WEATHER-AWARE FORECASTING OF HOUSEHOLD ELECTRICITY DEMAND
DOI:
https://doi.org/10.69980/b7mhfa95Keywords:
household electricity demand, weather-aware forecasting, time-series analysis, machine learning, energy consumptionAbstract
In Weather-aware forecasting method for the household electricity demand was developed based on real electricity consumption and climatological data in a small community located in Mexico. Analysis was conducted on the electricity-level records of the households with the relevant outdoor weather variables such as temperature, humidity, solar radiation, wind speed, rain fall, pressure etc. These methods included time-series preprocessing, lag feature construction, descriptive analysis, correlation assessment and comparative forecasting models to analyze the behavior of the demand and forecasting accuracy. Results revealed an obvious difference in household electricity usage across the hours, with higher demand for electricity in the evening hours. There is significant contextual value in the weather variables, but the strongest predictor was lagged electricity demand, which also worked well in nonlinear models. The weather-sensitive random forest model outperformed the other models and the persistence baseline, with gradient boosting closely behind. The results confirm that using these temporal demand features alongside some of the weather parameters selected will increase the accuracy of electricity forecasting and enable practical energy planning, anticipating peak demand, and managing residential demand in response to the weather.
References
1.Ahmed, M. M., Ditta, A., Siddiqa, A., Wazir, P., Shah, A. A., & Adnan, K. M. (2026). IoT‐Enabled Smart Metering With Transfer Learning for Optimized Energy Load Forecasting. International Journal of Energy Research, 2026(1), 1719445.
2.Aravanis, T., & Kanavos, A. (2026). Comparative Evaluation of Deep Learning Architectures for Electricity Demand Forecasting. Mathematics, 14(5), 827.
3.Bajrami, E., & Lameski, P. (2026). Weather-Aware Deep Reinforcement Learning for Predictive Modeling of Household Energy Dynamics. Journal of Data Analytics and Artificial Intelligence Applications, 2(1), 17-44.
4.Cavus, M., Jiang, J., & Sun, H. (2025, September). Weather-Aware Energy Forecasting with NeuroFusion: A Hybrid Deep Learning and Gradient Boosting Framework. In 2025 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) (pp. 1-6). IEEE.
5.Das, R., Debnath, S., Kandil, T., & Mia, M. U. (2026). Spatio-Temporal Forecasting of Municipal EV Charging Load Using Weather-Aware Transformer–LSTM Hybrid Models. AI, 7(6), 191.
6.Debnath, S., Basu, U., Abubakkar, M., Islam, M. R., Debnath, M., & Biswas, A. K. (2025, October A). Extreme weather grid load forecasting using weather-informed LSTM and transformer machine learning models. In 2025 57th North American Power Symposium (NAPS) (pp. 1-7). IEEE.
7.Debnath, S., Islam, M. R., Abubakkar, M., Islam, M. Z., Mridul, M. S. I., & Biswas, A. K. (2025 B, November). AI-Driven Hybrid Deep Learning Framework for Short-Term Renewable Energy Forecasting under Extreme Weather Events. In 2025 7th International Conference on Electrical, Control and Instrumentation Engineering (ICECIE) (pp. 362-369). IEEE.
8.Devanathan, B., Suyampulingam, A., Selvaraj, P., Karuppasamy, I., & Ilamparithi, T. (2025). A cloud-integrated virtual framework for lstm-driven solar forecasting and residential energy management. IEEE Access.
9.Huang, R., Zhao, P., Cao, D., Hu, W., Huang, Q., & Chen, Z. (2025). Complementary Online Learning Network for Probabilistic Load Forecasting Against Extreme Weather. IEEE Transactions on Industrial Informatics.
10.Indresh, T. B., & Parvathi, C. (2026, January). Forecast Residential Power Usage via Machine Learning and Climatic Feature Incorporations. In 2026 International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) (pp. 1-6). IEEE.
11.Jonah, S., Moses, Q., Babatunde, A., Ajao-Olarinoye, M., & Bammeke, D. (2026). LLMs for Agentic Home Energy Management. arXiv preprint arXiv:2607.04569.
