臺灣博碩士論文加值系統

　　如何能夠更有效的利用能源，是國內外都正在亟思要解決的問題。相較於傳統電網，智慧電網能夠更即時的控管用戶的用電情形與用電量，並且支援雙向的通訊方式，因此能夠提升電力的使用效率。然而，要將數量龐大的智慧電表串聯起來，會牽涉到許多網路設備在佈署上的問題以及需要大量的資金與人力。因此，能夠有效率的收集電表資訊並且能夠減少花費的成本，是推廣智慧電網的相當重要的關鍵。本論文提出了用於無線網路傳輸上的兩階段式資料收集架構，透過K-means分群法，將智慧電表分為許多較小的群集，並且期望能夠使用最少的資料匯集點(DAP)，來滿足整個智慧電網中傳送與接收資料，以更減少成本的花費。此外，由於K-means法在初始選點上有一些缺失，容易陷入區域最佳解，因此我們加入了PSO演算法來優化K-means，並試著找到全域最佳解。最後，從模擬結果可以得知，本論文所提出的兩階段資料收集方式比起其他一階段的資料收集方式能夠使用更少的DAP，以減少成本的花費。

　　How to use energy more efficiently is an important problem which we are thinking to solve positively at home and abroad. Compared with the traditional power grid, smart grid can monitor users’ electricity situation and electricity consumption more instantly. Besides, because of supporting bi-directional communication, smart grid can raise the efficiency of electricity. However, it will involve many problems of deploying network equipment, a lot of capital and manpower to connect with a large number of smart meters. Consequently, it is a vital key to promote smart grid by collecting data from smart meters efficiently and keeping costs down. In this paper, we propose a two-stage method of data collection for wireless network . By using K-means method, we can divide smart meters into many smaller parts. In addition, we expect to be able to meet the needs of transmitting and receiving data in entire smart grid by installing the least number of data aggregation points(DAPs) so that we can reduce the costs more. Furthermore, owing to bad choice of initial centroid locations and trapping into the local optimum easily, we improve K-means by PSO algorithm and try to find a global optimum. In the end, the simulations show that our two-stage method of data collection can install less number of DAPs than other methods which use one-stage methods to collect data, so we can keep costs down more.

致謝　I
摘要　II
ABSTRACT　III
目錄　IV
圖目錄　VI
表目錄　VII

第一章　緒論　1
　1.1 簡介　1
　1.2 智慧電網　1
　1.3 先進讀表基礎建設(ADVANCED METERING INFRASTRUCTURE；AMI)　3
　1.4 研究動機及目的　5
　1.5 論文架構　7
第二章　問題描述　8
　2.1 系統架構　8
　2.2 問題定義　9
第三章　關研究　14
　3.1 機器學習(MACHINE LEARNING)　14
　3.2 群聚分析( CLUSTER ANALYSIS )　15
　3.3 K-MEANS分群法　17
　3.4 粒子群演算法(PARTICLE SWARM OPTIMIZATION；PSO)　19
　3.5 相關文獻　22
第四章　研究方法　24
　4.1 SM分群方法　24
　4.2 CH推舉與DAP安裝方法　27
　4.3 距離閥值訂定　28
　4.4 演算法　29
　4.5 延遲(DELAY)分析　31
第五章　研究結果與分析　35
　5.1 模擬環境及參數設置　35
　5.2 模擬結果　36
第六章　結論　44
參考文獻　45

