We conduct an extensive empirical study on short-term electricity price forecasting (EPF) to address the long-standing question if the optimal model structure for EPF is univariate or multivariate. We provide evidence that despite a minor edge in predictive performance overall, the multivariate modeling framework does not uniformly outperform the univariate one across all 12 considered datasets, seasons of the year or hours of the day, and at times is outperformed by the latter. This is an indication that combining advanced structures or the corresponding forecasts from both modeling approaches can bring a further improvement in forecasting accuracy. We show that this indeed can be the case, even for a simple averaging scheme involving only two models. Finally, we also analyze variable selection for the best performing high-dimensional lasso-type models, thus provide guidelines to structuring better performing forecasting model designs.or a univariate framework, the latter generally perform better for the first half of the day, whereas the former are better in the second half of the day. However, there has been no through, empirical study to date, involving many fine-tuned specifications from both groups. With this paper we want to fill the gap and provide much needed evidence. In particular we want to address three pertinent questions:1. Which modeling frameworkmultivariate or univariate -is better for EPF? 2. If one of them is better, is it better across all hours, seasons of the year and markets? 3. How many and which past values of the spot price process should be used in EPF models?The remainder of the paper is structured as follows. In Section 2 we thoroughly discuss the univariate and multivariate modeling frameworks, which are driven by different data-format perspectives. This is a crucial, conceptual part of the paper, which sets ground for the empirical analysis in the following Sections. In Section 3 we briefly describe the 12 price series used and present the area hyperbolic sine transform for stabilizing the variance of spot price data. In Section 4 we define 10 forecasting models representing eight model classes: (C1) the mean values of the past prices, (C2) similar-day techniques, (C3) sets of 24 parsimonious, interrelated autoregressive (AR) structures (so-called expert models), (C4) sets of 24 univariate AR models, (C5) vector autoregressive (VAR) models, (C6) sets of 24 parameter-rich, interrelated AR models estimated using the least absolute shrinkage and selection operator (i.e., lasso or LASSO; which shrinks to zero the coefficients of redundant explanatory variables), (C7) univariate AR models and (C8) univariate, parameter-rich AR models estimated using the lasso. In Section 5 we evaluate their performance on the basis of the Mean Absolute Error (MAE), the mean percentage deviation from the best (m.p.d.f.b.) model and using two variants of the Diebold and Mariano (1995) test for significant differences in the forecasting performance. We also discuss variable selection for the best performin...
In this paper we present a regression based model for day-ahead electricity spot prices. We estimate the considered linear regression model by the lasso estimation method. The lasso approach allows for many possible parameters in the model, but also shrinks and sparsifies the parameters automatically to avoid overfitting. Thus, it is able to capture the autoregressive intraday dependency structure of the electricity price well. We discuss in detail the estimation results which provide insights to the intraday behavior of electricity prices. We perform an out-of-sample forecasting study for several European electricity markets. The results illustrate well that the efficient lasso based estimation technique can exhibit advantages from two popular model approaches.
In the following paper, we analyse the ID 3 -Price in the German Intraday Continuous electricity market using an econometric time series model. A multivariate approach is conducted for hourly and quarter-hourly products separately. We estimate the model using lasso and elastic net techniques and perform an out-of-sample, very short-term forecasting study. The model's performance is compared with benchmark models and is discussed in detail. Forecasting results provide new insights to the German Intraday Continuous electricity market regarding its efficiency and to the ID 3 -Price behaviour.
Most electricity spot price series exhibit price spikes. These extreme observations may significantly impact the obtained model estimates and hence reduce efficiency of the employed predictive algorithms. For markets with only positive prices the logarithmic transform is the single most commonly used technique to reduce spike severity and consequently stabilize the variance. However, for datasets with very close to zero (like the Spanish) or negative (like the German) prices the log-transform is not feasible. What reasonable choices do we have then? To address this issue, we conduct a comprehensive forecasting study involving 12 datasets from diverse power markets and evaluate 16 variance stabilizing transformations. We find that the probability integral transform (PIT) combined with the standard Gaussian distribution yields the best approach, significantly better than many of the considered alternatives.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.