Signal Piloted Processing of the Smart Meter Data for Effective Appliances Recognition
- PDF / 743,511 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 78 Downloads / 189 Views
ORIGINAL ARTICLE
Signal Piloted Processing of the Smart Meter Data for Effective Appliances Recognition Saeed Mian Qaisar1 · Futoon Alsharif1 Received: 27 January 2020 / Revised: 27 April 2020 / Accepted: 29 May 2020 © The Korean Institute of Electrical Engineers 2020
Abstract The installation of smart meters is fast growing to effectively support various smart grid stack holders. Collection and processing of fine-grained metering data is important for proper analysis and decision support. The traditional smart meters are based on standardized and time-invariant tactics to acquire and process the data. This results in the collection, storage, and processing of a huge amount of unneeded data. The focus of this paper is to enhance the contemporary smart meters data acquisition and processing chains. The objective is to attain real-time compression and computational effectiveness to enhance the system performance in terms of data analysis, storage and transmission and to diminish its consumption overhead. In this framework, the signal-piloted event-driven sampling and processing tactics are exploited. The novel adaptive rate techniques are used for data segmentation and extraction of features. Household appliances consumption patterns related features are being classified subsequently. It is realized by employing the mature K-Nearest Neighbor and the Artificial Neural Network classifiers. Results demonstrate a 3.8-fold compression gain and computational effectiveness of the designed solution over traditional counterpart while securing the best classification accuracy of 94.4% for the 6-class appliances dataset. Keywords Smart meter data · Automatic load identification · Signal-piloted processing · Feature extraction · K-nearest neighbor · Classifier · Artificial neural network
1 Introduction 1.1 Background Household smart meters calculate power usage in realtime at fine granularities and they are seen as the base of a potential smart electricity grid. Significant numbers of smart meters are deployed worldwide due to their advantages, which are expected to offer reliability of services to all smart grid holders [1–3]. During peak hours, residential sector electricity use accounts for more than a third of total electricity demand [1]. Consumer awareness can help to forecast demand and adjust future investments. Constant feedback on the use * Saeed Mian Qaisar [email protected] Futoon Alsharif [email protected] 1
Department of Electrical and Computer Engineering, College of Engineering, Effat University, Jeddah 22332, Saudi Arabia
of electricity is helpful for consumers to learn more about their electricity use and to encourage initiatives for energy efficiency [1–3]. In this context, interest is benefiting from automatic recognition of household appliances [3]. One of the potential applications is a comprehensive power consumption bill that is actually most often a blind calculation at the house meter. Another application may be to automate load-shedding by knowing which device can turn on
Data Loading...
