先進讀表基礎建設中的無線通訊網路是智慧電網佈建中重要的一環。其中如何有效的配置集中器，讓所有智慧電錶在有限時間內將資訊傳回，將是一個具有挑戰的問題：在實際佈建前，我們只知道電錶位置和集中器的候選位置，兩者間是否能建立連線，必須在實際測量後才能確定。但隨著集中器候選位置的增加，實際量測的成本也隨之提昇。
因此，本篇論文將提出一套特徵擷取方式，在實際量測前先從公開資訊站抓取資料並轉換成特徵，搭配各種現有的監督式分類器，只需要部份的實際測量結果訓練，即可預測智慧電錶/集中器間是否可建立連線。

Advanced Metering Infrastructure (AMI) wireless communications network is an important part of smart grid architecture. How to effectively deploy fewer concentrators to collect data from smart meters in time will be a challenging problem. In the actual deployment, all we know are the meter and candidate concentrator position. We don’t know the link between meter and candidate is connectable or not before deployment or actual measurement. As the increases of number of candidate concentrator position, the measurement cost also raise.
Therefore, this thesis will propose a feature extraction method from open data. With some test field data to training supervised classifier, we can predict the link is connectable or not before deployment.

[1] R. Rashed Mohassel, A. Fung, F. Mohammadi, and K. Raahemifar, "A survey on Advanced Metering Infrastructure," International Journal of Electrical Power & Energy Systems, vol. 63, pp. 473-484, 12// 2014.
[2] V. C. Gungor et al., "A Survey on Smart Grid Potential Applications and Communication Requirements," IEEE Transactions on Industrial Informatics, vol. 9, no. 1, pp. 28-42, 2013.
[3] D. Bian, M. Kuzlu, M. Pipattanasomporn, and S. Rahman, "Analysis of communication schemes for Advanced Metering Infrastructure (AMI)," in 2014 IEEE PES General Meeting | Conference & Exposition, 2014, pp. 1-5.
[4] N. Alon, D. Moshkovitz, and S. Safra, "Algorithmic construction of sets for k-restrictions," ACM Trans. Algorithms, vol. 2, no. 2, pp. 153-177, 2006.
[5] L. Breiman, "Random forests," Machine learning, vol. 45, no. 1, pp. 5-32, 2001.
[6] D. M. W. Powers, "Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation," International Journal of Machine Learning Technology, vol. 2, no. 1, pp. 37-63, 2011.
[7] F. V. Pedregosa, G. Gramfort, A. and Michel, V. and B. G. Thirion, O. Blondel, M. Prettenhofer, P.Weiss, R. and Dubourg, V. Vanderplas, J. Passos, A. Cournapeau, D. Brucher, M. Perrot, M. and Duchesnay, E., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825--2830, 2011.
[8] R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," presented at the Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2, Montreal, Quebec, Canada, 1995.
[9] J. Ghosh, H. Q. Ngo, S. Yoon, and C. Qiao, "On a Routing Problem Within Probabilistic Graphs and its Application to Intermittently Connected Networks," presented at the Proceedings of the IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications, 2007.