Abstract
Residential energy consumption constitutes a significant portion of the total electricity demand, emphasizing the urgent need for accurate short-term load forecasting to facilitate efficient energy management. Initially, a Bidirectional Long Short-Term Memory (BiLSTM) model was employed to analyze household energy consumption patterns using publicly available datasets. To further enhance forecasting accuracy and improve adaptability to real-world scenarios, a real-time data collection system was developed utilizing an ESP32. This system was designed to capture key parameters, including voltage, current, power, and energy consumption, thereby generating a custom dataset. Subsequently, this custom dataset was used to train the BiLSTM model, which was then deployed on an STM32 microcontroller for edge-based forecasting. For fine-tuning the model's hyperparameters, the Particle Swarm Optimization (PSO) technique was implemented. Pre-processing techniques were applied to filter and reduce noise within the datasets. Comparative studies conducted between the BiLSTM models trained on publicly available data and the customized data demonstrated the superiority of the customized data in terms of forecasting accuracy and sensitivity in edge-based performance. The proposed methodology outperforms traditional forecasting techniques by enabling a scalable, adaptive, and effective solution for residential energy management.
References
- Y. Wang et al.,” Short-Term Load Forecasting for Industrial Customers Based on TCN-LightGBM,” in IEEE Transactions on Power Systems, vol. 36, no. 3, May2021,https://doi.org/10.1109/TPWRS.2020.3028133. 1984-1997.
- Yuanyuan Wang, Shanfeng Sun, Xiaoqiao Chen, Xiangjun Zeng, Yang Kong, Jun Chen, Yongsheng Guo, Tingyuan Wang, “Shortterm load forecasting of industrial customers based on SVMD and XGBoost”, International Journal of Electrical Power & Energy Systems, Volume 129,2021,106830, ISSN 0142-0615, https://doi.org/10.1016/j.ijepes.2021.106830.
- Hong, Tao, and Shu Fan. "Probabilistic electric load forecasting: A tutorial review." International Journal of Forecasting 32, no. 3 (2016): 914-938.
- Kiruthiga, D., and V. Manikandan. "Levy flight-particle swarm optimization-assisted BiLSTM+ dropout deep learning model for short-term load forecasting." Neural Computing and Applications 35, no. 3 (2023): 2679-2700.
- Dai, LuPing. "Performance analysis of deep learning-based electric load forecasting model with particle swarm optimization." Heliyon 10, no. 16 (2024).
- Han, Lijia, Xiaohong Wang, Yin Yu, and Duan Wang. "Power Load Forecast Based on CS-LSTM Neural Network." Mathematics (2227-7390) 12, no. 9 (2024).
- Sun, Yiyang, Xiangwen Wang, and Junjie Yang. "Modified particle swarm optimization with attention-based LSTM for wind power prediction." Energies 15, no. 12 (2022): 4334.
- Cai, Changchun, Yuan Tao, Tianqi Zhu, and Zhixiang Deng. "Short-term load forecasting based on deep learning bidirectional lstm neural network." Applied Sciences 11, no. 17 (2021): 8129.
- Elsts, Atis, and Ryan McConville. "Are microcontrollers ready for deep learning-based human activity recognition?." Electronics 10, no. 21 (2021): 2640.
- Zhang, Chenjun, Fuqian Zhang, Fuyang Gou, and Wensi Cao. "Study on short-term electricity load forecasting based on the modified simplex approach sparrow search algorithm mixed with a bidirectional long-and short-term memory network." Processes 12, no. 9 (2024): 1796.