Comparison of the goodness-of-fit of intelligent-optimized wind speed distributions and calculation in high-altitude wind-energy potential assessment

Li, Qiwei; Wang, Jianzhou; Zhang, Haipeng

doi:10.1016/j.enconman.2021.114737

Cited by 15 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the sustainable development of energy, technological progress, and people's demand for environmental protection, efforts are underway to find alternative renewable energy sources to replace oil and gas. [1,2] Wind energy has great potential as a clean and pollution-free renewable energy, [3,4] which has been taken more seriously by countries around the world. [5] However, the instability and nonlinearity of wind power limit the development of wind power, which may bring many obstacles to the planning and application of electric systems.…”

Section: Introductionmentioning

confidence: 99%

A Novel Prediction‐Integration Forecasting System for Short Wind Speed Based on Combined Data Preprocessing Technique and Weight Determination Strategy

Wang,

An,

Wang

et al. 2023

Energy Tech

Self Cite

View full text Add to dashboard Cite

Based on the advanced theory research of artificial intelligence and data analysis strategy, a multimodel‐integrated wind speed prediction system is designed in this study, which contains a combined data preprocessing technique, weight determination strategy, and uncertainty prediction. The proposed system not only eliminates the impact of noise but also integrates the results of individual prediction models based on a weight determination strategy. In addition, uncertainty prediction is used to quantify the uncertainty caused by point prediction. The experimental results show that: 1) the mean absolute percentage error values of the proposed model at Site 1 are about 1% and 2%, respectively, which outperform some common basic models such as back propagation neural network (about 7% and 9%). 2) At the significant level α = 0.05, the prediction interval coverage probability values of the proposed model at Site 1 are about 98% and 94%, respectively, for the uncertainty forecasting, which is significantly better than most traditional methods such as extreme learning machine (about 86% and 41%). It is reasonable to conclude that the proposed system is superior to the traditional model in accuracy and stability, which can be a powerful tool for power grid planning.

show abstract