الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 132 |  |  |
| | | from | 132 | | |
Abstract
Internet of things (IoT) has become a very popular technology in the last few years. IoT provides an extremely flexible environment to express ideas and bring interactivity to projects in various fields, as well as providing for an easy way to implement, learn and prototype advanced projects and applications.
IoT system usages are expanding quickly, which becomes a difficult way to achieve quality services effectively. Therefore, in this thesis, we introduced two different algorithms to improve IoT services performance. The first is the K- Nearest Neighbors - Kalman Filter (KNN-KF) algorithm proposed to reduce error in Industrial IoT data streams.
The second is an Efficient Energy and Completion Time for Dependent Task Computation Offloading (ET-DTCO) algorithm proposed to determine the optimal computing model for dependent tasks to satisfy the minimum energy consumption and low completion time in Industry 4.0.
In IoT applications, sensor data quality has an essential role as it becomes useless if the quality of data is poor. When the data collected from IoT sensors is poor quality data, it will lead to distorted analysis results that yield to misdirection of smart services. Therefore, in the KNN-KF algorithm, both K- Nearest Neighbors (K-NN) algorithm and Kalman Filter (KF) algorithm are combined. The KNN algorithm is implemented to identify the error in data and output the transition matrix which is the input to KF which predicts the final estimated value.
Various tests are carried out to evaluate our proposed algorithm for comparison with state-of-the-art methods. The simulated results prove that the proposed KNN-KF algorithm improves accuracy well.
Moreover, Rapid technological development has revolutionized the industrial sector. Internet of Things (IoT) started to appear in many fields, such as health care and smart cities.
A few years later, IoT was supported by industry, leading to what is called Industry 4.0. A cloud-assisted fog-networking architecture is implemented in an IoT environment with a three-layer network. ET-DTCO algorithm is proposed, and it considers two quality-of-service (QoS) parameters: efficient energy and completion time offloading for dependent tasks in Industry 4.0.
The proposed solution employs the Firefly algorithm to optimize the process of the selection-offloading computing mode and determine the optimal solution for performing tasks locally or offloaded to fog or cloud considering the task dependency.
The proposed algorithm is compared with existing techniques. Simulation results proved that the proposed ET-DTCO algorithm outperforms other offloading algorithms in minimizing energy consumption and completion time while enhancing the overall efficiency of the system.