Search academic texts

Information × Registration Number 0223U000564, 0121U111848 , R & D reports Title Forecasting the total imbalance of electricity in the UES of Ukraine and its impact on the final cost of electricity popup.stage_title Head Blinov Ihor V., Доктор технічних наук Registration Date 12-01-2023 Organization Institute of Electrodynamics of the National Academy of Sciences of Ukraine popup.description2 The analysis of the tariff formation scheme for the end consumer of electricity was carried out with the selection of components that have a noticeable impact on the results of the decision to assess the feasibility of the consumer's transition to hourly electricity metering. Such components include the cost of electricity in the DAM segment and the cost of accrued imbalances. Conducted research on the volumes of electricity imbalances based on the results of the functioning of the balancing market for the market zones of the UES of Ukraine and the Burshtyn energy island to forecast their volumes. As part of the studies of samples of electricity imbalances, it was determined that the data are non-stationary random time series with high autocorrelation, therefore, for their short-term forecasting, it is appropriate to use one-factor models based on autoregression methods. Several LSTM and LSTMNet recurrent artificial neural network architectures were developed to compare the performance of short-term forecasting models. From the forecasting results, it was determined that the use of artificial neural networks made it possible to reduce the forecasting error for different testing periods depending on the type of electricity imbalance. The main scientific and scientific and technical results obtained as a result of the work include the following: - a mathematical model of the final cost of electrical energy on the retail market was developed, taking into account the cost of electrical energy imbalances, based on which an experimental computer program was created; - a statistical analysis of the time series of total imbalances of electrical energy was carried out and quantitative indicators of the forecast quality of various models were investigated to determine the most effective for forecasting imbalances in the IPS of Ukraine; - developed methods of short-term forecasting of total imbalances in the IPS of Ukraine using artificial neural networks of deep learning. Product Description popup.authors Miroshnyk Volodymyr Oleksandrovych Sychova Viktoriia V Shimanyuk Pavlo V popup.nrat_date 2023-01-12 Close