<![CDATA[Humans demand electricity to conduct their daily tasks. Indonesia undergoes a yearly escalation in its electricity use. Moreover, customers encounter the difficulty of overestimating their electrical energy consumption, since they remain unaware of the power utilization linked to each frequently utilized electrical load and possess limited control over their electricity expenditure. The Kalman Filter Algorithm was utilized to estimate electricity usage via the execution of a research system. The Kalman Filter can forecast future states using minimal information. This system incorporates an IoT framework with a network communication module, the Raspberry Pi, which relays data to the database. The PZEM-004T sensor is utilized to gather data on electrical parameters from loads, including voltage, current, active power, and energy consumption. The electrical consumption was documented every 15 minutes over a duration of 60 days. The dataset was divided in an 80:20 ratio, allocating 80% for training and 20% for testing. RMSE, MSE, and MAPE are utilized to determine the accuracy metrics of each test. Additionally, the fan load is assessed in one evaluation, yielding an error percentage of 0.077% for the training data and 0.076% for the test data, determined using RMSE. The error percentage calculated using the MSE equation is 0.006% for the training data and 0.005% for the test data. The error percentage calculated by MAPE is 0.789% for the training dataset and 0.202% for the testing dataset. The findings indicate that the Kalman Filter prediction method is exceptionally proficient in forecasting electrical load consumption]]>
Copyrights © 2025
