ISSN: 3079-8906 (Online)
3079-8892 (Print)
School of Electric Power Engineering, South China University of Technology, Guangzhou, China
Department of Electrical Energy and Information Engineering, University of Bologna, Viale del Risorgimento, 2, Bologna 40136, Italy
The ability to ensure safe and economic operation of power grids is challenging because of the large-scale integration of wind power as a result of its intermittent and fluctuating nature. Accurate wind power prediction is critical to overcome these concerns. This study proposed a novel hybrid encoder–decoder model by combining bidirectional gated recurrent unit, multi-head attention mechanism, and ensemble technique for multi-step ultra-short-term power prediction of wind farms. The bidirectional gated recurrent unit accurately details the complex temporal dependency of input sequence information in the encoder and outputs the encoded vector. To focus on features that contribute more to the output, two types of multi-head attention mechanism, including self-attention and cross-attention, were used in the decoder to decode the encoded vector and obtain the forecast wind power sequence. Furthermore, an ensemble technique was used to integrate forecast results from various individual predictors, which reduced the uncertainty of individual prediction results and improved predictive accuracy. The input data included historical information from the wind farm and future information from numerical weather prediction. The forecast model was validated using actual data, and results showed that it achieved superior accuracy and stability compared with other existing models in four multi-step prediction scenarios (1-, 2-, 3-, and 4-h prediction).
The rising power demand, driven by population growth, technological innovations, and the advent of smart cities, necessitates precise forecasting to ensure efficient energy distribution and align supply with demand. This paper presents a novel methodology for predicting short-term power consumption through machine learning approaches, specifically employing multiple linear regression for feature selection. In this study, two models are implemented and compared: Support Vector Regression (SVR) and Long-Short-Term Memory (LSTM). Exploratory data analysis was used to discover the relationships and associations between variables. It reveals that temperature, humidity, time of day, and season are major determinants of electricity use. The results indicate that the LSTM model surpasses Support Vector Regression (SVR) in terms of accuracy and precision. By incorporating multiple linear regression (MLR) for feature selection, the performance of both models improved, with precision gains of 29.1% for SVR and 18.19% for LSTM. Removing extraneous elements, such as wind speed and diffuse solar radiation, enhanced the models’ efficiency and interpretability, allowing for a focus on the most significant factors. The study’s findings underscore the need to optimize feature selection to enhance forecast accuracy and streamline models. This method provides critical insights for enhancing energy management strategies and facilitating sustainable power distribution in light of rising global energy demand.
This study presents the design and performance evaluation of a smart kinetic double-skin window system designed to enhance natural ventilation in buildings, especially those limited to single-sided airflow. The system dynamically adjusts external blade angles in response to real-time wind conditions, using environmental sensors and automated control to optimise airflow distribution and energy performance. Computational fluid dynamics (CFD) simulations were conducted for two blade configurations (7° and 15°) under varying wind speeds and directions. Results show that the 15° configuration enhances airflow reach and achieves up to 40% higher air change rates (ACH) compared to the 7°, making it more suitable for high-demand ventilation scenarios. In contrast, The 7° configuration produces lower but more uniform airflow, which is more appropriate for occupant comfort in residential or office environments. Detailed analysis of velocity fields, pressure distributions, and airflow paths confirms that the system effectively adapts to wind direction, maintaining balanced ventilation through integrated airflow channels. The simulations were validated against experimental data, achieving a Close correlation. While thermal and buoyancy effects were not included, future work will extend the model to hybrid ventilation scenarios. The proposed system demonstrates significant potential for sustainable ventilation applications in new and retrofitted building envelopes.
This study presents the design and performance evaluation of a smart kinetic double-skin window system designed to enhance natural ventilation in buildings, especially those limited to single-sided airflow. The system dynamically adjusts external blade angles in response to real-time wind conditions, using environmental sensors and automated control to optimise airflow distribution and energy performance. Computational fluid dynamics (CFD) simulations were conducted for two blade configurations (7° and 15°) under varying wind speeds and directions. Results show that the 15° configuration enhances airflow reach and achieves up to 40% higher air change rates (ACH) compared to the 7°, making it more suitable for high-demand ventilation scenarios. In contrast, The 7° configuration produces lower but more uniform airflow, which is more appropriate for occupant comfort in residential or office environments. Detailed analysis of velocity fields, pressure distributions, and airflow paths confirms that the system effectively adapts to wind direction, maintaining balanced ventilation through integrated airflow channels. The simulations were validated against experimental data, achieving a Close correlation. While thermal and buoyancy effects were not included, future work will extend the model to hybrid ventilation scenarios. The proposed system demonstrates significant potential for sustainable ventilation applications in new and retrofitted building envelopes.
