In this sense, the use of smart grids has become increasingly important in the urban scenario, as they offer the integration of various energy sources, such as hydroelectric, atomic, solar and wind power.It is expected that the use of the smart grid will become a reality in the next few years, since industry, universities and governments throughout the world have earmarked funds for the development of this technology. This trend can be confirmed by the existence of different projects and government initiatives at both national and international levels, as well as in industry and the academic world, which are devoted to smart grids [2�C7].Despite all the achievements in this area, typically, the electric power utilities provide only the total energy consumption spent on a residence and do not offer, for example, support for remotely managing the power consumption of electronic equipment.

This means more costs for companies. In addition, it is not a simple task to determine which piece of electronic equipment have the greatest influence on the electricity bill.Thereby, an alternative to overcome some electricity suppliers’ service limitations is to integrate a wireless sensors network (WSN) into the electronic equipment of the residences [3,6,8�C12]. With the aid of a WSN, a system can be established aiming at monitoring the use of each household socket in real time, consequently allowing the user to know his track record in terms of energy consumption. Thereafter, the user can find out punctually whether there is any type of waste and take proper actions.

Detailed energy consumption information can also be used to provide the household with optimal energy saving times in countries where utility companies offer distinct time-of-use (TOU) rates, for example, being able to take advantage of off-peak pricing.Studies show that providing information about how, when, where and what users are using can help us to make the right decisions [13�C15]. Hence, it is of crucial importance to use intelligent methods in the smart grids for novelty detection and to inform the users in an individual and autonomous way, when some anomaly has occurred in the energy consumption of electronic equipment. These anomalies can arise, for example, when a piece of equipment consumes more energy than expected and/or when the equipment begins to behave in a way outside the normal pattern.

In this context, we propose an intelligent Cilengitide method, named the Novelty Detection Power Meter (NodePM), to detect the novelties in the energy consumption of electronic equipment monitored by a smart grid. Considering the entropy of each device monitored, which is calculated based on a Markov chain model, the proposed method detects the novelties through a machine learning (ML) algorithm. As proof of concept, the NodePM is integrated into a platform for the remote monitoring of energy consumption, which consists of a WSN.