The integration of phase change material (PCM) into building envelopes can effectively regulate indoor temperature fluctuations and reduce building energy consumption. However, passive PCM-integrated walls cannot be actively controlled. As an innovative application of flexible envelope system, active phase change wall (APW) enable active control of the wall's thermal performance by integrating phase change material (PCM) with a cold water piping system.However, the complexity of thermal inertia and heat transfer processes poses a challenge in quickly predicting the thermal responsiveness of the system. In this study, a methodology for predicting the indoor thermal response of APW using machine learning is proposed to quickly and accurately predict the APW thermal storage process and offer a solution for the control of intelligent flexible envelope system. Comparing the predictive accuracy and extrapolative performance of three shallow machine learning models (random forest, support vector machines, and extreme learning machines) with six advanced deep learning models (long short-term memory, gated recurrent units, convolutional neural networks, and three type of Transformer-LSTM models). The machine learning models were trained using data from scaled experimental platforms. Results show that while machine learning models have a slight advantage in accuracy on training and test sets, deep learning models perform better in extrapolative tests. Notably, the Transformer-LSTM model improved the R2 value by 13.64% compared to the random forest model in extrapolative tests, with corresponding reductions in mean absolute error by 70.75%, mean absolute percentage error by 68.89%, and root mean square error by 65.05%.
Abstract Wind farm NWP data has regularity and difference, and making full use of the information contained in NWP data is the key to wind power prediction. A short-term forecasting method for wind power based on nutrosophic clustering and GA-ELM is proposed. Firstly, the wind farm NWP data is divided into several weather types by the Chinese wisdom clustering method, and then the GA-ELM model is established for different weather types. The Gaussian index method is used to classify the forecast data, and then the different types of forecast data are substituted into the corresponding model predictions. Taking a 14MW wind farm in Northeast China as an example, the experiment shows that the nutrosophic clustering method reduces the influence of boundary points and abnormal points on the clustering center. Compared with the traditional method, the method has higher precision and universality.
With the increase of the share of wind power in energy distribution, accurate ultra-short term wind power prediction results play key role in the optimal real-time scheduling of the power grid. A stacking integration method is proposed based on error correction in this paper. First, the support vector machine for regression (SVR), gradient boosting decision tree (GBDT), multilayer perceptron (MLP) and random forest (RF) are selected as the base models. Then, the linear regression is utilized as the meta-model. The error generated by the base model in the verification set and the spliced verification set are introduced into the training set of the meta-model. Finally, the prediction results and prediction errors in the prediction set are applied to the meta-model to predict the ultra-short term wind power. The experiment results show that the effectiveness of the proposed method by using the real wind power data.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)