The rising power demand, driven by population growth, technological innovations, and the advent of smart cities, necessitates precise forecasting to ensure efficient energy distribution and align supply with demand. This paper presents a novel methodology for predicting short-term power consumption through machine learning approaches, specifically employing multiple linear regression for feature selection. In this study, two models are implemented and compared: Support Vector Regression (SVR) and Long-Short-Term Memory (LSTM). Exploratory data analysis was used to discover the relationships and associations between variables. It reveals that temperature, humidity, time of day, and season are major determinants of electricity use. The results indicate that the LSTM model surpasses Support Vector Regression (SVR) in terms of accuracy and precision. By incorporating multiple linear regression (MLR) for feature selection, the performance of both models improved, with precision gains of 29.1% for SVR and 18.19% for LSTM. Removing extraneous elements, such as wind speed and diffuse solar radiation, enhanced the models’ efficiency and interpretability, allowing for a focus on the most significant factors. The study’s findings underscore the need to optimize feature selection to enhance forecast accuracy and streamline models. This method provides critical insights for enhancing energy management strategies and facilitating sustainable power distribution in light of rising global energy demand.
The ability to ensure safe and economic operation of power grids is challenging because of the large-scale integration of wind power as a result of its intermittent and fluctuating nature. Accurate wind power prediction is critical to overcome these concerns. This study proposed a novel hybrid encoder–decoder model by combining bidirectional gated recurrent unit, multi-head attention mechanism, and ensemble technique for multi-step ultra-short-term power prediction of wind farms. The bidirectional gated recurrent unit accurately details the complex temporal dependency of input sequence information in the encoder and outputs the encoded vector. To focus on features that contribute more to the output, two types of multi-head attention mechanism, including self-attention and cross-attention, were used in the decoder to decode the encoded vector and obtain the forecast wind power sequence. Furthermore, an ensemble technique was used to integrate forecast results from various individual predictors, which reduced the uncertainty of individual prediction results and improved predictive accuracy. The input data included historical information from the wind farm and future information from numerical weather prediction. The forecast model was validated using actual data, and results showed that it achieved superior accuracy and stability compared with other existing models in four multi-step prediction scenarios (1-, 2-, 3-, and 4-h prediction).
This study presents the design and performance evaluation of a smart kinetic double-skin window system designed to enhance natural ventilation in buildings, especially those limited to single-sided airflow. The system dynamically adjusts external blade angles in response to real-time wind conditions, using environmental sensors and automated control to optimise airflow distribution and energy performance. Computational fluid dynamics (CFD) simulations were conducted for two blade configurations (7° and 15°) under varying wind speeds and directions. Results show that the 15° configuration enhances airflow reach and achieves up to 40% higher air change rates (ACH) compared to the 7°, making it more suitable for high-demand ventilation scenarios. In contrast, The 7° configuration produces lower but more uniform airflow, which is more appropriate for occupant comfort in residential or office environments. Detailed analysis of velocity fields, pressure distributions, and airflow paths confirms that the system effectively adapts to wind direction, maintaining balanced ventilation through integrated airflow channels. The simulations were validated against experimental data, achieving a Close correlation. While thermal and buoyancy effects were not included, future work will extend the model to hybrid ventilation scenarios. The proposed system demonstrates significant potential for sustainable ventilation applications in new and retrofitted building envelopes.utf-8
The rising power demand, driven by population growth, technological innovations, and the advent of smart cities, necessitates precise forecasting to ensure efficient energy distribution and align supply with demand. This paper presents a novel methodology for predicting short-term power consumption through machine learning approaches, specifically employing multiple linear regression for feature selection. In this study, two models are implemented and compared: Support Vector Regression (SVR) and Long-Short-Term Memory (LSTM). Exploratory data analysis was used to discover the relationships and associations between variables. It reveals that temperature, humidity, time of day, and season are major determinants of electricity use. The results indicate that the LSTM model surpasses Support Vector Regression (SVR) in terms of accuracy and precision. By incorporating multiple linear regression (MLR) for feature selection, the performance of both models improved, with precision gains of 29.1% for SVR and 18.19% for LSTM. Removing extraneous elements, such as wind speed and diffuse solar radiation, enhanced the models’ efficiency and interpretability, allowing for a focus on the most significant factors. The study’s findings underscore the need to optimize feature selection to enhance forecast accuracy and streamline models. This method provides critical insights for enhancing energy management strategies and facilitating sustainable power distribution in light of rising global energy demand.utf-8
The ability to ensure safe and economic operation of power grids is challenging because of the large-scale integration of wind power as a result of its intermittent and fluctuating nature. Accurate wind power prediction is critical to overcome these concerns. This study proposed a novel hybrid encoder–decoder model by combining bidirectional gated recurrent unit, multi-head attention mechanism, and ensemble technique for multi-step ultra-short-term power prediction of wind farms. The bidirectional gated recurrent unit accurately details the complex temporal dependency of input sequence information in the encoder and outputs the encoded vector. To focus on features that contribute more to the output, two types of multi-head attention mechanism, including self-attention and cross-attention, were used in the decoder to decode the encoded vector and obtain the forecast wind power sequence. Furthermore, an ensemble technique was used to integrate forecast results from various individual predictors, which reduced the uncertainty of individual prediction results and improved predictive accuracy. The input data included historical information from the wind farm and future information from numerical weather prediction. The forecast model was validated using actual data, and results showed that it achieved superior accuracy and stability compared with other existing models in four multi-step prediction scenarios (1-, 2-, 3-, and 4-h prediction).utf-8