Title: Energy trading in day-ahead market Authors:  Ilyas Agakishev - Humboldt University of Berlin (Germany)
Karel Kozmik - Charles University (Czech Republic)
Alla Petukhina - ASE Bucharest (Romania) [presenting]
Abstract: A recently introduced approach is extended to probabilistic electricity price forecasting (EPF) utilizing distributional artificial neural networks, based on a regularized distributional multilayer perceptron (DMLP). We develop this technique for a multivariate case EPF with incorporated dependence. The performance of LSTM architecture and fully connected architecture of neural networks is tested. An empirical data application analyses two day-ahead electricity auctions for the United Kingdom market. Utilizing forecasting results, we develop trading strategies with various investors' objectives. We find that DMLP outperforms benchmarks for Mean-CVaR strategy.