基於設備成本與分佈密度之次經驗演算法於無線網路規劃

分群演算法在不同領域被廣泛的討論，本研究將探討在具有實際研究限制規範下，基於設備成本與分佈密度之次經驗演算法於無線網路規劃。因此，本研究針對普遍且具有實際效益的無線區域網路環境的建置規劃議題進行討論，雖然該議題大多屬於分群的相關研究，可是群中心位置與分佈數量的判斷大都是依照主觀的經驗法則，依照現場訊號涵蓋範圍作為參考。因此，本研究採用螢火蟲演算法作為主要研究技術，並分析比較其他四種分群演算法於相同問題資料處理上之表現；本研究依據單位空間內集中區域的分佈狀態，以及集中區域相較於整體區域上使用者分佈密集的程度，並且考慮設備成本，進而提出一個基於設備成本與分佈密度之次經驗演算法於無線網路規劃。

關鍵字

無線網路；分群；螢火蟲演算法；次經驗驗算法

並列摘要

Clustering techniques have been widely used in various fields. In this study, the application of metaheuristics in allocating wireless network based on equipment cost and the client density is investigated. The general issues in building wireless LAN environment are considered in this study. Most of the wireless networks allocation problems belong to clustering issues. Decision makers are used to determine the number of clusters and centers of clusters subjectively. In accordance with the rule of thumb, the signal coverage is the most important reference. Therefore, this study utilized glowworm algorithms to deal with the wireless networks allocation problems. In addition, four other clustering methods were employed to cope with the same data set to compare the performance. Various distributions of networks users and equipment costs were used to examine the feasibility and performance of glowworm algorithms.

並列關鍵字

Wireless networks ； Clustering ； Glowworm algorithm ； Metaheuristics

參考文獻

Google Scholar

[1] Al-kazemi, B. & Mohan, C. K. (2000). Multi-phase discrete particle swarm optimization. The Fourth International Workshop on Frontiers in Evolutionary Algorithm.

Google Scholar

[2] Barhak, J., & Fischer, A. (2002). Adaptive reconstruction of freeform objects with 3D SOM neural network grids. Computers & Graphics, Vol. 26, Issue 5, pp. 745–751.

Google Scholar

[3] Bellofiore, S., Balanis, C. A., Foutz J. & Spanias, A. S. (2002). Smart-antenna systems for mobile communication networks. Part 1: Overview and antenna design. IEEE Antenna’s and Propagation Magazine, pp. 145-154.