Probabilistic deep neural network price forecasting based on residential load and wind speed predictions

• Published in: IET renewable power generation 2019-08, Vol.13 (11), p.1840-1848
• Main Authors: Afrasiabi, Mousa, Mohammadi, Mohammad, Rastegar, Mohammad, Kargarian, Amin
• Format: Article
• Language: English
• Subjects: accurate forecast; adaptive kernel density estimator; AKDE; CNN; convolution neural network; day‐ahead prices; deep learning based methods; deep networks; deep neural network algorithm; deregulated electricity market; forecasting theory; GRU; high volatile parameters; historical data; historical price information; learning (artificial intelligence); load forecasting; neural nets; power engineering computing; power markets; power system economics; precise price forecasting; price forecast procedure; pricing; probabilistic deep neural network price forecasting; probability; probability density function; Research Article; residential load; residential loads prediction; shallow networks; wind speed predictions
• ISSN: 1752-1416; 1752-1424; 1752-1424
• DOI: 10.1049/iet-rpg.2018.6257

Precise price forecasting can lessen the risk of participation in the deregulated electricity market. On account of a large amount of historical data, deep learning based methods can be a promising solution to achieve an accurate forecast. This study presents a deep neural network algorithm to estimate the probability density function of price, incorporating the prediction of wind speed and residential load as two other high volatile parameters. To this end, first, a combination of convolution neural network (CNN) and gated recurrent unit (GRU) is utilised to predict wind speed and residential load. Then, the results are integrated into historical price information to form the input dataset for price forecasting. The proposed price forecast procedure consists of CNN, GRU, and adaptive kernel density estimator (AKDE). AKDE is used as a numerical algorithm to capture probabilistic characterisation of real-time and day-ahead prices. Several deep and shallow networks and the proposed algorithm are implemented, and the results are compared. Furthermore, the effectiveness of AKDE in providing complete statistical information is verified through comparison with conventional and fixed smooth KDEs. In addition, the gradient boosting tree method is incorporated to verify the dependence of the price to the wind and the residential loads.