Title: A method for electric load data verification and repair in home environment

Authors: Qi Liu; Shengjun Li; Xiaodong Liu; Nigel Linge

Addresses: Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology, Nanjing, 210044, China ' School of Computer and Software, Nanjing University of Information Science and Technology, 219 Ningliu Road, Nanjing, Jiangsu 210044, China ' School of Computing, Edinburgh Napier University, 10 Colinton Road, Edinburgh EH10 5DT, UK ' The University of Salford, Salford, Greater Manchester, M5 4WT, UK

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.

Keywords: data verify; data repair; load data quality; power system; home energy management; HEM.

DOI: 10.1504/IJES.2018.091788

International Journal of Embedded Systems, 2018 Vol.10 No.3, pp.248 - 256

Received: 03 Aug 2016
Accepted: 20 Jan 2017
Published online: 16 May 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article