Vol. 4 No. 2 (2026)

Article

• Open Access

  Article ID: 560

  

  Design and Experimental Evaluation of Electromagnetic Energy-Harvesting Speed Humps for Sustainable Urban Transportation

  by Wasan Theansuwan, Surachai Hemhirun

  Clean Energy Science and Technology, Vol.4, No.2, 2026;
  1 Views

  DOI: https://doi.org/10.18686/cest560

  This study presents the design and experimental evaluation of an electromagnetic energy-harvesting speed hump (EHSH), developed to capture vehicular kinetic energy and convert it into usable electrical power. The system incorporates a rack-and-pinion mechanism coupled with a flywheel and permanent-magnet generator to ensure efficient torque transfer and energy storage. Experimental trials were performed with vehicles weighing 1100 kg, 1500 kg, and 2300 kg, operated at speeds ranging from 3 to 12 km/h. The resulting power outputs were recorded in terms of rotational speed, voltage, current, and harvested power, with comparative analysis between front- and rear-axle loading conditions. The results show that higher vehicle weights and speeds significantly increase energy output, with rear wheels generating slightly higher values than front wheels. Recent literature highlights that EHSH systems can achieve average outputs between 9–20 W in field applications and up to 85% conversion efficiency with optimized permanent-magnet linear generators. The findings of this work confirm the potential of EHSHs as sustainable urban infrastructure solutions, while also identifying challenges of fluctuating performance under diverse traffic conditions. This research contributes to ongoing efforts toward integrating renewable energy systems into road safety devices and smart city applications.

  • PDF

• Open Access

  Article ID: 533

  

  Energy demand forecasting using deep models and autoencoder- transformer

  by Zohreh Dorrani

  Clean Energy Science and Technology, Vol.4, No.2, 2026;
  13 Views

  DOI: https://doi.org/10.18686/cest533

  This study evaluates five prominent deep learning models—CNN-LSTM, Bidirectional LSTM, GRU, Transformer, and the proposed Deep Autoencoder-Transformer for the task of energy demand forecasting. Accurate prediction of energy demand is essential for optimizing consumption and maintaining power grid stability amidst increasing complexity and multivariate data characteristics. While previous research has predominantly assessed more traditional models such as LSTM and GRU, this research fills an important gap by thoroughly comparing these with the Transformer and a novel hybrid autoencoder-Transformer model. The models were systematically trained on multivariate inputs after comprehensive preprocessing and evaluated using statistical metrics including MAE, RMSE, MAPE, and coefficient of determination (R²). The findings demonstrate that the Deep Autoencoder-Transformer model outperforms all other architectures, achieving the lowest error rates (MAE = 8.5, RMSE = 10.75, MAPE = 3.46%) and highest explanatory power (R² = 0.991). The Transformer also achieves strong performance (MAE = 10.14, R² = 0.988), reflecting its ability to model long-term dependencies effectively. GRU and Bidirectional LSTM models follow, balancing accuracy and computational efficiency, while CNN-LSTM, despite its combined spatial and temporal feature extraction abilities, shows comparatively lower precision likely due to architectural limitations with long-range temporal modeling. This study highlights the superior capability of attention-based Transformer architectures, especially when combined with deep autoencoding, to capture complex temporal patterns in multivariate energy data. It offers a scalable and systematic framework for benchmarking deep learning models applicable to energy demand forecasting. These insights are valuable to energy system operators and policymakers for selecting appropriate machine learning models, with the hybrid Deep Autoencoder-Transformer emerging as a promising solution for more accurate, long-horizon, multi-step forecasting in intelligent energy systems.

  • PDF