الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 121 |  |  |
| | | from | 121 | | |
Abstract
Wireless Sensor Networks, Internet of Things and smart phones play an important role in technology due to their capabilities. Wireless sensor networks provide significant environmental data using sensors to collect data, processors to process the collected data and communication units to transfer data. A decision can be made depending on the collected data. Today, most mobile applications require executing computationally intensive tasks. Despite the recent enormous enhancements in Wireless sensor networks and smart phones, the constraints of battery and processing units still remain. These constraints slow the execution time of computationally intensive tasks and consume huge power. To achieve the highest computation capabilities which can be useful for current and future mobile applications, computation offloading is a significant technique to achieve this goal as the execution time plays a significant role in real time applications. In order to follow the high-speed applications requirements; new technologies have to be developed. This is may be achieved using new and better task allocation schemes. The above goal can also be performed using technologies, such as Mobile Cloud Computing, Mobile Edge Computing, cloudlet and Fog Computing, which in turn decreases the task execution time. The present study introduces alternative solutions to decrease the task execution time taking into consideration the effect of devices mobility in real scenarios in which nearby devices may leave the cell or turn off before completing the task execution. A distributed framework for offloading a required task among nearby devices based on their speeds and costs in a heterogeneous network is proposed.In the Thesis, the wireless sensor networks performance using computation offloading was investigated. The main objective of the study reported here is to improve the computation performance for wireless sensor networks. For this study, some computation offloading analysis and algorithms were performed. After that, the performance of each algorithm is evaluated in terms of the task execution time and speedup. Differences between different network scenarios (i.e. 4G, Wi-Fi and ZigBee) were considered in simulations and analysis.