In this sense, this work differs from existing solutions in at least three aspects: (i) it employs an intelligent method to monitor electric energy consumption; (ii) it uses ML techniques to analyze the behavior of electronic equipment by means of the WSNs; and (iii) it sends alerts to a smartphone in an intelligent way when an anomaly is identified.To validate the performance of the NodePM, we built a prototype (see Section 3) to scan the power consumption of the electronic equipment. A number of experiments were conducted with this prototype, including an analysis of variance (ANOVA) and parametric and non-parametric tests. The results of these tests, which were obtained from a statistical analysis, provided evidence of the feasibility of the NodePM in the platform that was developed.

In addition, the NodePM provided better efficiency to detect novelties when compared with the Self-Organizing Novelty Detection (SONDE) [16] method, outperforming it in different scenarios in all evaluations carried out.The rest of this paper is structured in the following way. Section 2 reviews related studies. Section 3 describes the strategy employed for the development of the work and the method proposed. Sections 4 and 5 provide an assessment of the performance and include a discussion of the results obtained. Finally, Section 6 shows the conclusions and examines what contribution has been made by this study.2.?Related WorkSeveral studies have been published in the area of smart grids in the last few years. This section presents scientific papers [3,5,6,8,9,11,12] whose focus corresponds mostly to the monitoring of electric energy consumption.

However, despite all the recent advances that have been made, there are still a number of challenges and unresolved problems in this area. For example, the lack of a methodology to detect anomalies/novelties in the monitored environment.One of the oldest models of a smart grid is the Telegestore project [6]. Telegestore is a system Batimastat for the remote management of residential and commercial meters with a view toward exploring the low-voltage distribution system between the transformers and meters. The main limitations of Telegestore are as follows: (i) the disregard of a method for detecting anomalies (for example, black-outs) in the low voltage system; and (ii) the monitoring of the sectors is not examined, such as a room in a house, for example.Erol-Kantarci and Mouftah [5] propose the use of a WSN to manage the electricity of a residence by means of the smart grid. For this reason, researchers have proposed a work, called Appliance Coordination (ACORD), to reduce the cost of energy at peak times.