Forecasting and Performance Analysis of Energy Production in Solar Power Plants Using Long Short-Term Memory (LSTM) and Random Forest Models

The integration of machine learning techniques such as Long Short-Term Memory (LSTM) and Random Forest models enhances the efficiency and reliability of power plant monitoring systems. This project utilizes Raspberry Pi and Arduino to interface various sensors, including voltage and current sensors for monitoring electrical parameters, a vibration sensor to detect motor irregularities, and temperature sensors (DHT11 and DS18B20) to assess heat variations. Additionally, an MQ6 gas sensor ensures safety by detecting gas leaks. In case of any abnormal conditions, the system triggers alerts via a GSM module and a buzzer. The collected data is processed using LSTM for sequential pattern recognition and Random Forest for classification and anomaly detection, enabling predictive maintenance and fault prevention. This IoT-based smart monitoring system ensures improved safety, efficiency, and real-time fault detection in power plants.