A method for electric load data verification and repair in home environment
by Qi Liu; Shengjun Li; Xiaodong Liu; Nigel Linge
International Journal of Embedded Systems (IJES), Vol. 10, No. 3, 2018

Abstract: Home energy management (HEM) and smart home have been popular among people; HEM collects and analyses the electric load data to make the power use safe, reliable, economical, efficient and environmentally friendly. Without the correct data, the correct decisions and plans would not be made, so the data quality is of the great importance. This paper focuses on the verification and repair of the electric load data in family environment. Due to the irregularity of modern people's life styles, this paper proposes a system of 'N + 1' framework to handle this properly. The system collects information of every appliance and the power bus to make them verify each other, so it can solve the stochastic uncertainty problem and verify if the data is correct or not to ensure the data quality. In the course of data upload, there are many factors like smart meter malfunctions, communication failures and so on which will cause some wrong data. To repair the wrong data, we proposes a method called LBboosting, which integrates two curve fitting methods. As the results show, the method has a better performance than up-todate methods.

Online publication date: Wed, 16-May-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Embedded Systems (IJES):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com