大數據應用於商辦大樓之中央空調系統性能預測

Prediction of a central air conditioning system’s performance in a building by using data mining

蔡松翃(Sung-Hung TSAI)

指導教授 ： 傅武雄 ； 王啟川

國立交通大學/工學院/機械工程系所/碩士(2017年)

摘要

中央空調為大型建築物上在工業節能發展是很重要的議題，在臺灣氣候屬於亞熱帶氣候，夏季溫度較高，中央空調占總耗電量為建築物40%以上，夏季時空調用電量占總用電量之30%，於尖峰時段甚至高達41%～45%，而且空調負載每年仍以15%迅速成長，當使用中央空調建築大樓愈多，加裝儲存資料裝置也隨即增加。因此在大型建物空調資料取得也愈來愈容易，當資料取得更便利，將可利用中央空調過去之中找尋有意義的節能或耗能之關聯性。
因此，本研究透過大數據資料探勘演算法，找尋在過去歷史大量資料之中，潛藏耗能與節能之間相互的規則，透過決策樹演算法建立出預測中央空調之節能與耗能規則，將決策樹預測資料與共同的特徵與規則進行分類或做新的資料預測，並並對其節能與耗能規則之中央空調系統進行分析。

關鍵字

大數據 ； 中央空調 ； 資料探勘

並列摘要

The energy consumption of a central air conditioning systems is the most important issue when talking about energy saving in an office building. Nowadays, the data of the environment in the building can be collected from the sensors and stored in the cloud services easily by using computers. Therefore, with more data collected from the sensors, the usage of data mining is getting more important than before.
The present study uses the decision tree algorithm to find out the pattern of the data which might cause the system has better energy saving or, on the contrary, the worst energy consumption. With the algorithm, this study establishes a model for an air-conditioning system, and find out the meanings which were hiding behind the massive data we got from the sensors.

並列關鍵字

Big data ； Data mining ； central air conditioning

參考文獻

[1] The IEEE International Conference on Data Mining. “Top 10 algorithms in data mining” Knowledge and Information Systems, Jan 2008, p.p. 1-37.

[2] International Business Machines Corporation” What is big data ” From Internet. https://www-01.ibm.com/software/data/bigdata/what-is-big-data.html。

[3] W.J. Frawley, G. Piatetsky-Shapiro and C.J Matheus. ”Knowledge discovery in databases: an overview”, AI Magazine, Volume 13 Number 3, 1992 , p.p.213-228

[4] U. Fayyad, G. Piatetsky-Shapiro and P. Smyth. “From Data Mining to Knowledge Discovery in Databases” AI Magazine, Volume 17, Number 3, 1996, p.p.1-18

[5] P. Cabena, P. Hadjinian and R. Stadler “Discovering data mining: from concept to implementation.