Search NASA⌕ Search

Engineering topics

Gao, Yifeng

Publications and source records attributed to Gao, Yifeng.

Entropy-Infused Deep Learning Loss Function for Capturing Extreme Values in Wind Power Forecasting

Extreme scenarios in wind power generation occur with higher frequency and larger magnitude in the recent years due to the ever-increasing extreme meteorological factors. Accurate forecasting of the occurrence of extreme values in wind power generation is of great concern to ensure reliable power system operation. Recently, deep learning models have surged in popularity for wind power forecasting, with the mean squared error (MSE) loss function being commonly used. However, the MSE loss function, being sensitive to extreme values, disproportionately penalizes larger errors, cannot adequately capture the extreme values present in wind energy data, and novel loss functions have seldom been tailored for wind power forecasting. To this end, in this paper, we introduce a novel loss function specifically crafted to capture extreme values in wind power forecasting. The experimental results with four fundamental deep learning methods on open source wind power dataset validate that the new loss function is efficient and superior in all cases compared to MSE in capturing extreme values while maintaining forecasting performance.

17 WIND ENERGY↗

Condensation heat transfer characteristics of R410A-oil mixture in 5 mm and 4 mm outside diameter horizontal microfin tubes

Condensation heat transfer characteristics of R410A-oil mixture in 5 mm and 4 mm outside diameter horizontal microfin tubes were investigated experimentally. The experimental condensing temperature is 40 C, and nominal oil concentration range is from 0% to 5%. The test results indicate that the presence of oil deteriorates the heat transfer. The deterioration effect is negligible at nominal oil concentration of 1%, and becomes obvious with the increase of nominal oil concentration. At 5% nominal oil concentration, the heat transfer coefficient of R410A-oil mixture is found to have a maximum reduction of 25.1% and 23.8% for 5 mm and 4 mm tubes, respectively. The predictabilities of the existing condensation heat transfer correlations were verified with the experimental data, and Yu and Koyama correlation shows the best predictability. By replacing the pure refrigerant properties with the mixture's properties, Yu and Koyama correlation has a deviation of -15% to + 20% in predicting the local condensation heat transfer coefficient of R410A-oil mixture. (author)

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