Smart Household Energy Monitoring and Demand Forecasting Using ESP32 and Machine Learning

This paper presented an IoT-based household energy demand prediction system using Machine Learning techniques. The system uses voltage and current sensors with ESP32 to monitor real-time energy consumption and upload data to Firebase cloud storage. A Flask web application was developed for visualization and analysis of energy data. Machine learning algorithms such as Linear Regression, Random Forest, and LSTM were used for predicting future energy demand. The experimental results showed that the proposed system provides accurate prediction and effective real-time monitoring. Among all models, LSTM achieved the best performance for energy forecasting. The proposed system is low-cost, efficient, and suitable for smart home energy management applications.

1.      [1] B. Devanathan, S. R. Salkuti, and P. V. R. Reddy, “Explainable AI framework using XGBoost with SHAP and LIME for household energy forecasting,” IEEE Access, vol. 13, pp. 102345–102358, 2025. 2.      [2] M. Meyer, J. L. H. W. Bastian, and K. Morik, “Benchmarking time series foundation models for short-term household electricity load forecasting,” IEEE Access, vol. 13, pp. 115678–115692, 2025. 3.      [3] V. Kolluru, A. Sharma, and R. Singh, “AI-driven energy optimization: Household power consumption prediction using LSTM networks,” in Proc. IEEE Int. Conf. on Machine Learning (ICM), 2024, pp. 1–6. 4.      [4] A. Silva, J. Ferreira, and M. Carvalho, “A data-driven approach to predict electrical energy consumption in households,” in Proc. IEEE IECON, 2024, pp. 2345–2350. 5.      [5] Y. Li, X. Zhang, and H. Wang, “Temporal-spatial graph neural network for energy consumption prediction,” IEEE Trans. on Artificial Intelligence, vol. 6, no. 2, pp. 145–156, 2025. 6.      [6] A. Al-Dahhan, M. A. Khan, and S. Rehman, “Federated learning for privacy-preserving smart home energy prediction,” IEEE Internet of Things Journal, vol. 12, no. 3, pp. 3456–3468, 2025. 7.      [7] H. Zhou, Y. Chen, and L. Liu, “Personalized federated learning for household energy forecasting,” Applied Energy, vol. 356, pp. 125419, 2025. 8.      [8] J. Wang, Z. Liu, and K. Sun, “iTransformer-based energy consumption forecasting for smart buildings,” Energy and Buildings, vol. 310, pp. 114894, 2024. 9.      [9] S. Kumar, R. Patel, and A. Verma, “Hybrid CNN-BiLSTM model with attention mechanism for energy prediction,” Heliyon, vol. 10, no. 1, pp. e41507, 2025. 10.   [10] H. Kim and J. Lee, “Smart home energy management using IoT and machine learning algorithms,” IEEE Access, vol. 12, pp. 88765–88778, 2024.