臺灣博碩士論文加值系統

在無線通訊的世界中，都會遇到的相同問題便是無線基地台的部署，以及訊號覆蓋的議題。在近幾年來聯網設備的蓬勃發展，以及無線傳輸技術的日益進步，隨著第五代行動通訊技術(5th generation mobile networks, 5G)的逐步成形，甚至即將迎來6G技術的世界，在無線基地台的部署上，使用者所要求之訊號品質更高但在基地台部署上卻因發射頻率提高覆蓋率隨之下降，使得部署全覆蓋場域的難度大大上升，而全覆蓋演算法也更加受到重視。
本文根據發射頻率模擬訊號覆蓋範圍在未來可輕鬆套用在不同的無線傳輸技術下，並基於遺傳演算法提出了一全區覆蓋演算法並實做了無線基地台自動部署系統，使得各個使用者都可輕易操作此系統自動部署無線基地台，達到場域全覆蓋的效果。

In the wireless communications, will face the same problems in the deployment of unlimited base stations and the signal coverage problem. In recent years, there has been a boom in the development of connected devices and the advancement of wireless transmission technology. As the 5th generation mobile networks (5G) technology takes shape and the world of 6G technology is about to emerge, users are demanding higher signal quality but wireless base station's signal coverage is decreasing due to higher transmission frequencies, making it more difficult to deploy full coverage areas and full coverage algorithms are becoming more important.
In this paper, we propose a full coverage algorithm based on the genetic algorithm, which can be easily applied to different wireless transmission technologies in the future, and implement an automatic deployment system for wireless base stations, so that each user can easily operate the system to automatically deploy wireless base stations to achieve full coverage.

論文摘要 I
ABSTRACT II
致謝 III
目錄 IV
圖目錄 VI
表目錄 VII
第一章 緒論
1.1 前言
第二章 相關技術
2.1 使用機器學習達到室內網路覆蓋優化
2.2 演化式粒子演算法
2.3 使用模擬退火法達到全覆蓋場域
2.4 基因演算法
第三章 系統架構與設計
3.1 系統架構
3.2 前端系統執行流程
3.3 後端演算系統執行流程
第四章 使用演算法
4.1 Signal Attenuation
4.2 Middle Point Algorithm
4.3 Genetic Algorithm
4.3.1 基因演算法設計流程
4.3.2 製作適應矩陣
4.3.3 群體選擇流程
第五章 實驗測試與評估結果
5.1 系統實作流程
5.2 評估結果
第六章 結論
6.1 本文貢獻
6.2 未來規劃
參考資料

[1] State of IoT 2022: Number of connected IoT devices growing 18% to 14.4 billion globally. At: https://iot-analytics.com/number-connected-iot-devices/
[2] Battiti, R. & Brunato, M. & Delai, A. (2003) Optimal Wireless Access Point Placement for Location-Dependent Services in Technical report DIT-03-052, Universita` di Trento, October 2003
[3] C. Liu, C. Wang and J. Luo, (2020) Large-Scale Deep Learning Framework on FPGA for Fingerprint-Based Indoor Localization, in IEEE Access, vol. 8, pp. 65609-65617, 2020, doi: 10.1109/ACCESS.2020.2985162.
[4] Lue, F. Y & Lui, P. S (2010). A Channel Assignment and AP Deployment Scheme for Concentric-Hexagon Based Multi-channel Wireless Networks. In Network-Based Information Systems (NBIS)
[5] Kar, K. & Banerjee, S. (2003) Node Placement for Connected Coverage in Sensor Networks. In WiOpt’03: Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks, Mar 2003, Sophia Antipolis, France. 2 p.
[6] Eisenblatter, A.& Geerdes, H. F. & Siomina, I (2007) Integrated Access Point Placement and Channel Assignment for Wireless LANs in an Indoor Office Environment. In World of Wireless, Mobile and Multimedia Networks
[7] Reza, A. W., & Rifat, A. A. (2021). An Integrated Machine Learning Model for Indoor Network Optimization to Maximize Coverage. In Indonesian Journal of Electrical Engineering and Computer Science, Vol. 24, No. 1, October 2021, p. 394~402.
[8] Rufaida, S. I., & Leu, J. S. (2020). Construction of an Indoor Radio Environment Map Using Gradient Boosting Decision Tree. In Springer Science+Business Media, LLC, Part of Springer Nature 2020.
[9] Liu, S. H. (2020) Detecting Wireless Coverage Problem by Intelligent Computing for Self-Organization Network.
[10] Chen, B. H. (2018) Implementation of a Simulation System for Wireless Base Station Deployment Applied to Various Three-Dimensional Complex Environments
[11] Farkas, K. , Huszák, Árpád , Gódor, G. (2013). Optimization of Wi-Fi Access Point Placement for Indoor Localization. In Journal IIT(Informatics IT Today)
[12] Wang, C., & Kao, L. (2012). The Optimal Deployment of Wi-Fi Wireless Access Points Using the Genetic Algorithm. In Sixth International Conference on Genetic and Evolutionary Computing, 25-28 August 2012.