This page has only limited features, please log in for full access.
Due to flexible and clean nature, distributed photovoltaic (PV) power plants in micro-grid are essential for solving energy and environmental problems. However, because of the high cost of weather station, the meteorological data of distributed power plants is often absent. Therefore, this paper focuses on the accurate output prediction of the target PV station without meteorological data by incorporating the output series of the adjacent PV plants and grasping features by the proposed deep learning models. A novel ultra-short term PV power prediction model based on the improved bidirectional long short-term memory model with genetic algorithm (GA-BiLSTM) is proposed to improve the performance and multiple PV output series are innovatively taken as inputs of the prediction model. A case study is conducted with an actual target PV station in a micro-grid. Sensitivity analysis of input variables is studied and the performance of proposed GA-BiLSTM model is compared with other models under different time horizons to verify the effectiveness. The results illustrate the significance of the output series of adjacent PV plants and the proposed model performs best in the ultra-short term forecasting, with lowest RMSE value of 0.438, 0.806, 1.118 in 5min, 15min, 30min ahead output prediction without meteorological data.
Hao Zhen; Dongxiao Niu; Keke Wang; Yucheng Shi; Zhengsen Ji; Xiaomin Xu. Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information. Energy 2021, 231, 120908 .
AMA StyleHao Zhen, Dongxiao Niu, Keke Wang, Yucheng Shi, Zhengsen Ji, Xiaomin Xu. Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information. Energy. 2021; 231 ():120908.
Chicago/Turabian StyleHao Zhen; Dongxiao Niu; Keke Wang; Yucheng Shi; Zhengsen Ji; Xiaomin Xu. 2021. "Photovoltaic power forecasting based on GA improved Bi-LSTM in microgrid without meteorological information." Energy 231, no. : 120908.
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.
Hao Zhen; Dongxiao Niu; Min Yu; Keke Wang; Yi Liang; Xiaomin Xu. A Hybrid Deep Learning Model and Comparison for Wind Power Forecasting Considering Temporal-Spatial Feature Extraction. Sustainability 2020, 12, 9490 .
AMA StyleHao Zhen, Dongxiao Niu, Min Yu, Keke Wang, Yi Liang, Xiaomin Xu. A Hybrid Deep Learning Model and Comparison for Wind Power Forecasting Considering Temporal-Spatial Feature Extraction. Sustainability. 2020; 12 (22):9490.
Chicago/Turabian StyleHao Zhen; Dongxiao Niu; Min Yu; Keke Wang; Yi Liang; Xiaomin Xu. 2020. "A Hybrid Deep Learning Model and Comparison for Wind Power Forecasting Considering Temporal-Spatial Feature Extraction." Sustainability 12, no. 22: 9490.
Accurately predicting wind power is crucial for the large-scale grid-connected of wind power and the increase of wind power absorption proportion. To improve the forecasting accuracy of wind power, a hybrid forecasting model using data preprocessing strategy and improved extreme learning machine with kernel (KELM) is proposed, which mainly includes the following stages. Firstly, the Pearson correlation coefficient is calculated to determine the correlation degree between multiple factors of wind power to reduce data redundancy. Then, the complementary ensemble empirical mode decomposition (CEEMD) method is adopted to decompose the wind power time series to decrease the non-stationarity, the sample entropy (SE) theory is used to classify and reconstruct the subsequences to reduce the complexity of computation. Finally, the KELM optimized by harmony search (HS) algorithm is utilized to forecast each subsequence, and after integration processing, the forecasting results are obtained. The CEEMD-SE-HS-KELM forecasting model constructed in this paper is used in the short-term wind power forecasting of a Chinese wind farm, and the RMSE and MAE are as 2.16 and 0.39 respectively, which is better than EMD-SE-HS-KELM, HS-KELM, KELM and extreme learning machine (ELM) model. According to the experimental results, the hybrid method has higher forecasting accuracy for short-term wind power forecasting.
Keke Wang; Dongxiao Niu; Lijie Sun; Hao Zhen; Jian Liu; Gejirifu De; Xiaomin Xu. Wind Power Short-Term Forecasting Hybrid Model Based on CEEMD-SE Method. Processes 2019, 7, 843 .
AMA StyleKeke Wang, Dongxiao Niu, Lijie Sun, Hao Zhen, Jian Liu, Gejirifu De, Xiaomin Xu. Wind Power Short-Term Forecasting Hybrid Model Based on CEEMD-SE Method. Processes. 2019; 7 (11):843.
Chicago/Turabian StyleKeke Wang; Dongxiao Niu; Lijie Sun; Hao Zhen; Jian Liu; Gejirifu De; Xiaomin Xu. 2019. "Wind Power Short-Term Forecasting Hybrid Model Based on CEEMD-SE Method." Processes 7, no. 11: 843.
The construction of power transmission and transformation project is a basic construction related to the national economy. The factors affecting the construction cost are intricate. In this paper, the fishbone analysis method is used to identify the influencing factors, with a total of 17 influencing factors being identified. The clustering analysis method is used to divide 17 factors into 5 categories. Then, through correlation analysis, 7 key factors are screened out; Gray comprehensive correlation is used to measure the impact of various key factors on investment. Based on the analysis of the influencing factors of cost, the whole process control strategy of overhead line engineering cost is proposed from the investment estimation stage, design stage, construction stage and completion settlement stage.
Chen Wu; Bing-Jie Li; Qian Ma; Yin Wu; Hong-Da Zhao; Dong-Xiao Niu; Hao Zhen; Zhuoya Siqin. Analysis of Factors Affecting Construction Cost of Line Engineering and Cost Control Strategy. Advances in Intelligent Systems and Computing 2019, 945 -954.
AMA StyleChen Wu, Bing-Jie Li, Qian Ma, Yin Wu, Hong-Da Zhao, Dong-Xiao Niu, Hao Zhen, Zhuoya Siqin. Analysis of Factors Affecting Construction Cost of Line Engineering and Cost Control Strategy. Advances in Intelligent Systems and Computing. 2019; ():945-954.
Chicago/Turabian StyleChen Wu; Bing-Jie Li; Qian Ma; Yin Wu; Hong-Da Zhao; Dong-Xiao Niu; Hao Zhen; Zhuoya Siqin. 2019. "Analysis of Factors Affecting Construction Cost of Line Engineering and Cost Control Strategy." Advances in Intelligent Systems and Computing , no. : 945-954.