Search

More accurate multivariate load forecasting is conducive to integrated energy system planning optimization and economic operation. In this paper, based on the consideration of exogenous factors such as weather, endogenous factors are added into the prediction, and a short-term prediction model for integrated energy multivariate load based on endo-exogenous uncertainty is established using fine-tuned transfer learning. The LSTM pre-training model is first initially established using genetic algorithm and exogenous factors such as weather. Then the exogenous uncertainty of the pre-training model and the knowledge of endogenous uncertainty in the target model are combined using fine-tuned transfer learning to continuously optimize the basic parameters of the prediction model to obtain the final multivariate load prediction model. The performance of the four models is comprehensively evaluated after the historical load validation of the integrated energy system in Beijing, China. Compared with the traditional LSTM multivariate load forecasting model, the MAPE of the proposed model in this paper is reduced by 21.03 %, 13.00 %, and 24.39 % for electricity, heat, and cooling load forecasting, respectively. • The coupling mechanism between multiple energy sources of the integrated energy system is analyzed. • An endogenous-exogenous uncertainty method is proposed to extract the dynamic coupling relationship between multiple loads. • An endogenous-exogenous uncertainty-based GA-LSTM multivariate load prediction model is developed. • Optimizing model parameters using fine-tuned migration learning to deepen the impact of endo-exogenous uncertainty. [ABSTRACT FROM AUTHOR]

In order to establish a regional database on natural radioactivity, a series of measurements of 713 atmospheric aerosol samples collected on filters over a two-year period (2018–2019) in center of Beijing, northeastern China have been performed to analyze 7Be and 210Pb activity concentrations. The mean activity concentrations of 7Be and 210Pb were found to be 7.10 ± 2.44 mBq m−3 and 2.93 ± 1.52 mBq m−3, respectively. Both the radionuclides exhibited strong seasonal variations, with maximum concentration of 7Be occurring in the spring and that of 210Pb in the winter. The concentration of both the radionuclides was minimum in the rainy summer. Higher 7Be concentration in the spring was mainly caused by the stratosphere to troposphere exchange. Higher 210Pb concentration during winter was maybe attributed to the combustion processes in heating systems and the ingression of continental air masses resulted from winds originating from northwest. The dependence of the activity concentrations of 7Be and 210Pb with meteorological parameters such as rainfall, temperature, and humidity was studied through linear correlation analysis. Statistically significant negative correlations were observed between 7Be and 210Pb activity concentrations with rainfall, respectively, which suggested that the removal mechanisms of these two radionuclides were similar. Lead-210 showed statistically significant correlations with temperature, humidity and PM 10. A comparison of the data obtained in the present study for Beijing with the northern hemisphere literature values of 7Be and 210Pb in the atmospheric aerosols showed that the values were smaller than the ones observed in the present study. Overall, the study provides an improved understanding of the temporal variability and correlation of 7Be and 210Pb concentrations in the atmosphere in center of Beijing, northeastern China. • Regional database on7Be and 210Pb activity concentrations in the atmospheric aerosols in center of Beijing was established. • Rainfall is suggested as the major removal means for 7Be and 210Pb from the atmosphere. • Causal factors for the temporal variability of7Be and 210Pb activity concentrations were identified. • Correlations of temperature, relative humidity and PM 10 with 7Be and 210Pb were explored. • Correlation between 7Be and 210Pb activity concentrations was studied. [ABSTRACT FROM AUTHOR]