging is investigated with the aid of molecular dynamics (MD) analysis based on the Sutton-Chen (SC) interatomic potential. Particular attention is devoted to the tip and sample flexibility at different temperatures. When a gold coated probe is brought close to the Au (001) surface at high temperatures, the tip and surface atoms are pulled together and their distance becomes smaller. The tip and sample atoms displacement varies in the different environment temperatures and this leads to the different interaction forces. Along this line, to study the effect of temperature on the resulting images, we have...
Developing an Analytical Model for Predicting the Residual Stresses Induced by Shot Peening with Considering the Effect of Initial Surface Treatment
, Ph.D. Dissertation Sharif University of Technology ; Farrahi, Gholam Hossein (Supervisor) ; Mahmoudi, Amir Hossein (Co-Supervisor)
Abstract
Shot peening is a cold-working process commonly used in industry to improve the fatigue performance, stress corrosion resistance and surface nano-crystallization of metallic parts. This process extends fatigue life via two mechanisms: Preventing the crack growth due to compressive residual stresses and, preventing the crack initiation because of increased material hardness. These mechanisms are the results of the bombardment of the component's surface with small spherical particles. In this research, an analytical model is developed for estimating the residual stress distribution induced by shot peening process. The modifications of the developed analytical model are related to...
Combustible organic materials : determination and prediction of combustion properties
, Book
De Gruyter
2018
Evaluating Reliability of SSDs Against Power Outage
, M.Sc. Thesis Sharif University of Technology ; Asadi, Hossein (Supervisor)
Abstract
Solid-State Drives (SSDs) provide high performance, low power consumption, and hence are widely used in the I/O cache of enterprise storage systems and high performance servers. Although employing high performance SSDs in the I/O cache of storage systems significantly improves system performance, it comes with significant reliability threats for write operations upon power failures. In order to provide high level of reliability, storage architectures employ SSDs in I/O cache with RAID-1 configuration, however, such configuration only partially mitigates the reliability issues of the SSDs. In this thesis, we analyze the reliability of SSD-based I/O caches against power outage and high...