近年資訊科技快速發展,行動通訊產業日漸興盛,國內行動通訊人口迅速增加,相對無線基地台數目與日俱增,而通訊業首要重視的問題即是通話品質之良窳,本研究以無線基地台配置為基礎問題,加上區域性通訊品質最低限制的條件下,要如何將不同種類功率無線基地台建置在各個區域當中並符合各個區域最低通訊品質的要求達到最小成本的無線基地台配置組合,是本研究所要探討的重要議題。對於求解最佳化的問題,在目前人工智慧是常被採用的啟發式演算法之一。本研究結合免疫演算法及粒子群最佳化演算法之混合式進化演算法,將免疫演算法決定無線基地台數量跟種類,並且利用網格技術提高運算速度與效率,傳遞至粒子群演算法中決定各無線基地台之位址,經實驗結果顯示在各別區域最低通訊品質限制下,所提出的方法可決定不同功率大小以及成本之無線基地台數目與位址,提供業者作為設置參考以及提供使用者最理想與滿意的收訊品質。
Due to the rapid development of information technology in recent years, the cellular phone users have been increased tremendously. For this reason, the signal transmission stations are widely built so as to enhance the communication quality. Inappropriate setup of stations is not only causing the unnecessary cost but also making the poor service quality. How to allocate the base stations optimally is a very important issue. According to the above difficulties, this thesis is to investigate the a communications base station allocation problems with the restricted regional differences constraints in which the types of base stations and the corresponding numbers and locations are to be decided simultaneously so as to minimize the setup cost subject to the maximum failure rate specified in different regions . In this study, we applied a grid computing based hybrid evolutionary algorithm containing the Immune algorithm and Particle Swarm Optimization (IAPSO). We use the IAPSO on the grid computation architecture to solve the multiple stations location problems. The computational results show that the proposed algorithm is feasibly to solve the problems. It is wished that our study can provide the Telecommunication Enterprise the optimal/near optimal strategies for the setup of base stations.