[1]G. Wang, Y. Zhao, J. Huang and R. M. Winter, "On the Data Aggregation Point Placement in Smart Meter Networks," 2017 26th International Conference on Computer Communication and Networks (ICCCN), Vancouver, BC, pp. 1-6, 2017.
[2]P. Y. Kong, "Cost Efficient Data Aggregation Point Placement with Interdependent Communication and Power Networks in Smart Grid," in IEEE Transactions on Smart Grid, vol. PP, no. 99, pp. 1-1, 2017.
[3]H. A. Latchman and R. Newman, "Lunch Speech II. HomePlug Standards for Worldwide Multimedia In-Home Networking and Broadband Powerline Access," 2007 IEEE International Symposium on Power Line Communications and Its Applications, Pisa, pp. 21-22, 2007.
[4]Andrew McCallum , Kamal Nigam , Lyle H. Ungar, "Efficient clustering of high-dimensional data sets with application to reference matching," Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, p.169-178, Aug. 20-23, 2000.
[5]張軒豪（2014）。IEEE 802.15.4用於智慧電網家庭區域網路之有效傳輸機制研究。國立臺灣科技大學電機工程系碩士論文，臺北市。
[6]賴品君（2015）。IEEE 802.15.7用於智慧電網家庭區域網路之訊號服務品質研究。國立臺灣科技大學電機工程系碩士論文，臺北市。
[7]V. C. Gungor et al., "Smart Grid Technologies: Communication Technologies and Standards," in IEEE Transactions on Industrial Informatics, vol. 7, no. 4, pp. 529-539, Nov. 2011.
[8]D. J. Leeds, "The Smart Grid In 2010 : Market segments, applications and industry players, "GTM Research, pp.1-145, Jul. 2009.
[9]程柏銓（2012）。智慧電網中繞線通訊之增進可靠度容錯方法。國立中山大學資訊工程學系碩士論文，高雄市。
[10]B. Briscoe, A. Brunstrom, A. Petlund, D. Hayes, D. Ros, J. Tsang, S. Gjessing, G. Fairhurst, C. Griwodz, and M. Welzl, “Reducing internet latency: A survey of techniques and their merits,” IEEE Communications Surveys & Tutorials, vol. 18, no. 3, pp. 2149–2196, 2014.
[11]G. Wang, Y. Ren, and J. Li, “An effective approach to alleviating the challenges of transmission control protocol,” IET Communications, vol. 8, no. 6, pp. 860–869, 2014.
[12]G. Wang, Y. Wu, K. Dou, Y. Ren, J. Li, “AppTCP: The design and evaluation of application-based TCP for e-VLBI in fast long distance networks”, Future Generation Computer Systems, vol. 39, pp. 67–74, 2014.
[13]Guilherme Rolim, Diego Passos, Celio Albuquerque, Igor Moraes, Ricardo Carrano, Cledson Sousa, Arlan Bettiol, Luis Passos, Rafael Homma, Rodrigo Andrade and Fernando Molina, “Scalability evaluation of the data aggregator positioning problem in smart grids,” in Proc. IEEE PES Transmission & Distribution Conference and ExpositionLatin America, pp. 1-6, Sep. 2016.
[14]L. Vrbský, M. S. da Silva, D. L. Cardoso and C. R. L. Francês, "Clustering techniques for data network planning in Smart Grids," 2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC), Calabria, pp. 7-12, 2017.
[15]X. Huang, S. Wang and C. Wang, "Aggregation Points Planning for Smart Grid Communications: Wired and Wireless Cases," 2015 IEEE Global Communications Conference (GLOBECOM), San Diego, CA, pp. 1-6, 2015.
[16]黃士耘（2013）。利用類擬剛體改善智慧電網傳輸可靠性。國立宜蘭大學電子工程學系碩士論文，宜蘭縣。
[17]G. Rolim, D. Passos, I. Moraes and C. Albuquerque, "Modelling the Data Aggregator Positioning Problem in Smart Grids," 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing, Liverpool, pp. 632-639, 2015.
[18]F. Aalamifar, G. N. Shirazi, M. Noori and L. Lampe, "Cost-efficient data aggregation point placement for advanced metering infrastructure," 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), Venice, pp. 344-349, 2014.
[19]H. Suoto and S. B. Sen, "Cluster-Based Region Formation for Modeling MANET," MILCOM 2007 - IEEE Military Communications Conference, Orlando, FL, USA, pp. 1-7, 2007.
[20]J. Kennedy and R. Eberhart, "Particle swarm optimization," Neural Networks, 1995. Proceedings., IEEE International Conference on, Perth, WA, pp. 1942-1948 vol.4, 1995.
[21]L. Tan, "A Clustering K-means Algorithm Based on Improved PSO Algorithm," 2015 Fifth International Conference on Communication Systems and Network Technologies, Gwalior, pp. 940-944, 2015.
[22]A. F. Sheta and B. Solaiman, "Evolving clustering algorithms for wireless sensor networks with various radiation patterns to reduce energy consumption," 2015 Science and Information Conference (SAI), London, pp. 1037-1045, 2015.
[23]A. J. M. Rani and L. Parthiban, "Improved particle swarm optimization and K-means clustering algorithm for news article," IET Chennai Fourth International Conference on Sustainable Energy and Intelligent Systems (SEISCON 2013), Chennai, pp. 412-420, 2013.
[24]Doreswamy and M. U. Salma, "PSO based fast K-means algorithm for feature selection from high dimensional medical data set," 2016 10th International Conference on Intelligent Systems and Control (ISCO), Coimbatore, pp. 1-6, 2016.
[25] 股感知識庫(2016)。節能時代─智慧電網。取自: https://www.stockfeel.com.tw
[26] T. Elshabrawy and J. Robert, "Closed Form Approximation of LoRa Modulation BER Performance," in IEEE Communications Letters, 2018.