Sharif Digital Repository

The applications that consist ofprecedence-constrained parallel taskshave used in business activities and scientific projects and the energy consumption of these application has become a major concern in datacenters. At the software level, energy-aware task scheduling algorithmsare an effective technique for energy reduction and optimizing performance in data centers. The related works in this areahave traditionally ignore the utilization value of physical machines (PMs) and while the main reason of the energy inefficiency in datacenters is low average utilization of the PMs.In this paper, we propose a new energy-aware scheduling (EASy) algorithm forprecedence-constrained parallel taskswith... 

Today with the development of te?nology, human ?allenges and problems have become even more complicated. In a way that as time went by the need for higher processing power to solve these problems has increased. High performance computers, are a category of computers whi? are used to solve su? problems. In the last two decade, distributed systems have become the most common way of gaining high performance. Here, Virtualization, an old te?nology whi? has revived in the last decade, providing spectacular features like isolation, migration, ease of management and creating opportunities like virtual clusters has proved to facilitate distributed processing. With the improvement of virtualizer’s... 

In the past few years, because of the high energy price in data centers, optimizing energy consumption has become of real importance. The disproportionate energy consumption of network devices to their utilization has led them to become one of the biggest consumers of energy inside data centers. On the other hand, the stochastic nature of network traffic among virtual machines has made the assumption of known or fixed communication volume superficial. In this research we considered a stochastic distribution of network traffic and communication volume among virtual machines trying to change the communication inside data center to communication inside hosts. Initially, we start by evaluating... 

When multicore processors entered in industry and parallel processing became popular, most challenges have started. Some of the challenges include binding and time sharing of an application with deadline meating constraint. Another important challenge is that, these kinds of processors become more susceptible to transient faults. Among solutions to the mentioned challenges, virtualization which was one of the well known ones becomes applicable again because of some of its advantages such as flexibility, high abstraction and low cost implementation. But this technology has some drawbacks too. It can make system complex and leads to memory and performance overhead. Constructing a reliable... 

Virtualization is one of the widely used technologies which has enhanced the utilization of the hardware resources and made the computer management easier. Cloud computing is one of its appealing application providing various electronic services in the form of virtual machines to users. A common security threat in the virtual machines in cloud services is the vulnerabilities the programs and operating systems have. Attackers can take the advantage of these vulnerable machines and abuse them to carry out attacks. Virtual Machine Introspection (VMI) techniques are proposed and used by the cloud providers utilizing the management capabilities in the hypervisor to intercept hardware accesses and... 

The proliferation of cloud services and drastic growing of IaaS data centers,encourage providers to adopt more intelligent approaches to save more energy and as a result, save more money. Today’s novel techniques such as virtualization and live virtual machine migration, provide effective solutions to service providers to fulfill this need. However, investigate the effect of different resource management and virtual machine migration approaches in virtualized data centers, require great efforts. Therefore, in this research work, we propose a model based on Colored Petri Nets to investigate the effect of live virtual machine migration in cloud data centers. Our proposed model is able to... 

In recent years, cloud computing has provided a well-known platform to provide on-the-fly and cost-efficient services on local and world area networks. As a result, the number of cloud data centers is increasing due to the increasing number of customers. For this reason, the energy consumption of numerous cloud data centers is one of the biggest bottlenecks for cloud providers. In general, various hardware and software-based solutions can be used to optimize power consumption at the same time of guaranty service level agreements. One of the most popular of these software-based solutions is dynamic allocation of resources to virtual machines (VM), i.e. a sandboxing technique responsible for... 

In the next generation of wireless networks, wireless network virtualization is considered as an efficient technology to enhance the network capacity. This technology enables the separation between wireless network infrastructure and the services it provides that enhances some of the existing capabilities and make new capabilities in the network. Spectrum sharing,infrastructure sharing, network sharing, resource slicing are some of these capabilities.Furthermore, the mentioned separation causes the lower entry barriers for small beneficiary entities. The increment in the number of beneficiary entities makes intense competitions among them leading to lower costs for different services. Also,... 

Considering current problems in performance evaluation of the Cloud and its management policies and strategies, this thesis presents different approaches for simultaneous evaluation of the performance, dependability, and power consumption of Infrastructure-as-a-Service (IaaS) clouds. The proposed approaches use Stochastic Reward Nets (SRNs) and Stochastic Activity Networks (SANs) to model and evaluate performability and power consumption of cloud systems. In all of the proposed approaches, the cloud resource management system is power-aware. It means that idle Physical Machines (PMs), network equipment, and supporting subsystems are kept in powered-off or standby modes, as much as possible,... 

In recent years, high interest in using virtualization platforms and Virtual Machines (VMs) in enterprise data centers and Clouds has significantly increased the demand for high performance data storage systems. Recent studies in virtualized platforms have suggested using high-performance storage elements such as Solid-State Drives (SSDs) as a caching layer for storage subsystems mainly built upon Hard Disk Drives (HDDs). Such studies implicitly focus on sharing and partitioning the I/O cache space between VMs, while they neglect to address other important parameters such as SSD lifetime, reliability, and cache policies, which can significantly affect the efficiency of I/O caching in terms... 

In the fifth generation of mobile networks there is a move to replace hardware with software. Meaning that instead of buying dedicated hardware for mobile networks, we only need some general-purpose hardware and will run virtualized network functions on top of that using software. Besides, in the past few years there has been a handful of great opensource cloud management tools that facilitates management of infrastructure and has accelerated this move towards softwarization. Some of these include ONAP, Openstack and Kubernetes. These tools help network engineers to sofwarize functionalities that where previously run on dedicated hardware and manage them automatically. In this project we... 

The significant increase in the penetration of mobile phones and the significant growth of traffic generated in these networks has posed many challenges in the field of cost management, and the expansion of the existing network for mobile operators and has encouraged operators to change the current network architecture. On the other hand, the standard of the next mobile communication, i.e. the fifth generation, has a completely different architecture from the current architecture. Many of the logical and physical entities of the current network have undergone fundamental changes in the new network, and at first glance it does not seem that there is a direct transition from the previous... 

Network Function Virtualization (NFV) is a new paradigm for designing modern computer networks and data centers. NFV leverages the IT virtualization technologies to virtualize entire classes of network node functions into building blocks that may connect, or chain together to create communication services. In this research, we analysed and designed two offline and online algorithms for the problem of join optimization over placement and routing of network function chains in data centers. In the offline case, we showed that traditional randomized rouding works well and by help of chrnoff bound, we derive a new bound on performance gap. The online algorithm in both performance and resource... 

Virtualizing the cloud data center as multiple VMs running parallel on a cloud server is a practical solution to the exponentially grown number of cloud users. The fluctuations in the number of required resources, like networking, storage, and computing resources, can be met by dynamic VM migration. The method by which cloud providers manage VMs and hardware resources to decrease costs and ensure the quality of services is of great importance, especially when the cloud is under a heavy workload. VM migration is one of the most fundamental and practical practices in managing the clouds. Despite all the benefits of VM migration, it also brings overhead on the source host, destination host, and... 

In this work, a virtualized ball-end milling model is presented in Unity game engine environment, in which the machining process is simulated by proposing a new geometric approach. The model calculates and illustrates cutter-workpiece engagement area and cutting forces in a real-time manner. To calculate cutter-workpiece engagement, the workpiece’s top surface is considered a set of nodes. Then, using a new geometric method, the engagement area is calculated at any node on the engaging surface. Utilizing the calculated engagement area and adopting mechanistic force model, the cutting forces applied from each node on the workpiece surface to the tool’s cutting edge are calculated. The cutting...