<![CDATA[ABSTRACT Electrical energy consumption continues to increase along with the rapid development of technology, creating the need for an efficient system capable of monitoring and predicting power usage automatically and in real-time. This research aims to design and implement an Internet of Things (IoT)-based electrical power prediction system integrated with Machine Learning using the Random Forest algorithm. The system utilizes an ESP32 microcontroller and a PZEM-004T sensor to collect electrical parameters such as voltage, current, and power consumption. The collected data are transmitted through the MQTT protocol to Node-RED and stored as datasets for further analysis using Google Colaboratory. The research method includes literature study, system design, hardware and software implementation, data collection, and model training using Random Forest regression. The results show that the system successfully performs real-time monitoring and predicts future electricity consumption with an RMSE value of 100.64 and a total predicted monthly consumption of 624,860.59 kW. The system can assist users in monitoring, analyzing, and optimizing electrical energy consumption more effectively and efficiently.]]>
Copyrights © 2026
