Load recognition by interpreting the smart meter data

Abstract

The technological advancements have evolved the deployment of smart meters in place of the conventional ones. These smart meters are the vital elements of smart grids and are offering significant advantages for various stakeholders in terms of the social, environmental and economical constraints. The extensive installations of smart meters allow an enormous amount of data collection with a wanted granularity. Automatic data acquisition, transmission, processing and analysis are key factors behind the success of smart meters. The usage of smart meters is increasing in modern societies. A fine–grained metering data collection and analysis is necessary to bring benefits to multiple smart grid stakeholders such as energy providers, distributors, consumers and governments. The classical sensing mechanism is time–invariant. Therefore, it results in the collection, transmission, and processing of a large amount of unnecessary data. This work employs the event–driven sensing mechanism to achieve real–time data compression. Afterward, the novel adaptive rate techniques are employed for the data conditioning, segmentation, and extraction of features. The pertinent features regarding the appliances' consumption patterns are afterward used for their identification. It is realized by employing the mature Support Vector Machine, k–Nearest Neighbor, Naïve Bias and Artificial Neural Network classifiers. The applicability of the devised solution is evaluated with the help of five case studies. Final results confirm a significant compression gain and the computational effectiveness of the suggested solution while securing high classification precisions. This study works in alignment with the 2030 vision of Saudi Arabia and the goals of NEOM city. It contributes in realizing modern smart–energy related services such as detailed electricity consumption billing systems, effective load identification, decision–support for dynamic load management, support to hourly price charges, activity of daily living recognition, occupancy detection, and monitoring of user–appliance interaction.