Distributional neural networks for electricity price forecasting

Marcjasz, Grzegorz; Narajewski, Michał; Weron, Rafał; Ziel, Florian

doi:10.48550/arxiv.2207.02832

Cited by 2 publications

(3 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictive models typically use the price of different fuels as regressors, among them the Fig. 5 Histograms (for the 81 cases) of the difference of the mean MAE of the proposed method with every other algorithm for the incremental shift case price of gas [32][33][34], so this change of behavior has created a situation of uncertainty around the models. Figures 8 and 9 graphically show the change in the relationship between the variables.…”

Section: Electricity Price Forecasting (Epf)mentioning

confidence: 99%

A feature selection method based on Shapley values robust for concept shift in regression

Sebastián,

González-Guillén

2024

Neural Comput & Applic

View full text Add to dashboard Cite

Feature selection is one of the most relevant processes in any methodology for creating a statistical learning model. Usually, existing algorithms establish some criterion to select the most influential variables, discarding those that do not contribute to the model with any relevant information. This methodology makes sense in a static situation where the joint distribution of the data does not vary over time. However, when dealing with real data, it is common to encounter the problem of the dataset shift and, specifically, changes in the relationships between variables (concept shift). In this case, the influence of a variable cannot be the only indicator of its quality as a regressor of the model, since the relationship learned in the training phase may not correspond to the current situation. In tackling this problem, our approach establishes a direct relationship between the Shapley values and prediction errors, operating at a more local level to effectively detect the individual biases introduced by each variable. The proposed methodology is evaluated through various examples, including synthetic scenarios mimicking sudden and incremental shift situations, as well as two real-world cases characterized by concept shifts. Additionally, we perform three analyses of standard situations to assess the algorithm’s robustness in the absence of shifts. The results demonstrate that our proposed algorithm significantly outperforms state-of-the-art feature selection methods in concept shift scenarios, while matching the performance of existing methodologies in static situations.

show abstract

Section: Electricity Price Forecasting (Epf)mentioning

confidence: 99%

A feature selection method based on Shapley values robust for concept shift in regression

Sebastián,

González-Guillén

2024

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…To obtain a distribution of imbalance prices, we use additionally the bootstrap method [45] which was successfully applied in previous EPF research studies [18,29,36,46]. The insample bootstrapped errors are added to the forecasted expected price to derive the distribution forecast…”

Section: Naivementioning

confidence: 99%

“…Let us note that, if we remove the hidden layers, we obtain the gamlss model described in the previous section. The approach of probabilistic MLP in EPF was first introduced by Marcjasz et al [46] for the day-ahead prices. For mathematical details, see the aforementioned manuscript.…”

Section: Probabilistic Neural Networkmentioning

confidence: 99%

Probabilistic Forecasting of German Electricity Imbalance Prices

Narajewski

2022

Energies

Self Cite

View full text Add to dashboard Cite

The imbalance market is very volatile and often exhibits extreme price spikes. This makes it very hard to model; however, if predicted correctly, one could make significant gains by participating on the right side of the market. In this manuscript, we conduct a very short-term probabilistic forecasting of imbalance prices, contributing to the scarce literature in this novel subject. The forecasting is performed 30 min before the delivery, so that the trader might still choose the trading place. The distribution of the imbalance prices is modelled and forecasted using methods well-known in the electricity price forecasting literature: lasso with bootstrap, gamlss, and probabilistic neural networks. The methods are compared with a naive benchmark in a meaningful rolling window study. The results provide evidence of the efficiency between the intraday and balancing markets as the sophisticated methods do not substantially overperform the intraday continuous price index. On the other hand, they significantly improve the empirical coverage. Therefore, the traders should avoid participating in the balancing market, which is inline with the objective and current regulations of the market. The analysis was conducted on the German market; however, it could be easily applied to any other market of a similar structure.

show abstract

Distributional neural networks for electricity price forecasting

Cited by 2 publications

References 63 publications

A feature selection method based on Shapley values robust for concept shift in regression

A feature selection method based on Shapley values robust for concept shift in regression

Probabilistic Forecasting of German Electricity Imbalance Prices

Contact Info

Product

Resources

About