The paradigm of the Internet of Things (IoT) has incorporated new applications for human daily life. Some of these applications are based on architectures which include wireless sensor-actuator networks. The information which is collected by the sensors is processed in order to decide when to enable or disable an actuator to perform a particular task. Often, the processing of the information is performed in the cloud consuming a lot of computing resources and bandwidth. In this paper, we propose a circuit which includes the SCT-013030 sensor and the ESP8266 NodeMcu V2 module for energy monitoring consumption in smart homes using a wireless sensor network. An artificial neural network is implemented using the processor of the ESP8266 NodeMcu module to recognise when there is unusual energy consumption in home appliances. The consumption information obtained by the wireless sensor is collected in a MySQL database, for which a Raspberry Pi 3B is used as server. Our artificial-neural-network-enabled circuit will be capable of warning the user of an abnormal energy consumption.