Neural Network Based Model Comparison for Intraday Electricity Price Forecasting

Abstract

The intraday electricity markets are continuous trade platforms for each hour of the day and have specific characteristics. These markets have shown an increasing number of transactions due to the requirement of close to delivery electricity trade. Recently, intraday electricity price market research has seen a rapid increase in a number of works for price prediction. However, most of these works focus on the features and descriptive statistics of the intraday electricity markets and overlook the comparison of different available models. In this paper, we compare a variety of methods including neural networks to predict intraday electricity market prices in Turkish intraday market. The recurrent neural networks methods outperform the classical methods. Furthermore, gated recurrent unit network architecture achieves the best results with a mean absolute error of 0.978 and a root mean square error of 1.302. Moreover, our results indicate that day-ahead market price of the corresponding hour is a key feature for intraday price forecasting and estimating spread values with day-ahead prices proves to be a more efficient method for prediction.

Beating the Naïve—Combining LASSO with Naïve Intraday Electricity Price Forecasts

“…Furthermore, we have focused on point forecasting, ignoring the full predictive distribution [8,29] or-what may be even more important in continuous-time intraday markets-the trajectories [13,30]. We have restricted ourselves to using regression-based models, however, machine learning techniques could be used in this context as well [12,22,23,31], naturally at the cost of an increased computational burden. Finally, recall from Section 4.4, that the ensemble we use balances the generalization of the LASSO forecasts with the ability to quickly adapt to non-recurring phenomena of the naïve benchmark.…”

Balancing Generation from Renewable Energy Sources: Profitability of an Energy Trader

“…We should also emphasize that in this study we are using only one, relatively simple way of improving wind generation forecasts. More complex approaches, like LASSO [9,28] or deep learning [29,30], and the addition of other exogenous variables, like power plant availability, control area balances or updated forecasts of RES generation [7], can be easily addressed in future work. Instead of using point predictions, one could improve the spot trading activities based on probabilities instead of the expected outcome alone [31,32].…”

Modeling of frequency containment reserve prices with econometrics and artificial intelligence

“…Lago, Ridder, and Schutter (2018) study the Belgian day‐ahead electricity market and consider a large set of possible forecasting models, concluding a significant dominance of machine learning over the statistical models in terms of forecasting accuracy. Ugurlu, Oksuz, and Tas (2018) and Oksuz and Ugurlu (2019) forecast the Turkish day‐ahead and intraday market electricity prices with different neural networks configurations, including feedforward, gated recurrent unit (GRU) and long short‐term‐memory (LSTM) model designs. The authors conclude a significant dominance of GRU model designs and state an improvement with increasingly sophisticated network structures.…”