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.

With the deteriorating ecological environment and increasing energy consumption, developing clean and renewable energy sources has become a key measure to solve environmental problems and energy shortages. The multicriteria decision-making (MCDM) technique is widely used in the assessment of renewable energy alternatives (REA) to determine the most sustainable and appropriate option for a country or region. Classic REA ranking is conducted in a deterministic environment through MCDM techniques. However, with the increasing complexity of environmental and energy issues, the REA ranking method is unsuitable for use in today’s China. Therefore, in this paper, a fuzzy MCDM technique based on the interval-valued hesitant fuzzy elimination and choice expressing reality (IVHF-ELECTRE II) method, taking into account the uncertainty and ambiguity of the information, is proposed for REA ranking. A case study in China is conducted to elaborate on the rationality and feasibility of the proposed framework. According to the ranking results, hydro is determined as the best REA in China, followed by wind energy, solar photovoltaic, geothermal, biomass energy, and solar thermal. This research provides a feasible method and insightful reference for national decision-makers to utilize when evaluating the REA and establishing a macroplanning policy for renewable energy under an uncertain environment.

The green development of electric power is a key measure to alleviate the shortage of energy supply, adjust the energy structure, reduce environmental pollution and improve energy efficiency. Firstly, the situation and challenges of China’s power green development is analyzed. On this basis, the power green development models are categorized into two typical research objects, which are multi-energy synergy mode, represented by integrated energy systems, and multi-energy combination mode with clean energy participation. The key points of the green power development model with the consumption of new energy as the core are reviewed, and then China’s exploration of the power green development system and the latest research results are reviewed. Finally, the key scientific issues facing China’s power green development are summarized and put forward targeted countermeasures and suggestions.

The authors would like to make the following corrections to the published paper