Search

Electricity Price Forecasting (EPF) IS A branch of forecasting at the interface of electrical engineering, statistics, computer science, and finance that focuses on predicting prices in wholesale electricity markets for a whole spectrum of horizons. These range from a few minutes (real-time/intraday auctions and continuous trading); through days (day-ahead [DA] auctions); to weeks, months, or even years (exchange and over-the-counter traded futures and forward contracts). DA markets are the workhorse of power trading, particularly in Europe, and a commonly used proxy for “the electricity price.” The vast majority—up to 90%—of the EPF literature has focused on predicting DA prices. These are typically determined around noon during 24 uniform-price auctions, one for each hour of the next day. This has direct implications for the way EPF models are built. [ABSTRACT FROM AUTHOR]

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 evaluate 16 variance stabilizing transformations within a comprehensive forecasting study involving two model classes (regression models, neural networks) and 12 datasets from diverse power markets. We show that the probability integral transform combined with the standard Gaussian distribution yields the best approach, significantly better than many of the considered alternatives. [ABSTRACT FROM AUTHOR]

The majority of the load forecasting literature has been on point forecasting, which provides the expected value for each step throughout the forecast horizon. In the smart grid era, the electricity demand is more active and less predictable than ever before. As a result, probabilistic load forecasting, which provides additional information on the variability and uncertainty of future load values, is becoming of great importance to power systems planning and operations. This paper proposes a practical methodology to generate probabilistic load forecasts by performing quantile regression averaging on a set of sister point forecasts. There are two major benefits of the proposed approach. It can leverage the development in the point load forecasting literature over the past several decades and it does not rely so much on high-quality expert forecasts, which are rarely achievable in load forecasting practice. To demonstrate the effectiveness of the proposed approach and make the results reproducible to the load forecasting community, we construct a case study using the publicly available data from the Global Energy Forecasting Competition 2014. Compared with several benchmark methods, the proposed approach leads to dominantly better performance as measured by the pinball loss function and the Winkler score. [ABSTRACT FROM PUBLISHER]

We propose a novel concept in energy forecasting and show that averaging day-ahead electricity price forecasts of a predictive model across 28–728 day calibration windows yields better results than selecting only one “optimal” window length. Even more significant accuracy gains can be achieved by averaging over a few, carefully selected windows. [ABSTRACT FROM AUTHOR]

In this paper we investigate whether considering the fine structure of half-hourly electricity prices, the market closing prices of fundamentals (natural gas, coal and CO2) and the system-wide demand can lead to significantly more accurate short- and mid-term forecasts of APX U.K. baseload prices. We evaluate the predictive accuracy of a number of univariate and multivariate time series models over a three-year out-of-sample forecasting period and compare it against that of a benchmark autoregressive model. We find that in the short-term, up to a few business days ahead, a disaggregated model which independently predicts the intra-day prices and then takes their average to yield baseload price forecasts is the best performer. However, in the mid-term, factor models which explore the correlation structure of intra-day prices lead to significantly (as measured by the Diebold-Mariano test) better baseload price forecasts. At the same time, we observe that the inclusion of fundamental variables—especially natural gas prices (in the short-term) and coal prices (in the mid-term)—provides significant gains. The CO2 prices, on the other hand, generally do not improve the price forecasts at all, at least in the time period considered in this study (April 2009–December 2013). [ABSTRACT FROM PUBLISHER]