Author: nccmne

The day-ahead energy market lets market participants commit to buy or sell wholesale electricity one day before the operating day, to help avoid price volatility. Forecasting day-ahead electricity prices and loads creates basis for decision making in this process. Mr. Milutin Pavićević, a young researcher from the University of Donja Gorica , explored the possibility to utilize artificial neural networks in order to improve the forecasting day-ahead electricity prices and loads based on the historical data. This was the topic of his Master thesis research work done under supervision of professor Tomo Popovic, which finally resulted in a scientific article published in MDPI journal Sensors. The paper is titled ”Forecasting Day-Ahead Electricity Metrics with Artificial Neural Networks” within the Special Issue Complex Data Processing Systems and Computing Algorithms: New Concepts and Applications.

During this research effort the researchers engaged the domain experts which provided us with generous help in obtaining datasets and understanding the problem of day-ahead consumption, spot price prediction, and the electricity market. The results show the promising efficiency of AI and machine learning for the task of short-term prediction of electricity metrics. With the support of EuroCC Montenegro, the future work will include experimenting on the HPC infrastructure and creation of an industry pilot demonstration for the energy sector.

ABSTRACT – As artificial neural network architectures grow increasingly more efficient in time-series prediction tasks, their use for day-ahead electricity price and demand prediction, a task with very specific rules and highly volatile dataset values, grows more attractive. Without a standardized way to compare the efficiency of algorithms and methods for forecasting electricity metrics, it is hard to have a good sense of the strengths and weaknesses of each approach. In this paper, we create models in several neural network architectures for predicting the electricity price on the HUPX market and electricity load in Montenegro and compare them to multiple neural network models on the same basis (using the same dataset and metrics). The results show the promising efficiency of neural networks in general for the task of short-term prediction in the field, with methods combining fully connected layers and recurrent neural or temporal convolutional layers performing the best. The feature extraction power of convolutional layers shows very promising results and recommends the further exploration of temporal convolutional networks in the field.

The paper can be accessed at the Sensors website at the following link.