Evaluation of quality of service in fourth generation wireless and mobile networks
Communication networks extend network capacity and coverage by leveraging network and resource architecture in a dynamic way. However, because of the different communication technologies and quality of service (QoS, managing and monitoring these networks are too difficult. All communication technolo...
Saved in:
| 主要作者: | |
|---|---|
| 格式: | Thesis |
| 語言: | English English English |
| 出版: |
2019
|
| 主題: | |
| 在線閱讀: | http://eprints.uthm.edu.my/664/1/24p%20SABAH%20HASSAN%20GHADEER.pdf http://eprints.uthm.edu.my/664/2/SABAH%20HASSAN%20GHADEER%20COPYRIGHT%20DECLARATION.pdf http://eprints.uthm.edu.my/664/3/SABAH%20HASSAN%20GHADEER%20WATERMARK.pdf |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Communication networks extend network capacity and coverage by leveraging network and resource architecture in a dynamic way. However, because of the different communication technologies and quality of service (QoS, managing and monitoring these networks are too difficult. All communication technology has its own characteristics while the applications you use have their own QoS requirements. The methods are based on the QoS analysis for each application or access network separately. However, these methods do not combine all performance and wireless access networks while reporting QoS quality to the group Arrangement. Therefore, it is difficult to obtain any aggregate performance results using these methods. In this project, a methodical method is applied for the QoS analysis of these types of networks. The method uses a fuzzy logic (FL), artificial neural network (ANN) and Adaptive Neuro-fuzzy Interference System (ANFIS) to evaluate and predict the performance QoS of networks. The proposed methods consider the significance of QoS-related parameters, the available network-based applications, and the available Radio Access Networks (RANs) to characterize the network performance with a set of three integrated QoS metrics. The first metric denotes the performance of each available application on the network, the second one represents the performance of each active RAN on the network, and the third one characterizes the QoS level of the entire network configuration. The obtained predicting output were compared to the actual data and to each other to test which system the best for this study. The results ANN model were the closed to the real data than outcome ANFIS model. |
|---|