Abstract
As people increasingly rely on electrical devices for their daily tasks. As a result, energy consumption rates have sharply risen, leading to higher household electricity bills. This has produced a growing demand for energy monitoring systems that can accurately estimate energy usage, especially for older residential appliances that are difficult or expensive to update with monitoring sensors. However, current energy monitoring systems have some drawbacks, such as the inability to detect different types of appliances and the deployment complexity accurately. Moreover, such systems are too costly to use in older power infrastructures. To address this issue, we propose a centralized smart energy monitoring system that utilizes prediction algorithms to calculate the power consumption of legacy home appliances. The primary goal of our proposed system is to overcome the limitations of legacy home appliances that require infrastructure upgrades. The system consists of two layers: a hardware layer that includes an Emontx device, Analog-to-Digital Converters (ADC), and Current Transformer (CT) sensors, and a software layer that includes Artificial Intelligence (AI) proposed predictors using a pre-defined set of rules and K Nearest Neighbours (KNN) algorithms. We conducted experiments on real home appliances to evaluate the proposed model. The accuracy of the proposed models showed positive results after several modifications and hard tuning of several parameters in the hardware devices, specifically for Jordanian power plants.