12.Kayum, M. A., Islam, A. M. M. S., Hasan, R. R., Islam, M. A., & Khan, S. A. (2025). Weather-Informed Machine Learning for Predictive Modeling in Residential Air-Conditioning Supply Chain Management. Journal of Modern Thermodynamics in Mechanical Systems, 7(2), 8-20.
13.Khankal, D. V., Dev, A., Garg, A., Ravivarman, G., Vijay, S. A. A., & Wong, L. S. (2025, December). A Hybrid Method for Solar Energy Forecasting Using Weather Data and Machine Learning. In 2025 Asian Conference on Communication and Networks (ASIANComNet) (pp. 1-4). IEEE.
14.Lekhel, C. E. S., Mbayed, R., Velihorskyi, O., Husev, O., & Monmasson, E. (2025). Generic residential load profile generator based on weather data and occupancy. Mathematics and Computers in Simulation, 237, 373-389.
15.Nouhaila, I., Raja, E., Hamada, E. K., & Elyes, N. (2025, November). Weather-Aware Machine Learning Models for Energy Consumption Forecasting of Buildings in Semi-Arid Climate Zones. In International Conference of Machine Intelligence and Computer Science Applications (pp. 247-257). Cham: Springer Nature Switzerland.
16.Qiu, Z., Li, S., Cui, Y., Yang, L., Kang, Y., & Ma, X. (2026). Stochastic urban EV load forecasting: integrating markov-monte carlo simulation with spatio-temporal and traffic-weather dynamics. International Journal of Electrical Power & Energy Systems, 174, 111510.
17.Ramirez-Prado, G., Barmada, B., Bahadornejad, M., Castaño-Rosa, R., & Vilches, T. C. (2026, July). Household Energy Wellbeing in New Zealand Using Smart Meter Forecasting and Weather Data Integration. In 2026 6th International Conference on Electrical, Computer and Energy Technologies (ICECET) (pp. 1-6). IEEE.
18.Santos-Moreno, M., González-Ordiano, J. Á., Quiroz, E., Perez-DeLaMora, D. A., Mizrahi-Cojab, J., Román-Sánchez, E., Montero-Cantú, J. P., & Bustio-Martinez, L. (2023). Electrical demand/consumption and climatological data of a small Mexican community (Version 4) [Data set]. Mendeley Data. https://doi.org/10.17632/vsjtbzjttb.4
19.Savaş, A. D. (2026). Regime-aware day-ahead electricity consumption forecasting for Türkiye: A meta-learning-based ensemble approach (Master's thesis, Middle East Technical University).
20.Štěpanec, L., Aye, H. Y., Lin, O. Z., Koutroulis, E., & Juchelkova, D. (2026). Unsupervised learning-based operational regime discovery and weather sensitivity analysis of a residential photovoltaic battery system for energy management. Engineering Applications of Artificial Intelligence, 181, 115336.
21.Tang, F., Wang, Y., Zhang, Y., Guo, H., Gao, S., Shen, C., & Zhang, Z. (2026). Weather‐Aware Reinforcement Learning for Power Grid Topology Control Under Extreme Events. IET Smart Grid, 9(1), e70099.
22.Wahyuzi, Z., & Abdurrahim, A. (2025). Integrating Causal Analysis with Machine Learning for Meteorological-Based Energy Consumption Forecasting: A Multi-Method Approach. International Journal of Informatics and Computation, 7(2), 384-399.
23.Xia, X., Jiang, R., Yang, J., Wang, M., Wang, L., Wang, Q., & Gao, X. (2026). SWeDeformer: A Similar Weather Guided Decomposition Transformer for Accurate Residential Short-Term Load Forecasting. IEEE Transactions on Consumer Electronics.
24.Yaseen, M., Afnan, M., Raheel, K., Durrani, A. M., Rehman, K., Farooq, Z., ... & Aziz, A. (2025). OPTIMIZATION OF TRANSFORMER LOAD FORECASTS IN SMART GRIDS THROUGH AI-DRIVEN REGRESSION AND WEATHER DATA FUSION. Spectrum of Engineering Sciences, 937-954.
25.Zhou, M., Zhao, Z., Hu, F., Li, J., Wang, K., Jia, X., ... & Li, Y. (2026). Cooling Load Prediction via Weather-Aware Dual Adaptive Graph Learning and Exogenous Fusion. Journal of Building Engineering, 116907.
