STEMedu logo

STEMedu - Science, Technology, Engineering, (Art), Mathematics, Education

    Прогнозиране на цените на електроенергията ден напред чрез рекурентна невронна мрежа за изследване с дългосрочна-краткосрочна памет

PDF файл
Автор(и):
Екатерина Поповска, Institute of Robotics, Bulgarian Academy of Sciences, ekaterina.popovska@gmail.com

Галя Цанева, Institute of Robotics, Bulgarian Academy of Sciences, galitsaneva@abv.bg

https://doi.org/10.55630/STEM.2022.0417
Абстракт:
    The availability of accurate day-ahead electricity price forecasts is very important for electricity market participants and it is an essential challenge to accurately forecast the electricity price. Therefore, this study proposes an efficient method suitable for electricity price forecasting (EPF) and processing time-series data from the Bulgarian day-ahead market based on a long-short term memory (LSTM) recurrent neural network model. The LSTM model is used to forecast the day-ahead electricity price for the Bulgarian day-ahead market. As inputs to the model are used historical hourly prices for the period between 20.01.2016 and 05.03.2022. The output is the electricity price forecasts for hours and days ahead. The future values of prices are forecasted recursively. LSTM can model temporal dependencies in larger Time Series set horizons without forgetting the short-term patterns. LSTM networks are composed of units that are called LSTM memory cells and these cells contain some gates that process the inputs. Since electricity price is affected by various seasonal effects, the model is trained for several years. The effectiveness of the proposed method is verified using real market data.
Ключови думи:
Electricity Price Forecasting; Deep Learning; Day-Ahead Market; Time Series Forecasting; Long Short-Term Memory (LSTM); Machine Learning;
Цитиране (APA style):
Popovska, E., Georgieva-Tsaneva, G. (2022). Day-ahead Electricity Price Forecasting using Long-short Term Memory Recurrent Neural Network, Science Series "Innovative STEM Education", volume 04, ISSN: 2683-1333, Institute of Mathematics and Informatics – Bulgarian Academy of Sciences, pp. 139-148, DOI: https://doi.org/10.55630/STEM.2022.0417
Адрес на PDF файл:
http://www.math.bas.bg/vt/stemedu/book-4/STEMedu-2022-xvii.pdf