東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

A Framework for Enabling Energy-Awar...

Berges Gonzalez, Mario E.

FindBook

Google Book

Amazon

博客來

A Framework for Enabling Energy-Aware Facilities Through Minimally-Intrusive Approaches.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	A Framework for Enabling Energy-Aware Facilities Through Minimally-Intrusive Approaches./
作者:	Berges Gonzalez, Mario E.
面頁冊數:	184 p.
附註:	Source: Dissertation Abstracts International, Volume: 72-02, Section: B, page: 1059.
Contained By:	Dissertation Abstracts International72-02B.
標題:	Engineering, Electronics and Electrical. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3438459
ISBN:	9781124414607

A Framework for Enabling Energy-Aware Facilities Through Minimally-Intrusive Approaches.
Berges Gonzalez, Mario E.

A Framework for Enabling Energy-Aware Facilities Through Minimally-Intrusive Approaches. - 184 p.

Source: Dissertation Abstracts International, Volume: 72-02, Section: B, page: 1059.

Thesis (Ph.D.)--Carnegie Mellon University, 2010.

This thesis presents a framework for leveraging easy-to-obtain data sources in a residential building to infer the operational schedule and electricity consumption of the appliances present in it. The framework, which utilizes and extends techniques from the Non-Intrusive Load Monitoring (NILM) domain, is designed around the end-user experience with a particular focus on attempting to automate the process of training and calibrating the algorithms. To simplify the training I developed an approach for generating electrical signatures that can generalize the state transition transients for a particular type of appliance. These new generalized signatures, the eigen-transients, reduce the need of the user to train the system on the appliance class in question. A continuous calibration process for the appliance models learned by the system is also developed. This approach can leverage user input as well as triggers based on non-electrical sensor data (e.g., environmental sensors, motion sensors, etc.), to update the models and adapt to the changing conditions in the home (e.g., degradation of appliances, change in the load composition, etc.). Moreover, I present a series of performance metrics, called Energy Identification Ratios, that allow objective comparisons between different NILM algorithms to be made.

ISBN: 9781124414607Subjects--Topical Terms:

626636
Engineering, Electronics and Electrical.

A Framework for Enabling Energy-Aware Facilities Through Minimally-Intrusive Approaches.
LDR:03591nam a2200313 4500 001 1967722
005 20141124124223.5
008 150210s2010 ||||||||||||||||| ||eng d
020 $a 9781124414607
035 $a (MiAaPQ)AAI3438459
035 $a AAI3438459
040 $a MiAaPQ $c MiAaPQ
100 1 $a Berges Gonzalez, Mario E. $3 2104783
245 1 2 $a A Framework for Enabling Energy-Aware Facilities Through Minimally-Intrusive Approaches.
300 $a 184 p.
500 $a Source: Dissertation Abstracts International, Volume: 72-02, Section: B, page: 1059.
500 $a Adviser: Lucio Soibelman.
502 $a Thesis (Ph.D.)--Carnegie Mellon University, 2010.
520 $a This thesis presents a framework for leveraging easy-to-obtain data sources in a residential building to infer the operational schedule and electricity consumption of the appliances present in it. The framework, which utilizes and extends techniques from the Non-Intrusive Load Monitoring (NILM) domain, is designed around the end-user experience with a particular focus on attempting to automate the process of training and calibrating the algorithms. To simplify the training I developed an approach for generating electrical signatures that can generalize the state transition transients for a particular type of appliance. These new generalized signatures, the eigen-transients, reduce the need of the user to train the system on the appliance class in question. A continuous calibration process for the appliance models learned by the system is also developed. This approach can leverage user input as well as triggers based on non-electrical sensor data (e.g., environmental sensors, motion sensors, etc.), to update the models and adapt to the changing conditions in the home (e.g., degradation of appliances, change in the load composition, etc.). Moreover, I present a series of performance metrics, called Energy Identification Ratios, that allow objective comparisons between different NILM algorithms to be made.
520 $a A total of 5 data-sets were used to perform the experiments and validate the framework. They were obtained from measurements taken in residential buildings around the city of Pittsburgh, Pennsylvania, USA. Of the approaches investigated to produce generalized signatures, the eigen-transients achieved the best results. For the case of microwave and refrigerator transients, the combined detection/classification accuracy was close to perfect in certain data-sets. However, further research is needed to evaluate the ability of the approach to be generalized and to determine its limitations. The algorithms for learning the appliance models were able to estimate the energy consumption of individual appliances with an error of 15% in some cases, during a week-long test. The Energy Identification Ratios were able to capture the event-detection and classification errors and summarize them into a single number that reflected how well the algorithms performed.
520 $a It is envisioned that the framework presented herein could help to increase awareness about energy consumption by making use of existing infrastructure and minimal additional hardware. It could also help to empower the users by providing then with actionable information that can directly affect their behavior and have better control on their expenditure.
590 $a School code: 0041.
650 4 $a Engineering, Electronics and Electrical. $3 626636
650 4 $a Engineering, Architectural. $3 1671790
650 4 $a Computer Science. $3 626642
690 $a 0544
690 $a 0462
690 $a 0984
710 2 $a Carnegie Mellon University. $3 1018096
773 0 $t Dissertation Abstracts International $g 72-02B.
790 $a 0041
791 $a Ph.D.
792 $a 2010
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3438459