The inherent intermittency and uncertainty of wind power have brought challenges in accurate wind power output forecasting, which also cause tricky problems in the integration of wind power to the grid. In this paper, a hybrid deep learning model bidirectional long short term memory-convolutional neural network (BiLSTM-CNN) is proposed for short-term wind power forecasting. First, the grey correlation analysis is utilized to select the inputs for forecasting model; Then, the proposed hybrid model extracts multi-dimension features of inputs to predict the wind power from the temporal-spatial perspective, where the Bi-LSTM model is utilized to mine the bidirectional temporal characteristics while the convolution and pooling operations of CNN are utilized to extract the spatial characteristics from multiple input time series. Lastly, a case study is conducted to verify the superiority of the proposed model. Other deep learning models (Bi-LSTM, LSTM, CNN, LSTM-CNN, CNN-BiLSTM, CNN-LSTM) are also simulated to conduct comparison from three aspects. The results show that the BiLSTM-CNN model has the best accuracy with the lowest RMSE of 2.5492, MSE of 6.4984, MAE of 1.7344 and highest R² of 0.9929. CNN has the fastest speed with an average computational time of 0.0741s. The hybrid model that mines the spatial feature based on the extracted temporal feature has a better performance than the model mines the temporal feature based on the extracted spatial feature.

China has now become the largest country in carbon emissions all over the world. Furthermore, with transportation accounting for an increasing proportion of CO₂ emissions year by year, the transportation sector has turned out to be one of the main sectors which possesses a high growth speed in CO₂ emissions. To accurately analyze potentially influencing factors which accelerate the process of CO₂ emissions of transportation sector in China, based on carbon accounting by the checklists method of Intergovernmental Panel on Climate Change’s (IPCC), in this paper, we propose a decomposition model using Logarithmic Mean Divisia Index (LMDI) decomposition analysis technology and modified fixed growth rate method. Then effects of six influencing factors including energy structure, energy efficiency, transport form, transportation development, economic development and population size from 2001 to 2014 were quantitatively analyzed. Consequently, the results indicate that: (1) economic development accounts most for driving CO₂ emissions growth of the transportation sector, while energy efficiency accounts most for suppressing CO₂ emissions growth; (2) the pulling effects of natural gas, electricity and other clean energy consumption on CO₂ emissions growth offset the inhibitory effects of traditional fossil fuels, making energy structure play a significant role in promoting CO₂ emissions growth; (3) the inhibitory effects of railways and highways lead to inhibitory effects of transport form on CO₂ emissions growth; (4) transportation development plays an obvious role in promoting CO₂ emissions, while the effects of population size is relatively weaker compared with those of transportation development. Furthermore, the decomposition model of CO₂ emissions factors in transport industry constructed in this paper can also be applied to other countries so as to provide guidance and reference for CO₂ emissions analysis of transportation industry.

The research on the sustainability evaluation of innovation and entrepreneurship education for clean energy majors in colleges and universities can not only cultivate more and better innovative and entrepreneurial talents for the development of sustainable energy but also provide a reference for the sustainable development of innovation and entrepreneurship education for other majors. To achieve systematic and comprehensive scientific evaluation, this paper proposes an evaluation model based on SPA-VFS and Chaos bat algorithm to optimize GRNN. Firstly, the sustainability evaluation index system of innovation and entrepreneurship education for clean energy major in colleges and universities is constructed from the four aspects of the environment, investment, process, and results, and the meaning of each evaluation index is explained; Then, combined with variable fuzzy set evaluation theory (VFS) and set pair analysis theory (SPA), the classical evaluation model based on SPA-VFS is constructed, and the entropy weight method and rank method are coupled to obtain the index weight. The basic bat algorithm is improved by using Tent chaotic mapping, and the chaotic bat algorithm (CBA) is proposed. The generalized regression neural network (GRNN) model is optimized by CBA, and the intelligent evaluation model based on CBA-GRNN is obtained to realize fast real-time calculation; finally, a numerical example is used to verify the scientificity and accuracy of the model proposed in this paper. This study is conducive to a comprehensive evaluation of the sustainability of innovation and entrepreneurship education for clean energy major in colleges and universities, and is conducive to the healthy and sustainable development of innovation and entrepreneurship education for clean energy major in colleges and universities, so as to provide more innovative and entrepreneurial talents for the clean energy industry.

As a kind of clean and renewable energy, wind power is winning more and more attention across the world. Regarding wind power utilization, safety is a core concern and such concern has led to many studies on predicting wind speed. To obtain a more accurate prediction of the wind speed, this paper adopts a new hybrid forecasting model, combing empirical mode decomposition (EMD) and the general regression neural network (GRNN) optimized by the fruit fly optimization algorithm (FOA). In this new model, the original wind speed series are first decomposed into a collection of intrinsic mode functions (IMFs) and a residue. Next, the inherent relationship (partial correlation) of the datasets is analyzed, and the results are then used to select the input for the forecasting model. Finally, the GRNN with the FOA to optimize the smoothing factor is used to predict each sub-series. The mean absolute percentage error of the forecasting results in two cases are respectively 8.95% and 9.87%, suggesting that the hybrid approach outperforms the compared models, which provides guidance for future wind speed forecasting.