Sharif Digital Repository

In this thesis, we want to present methods that are able to solve the assignment tasks problem in a heterogeneous computing system. These methods are two hybrid methods that are constructed by composing Hopefield Neural Networks with Genetic Algorithms and the Simulated Annealing. First, we solve the relaxed problem by applying Genetic Algorithms and the Simulated Annealing and we compare the results of these ways with other traditional methods. Then, we solve the constrained problem with mentioned hybrid methods. The definition of the problem is as following: Consider a distributed computing system which is comprised of set of processors with different speeds but the same structure. We want... 

Size and number of high-performance data centers are fast growing all over the world in recent years. The growth in the leakage power consumption of servers along with its exponential dependency on the ever increasing process variation in nanometer technologies have made it inevitable to move toward variation-aware power reduction strategies. In this thesis, we simultaneously apply thermal- and variation-aware server placement and chassis consolidation methods to reduce total power consumption of data centers. We introduce two server placement heuristics as well as an Integer Linear Programming (ILP)-based server placement method based on power consumption of each server and the data center... 

Reducing the size of transistors has dramatically increased the impacts of NBTI, HCI, and EM phenomena in comparison with decade ago. These phenomena are able to have influence on properties of different parts of a chip to make it changed gradually; including threshold voltage of a transistor and electrical conductivity of interconnections. These changes are known as the aging of a transistors that diminish the performance and reliability of a chip. A common reason that plays a significant role in all these phenomena is temperature. The temperature becomes more important when the power density increases per unit area due to decreased size of transistors, which is a trend in multi-core... 

A workflow management system is a software system which manages and coordinates the operational tasks of an organization. Typically, the def­ inition of a workflow involves human and computer resources and tools on various geographic locations, and thus the concerns of distributed systems are one of the main challenges in this domain. Following this,allocating various resources to different tasks of a workflow and schedul­ ing them in a manner which satisfies some predefined constraints is one of the new and fundamental challenges in this field.The main goal of this research is to design an agent-oriented workflow system which utilizes a novel method for resource allocation and schedul­ ing... 

Cloud computing has provided a suitable platform for processing and storing Internet of Things data over the last few decades by establishing data centers with high processing power. Today, with the rise of real-time processing applications in the Internet of Things, such as voice assistants, smart health controls, and self-driving cars, the number of real-time tasks has increased rapidly; this is despite the fact that cloud servers cannot meet the deadline constraint due to physical distance delays. To address this challenge, Fog computing has been introduced. By moving computational and storage resources closer to the edge of the network, fog computing enables executing real-time tasks...